<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD Journal Publishing DTD v2.0 20040830//EN" "http://dtd.nlm.nih.gov/publishing/2.0/journalpublishing.dtd">
<article article-type="review-article" dtd-version="2.0" xmlns:xlink="http://www.w3.org/1999/xlink">
  <front>
    <journal-meta>
      <journal-id journal-id-type="publisher-id">JMIR</journal-id>
      <journal-id journal-id-type="nlm-ta">J Med Internet Res</journal-id>
      <journal-title>Journal of Medical Internet Research</journal-title>
      <issn pub-type="epub">1438-8871</issn>
      <publisher>
        <publisher-name>JMIR Publications</publisher-name>
        <publisher-loc>Toronto, Canada</publisher-loc>
      </publisher>
    </journal-meta>
    <article-meta>
      <article-id pub-id-type="publisher-id">v28i1e104060</article-id>
      <article-id pub-id-type="pmid"/>
      <article-id pub-id-type="doi">10.2196/104060</article-id>
      <article-categories>
        <subj-group subj-group-type="heading">
          <subject>Review</subject>
        </subj-group>
        <subj-group subj-group-type="article-type">
          <subject>Review</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title>Diagnostic Performance of Radiomics-Based Machine Learning in Differentiating Glioblastoma From Brain Metastasis: Systematic Review and Meta-Analysis</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="editor">
          <name>
            <surname>Balcarras</surname>
            <given-names>Matthew</given-names>
          </name>
        </contrib>
      </contrib-group>
      <contrib-group>
        <contrib contrib-type="reviewer">
          <name>
            <surname>Iranmanesh</surname>
            <given-names>Pedram</given-names>
          </name>
        </contrib>
        <contrib contrib-type="reviewer">
          <name>
            <surname>Ramireddy</surname>
            <given-names>Indumati</given-names>
          </name>
        </contrib>
      </contrib-group>
      <contrib-group>
        <contrib id="contrib1" contrib-type="author">
          <name name-style="western">
            <surname>Hong</surname>
            <given-names>Chen</given-names>
          </name>
          <degrees>MD</degrees>
          <xref rid="aff1" ref-type="aff">1</xref>
          <ext-link ext-link-type="orcid">https://orcid.org/0009-0004-1964-3839</ext-link>
        </contrib>
        <contrib id="contrib2" contrib-type="author">
          <name name-style="western">
            <surname>Liu</surname>
            <given-names>Gemingtian</given-names>
          </name>
          <degrees>MD</degrees>
          <xref rid="aff1" ref-type="aff">1</xref>
          <ext-link ext-link-type="orcid">https://orcid.org/0009-0001-0282-4906</ext-link>
        </contrib>
        <contrib id="contrib3" contrib-type="author">
          <name name-style="western">
            <surname>Bie</surname>
            <given-names>Zhixu</given-names>
          </name>
          <degrees>MD</degrees>
          <xref rid="aff1" ref-type="aff">1</xref>
          <ext-link ext-link-type="orcid">https://orcid.org/0009-0003-9319-1933</ext-link>
        </contrib>
        <contrib id="contrib4" contrib-type="author">
          <name name-style="western">
            <surname>Guo</surname>
            <given-names>Yuanhang</given-names>
          </name>
          <degrees>MD</degrees>
          <xref rid="aff1" ref-type="aff">1</xref>
          <ext-link ext-link-type="orcid">https://orcid.org/0009-0008-0790-4973</ext-link>
        </contrib>
        <contrib id="contrib5" contrib-type="author">
          <name name-style="western">
            <surname>Du</surname>
            <given-names>Yi</given-names>
          </name>
          <degrees>MBBS</degrees>
          <xref rid="aff1" ref-type="aff">1</xref>
          <ext-link ext-link-type="orcid">https://orcid.org/0009-0009-4602-9523</ext-link>
        </contrib>
        <contrib id="contrib6" contrib-type="author">
          <name name-style="western">
            <surname>Hu</surname>
            <given-names>Yanan</given-names>
          </name>
          <degrees>MBBS</degrees>
          <xref rid="aff1" ref-type="aff">1</xref>
          <ext-link ext-link-type="orcid">https://orcid.org/0009-0004-7637-0371</ext-link>
        </contrib>
        <contrib id="contrib7" contrib-type="author">
          <name name-style="western">
            <surname>Li</surname>
            <given-names>Shiwei</given-names>
          </name>
          <degrees>PhD</degrees>
          <xref rid="aff1" ref-type="aff">1</xref>
          <ext-link ext-link-type="orcid">https://orcid.org/0009-0002-3215-1412</ext-link>
        </contrib>
        <contrib id="contrib8" contrib-type="author" corresp="yes">
          <name name-style="western">
            <surname>Liu</surname>
            <given-names>Pinan</given-names>
          </name>
          <degrees>PhD</degrees>
          <xref rid="aff1" ref-type="aff">1</xref>
          <address>
            <institution>Department of Neurosurgery</institution>
            <institution>Beijing Tiantan Hospital, Capital Medical University</institution>
            <addr-line>119 South Fourth Ring West Road, Fengtai District</addr-line>
            <addr-line>Beijing, 100070</addr-line>
            <country>China</country>
            <phone>86 13716372500</phone>
            <email>pinanliu@ccmu.edu.cn</email>
          </address>
          <ext-link ext-link-type="orcid">https://orcid.org/0000-0002-6479-7376</ext-link>
        </contrib>
      </contrib-group>
      <aff id="aff1">
        <label>1</label>
        <institution>Department of Neurosurgery</institution>
        <institution>Beijing Tiantan Hospital, Capital Medical University</institution>
        <addr-line>Beijing</addr-line>
        <country>China</country>
      </aff>
      <author-notes>
        <corresp>Corresponding Author: Pinan Liu <email>pinanliu@ccmu.edu.cn</email></corresp>
      </author-notes>
      <pub-date pub-type="collection">
        <year>2026</year>
      </pub-date>
      <pub-date pub-type="epub">
        <day>19</day>
        <month>11</month>
        <year>2026</year>
      </pub-date>
      <volume>28</volume>
      <elocation-id>e104060</elocation-id>
      <history>
        <date date-type="received">
          <day>9</day>
          <month>6</month>
          <year>2026</year>
        </date>
        <date date-type="rev-request">
          <day>28</day>
          <month>9</month>
          <year>2026</year>
        </date>
        <date date-type="rev-recd">
          <day>15</day>
          <month>10</month>
          <year>2026</year>
        </date>
        <date date-type="accepted">
          <day>22</day>
          <month>10</month>
          <year>2026</year>
        </date>
      </history>
      <copyright-statement>©Chen Hong, Gemingtian Liu, Zhixu Bie, Yuanhang Guo, Yi Du, Yanan Hu, Shiwei Li, Pinan Liu. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 19.11.2026.</copyright-statement>
      <copyright-year>2026</copyright-year>
      <license license-type="open-access" xlink:href="https://creativecommons.org/licenses/by/4.0/">
        <p>This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research (ISSN 1438-8871), is properly cited. The complete bibliographic information, a link to the original publication on https://www.jmir.org/, as well as this copyright and license information must be included.</p>
      </license>
      <self-uri xlink:href="https://www.jmir.org/2026/1/e104060" xlink:type="simple"/>
      <abstract>
        <sec sec-type="background">
          <title>Background</title>
          <p>Glioblastoma (GBM) and brain metastasis (BM) are the most common malignant intracranial tumors in adults. Noninvasive differentiation between them remains challenging, as they frequently share similar imaging features. Although radiomics-based machine learning (ML) models show promise, systematic evidence of their performance remains limited.</p>
        </sec>
        <sec sec-type="objective">
          <title>Objective</title>
          <p>We aimed to systematically estimate the diagnostic performance of radiomics-based ML models in differentiating GBM from BM and to explore multiclass classification involving primary central nervous system lymphoma (PCNSL), thereby assessing their potential for clinical use.</p>
        </sec>
        <sec sec-type="methods">
          <title>Methods</title>
          <p>We systematically searched PubMed, Embase, Web of Science, and Cochrane Library databases from inception to January 22, 2026, for studies reporting the diagnostic performance of radiomics-based ML models for differentiating GBM from BM. Multiclass studies involving PCNSL were also retained. Methodological quality was appraised via the Radiomics Quality Score 2.0. Binary diagnostic accuracy was pooled using a bivariate random-effects model, stratified by internal and independent external validation. Multiclass sensitivities and specificities were pooled using separate joint generalized linear mixed models. Physician assessments were evaluated as an exploratory benchmark.</p>
        </sec>
        <sec sec-type="results">
          <title>Results</title>
          <p>A total of 39 studies (31 binary and 8 multiclass), involving 11,558 patients, were included. For binary classification, pooled sensitivity and specificity were 88.9% (95% CI 84.1%-92.4%) and 83.0% (95% CI 76.8%-87.9%) in internal validation, and 83.8% (95% CI 77.4%-88.7%) and 80.7% (95% CI 71.1%-87.7%) in external validation, respectively. In multiclass analyses, pooled sensitivity was 84.4% (95% CI 72.4%-91.8%) for GBM, 70.6% (95% CI 54.4%-82.8%) for BM, and 75.0% (95% CI 62.7%-84.3%) for PCNSL, with corresponding specificities of 82.5% (95% CI 70.1%-90.4%), 88.8% (95% CI 81.9%-93.3%), and 94.4% (95% CI 88.4%-97.4%), respectively.</p>
        </sec>
        <sec sec-type="conclusions">
          <title>Conclusions</title>
          <p>Radiomics-based ML models could distinguish between GBM and BM in the included cohorts. However, due to methodological limitations and scarce evidence, their generalizability and clinical utility remain unclear. Further multicenter prospective studies should conduct independent external validation in consecutive patients.</p>
        </sec>
        <sec sec-type="Trial Registration">
          <title>Trial Registration</title>
          <p>PROSPERO CRD420261295269; https://www.crd.york.ac.uk/PROSPERO/view/CRD420261295269</p>
        </sec>
      </abstract>
      <kwd-group>
        <kwd>glioblastoma</kwd>
        <kwd>brain metastasis</kwd>
        <kwd>machine learning</kwd>
        <kwd>radiomics</kwd>
        <kwd>differential diagnosis</kwd>
      </kwd-group>
    </article-meta>
  </front>
  <body>
    <sec sec-type="introduction">
      <title>Introduction</title>
      <p>Glioblastoma (GBM) and brain metastasis (BM) are the most common malignant intracranial neoplasms in adults. It is crucial to distinguish between these 2 entities, as they differ significantly in terms of their natural course, therapeutic strategies, and prognosis [<xref ref-type="bibr" rid="ref1">1</xref>,<xref ref-type="bibr" rid="ref2">2</xref>]. GBM has a median overall survival (OS) of 16 to 18 months and a 5-year OS rate of approximately 7%. The standard treatment consists of chemoradiation following maximal safe resection [<xref ref-type="bibr" rid="ref1">1</xref>,<xref ref-type="bibr" rid="ref3">3</xref>]. BM affects an estimated 20% of patients with cancer [<xref ref-type="bibr" rid="ref4">4</xref>]. The management of BM depends heavily on the primary malignancy and typically involves surgery, radiosurgery, or systemic therapy [<xref ref-type="bibr" rid="ref5">5</xref>]. Although histopathological examination remains the reference standard for definitive diagnosis, tissue sampling is invasive; the reported rate of perioperative complications ranges from 6% to 12%, and the mortality rate ranges from 0% to 1.7% after stereotactic needle biopsy [<xref ref-type="bibr" rid="ref6">6</xref>]. Consequently, neurosurgeons rely heavily on contrast-enhanced magnetic resonance imaging (MRI) for preoperative diagnosis. GBM and BM frequently share imaging features, including ring enhancement, marked peritumoral edema, and central necrosis. Furthermore, neurosurgeons must distinguish these tumors from other intracranial neoplasms, such as primary central nervous system lymphoma (PCNSL) [<xref ref-type="bibr" rid="ref7">7</xref>], which has a 10-year survival rate of approximately 30% and requires different therapeutic strategies [<xref ref-type="bibr" rid="ref1">1</xref>]. These overlapping features complicate preoperative differentiation, even for experienced neuroradiologists.</p>
      <p>Advanced MRI techniques, including perfusion-weighted imaging, diffusion-weighted imaging, and magnetic resonance spectroscopy, have been investigated to distinguish these tumors based on vascularity, microstructure, and metabolism [<xref ref-type="bibr" rid="ref8">8</xref>-<xref ref-type="bibr" rid="ref10">10</xref>]. Despite considerable research attention, their diagnostic performance remains variable. Their value as stand-alone tools for routinely distinguishing between GBM and BM remains uncertain.</p>
      <p>Radiomics-based machine learning (ML) models have shown considerable promise for tumor classification across diverse imaging modalities [<xref ref-type="bibr" rid="ref11">11</xref>-<xref ref-type="bibr" rid="ref13">13</xref>]. Deep learning (DL), a branch of ML, can extract high-dimensional quantitative features and capture spatial heterogeneity, reducing reliance on handcrafted feature design. ML approaches have also been applied to the 3-class differentiation of GBM, BM, and PCNSL [<xref ref-type="bibr" rid="ref14">14</xref>].</p>
      <p>However, heterogeneity in imaging inputs, model types, and feature extraction approaches limits comparability and clinical translation. Chen et al [<xref ref-type="bibr" rid="ref15">15</xref>] evaluated 30 combinations of feature-selection methods and classifiers using conventional MRI, illustrating the potential of MRI-based radiomics for distinguishing between GBM and BM and the variability in performance across modeling approaches. Building on such evidence and previous reviews [<xref ref-type="bibr" rid="ref16">16</xref>,<xref ref-type="bibr" rid="ref17">17</xref>], this meta-analysis updated the evidence through January 2026 and estimated the pooled diagnostic performance of radiomics-based ML models for differentiating GBM from BM, separating internal from external validation. We further performed subgroup analyses by model type, MRI input, and feature extraction approach and assessed methodological quality using the Radiomics Quality Score (RQS) 2.0. We also considered multiclass classification (GBM, BM, and PCNSL) and summarized physician assessments as an exploratory benchmark.</p>
    </sec>
    <sec sec-type="methods">
      <title>Methods</title>
      <sec>
        <title>Study Registration</title>
        <p>This meta-analysis followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 statement and the PRISMA Diagnostic Test Accuracy guidelines [<xref ref-type="bibr" rid="ref18">18</xref>,<xref ref-type="bibr" rid="ref19">19</xref>]. The study protocol was registered in PROSPERO (CRD420261295269). Validation stratification was prespecified; its operational definitions were clarified during revision. The completed PRISMA 2020 checklist is provided separately (<xref ref-type="supplementary-material" rid="app1">Multimedia Appendix 1</xref>).</p>
      </sec>
      <sec>
        <title>Ethical Considerations</title>
        <p>Ethics approval was not needed because this review used published data and involved no new participant recruitment or individual patient data.</p>
      </sec>
      <sec>
        <title>Eligibility Criteria</title>
        <p>This meta-analysis used the PIRD (population, index test, reference standard, and diagnosis of interest) framework to define its research question. The population comprised patients undergoing preoperative evaluation for GBM or BM. The index test was the diagnostic performance of radiomics-based ML and/or DL models. The reference standard was histopathology or, for BM, a clinical and imaging reference standard. The diagnosis of interest was the differentiation of GBM from BM.</p>
        <p>Fully published English-language studies that met the following criteria were included: (1) a radiomics-based ML and/or DL model was developed to differentiate GBM from BM or distinguish among GBM, BM, and PCNSL and (2) diagnoses were established by histopathology or, for BM, by a clinical and imaging diagnosis in patients with known systemic malignancy.</p>
        <p>Exclusion criteria included the following: (1) conference abstracts, (2) only image segmentation or texture analysis without constructing an ML and/or DL model for differentiating these entities, (3) binary classification studies without sufficient data to report or reconstruct patient-level 2×2 tables, and (4) multiclass studies reporting only overall classification accuracy.</p>
      </sec>
      <sec>
        <title>Data Sources and Search Strategy</title>
        <p>Web of Science, PubMed, Embase, and Cochrane Library databases were comprehensively searched from inception to January 22, 2026, for eligible studies evaluating the diagnostic performance of radiomics-based models for differentiating relevant brain tumors. The search strategy combined 2 main domains: (1) radiomics, ML, and DL (eg, “radiomics,” “machine learning,” “deep learning,” “support vector machine,” and “convolutional neural network”) and (2) targeted diseases (eg, “glioblastoma,” “brain metastasis,” and “cerebral metastasis”). The search was confined to human studies and full-text articles with peer review. The full search strategy for each database is detailed in Table S1 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>.</p>
      </sec>
      <sec>
        <title>Study Selection</title>
        <p>ZB and YG independently screened titles, abstracts, and full texts according to the eligibility criteria, using EndNote 21 (Clarivate) for reference management and screening. They also screened the reference lists of relevant articles and reviews to identify additional studies. Interrater reliability for study selection was evaluated using the Cohen κ coefficient (κ=0.68), indicating substantial agreement. Disagreements were resolved through discussion. If consensus could not be reached, PL made the final decision.</p>
      </sec>
      <sec>
        <title>Data Extraction</title>
        <p>CH, ZB, and YG independently undertook data extraction from eligible studies using a standardized form, including first author, year of publication, country, task category, patient source, metastasis background, segmentation method and software, optimal model types, imaging modalities, validation method, feature extraction approach, comparison with human experts, and diagnostic performance metrics (Table S2 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>) [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>-<xref ref-type="bibr" rid="ref57">57</xref>]. Disagreements were resolved through discussion; unresolved cases were adjudicated by PL.</p>
      </sec>
      <sec>
        <title>Assessment of Study Quality</title>
        <p>CH, YH, and YD independently assessed methodological quality using the RQS 2.0 [<xref ref-type="bibr" rid="ref58">58</xref>]. Handcrafted radiomics (HCR) and DL radiomics (DLR) were assessed separately. Radiomics readiness levels (RRLs) were grouped into model development (RRLs 1-5) and clinical translation (RRLs 6-9). Disagreements were resolved through discussion; unresolved cases were adjudicated by PL. Summary scores, item-level ratings, and scoring calculations are provided in Table S3 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref> [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>-<xref ref-type="bibr" rid="ref57">57</xref>].</p>
      </sec>
      <sec>
        <title>Synthesis Methods</title>
        <p>Binary sensitivity and specificity were pooled using bivariate random-effects models fitted by maximum likelihood, with GBM as the positive class [<xref ref-type="bibr" rid="ref59">59</xref>]. The same model was used for subgroup analyses and exploratory physician analyses. Summary receiver operating characteristic curves and the area under the curve (AUC) were derived from the fitted models. Approximate AUCs (95% CIs) were calculated using the logit-scale delta method. Heterogeneity was assessed using approximate model-based <italic>I</italic>². The Deeks test and Fagan nomograms were used to assess small-study effects and posttest probabilities [<xref ref-type="bibr" rid="ref60">60</xref>,<xref ref-type="bibr" rid="ref61">61</xref>].</p>
        <p>Internal and external validation were analyzed separately, retaining 1 optimal model per study within each validation category. Internal validation included resampling and holdout or temporal testing, while external validation used independent institutions or public databases. For subgroup analyses by model type, MRI input, and feature extraction approach, 1 validation cohort was selected per study, separately for HCR and DLR, prioritizing external validation, internal holdout testing, then cross-validation. Within internal validation, bivariate metaregression was used to compare holdout testing with cross-validation.</p>
        <p>For multiclass tasks, class-specific sensitivity and specificity were pooled using separate multivariate generalized linear mixed models with a logit link [<xref ref-type="bibr" rid="ref62">62</xref>]. <italic>P</italic> values were Holm adjusted separately for sensitivity and specificity.</p>
        <p>Statistical analyses and postestimation were performed using Stata (version 19.0; StataCorp; <italic>midas</italic>, <italic>gsem</italic>, and <italic>nlcom</italic>), with Python (version 3.14; Python Software Foundation) used for plotting.</p>
      </sec>
    </sec>
    <sec sec-type="results">
      <title>Results</title>
      <sec>
        <title>Study Selection</title>
        <p>Our search identified 761 records from 4 databases: Embase (n=397, 52.2%), Web of Science (n=277, 36.4%), PubMed (n=84, 11%), and Cochrane Library (n=3, 0.4%). After 227 duplicate records were eliminated, 534 records underwent title and abstract screening, of which 483 articles were excluded due to subject mismatch (n=304), reviews or meta-analyses (n=91), conference abstracts (n=63), editorials (n=15), and preprints or non-English papers (n=10). Full texts were retrieved for the remaining 51 documents. Following rigorous full-text assessment, we excluded 12 articles for inappropriate study designs (n=3) and insufficient outcome data (n=9). A total of 39 studies were included [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>-<xref ref-type="bibr" rid="ref57">57</xref>] (<xref rid="figure1" ref-type="fig">Figure 1</xref>; Table S2 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>). Full exclusion reasons are provided in Table S4 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref> [<xref ref-type="bibr" rid="ref63">63</xref>-<xref ref-type="bibr" rid="ref74">74</xref>].</p>
        <fig id="figure1" position="float">
          <label>Figure 1</label>
          <caption>
            <p>Study selection flow diagram.</p>
          </caption>
          <graphic xlink:href="jmir_v28i1e104060_fig1.png" alt-version="no" mimetype="image" position="float" xlink:type="simple"/>
        </fig>
      </sec>
      <sec>
        <title>Study Characteristics</title>
        <sec>
          <title>General Features and Patient Source</title>
          <p>The 39 included studies (31 binary [GBM vs BM] and 8 multiclass [GBM, BM, and PCNSL]) were published between 2019 and 2025 and conducted in China (n=19), South Korea (n=5), the United States (n=5), Spain (n=2), Italy (n=2), and 6 other countries (n=1 each). Studies used single-center (n=22) or multicenter (n=17) datasets; 5 also incorporated public databases, such as the Cancer Imaging Archive (Table S2 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>) [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>-<xref ref-type="bibr" rid="ref57">57</xref>].</p>
        </sec>
        <sec>
          <title>Imaging Inputs, Model Types, and Feature Extraction Approaches</title>
          <p>At the study level, imaging inputs were classified into conventional MRI (n=26; T1-weighted imaging, T2-weighted imaging, fluid-attenuated inversion recovery, and contrast-enhanced T1-weighted imaging) and advanced MRI (n=11; including diffusion, perfusion, susceptibility-sensitive imaging, and quantitative physiological maps) [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>-<xref ref-type="bibr" rid="ref22">22</xref>,<xref ref-type="bibr" rid="ref24">24</xref>-<xref ref-type="bibr" rid="ref40">40</xref>,<xref ref-type="bibr" rid="ref42">42</xref>-<xref ref-type="bibr" rid="ref57">57</xref>]. Dual-energy computed tomography and MRI combined with positron emission tomography were each used in 1 study [<xref ref-type="bibr" rid="ref23">23</xref>,<xref ref-type="bibr" rid="ref41">41</xref>]. MRI-only models using any advanced input were classified as advanced MRI (Table S2 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>) [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>-<xref ref-type="bibr" rid="ref57">57</xref>].</p>
          <p>In total, 25 studies evaluated HCR alone, 7 evaluated DLR alone, and 7 evaluated both approaches. Model types were grouped into neural networks, tree-based and ensemble models, and other classical classifiers (Table S2 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>) [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>-<xref ref-type="bibr" rid="ref57">57</xref>].</p>
        </sec>
        <sec>
          <title>Comparison With Human Experts</title>
          <p>A total of 8 binary classification studies reported unassisted physician diagnostic performance [<xref ref-type="bibr" rid="ref21">21</xref>,<xref ref-type="bibr" rid="ref26">26</xref>,<xref ref-type="bibr" rid="ref34">34</xref>,<xref ref-type="bibr" rid="ref42">42</xref>,<xref ref-type="bibr" rid="ref43">43</xref>,<xref ref-type="bibr" rid="ref49">49</xref>,<xref ref-type="bibr" rid="ref54">54</xref>,<xref ref-type="bibr" rid="ref56">56</xref>]. Assessments were grouped by experience (&gt;10 or ≤10 years). One study reported assessments by a multidisciplinary team of 3 physicians, all with &gt;10 years of experience; these assessments were included in the &gt;10-year group [<xref ref-type="bibr" rid="ref42">42</xref>].</p>
        </sec>
      </sec>
      <sec>
        <title>Assessment of Study Quality</title>
        <p>RQS 2.0 assessment comprised 46 evaluations from 39 studies, including 7 studies that developed separate HCR and DLR models: 32 HCR and 14 DLR evaluations. Mean total scores were 16.8 (SD 4) of a maximum of 56 points (30.1% of the maximum RQS 2.0 score) for HCR and 16.4 (SD 4) of a maximum of 52 points (31.6% of the maximum RQS 2.0 score) for DLR. Mean scores were 14.7 points (45.0% of maximum) for model development (RRLs 1-5) and 2 points (9.0% of maximum) for clinical translation (RRLs 6-9; Table S3 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>) [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>-<xref ref-type="bibr" rid="ref57">57</xref>].</p>
      </sec>
      <sec>
        <title>Meta-Analysis of ML for Binary Classification</title>
        <sec>
          <title>Overall Diagnostic Performance</title>
          <p>To examine generalizability, we stratified the analysis by validation setting (internal vs independent external validation).</p>
          <p>In internal validation cohorts (23 studies; 1188 patients), pooled sensitivity and specificity were 88.9% (95% CI 84.1%-92.4%) and 83.0% (95% CI 76.8%-87.9%), respectively (<xref rid="figure2" ref-type="fig">Figure 2</xref>) [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>,<xref ref-type="bibr" rid="ref23">23</xref>-<xref ref-type="bibr" rid="ref25">25</xref>,<xref ref-type="bibr" rid="ref27">27</xref>-<xref ref-type="bibr" rid="ref29">29</xref>,<xref ref-type="bibr" rid="ref32">32</xref>,<xref ref-type="bibr" rid="ref35">35</xref>,<xref ref-type="bibr" rid="ref39">39</xref>,<xref ref-type="bibr" rid="ref41">41</xref>,<xref ref-type="bibr" rid="ref43">43</xref>,<xref ref-type="bibr" rid="ref44">44</xref>,<xref ref-type="bibr" rid="ref47">47</xref>-<xref ref-type="bibr" rid="ref53">53</xref>,<xref ref-type="bibr" rid="ref55">55</xref>,<xref ref-type="bibr" rid="ref57">57</xref>]. Pooled positive and negative likelihood ratios were 5.24 (95% CI 3.80-7.22) and 0.13 (95% CI 0.09-0.19), respectively. The diagnostic odds ratio was 39.17 (95% CI 23.35-65.71). The Deeks funnel plot asymmetry test did not detect small-study effects (<italic>P</italic>=.36; Figure S1 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>). Assuming a pretest probability of 33%, the Fagan nomogram yielded posttest GBM probabilities of 72.1% after a positive result and 6.2% after a negative result (Figure S2 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>).</p>
          <fig id="figure2" position="float">
            <label>Figure 2</label>
            <caption>
              <p>Forest plots of sensitivity and specificity in internal validation cohorts [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>,<xref ref-type="bibr" rid="ref23">23</xref>-<xref ref-type="bibr" rid="ref25">25</xref>,<xref ref-type="bibr" rid="ref27">27</xref>-<xref ref-type="bibr" rid="ref29">29</xref>,<xref ref-type="bibr" rid="ref32">32</xref>,<xref ref-type="bibr" rid="ref35">35</xref>,<xref ref-type="bibr" rid="ref39">39</xref>,<xref ref-type="bibr" rid="ref41">41</xref>,<xref ref-type="bibr" rid="ref43">43</xref>,<xref ref-type="bibr" rid="ref44">44</xref>,<xref ref-type="bibr" rid="ref47">47</xref>-<xref ref-type="bibr" rid="ref53">53</xref>,<xref ref-type="bibr" rid="ref55">55</xref>,<xref ref-type="bibr" rid="ref57">57</xref>]. BM: brain metastasis; GBM: glioblastoma.</p>
            </caption>
            <graphic xlink:href="jmir_v28i1e104060_fig2.png" alt-version="no" mimetype="image" position="float" xlink:type="simple"/>
          </fig>
          <p>In external validation cohorts (12 studies; 1120 patients), pooled sensitivity and specificity were 83.8% (95% CI 77.4%-88.7%) and 80.7% (95% CI 71.1%-87.7%), respectively (<xref rid="figure3" ref-type="fig">Figure 3</xref>) [<xref ref-type="bibr" rid="ref21">21</xref>,<xref ref-type="bibr" rid="ref24">24</xref>,<xref ref-type="bibr" rid="ref26">26</xref>,<xref ref-type="bibr" rid="ref29">29</xref>,<xref ref-type="bibr" rid="ref34">34</xref>,<xref ref-type="bibr" rid="ref40">40</xref>,<xref ref-type="bibr" rid="ref42">42</xref>,<xref ref-type="bibr" rid="ref43">43</xref>,<xref ref-type="bibr" rid="ref46">46</xref>,<xref ref-type="bibr" rid="ref47">47</xref>,<xref ref-type="bibr" rid="ref54">54</xref>,<xref ref-type="bibr" rid="ref56">56</xref>]. Positive likelihood ratio, negative likelihood ratio, and diagnostic odds ratio were 4.35 (95% CI 2.93-6.45), 0.20 (95% CI 0.15-0.27), and 21.71 (95% CI 13.93-33.83), respectively. The Deeks funnel plot asymmetry test did not detect small-study effects (<italic>P</italic>=.96; Figure S3 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>). Assuming a pretest probability of 33%, the Fagan nomogram yielded posttest GBM probabilities of 68.2% after a positive result and 9.0% after a negative result (Figure S4 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>). Pooled sensitivity and specificity were lower than those in internal validation.</p>
          <fig id="figure3" position="float">
            <label>Figure 3</label>
            <caption>
              <p>Forest plots of sensitivity and specificity in external validation cohorts [<xref ref-type="bibr" rid="ref21">21</xref>,<xref ref-type="bibr" rid="ref24">24</xref>,<xref ref-type="bibr" rid="ref26">26</xref>,<xref ref-type="bibr" rid="ref29">29</xref>,<xref ref-type="bibr" rid="ref34">34</xref>,<xref ref-type="bibr" rid="ref40">40</xref>,<xref ref-type="bibr" rid="ref42">42</xref>,<xref ref-type="bibr" rid="ref43">43</xref>,<xref ref-type="bibr" rid="ref46">46</xref>,<xref ref-type="bibr" rid="ref47">47</xref>,<xref ref-type="bibr" rid="ref54">54</xref>,<xref ref-type="bibr" rid="ref56">56</xref>]. BM: brain metastasis; GBM: glioblastoma.</p>
            </caption>
            <graphic xlink:href="jmir_v28i1e104060_fig3.png" alt-version="no" mimetype="image" position="float" xlink:type="simple"/>
          </fig>
          <p>The AUCs were 0.926 (95% CI 0.889-0.951) for internal validation (<xref rid="figure4" ref-type="fig">Figure 4</xref>A) and 0.893 (95% CI 0.860-0.919) for external validation (<xref rid="figure4" ref-type="fig">Figure 4</xref>B).</p>
          <fig id="figure4" position="float">
            <label>Figure 4</label>
            <caption>
              <p>Summary receiver operating characteristic (SROC) curves by validation setting: (A) internal validation and (B) external validation. AUC: area under the curve.</p>
            </caption>
            <graphic xlink:href="jmir_v28i1e104060_fig4.png" alt-version="no" mimetype="image" position="float" xlink:type="simple"/>
          </fig>
        </sec>
        <sec>
          <title>Subgroup Analyses</title>
          <p>Within the internal validation data, exploratory subgroup analyses included results from cross-validation (n=5) and holdout validation (n=20; Figure S5 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>) [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>,<xref ref-type="bibr" rid="ref23">23</xref>-<xref ref-type="bibr" rid="ref25">25</xref>,<xref ref-type="bibr" rid="ref27">27</xref>-<xref ref-type="bibr" rid="ref29">29</xref>,<xref ref-type="bibr" rid="ref32">32</xref>,<xref ref-type="bibr" rid="ref35">35</xref>,<xref ref-type="bibr" rid="ref39">39</xref>,<xref ref-type="bibr" rid="ref41">41</xref>,<xref ref-type="bibr" rid="ref43">43</xref>,<xref ref-type="bibr" rid="ref44">44</xref>,<xref ref-type="bibr" rid="ref47">47</xref>-<xref ref-type="bibr" rid="ref53">53</xref>,<xref ref-type="bibr" rid="ref55">55</xref>,<xref ref-type="bibr" rid="ref57">57</xref>]. Cross-validation yielded a pooled sensitivity of 93.5% (95% CI 83.2%-97.7%) and a specificity of 85.1% (95% CI 77.8%-90.4%), with an AUC of 0.955 (95% CI 0.895-0.981). Holdout validation yielded a pooled sensitivity of 87.1% (95% CI 82.7%-90.6%) and a specificity of 81.7% (95% CI 75.1%-86.8%), with an AUC of 0.911 (95% CI 0.873-0.939; Figure S6 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>). Bivariate metaregression did not detect a difference in sensitivity and specificity between cross-validation and holdout validation (<italic>P</italic>=.29).</p>
          <p>Model results were grouped into neural networks (n=12), tree-based and ensemble models (n=11), and other classical classifiers (n=12; <xref rid="figure5" ref-type="fig">Figure 5</xref>) [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>,<xref ref-type="bibr" rid="ref21">21</xref>,<xref ref-type="bibr" rid="ref23">23</xref>-<xref ref-type="bibr" rid="ref29">29</xref>,<xref ref-type="bibr" rid="ref32">32</xref>,<xref ref-type="bibr" rid="ref34">34</xref>,<xref ref-type="bibr" rid="ref35">35</xref>,<xref ref-type="bibr" rid="ref39">39</xref>-<xref ref-type="bibr" rid="ref44">44</xref>,<xref ref-type="bibr" rid="ref46">46</xref>-<xref ref-type="bibr" rid="ref57">57</xref>]. Neural networks yielded a pooled sensitivity of 86.7% (95% CI 83.0%-89.7%) and a specificity of 83.8% (95% CI 76.6%-89.1%), with an AUC of 0.870 (95% CI 0.801-0.918). Tree-based and ensemble models yielded a pooled sensitivity of 82.3% (95% CI 69.1%-90.6%) and a specificity of 80.8% (95% CI 69.3%-88.7%), with an AUC of 0.881 (95% CI 0.809-0.928). Other classical classifiers yielded a pooled sensitivity of 87.6% (95% CI 79.8%-92.6%) and a specificity of 82.5% (95% CI 75.6%-87.8%), with an AUC of 0.917 (95% CI 0.878-0.945; Figure S7 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>).</p>
          <fig id="figure5" position="float">
            <label>Figure 5</label>
            <caption>
              <p>Forest plots of sensitivity and specificity by model type: neural networks, tree-based and ensemble models, and other classical classifiers [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>,<xref ref-type="bibr" rid="ref21">21</xref>,<xref ref-type="bibr" rid="ref23">23</xref>-<xref ref-type="bibr" rid="ref29">29</xref>,<xref ref-type="bibr" rid="ref32">32</xref>,<xref ref-type="bibr" rid="ref34">34</xref>,<xref ref-type="bibr" rid="ref35">35</xref>,<xref ref-type="bibr" rid="ref39">39</xref>-<xref ref-type="bibr" rid="ref44">44</xref>,<xref ref-type="bibr" rid="ref46">46</xref>-<xref ref-type="bibr" rid="ref57">57</xref>]. BM: brain metastasis; DLR: deep learning radiomics; GBM: glioblastoma; HCR: handcrafted radiomics.</p>
            </caption>
            <graphic xlink:href="jmir_v28i1e104060_fig5.png" alt-version="no" mimetype="image" position="float" xlink:type="simple"/>
          </fig>
          <p>Imaging inputs were grouped into conventional MRI (n=23) and advanced MRI (n=10; <xref rid="figure6" ref-type="fig">Figure 6</xref>) [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>,<xref ref-type="bibr" rid="ref21">21</xref>,<xref ref-type="bibr" rid="ref24">24</xref>-<xref ref-type="bibr" rid="ref29">29</xref>,<xref ref-type="bibr" rid="ref32">32</xref>,<xref ref-type="bibr" rid="ref34">34</xref>,<xref ref-type="bibr" rid="ref35">35</xref>,<xref ref-type="bibr" rid="ref39">39</xref>,<xref ref-type="bibr" rid="ref40">40</xref>,<xref ref-type="bibr" rid="ref42">42</xref>-<xref ref-type="bibr" rid="ref44">44</xref>,<xref ref-type="bibr" rid="ref46">46</xref>-<xref ref-type="bibr" rid="ref57">57</xref>]. Conventional MRI yielded a pooled sensitivity of 83.2% (95% CI 78.8%-86.9%) and a specificity of 81.5% (95% CI 75.2%-86.5%), with an AUC of 0.893 (95% CI 0.863-0.917). Advanced MRI yielded a pooled sensitivity of 93.3% (95% CI 88.8%-96.0%) and a specificity of 82.1% (95% CI 75.0%-87.5%), with an AUC of 0.911 (95% CI 0.580-0.987; Figure S8 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>).</p>
          <fig id="figure6" position="float">
            <label>Figure 6</label>
            <caption>
              <p>Forest plots of sensitivity and specificity by magnetic resonance imaging (MRI) input: conventional MRI and advanced MRI [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>,<xref ref-type="bibr" rid="ref21">21</xref>,<xref ref-type="bibr" rid="ref24">24</xref>-<xref ref-type="bibr" rid="ref29">29</xref>,<xref ref-type="bibr" rid="ref32">32</xref>,<xref ref-type="bibr" rid="ref34">34</xref>,<xref ref-type="bibr" rid="ref35">35</xref>,<xref ref-type="bibr" rid="ref39">39</xref>,<xref ref-type="bibr" rid="ref40">40</xref>,<xref ref-type="bibr" rid="ref42">42</xref>-<xref ref-type="bibr" rid="ref44">44</xref>,<xref ref-type="bibr" rid="ref46">46</xref>-<xref ref-type="bibr" rid="ref57">57</xref>]. BM: brain metastasis; DLR: deep learning radiomics; GBM: glioblastoma; HCR: handcrafted radiomics.</p>
            </caption>
            <graphic xlink:href="jmir_v28i1e104060_fig6.png" alt-version="no" mimetype="image" position="float" xlink:type="simple"/>
          </fig>
          <p>For the subgroup analysis by feature extraction approach, 25 HCR and 10 DLR model results were summarized separately (<xref rid="figure7" ref-type="fig">Figure 7</xref>) [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>,<xref ref-type="bibr" rid="ref21">21</xref>,<xref ref-type="bibr" rid="ref23">23</xref>-<xref ref-type="bibr" rid="ref29">29</xref>,<xref ref-type="bibr" rid="ref32">32</xref>,<xref ref-type="bibr" rid="ref34">34</xref>,<xref ref-type="bibr" rid="ref35">35</xref>,<xref ref-type="bibr" rid="ref39">39</xref>-<xref ref-type="bibr" rid="ref44">44</xref>,<xref ref-type="bibr" rid="ref46">46</xref>-<xref ref-type="bibr" rid="ref57">57</xref>]. HCR models yielded a pooled sensitivity of 86.2% (95% CI 80.7%-90.4%) and a specificity of 80.8% (95% CI 75.4%-85.2%), with an AUC of 0.899 (95% CI 0.867-0.924). DLR models yielded a pooled sensitivity of 85.4% (95% CI 80.8%-89.0%) and a specificity of 85.9% (95% CI 77.7%-91.4%), with an AUC of 0.869 (95% CI 0.825-0.903; Figure S9 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>).</p>
          <fig id="figure7" position="float">
            <label>Figure 7</label>
            <caption>
              <p>Forest plots of sensitivity and specificity by feature extraction approach: handcrafted radiomics (HCR) and deep learning radiomics (DLR) [<xref ref-type="bibr" rid="ref15">15</xref>,<xref ref-type="bibr" rid="ref20">20</xref>,<xref ref-type="bibr" rid="ref21">21</xref>,<xref ref-type="bibr" rid="ref23">23</xref>-<xref ref-type="bibr" rid="ref29">29</xref>,<xref ref-type="bibr" rid="ref32">32</xref>,<xref ref-type="bibr" rid="ref34">34</xref>,<xref ref-type="bibr" rid="ref35">35</xref>,<xref ref-type="bibr" rid="ref39">39</xref>-<xref ref-type="bibr" rid="ref44">44</xref>,<xref ref-type="bibr" rid="ref46">46</xref>-<xref ref-type="bibr" rid="ref57">57</xref>]. BM: brain metastasis; GBM: glioblastoma.</p>
            </caption>
            <graphic xlink:href="jmir_v28i1e104060_fig7.png" alt-version="no" mimetype="image" position="float" xlink:type="simple"/>
          </fig>
        </sec>
      </sec>
      <sec>
        <title>Human Expert Performance</title>
        <p>There were 29 physician assessments: 12 in the &gt;10-year group and 17 in the ≤10-year group (Figure S10 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>) [<xref ref-type="bibr" rid="ref21">21</xref>,<xref ref-type="bibr" rid="ref26">26</xref>,<xref ref-type="bibr" rid="ref34">34</xref>,<xref ref-type="bibr" rid="ref42">42</xref>,<xref ref-type="bibr" rid="ref43">43</xref>,<xref ref-type="bibr" rid="ref49">49</xref>,<xref ref-type="bibr" rid="ref54">54</xref>,<xref ref-type="bibr" rid="ref56">56</xref>]. Pooled sensitivity and specificity were 84.3% (95% CI 71.6%-91.9%) and 79.7% (95% CI 70.8%-86.4%) in the &gt;10-year group, and 70.8% (95% CI 61.1%-78.9%) and 68.3% (95% CI 56.3%-78.2%) in the ≤10-year group. The AUCs were 0.885 (95% CI 0.752-0.951) and 0.753 (95% CI 0.660-0.828), respectively (Figure S11 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>).</p>
      </sec>
      <sec>
        <title>Multiclass Classification (GBM, BM, and PCNSL)</title>
        <p>Multiclass analyses included 8 studies (Figure S12 in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>) [<xref ref-type="bibr" rid="ref22">22</xref>,<xref ref-type="bibr" rid="ref30">30</xref>,<xref ref-type="bibr" rid="ref31">31</xref>,<xref ref-type="bibr" rid="ref33">33</xref>,<xref ref-type="bibr" rid="ref36">36</xref>-<xref ref-type="bibr" rid="ref38">38</xref>,<xref ref-type="bibr" rid="ref45">45</xref>]. The pooled sensitivity was 84.4% (95% CI 72.4%-91.8%) for GBM, 70.6% (95% CI 54.4%-82.8%) for BM, and 75.0% (95% CI 62.7%-84.3%) for PCNSL. The corresponding specificities were 82.5% (95% CI 70.1%-90.4%), 88.8% (95% CI 81.9%-93.3%), and 94.4% (95% CI 88.4%-97.4%), respectively. Sensitivity differences were 13.8 percentage points for GBM-BM, 9.4 for GBM-PCNSL, and −4.4 for BM-PCNSL (Holm-adjusted <italic>P</italic>=.18 for GBM-BM, <italic>P</italic>=.45 for GBM-PCNSL, and <italic>P</italic>=.51 for BM-PCNSL). Specificity differences were −6.3, −11.9, and −5.6 percentage points for GBM-BM, GBM-PCNSL, and BM-PCNSL, respectively (Holm-adjusted <italic>P</italic>=.16 for GBM-BM, <italic>P</italic>=.15 for GBM-PCNSL, and <italic>P</italic>=.15 for BM-PCNSL).</p>
      </sec>
    </sec>
    <sec sec-type="discussion">
      <title>Discussion</title>
      <sec>
        <title>Summary of Main Findings</title>
        <p>Radiomics-based ML models could discriminate between GBM and BM in the included cohorts, although pooled sensitivity and specificity were lower in external validation than in internal validation. In multiclass tasks, pooled class-specific sensitivity and specificity differed, although the adjusted comparisons were not statistically significant.</p>
        <p>Subgroup analyses showed a higher pooled sensitivity for advanced MRI models than for conventional MRI models, with a similar specificity. Advanced MRI may provide additional microstructural information relevant to tumor infiltration and peritumoral edema [<xref ref-type="bibr" rid="ref39">39</xref>,<xref ref-type="bibr" rid="ref44">44</xref>]. The biological interpretation and reproducibility of these features require further validation. HCR and DLR showed a similar pooled sensitivity, while DLR had a higher pooled specificity. Neural networks and other classical classifiers showed a higher pooled sensitivity than tree-based and ensemble models. These subgroup comparisons were descriptive.</p>
        <p>The internal and external validation estimates were not fully paired, so the observed differences cannot be attributed solely to the validation setting. Differences in patient populations, imaging protocols, and model development may also contribute. Most included studies lacked independent external validation; therefore, their generalizability remains unclear. Further evaluation through multicenter prospective cohorts is needed to determine model performance across clinical settings.</p>
      </sec>
      <sec>
        <title>Comparison With Prior Work</title>
        <p>Building on previous reviews of ML-based discrimination between GBM and BM and the broader classification of brain tumors [<xref ref-type="bibr" rid="ref16">16</xref>,<xref ref-type="bibr" rid="ref17">17</xref>], this review further expanded the research scope by updating the literature search time frame to January 2026 and conducting separate analyses for internal and independent external validation. Furthermore, we examined model type, MRI input, and feature extraction approach in subgroup analyses and summarized physician performance as an exploratory benchmark. These subgroup analyses provide additional information for interpreting pooled diagnostic performance and its generalizability across clinical settings.</p>
        <p>Habibi et al [<xref ref-type="bibr" rid="ref16">16</xref>] used QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies 2) to assess the risk of bias in diagnostic accuracy studies [<xref ref-type="bibr" rid="ref75">75</xref>]. In contrast, we used the RQS 2.0 assessment for radiomics-specific methodological quality and clinical readiness [<xref ref-type="bibr" rid="ref58">58</xref>]. Its criteria addressed reproducibility, robustness, and explainability in both HCR and DLR. RRLs helped distinguish model development from clinical translation, with low clinical translation scores indicating limited evidence for deployment readiness.</p>
      </sec>
      <sec>
        <title>Limitations</title>
        <p>Our meta-analysis is constrained by the methodological quality of the included literature. The included studies primarily used retrospective designs, and nearly half were conducted in China (19/39, 48.7%), which may limit geographic representativeness. The scarcity of independent external validation limited the precision of our analysis and restricted further subgroup analyses.</p>
        <p>Although external validation was prioritized, validation types remained unevenly distributed across subgroups. Differences in pooled diagnostic performance may therefore be partly attributed to validation design, model type, MRI input, and feature extraction approach. Physician assessments provided an exploratory benchmark, with interpretation dependent on reader experience, image quality, and available clinical information. Differences in patient populations and imaging protocols also affect comparability with model estimates. Future comparisons using the same patients and comparable diagnostic information would more clearly assess the performance of models and physicians. Clinical variables, including age and systemic malignancy history, may complement imaging features, although their incremental value requires further evaluation [<xref ref-type="bibr" rid="ref27">27</xref>,<xref ref-type="bibr" rid="ref42">42</xref>,<xref ref-type="bibr" rid="ref57">57</xref>].</p>
        <p>Some 2×2 tables were reconstructed from reported diagnostic metrics and sample sizes, which may introduce additional uncertainty into the pooled estimates. Selecting the best reported model may also lead to overly optimistic estimates. Reference standards also varied. Some BM diagnoses were based on clinical and imaging reference standards rather than histopathology, which may result in misclassifications. Furthermore, heterogeneity in imaging protocols, scanners, feature extraction approaches, and model architectures limits comparability.</p>
      </sec>
      <sec>
        <title>Conclusions</title>
        <p>Radiomics-based ML models could distinguish between GBM and BM in the included cohorts, with lower pooled sensitivity and specificity in external validation. Consequently, the generalizability and clinical utility of such models remain uncertain, owing to methodological limitations and scarce prospective evidence. Further multicenter prospective studies should conduct independent external validation in consecutive patients.</p>
      </sec>
    </sec>
  </body>
  <back>
    <app-group>
      <supplementary-material id="app1">
        <label>Multimedia Appendix 1</label>
        <p>PRISMA 2020 checklist.</p>
        <media xlink:href="jmir_v28i1e104060_app1.docx" xlink:title="DOCX File , 21 KB"/>
      </supplementary-material>
      <supplementary-material id="app2">
        <label>Multimedia Appendix 2</label>
        <p>Search strategies, study characteristics, quality assessments, and supplementary analyses.</p>
        <media xlink:href="jmir_v28i1e104060_app2.docx" xlink:title="DOCX File , 4025 KB"/>
      </supplementary-material>
    </app-group>
    <glossary>
      <title>Abbreviations</title>
      <def-list>
        <def-item>
          <term id="abb1">AUC</term>
          <def>
            <p>area under the curve</p>
          </def>
        </def-item>
        <def-item>
          <term id="abb2">BM</term>
          <def>
            <p>brain metastasis</p>
          </def>
        </def-item>
        <def-item>
          <term id="abb3">DL</term>
          <def>
            <p>deep learning</p>
          </def>
        </def-item>
        <def-item>
          <term id="abb4">DLR</term>
          <def>
            <p>deep learning radiomics</p>
          </def>
        </def-item>
        <def-item>
          <term id="abb5">GBM</term>
          <def>
            <p>glioblastoma</p>
          </def>
        </def-item>
        <def-item>
          <term id="abb6">HCR</term>
          <def>
            <p>handcrafted radiomics</p>
          </def>
        </def-item>
        <def-item>
          <term id="abb7">ML</term>
          <def>
            <p>machine learning</p>
          </def>
        </def-item>
        <def-item>
          <term id="abb8">MRI</term>
          <def>
            <p>magnetic resonance imaging</p>
          </def>
        </def-item>
        <def-item>
          <term id="abb9">PCNSL</term>
          <def>
            <p>primary central nervous system lymphoma</p>
          </def>
        </def-item>
        <def-item>
          <term id="abb10">PIRD</term>
          <def>
            <p>population, index test, reference standard, and diagnosis of interest</p>
          </def>
        </def-item>
        <def-item>
          <term id="abb11">PRISMA</term>
          <def>
            <p>Preferred Reporting Items for Systematic Reviews and Meta-Analyses</p>
          </def>
        </def-item>
        <def-item>
          <term id="abb12">QUADAS-2</term>
          <def>
            <p>Quality Assessment of Diagnostic Accuracy Studies 2</p>
          </def>
        </def-item>
        <def-item>
          <term id="abb13">RQS</term>
          <def>
            <p>Radiomics Quality Score</p>
          </def>
        </def-item>
        <def-item>
          <term id="abb14">RRL</term>
          <def>
            <p>radiomics readiness level</p>
          </def>
        </def-item>
      </def-list>
    </glossary>
    <notes>
      <title>Data Availability</title>
      <p>The full study characteristics and complete Radiomics Quality Score 2.0 scoring are provided in <xref ref-type="supplementary-material" rid="app2">Multimedia Appendix 2</xref>. The extracted data used in the meta-analyses and the analysis code are available from the corresponding author upon reasonable request.</p>
    </notes>
    <notes>
      <title>Funding</title>
      <p>This work was supported by the National Natural Science Foundation of China (grant 82304952), the Beijing Natural Science Foundation (grant L2510078), and the Young Scientist Project of the National Key Research and Development Program of China (grant 2025YFC3510000). The funders provided financial support only and had no role in the study design, data collection, analysis, interpretation, or preparation of the manuscript.</p>
    </notes>
    <fn-group>
      <fn fn-type="con">
        <p>All authors contributed to the study conception and design. CH contributed to writing—original draft preparation. CH, GL, and ZB contributed to writing—review and editing. CH, PL, and SL contributed to conceptualization. YG contributed to methodology. YD and YH contributed to formal analysis. CH, ZB, YD, and YH contributed to investigation. CH, PL, and SL contributed to resources. PL and SL contributed to supervision. All authors commented on previous versions of the manuscript. All authors read and approved the final manuscript. SL is a co-corresponding author and can be reached at shiweili@mail.ccmu.edu.cn.</p>
      </fn>
      <fn fn-type="conflict">
        <p>None declared.</p>
      </fn>
    </fn-group>
    <notes>
      <sec>
        <title>Generative AI Use</title>
        <p>Codex (GPT-6 Astra; OpenAI) was used solely to assist with figure preparation. All authors take full responsibility for the accuracy of the data, the rigor of the analyses, and the integrity of the manuscript.</p>
      </sec>
    </notes>
    <ref-list>
      <ref id="ref1">
        <label>1</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Schaff</surname>
              <given-names>LR</given-names>
            </name>
            <name name-style="western">
              <surname>Mellinghoff</surname>
              <given-names>IK</given-names>
            </name>
          </person-group>
          <article-title>Glioblastoma and other primary brain malignancies in adults: a review</article-title>
          <source>JAMA</source>
          <year>2023</year>
          <month>02</month>
          <day>21</day>
          <volume>329</volume>
          <issue>7</issue>
          <fpage>574</fpage>
          <lpage>87</lpage>
          <pub-id pub-id-type="doi">10.1001/jama.2023.0023</pub-id>
          <pub-id pub-id-type="medline">36809318</pub-id>
          <pub-id pub-id-type="pii">2801673</pub-id>
          <pub-id pub-id-type="pmcid">PMC11445779</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref2">
        <label>2</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Obrador</surname>
              <given-names>E</given-names>
            </name>
            <name name-style="western">
              <surname>Moreno-Murciano</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Oriol-Caballo</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>López-Blanch</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Pineda</surname>
              <given-names>B</given-names>
            </name>
            <name name-style="western">
              <surname>Gutiérrez-Arroyo</surname>
              <given-names>JL</given-names>
            </name>
            <name name-style="western">
              <surname>Loras</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Gonzalez-Bonet</surname>
              <given-names>LG</given-names>
            </name>
            <name name-style="western">
              <surname>Martinez-Cadenas</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Estrela</surname>
              <given-names>JM</given-names>
            </name>
            <name name-style="western">
              <surname>Marqués-Torrejón</surname>
              <given-names>MÁ</given-names>
            </name>
          </person-group>
          <article-title>Glioblastoma therapy: past, present and future</article-title>
          <source>Int J Mol Sci</source>
          <year>2024</year>
          <month>02</month>
          <day>21</day>
          <volume>25</volume>
          <issue>5</issue>
          <fpage>2529</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://www.mdpi.com/resolver?pii=ijms25052529"/>
          </comment>
          <pub-id pub-id-type="doi">10.3390/ijms25052529</pub-id>
          <pub-id pub-id-type="medline">38473776</pub-id>
          <pub-id pub-id-type="pii">ijms25052529</pub-id>
          <pub-id pub-id-type="pmcid">PMC10931797</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref3">
        <label>3</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Gritsch</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Batchelor</surname>
              <given-names>TT</given-names>
            </name>
            <name name-style="western">
              <surname>Gonzalez Castro</surname>
              <given-names>LN</given-names>
            </name>
          </person-group>
          <article-title>Diagnostic, therapeutic, and prognostic implications of the 2021 World Health Organization classification of tumors of the central nervous system</article-title>
          <source>Cancer</source>
          <year>2022</year>
          <month>01</month>
          <day>01</day>
          <volume>128</volume>
          <issue>1</issue>
          <fpage>47</fpage>
          <lpage>58</lpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://onlinelibrary.wiley.com/doi/10.1002/cncr.33918"/>
          </comment>
          <pub-id pub-id-type="doi">10.1002/cncr.33918</pub-id>
          <pub-id pub-id-type="medline">34633681</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref4">
        <label>4</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Achrol</surname>
              <given-names>AS</given-names>
            </name>
            <name name-style="western">
              <surname>Rennert</surname>
              <given-names>RC</given-names>
            </name>
            <name name-style="western">
              <surname>Anders</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Soffietti</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Ahluwalia</surname>
              <given-names>MS</given-names>
            </name>
            <name name-style="western">
              <surname>Nayak</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Peters</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Arvold</surname>
              <given-names>ND</given-names>
            </name>
            <name name-style="western">
              <surname>Harsh</surname>
              <given-names>GR</given-names>
            </name>
            <name name-style="western">
              <surname>Steeg</surname>
              <given-names>PS</given-names>
            </name>
            <name name-style="western">
              <surname>Chang</surname>
              <given-names>SD</given-names>
            </name>
          </person-group>
          <article-title>Brain metastases</article-title>
          <source>Nat Rev Dis Primers</source>
          <year>2019</year>
          <month>01</month>
          <day>17</day>
          <volume>5</volume>
          <issue>1</issue>
          <fpage>5</fpage>
          <pub-id pub-id-type="doi">10.1038/s41572-018-0055-y</pub-id>
          <pub-id pub-id-type="medline">30655533</pub-id>
          <pub-id pub-id-type="pii">10.1038/s41572-018-0055-y</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref5">
        <label>5</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Pellerino</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Garbossa</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Rudà</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Soffietti</surname>
              <given-names>R</given-names>
            </name>
          </person-group>
          <article-title>The role of the neurologist in the diagnosis and treatment of brain metastases and carcinomatous meningitis</article-title>
          <source>Rev Neurol (Paris)</source>
          <year>2023</year>
          <month>06</month>
          <volume>179</volume>
          <issue>5</issue>
          <fpage>464</fpage>
          <lpage>74</lpage>
          <pub-id pub-id-type="doi">10.1016/j.neurol.2023.03.005</pub-id>
          <pub-id pub-id-type="medline">36990824</pub-id>
          <pub-id pub-id-type="pii">S0035-3787(23)00882-2</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref6">
        <label>6</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Malone</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Yang</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Hershman</surname>
              <given-names>DL</given-names>
            </name>
            <name name-style="western">
              <surname>Wright</surname>
              <given-names>JD</given-names>
            </name>
            <name name-style="western">
              <surname>Bruce</surname>
              <given-names>JN</given-names>
            </name>
            <name name-style="western">
              <surname>Neugut</surname>
              <given-names>AI</given-names>
            </name>
          </person-group>
          <article-title>Complications following stereotactic needle biopsy of intracranial tumors</article-title>
          <source>World Neurosurg</source>
          <year>2015</year>
          <month>10</month>
          <volume>84</volume>
          <issue>4</issue>
          <fpage>1084</fpage>
          <lpage>9</lpage>
          <pub-id pub-id-type="doi">10.1016/j.wneu.2015.05.025</pub-id>
          <pub-id pub-id-type="medline">26008141</pub-id>
          <pub-id pub-id-type="pii">S1878-8750(15)00588-4</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref7">
        <label>7</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Louis</surname>
              <given-names>DN</given-names>
            </name>
            <name name-style="western">
              <surname>Perry</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Wesseling</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Brat</surname>
              <given-names>DJ</given-names>
            </name>
            <name name-style="western">
              <surname>Cree</surname>
              <given-names>IA</given-names>
            </name>
            <name name-style="western">
              <surname>Figarella-Branger</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Hawkins</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Ng</surname>
              <given-names>HK</given-names>
            </name>
            <name name-style="western">
              <surname>Pfister</surname>
              <given-names>SM</given-names>
            </name>
            <name name-style="western">
              <surname>Reifenberger</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Soffietti</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>von Deimling</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Ellison</surname>
              <given-names>DW</given-names>
            </name>
          </person-group>
          <article-title>The 2021 WHO Classification of Tumors of the Central Nervous System: a summary</article-title>
          <source>Neuro Oncol</source>
          <year>2021</year>
          <month>08</month>
          <day>02</day>
          <volume>23</volume>
          <issue>8</issue>
          <fpage>1231</fpage>
          <lpage>51</lpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/34185076"/>
          </comment>
          <pub-id pub-id-type="doi">10.1093/neuonc/noab106</pub-id>
          <pub-id pub-id-type="medline">34185076</pub-id>
          <pub-id pub-id-type="pii">6311214</pub-id>
          <pub-id pub-id-type="pmcid">PMC8328013</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref8">
        <label>8</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Chiang</surname>
              <given-names>IC</given-names>
            </name>
            <name name-style="western">
              <surname>Kuo</surname>
              <given-names>YT</given-names>
            </name>
            <name name-style="western">
              <surname>Lu</surname>
              <given-names>CY</given-names>
            </name>
            <name name-style="western">
              <surname>Yeung</surname>
              <given-names>KW</given-names>
            </name>
            <name name-style="western">
              <surname>Lin</surname>
              <given-names>WC</given-names>
            </name>
            <name name-style="western">
              <surname>Sheu</surname>
              <given-names>FO</given-names>
            </name>
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>GC</given-names>
            </name>
          </person-group>
          <article-title>Distinction between high-grade gliomas and solitary metastases using peritumoral 3-T magnetic resonance spectroscopy, diffusion, and perfusion imagings</article-title>
          <source>Neuroradiology</source>
          <year>2004</year>
          <month>08</month>
          <volume>46</volume>
          <issue>8</issue>
          <fpage>619</fpage>
          <lpage>27</lpage>
          <pub-id pub-id-type="doi">10.1007/s00234-004-1246-7</pub-id>
          <pub-id pub-id-type="medline">15243726</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref9">
        <label>9</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Law</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Cha</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Knopp</surname>
              <given-names>EA</given-names>
            </name>
            <name name-style="western">
              <surname>Johnson</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Arnett</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Litt</surname>
              <given-names>AW</given-names>
            </name>
          </person-group>
          <article-title>High-grade gliomas and solitary metastases: differentiation by using perfusion and proton spectroscopic MR imaging</article-title>
          <source>Radiology</source>
          <year>2002</year>
          <month>03</month>
          <volume>222</volume>
          <issue>3</issue>
          <fpage>715</fpage>
          <lpage>21</lpage>
          <pub-id pub-id-type="doi">10.1148/radiol.2223010558</pub-id>
          <pub-id pub-id-type="medline">11867790</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref10">
        <label>10</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Neska-Matuszewska</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Bladowska</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Sąsiadek</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Zimny</surname>
              <given-names>A</given-names>
            </name>
          </person-group>
          <article-title>Differentiation of glioblastoma multiforme, metastases and primary central nervous system lymphomas using multiparametric perfusion and diffusion MR imaging of a tumor core and a peritumoral zone-searching for a practical approach</article-title>
          <source>PLoS One</source>
          <year>2018</year>
          <month>01</month>
          <day>17</day>
          <volume>13</volume>
          <issue>1</issue>
          <fpage>e0191341</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://dx.plos.org/10.1371/journal.pone.0191341"/>
          </comment>
          <pub-id pub-id-type="doi">10.1371/journal.pone.0191341</pub-id>
          <pub-id pub-id-type="medline">29342201</pub-id>
          <pub-id pub-id-type="pii">PONE-D-17-14592</pub-id>
          <pub-id pub-id-type="pmcid">PMC5771619</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref11">
        <label>11</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Lambin</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Leijenaar</surname>
              <given-names>RT</given-names>
            </name>
            <name name-style="western">
              <surname>Deist</surname>
              <given-names>TM</given-names>
            </name>
            <name name-style="western">
              <surname>Peerlings</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>de Jong</surname>
              <given-names>EE</given-names>
            </name>
            <name name-style="western">
              <surname>van Timmeren</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Sanduleanu</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Larue</surname>
              <given-names>RT</given-names>
            </name>
            <name name-style="western">
              <surname>Even</surname>
              <given-names>AJ</given-names>
            </name>
            <name name-style="western">
              <surname>Jochems</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>van Wijk</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Woodruff</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>van Soest</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Lustberg</surname>
              <given-names>T</given-names>
            </name>
            <name name-style="western">
              <surname>Roelofs</surname>
              <given-names>E</given-names>
            </name>
            <name name-style="western">
              <surname>van Elmpt</surname>
              <given-names>W</given-names>
            </name>
            <name name-style="western">
              <surname>Dekker</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Mottaghy</surname>
              <given-names>FM</given-names>
            </name>
            <name name-style="western">
              <surname>Wildberger</surname>
              <given-names>JE</given-names>
            </name>
            <name name-style="western">
              <surname>Walsh</surname>
              <given-names>S</given-names>
            </name>
          </person-group>
          <article-title>Radiomics: the bridge between medical imaging and personalized medicine</article-title>
          <source>Nat Rev Clin Oncol</source>
          <year>2017</year>
          <month>12</month>
          <volume>14</volume>
          <issue>12</issue>
          <fpage>749</fpage>
          <lpage>62</lpage>
          <pub-id pub-id-type="doi">10.1038/nrclinonc.2017.141</pub-id>
          <pub-id pub-id-type="medline">28975929</pub-id>
          <pub-id pub-id-type="pii">nrclinonc.2017.141</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref12">
        <label>12</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Aerts</surname>
              <given-names>HJ</given-names>
            </name>
            <name name-style="western">
              <surname>Velazquez</surname>
              <given-names>ER</given-names>
            </name>
            <name name-style="western">
              <surname>Leijenaar</surname>
              <given-names>RT</given-names>
            </name>
            <name name-style="western">
              <surname>Parmar</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Grossmann</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Carvalho</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Bussink</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Monshouwer</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Haibe-Kains</surname>
              <given-names>B</given-names>
            </name>
            <name name-style="western">
              <surname>Rietveld</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Hoebers</surname>
              <given-names>F</given-names>
            </name>
            <name name-style="western">
              <surname>Rietbergen</surname>
              <given-names>MM</given-names>
            </name>
            <name name-style="western">
              <surname>Leemans</surname>
              <given-names>CR</given-names>
            </name>
            <name name-style="western">
              <surname>Dekker</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Quackenbush</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Gillies</surname>
              <given-names>RJ</given-names>
            </name>
            <name name-style="western">
              <surname>Lambin</surname>
              <given-names>P</given-names>
            </name>
          </person-group>
          <article-title>Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach</article-title>
          <source>Nat Commun</source>
          <year>2014</year>
          <month>06</month>
          <day>03</day>
          <volume>5</volume>
          <fpage>4006</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://doi.org/10.1038/ncomms5006"/>
          </comment>
          <pub-id pub-id-type="doi">10.1038/ncomms5006</pub-id>
          <pub-id pub-id-type="medline">24892406</pub-id>
          <pub-id pub-id-type="pii">ncomms5006</pub-id>
          <pub-id pub-id-type="pmcid">PMC4059926</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref13">
        <label>13</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Lambin</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Rios-Velazquez</surname>
              <given-names>E</given-names>
            </name>
            <name name-style="western">
              <surname>Leijenaar</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Carvalho</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>van Stiphout</surname>
              <given-names>RG</given-names>
            </name>
            <name name-style="western">
              <surname>Granton</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Zegers</surname>
              <given-names>CM</given-names>
            </name>
            <name name-style="western">
              <surname>Gillies</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Boellard</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Dekker</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Aerts</surname>
              <given-names>HJ</given-names>
            </name>
          </person-group>
          <article-title>Radiomics: extracting more information from medical images using advanced feature analysis</article-title>
          <source>Eur J Cancer</source>
          <year>2012</year>
          <month>03</month>
          <volume>48</volume>
          <issue>4</issue>
          <fpage>441</fpage>
          <lpage>6</lpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/22257792"/>
          </comment>
          <pub-id pub-id-type="doi">10.1016/j.ejca.2011.11.036</pub-id>
          <pub-id pub-id-type="medline">22257792</pub-id>
          <pub-id pub-id-type="pii">S0959-8049(11)00999-3</pub-id>
          <pub-id pub-id-type="pmcid">PMC4533986</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref14">
        <label>14</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Rudie</surname>
              <given-names>JD</given-names>
            </name>
            <name name-style="western">
              <surname>Rauschecker</surname>
              <given-names>AM</given-names>
            </name>
            <name name-style="western">
              <surname>Bryan</surname>
              <given-names>RN</given-names>
            </name>
            <name name-style="western">
              <surname>Davatzikos</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Mohan</surname>
              <given-names>S</given-names>
            </name>
          </person-group>
          <article-title>Emerging applications of artificial intelligence in neuro-oncology</article-title>
          <source>Radiology</source>
          <year>2019</year>
          <month>03</month>
          <volume>290</volume>
          <issue>3</issue>
          <fpage>607</fpage>
          <lpage>18</lpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/30667332"/>
          </comment>
          <pub-id pub-id-type="doi">10.1148/radiol.2018181928</pub-id>
          <pub-id pub-id-type="medline">30667332</pub-id>
          <pub-id pub-id-type="pmcid">PMC6389268</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref15">
        <label>15</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Chen</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Ou</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Wang</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Guo</surname>
              <given-names>W</given-names>
            </name>
            <name name-style="western">
              <surname>Ma</surname>
              <given-names>X</given-names>
            </name>
          </person-group>
          <article-title>Radiomics-based machine learning in differentiation between glioblastoma and metastatic brain tumors</article-title>
          <source>Front Oncol</source>
          <year>2019</year>
          <month>08</month>
          <day>22</day>
          <volume>9</volume>
          <fpage>806</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/31508366"/>
          </comment>
          <pub-id pub-id-type="doi">10.3389/fonc.2019.00806</pub-id>
          <pub-id pub-id-type="medline">31508366</pub-id>
          <pub-id pub-id-type="pmcid">PMC6714109</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref16">
        <label>16</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Habibi</surname>
              <given-names>MA</given-names>
            </name>
            <name name-style="western">
              <surname>Omid</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Asgarzade</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Derakhshandeh</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Soltani Farsani</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Tajabadi</surname>
              <given-names>Z</given-names>
            </name>
          </person-group>
          <article-title>Distinguishing glioblastoma from brain metastasis; a systematic review and meta-analysis on the performance of machine learning</article-title>
          <source>Egypt J Neurosurg</source>
          <year>2025</year>
          <month>02</month>
          <day>06</day>
          <volume>40</volume>
          <fpage>26</fpage>
          <pub-id pub-id-type="doi">10.1186/s41984-025-00386-w</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref17">
        <label>17</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Silva Santana</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Borges Camargo Diniz</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Mothé Glioche Gasparri</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Buccaran Canto</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Batista Dos Reis</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Santana Neville Ribeiro</surname>
              <given-names>I</given-names>
            </name>
            <name name-style="western">
              <surname>Gadelha Figueiredo</surname>
              <given-names>E</given-names>
            </name>
            <name name-style="western">
              <surname>Paulo Mota Telles</surname>
              <given-names>J</given-names>
            </name>
          </person-group>
          <article-title>Application of machine learning for classification of brain tumors: a systematic review and meta-analysis</article-title>
          <source>World Neurosurg</source>
          <year>2024</year>
          <month>06</month>
          <volume>186</volume>
          <fpage>204</fpage>
          <lpage>18.e2</lpage>
          <pub-id pub-id-type="doi">10.1016/j.wneu.2024.03.152</pub-id>
          <pub-id pub-id-type="medline">38580093</pub-id>
          <pub-id pub-id-type="pii">S1878-8750(24)00538-2</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref18">
        <label>18</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Page</surname>
              <given-names>MJ</given-names>
            </name>
            <name name-style="western">
              <surname>McKenzie</surname>
              <given-names>JE</given-names>
            </name>
            <name name-style="western">
              <surname>Bossuyt</surname>
              <given-names>PM</given-names>
            </name>
            <name name-style="western">
              <surname>Boutron</surname>
              <given-names>I</given-names>
            </name>
            <name name-style="western">
              <surname>Hoffmann</surname>
              <given-names>TC</given-names>
            </name>
            <name name-style="western">
              <surname>Mulrow</surname>
              <given-names>CD</given-names>
            </name>
            <name name-style="western">
              <surname>Shamseer</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Tetzlaff</surname>
              <given-names>JM</given-names>
            </name>
            <name name-style="western">
              <surname>Akl</surname>
              <given-names>EA</given-names>
            </name>
            <name name-style="western">
              <surname>Brennan</surname>
              <given-names>SE</given-names>
            </name>
            <name name-style="western">
              <surname>Chou</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Glanville</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Grimshaw</surname>
              <given-names>JM</given-names>
            </name>
            <name name-style="western">
              <surname>Hróbjartsson</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Lalu</surname>
              <given-names>MM</given-names>
            </name>
            <name name-style="western">
              <surname>Li</surname>
              <given-names>T</given-names>
            </name>
            <name name-style="western">
              <surname>Loder</surname>
              <given-names>EW</given-names>
            </name>
            <name name-style="western">
              <surname>Mayo-Wilson</surname>
              <given-names>E</given-names>
            </name>
            <name name-style="western">
              <surname>McDonald</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>McGuinness</surname>
              <given-names>LA</given-names>
            </name>
            <name name-style="western">
              <surname>Stewart</surname>
              <given-names>LA</given-names>
            </name>
            <name name-style="western">
              <surname>Thomas</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Tricco</surname>
              <given-names>AC</given-names>
            </name>
            <name name-style="western">
              <surname>Welch</surname>
              <given-names>VA</given-names>
            </name>
            <name name-style="western">
              <surname>Whiting</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Moher</surname>
              <given-names>D</given-names>
            </name>
          </person-group>
          <article-title>The PRISMA 2020 statement: an updated guideline for reporting systematic reviews</article-title>
          <source>BMJ</source>
          <year>2021</year>
          <month>03</month>
          <day>29</day>
          <volume>372</volume>
          <fpage>n71</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://www.bmj.com/lookup/pmidlookup?view=long&amp;pmid=33782057"/>
          </comment>
          <pub-id pub-id-type="doi">10.1136/bmj.n71</pub-id>
          <pub-id pub-id-type="medline">33782057</pub-id>
          <pub-id pub-id-type="pmcid">PMC8005924</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref19">
        <label>19</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>McInnes</surname>
              <given-names>MD</given-names>
            </name>
            <name name-style="western">
              <surname>Moher</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Thombs</surname>
              <given-names>BD</given-names>
            </name>
            <name name-style="western">
              <surname>McGrath</surname>
              <given-names>TA</given-names>
            </name>
            <name name-style="western">
              <surname>Bossuyt</surname>
              <given-names>PM</given-names>
            </name>
            <collab>the PRISMA-DTA Group</collab>
            <name name-style="western">
              <surname>Clifford</surname>
              <given-names>T</given-names>
            </name>
            <name name-style="western">
              <surname>Cohen</surname>
              <given-names>JF</given-names>
            </name>
            <name name-style="western">
              <surname>Deeks</surname>
              <given-names>JJ</given-names>
            </name>
            <name name-style="western">
              <surname>Gatsonis</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Hooft</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Hunt</surname>
              <given-names>HA</given-names>
            </name>
            <name name-style="western">
              <surname>Hyde</surname>
              <given-names>CJ</given-names>
            </name>
            <name name-style="western">
              <surname>Korevaar</surname>
              <given-names>DA</given-names>
            </name>
            <name name-style="western">
              <surname>Leeflang</surname>
              <given-names>MM</given-names>
            </name>
            <name name-style="western">
              <surname>Macaskill</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Reitsma</surname>
              <given-names>JB</given-names>
            </name>
            <name name-style="western">
              <surname>Rodin</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Rutjes</surname>
              <given-names>AW</given-names>
            </name>
            <name name-style="western">
              <surname>Salameh</surname>
              <given-names>JP</given-names>
            </name>
            <name name-style="western">
              <surname>Stevens</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Takwoingi</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Tonelli</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Weeks</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Whiting</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Willis</surname>
              <given-names>BH</given-names>
            </name>
          </person-group>
          <article-title>Preferred reporting items for a systematic review and meta-analysis of diagnostic test accuracy studies: the PRISMA-DTA statement</article-title>
          <source>JAMA</source>
          <year>2018</year>
          <month>01</month>
          <day>23</day>
          <volume>319</volume>
          <issue>4</issue>
          <fpage>388</fpage>
          <lpage>96</lpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://boris-portal.unibe.ch/handle/20.500.12422/158031"/>
          </comment>
          <pub-id pub-id-type="doi">10.1001/jama.2017.19163</pub-id>
          <pub-id pub-id-type="medline">29362800</pub-id>
          <pub-id pub-id-type="pii">2670259</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref20">
        <label>20</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Xia</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Wu</surname>
              <given-names>W</given-names>
            </name>
            <name name-style="western">
              <surname>Tan</surname>
              <given-names>Q</given-names>
            </name>
            <name name-style="western">
              <surname>Gou</surname>
              <given-names>Q</given-names>
            </name>
          </person-group>
          <article-title>Interpretable machine learning models for differentiating glioblastoma from solitary brain metastasis using radiomics</article-title>
          <source>Acad Radiol</source>
          <year>2025</year>
          <month>09</month>
          <volume>32</volume>
          <issue>9</issue>
          <fpage>5388</fpage>
          <lpage>400</lpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://linkinghub.elsevier.com/retrieve/pii/S1076-6332(25)00444-1"/>
          </comment>
          <pub-id pub-id-type="doi">10.1016/j.acra.2025.05.016</pub-id>
          <pub-id pub-id-type="medline">40436711</pub-id>
          <pub-id pub-id-type="pii">S1076-6332(25)00444-1</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref21">
        <label>21</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Wu</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Luan</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Ma</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Chen</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Mu</surname>
              <given-names>F</given-names>
            </name>
            <name name-style="western">
              <surname>Wang</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Liang</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Zhao</surname>
              <given-names>Y</given-names>
            </name>
          </person-group>
          <article-title>Automatic segmentation and classification of glioblastoma and solitary brain metastasis using a deep learning model on multiparametric MRI</article-title>
          <source>J Imaging Inform Med</source>
          <year>2026</year>
          <month>08</month>
          <volume>39</volume>
          <issue>4</issue>
          <fpage>3563</fpage>
          <lpage>72</lpage>
          <pub-id pub-id-type="doi">10.1007/s10278-025-01695-0</pub-id>
          <pub-id pub-id-type="medline">41326876</pub-id>
          <pub-id pub-id-type="pii">10.1007/s10278-025-01695-0</pub-id>
          <pub-id pub-id-type="pmcid">PMC13481604</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref22">
        <label>22</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Sun</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Xu</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Kong</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Wu</surname>
              <given-names>Q</given-names>
            </name>
            <name name-style="western">
              <surname>Wei</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Zhu</surname>
              <given-names>Z</given-names>
            </name>
            <name name-style="western">
              <surname>Li</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Feng</surname>
              <given-names>S</given-names>
            </name>
          </person-group>
          <article-title>Development and validation of a preoperative magnetic resonance imaging-based and machine learning model for the noninvasive differentiation of intracranial glioblastoma, primary central nervous system lymphoma and brain metastases: a retrospective analysis</article-title>
          <source>Front Oncol</source>
          <year>2025</year>
          <month>04</month>
          <day>22</day>
          <volume>15</volume>
          <fpage>1541350</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://doi.org/10.3389/fonc.2025.1541350"/>
          </comment>
          <pub-id pub-id-type="doi">10.3389/fonc.2025.1541350</pub-id>
          <pub-id pub-id-type="medline">40330833</pub-id>
          <pub-id pub-id-type="pmcid">PMC12052887</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref23">
        <label>23</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Nakano</surname>
              <given-names>T</given-names>
            </name>
            <name name-style="western">
              <surname>Hirahara</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Hasegawa</surname>
              <given-names>T</given-names>
            </name>
            <name name-style="western">
              <surname>Kamimura</surname>
              <given-names>K</given-names>
            </name>
            <name name-style="western">
              <surname>Nakajo</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Kamizono</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Takumi</surname>
              <given-names>K</given-names>
            </name>
            <name name-style="western">
              <surname>Nakajo</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Ejima</surname>
              <given-names>F</given-names>
            </name>
            <name name-style="western">
              <surname>Nakanosono</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Yamagishi</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Kanzaki</surname>
              <given-names>F</given-names>
            </name>
            <name name-style="western">
              <surname>Muraoka</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Higa</surname>
              <given-names>N</given-names>
            </name>
            <name name-style="western">
              <surname>Yonezawa</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Kitazono</surname>
              <given-names>I</given-names>
            </name>
            <name name-style="western">
              <surname>Kwon</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Pahn</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Langzam</surname>
              <given-names>E</given-names>
            </name>
            <name name-style="western">
              <surname>Higuchi</surname>
              <given-names>K</given-names>
            </name>
            <name name-style="western">
              <surname>Yoshiura</surname>
              <given-names>T</given-names>
            </name>
          </person-group>
          <article-title>Electron density and effective atomic number as quantitative biomarkers for differentiating malignant brain tumors: an exploratory study with machine learning</article-title>
          <source>Tomography</source>
          <year>2025</year>
          <month>10</month>
          <day>29</day>
          <volume>11</volume>
          <issue>11</issue>
          <fpage>120</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://www.mdpi.com/resolver?pii=tomography11110120"/>
          </comment>
          <pub-id pub-id-type="doi">10.3390/tomography11110120</pub-id>
          <pub-id pub-id-type="medline">41295554</pub-id>
          <pub-id pub-id-type="pii">tomography11110120</pub-id>
          <pub-id pub-id-type="pmcid">PMC12656531</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref24">
        <label>24</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Kong</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Yan</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>K</given-names>
            </name>
            <name name-style="western">
              <surname>Yin</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Ma</surname>
              <given-names>C</given-names>
            </name>
          </person-group>
          <article-title>Multiple deep learning models based on MRI images in discriminating glioblastoma from solitary brain metastases: a multicentre study</article-title>
          <source>BMC Med Imaging</source>
          <year>2025</year>
          <month>05</month>
          <day>19</day>
          <volume>25</volume>
          <issue>1</issue>
          <fpage>171</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://bmcmedimaging.biomedcentral.com/articles/10.1186/s12880-025-01703-3"/>
          </comment>
          <pub-id pub-id-type="doi">10.1186/s12880-025-01703-3</pub-id>
          <pub-id pub-id-type="medline">40389875</pub-id>
          <pub-id pub-id-type="pii">10.1186/s12880-025-01703-3</pub-id>
          <pub-id pub-id-type="pmcid">PMC12090387</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref25">
        <label>25</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Hosseini</surname>
              <given-names>SA</given-names>
            </name>
            <name name-style="western">
              <surname>Servaes</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Hall</surname>
              <given-names>B</given-names>
            </name>
            <name name-style="western">
              <surname>Bhaduri</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Rajan</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Rosa-Neto</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Brem</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Loevner</surname>
              <given-names>LA</given-names>
            </name>
            <name name-style="western">
              <surname>Mohan</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Chawla</surname>
              <given-names>S</given-names>
            </name>
          </person-group>
          <article-title>Quantitative physiologic MRI combined with feature engineering for developing machine learning-based prediction models to distinguish glioblastomas from single brain metastases</article-title>
          <source>Diagnostics (Basel)</source>
          <year>2024</year>
          <month>12</month>
          <day>27</day>
          <volume>15</volume>
          <issue>1</issue>
          <fpage>38</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://www.mdpi.com/resolver?pii=diagnostics15010038"/>
          </comment>
          <pub-id pub-id-type="doi">10.3390/diagnostics15010038</pub-id>
          <pub-id pub-id-type="medline">39795566</pub-id>
          <pub-id pub-id-type="pii">diagnostics15010038</pub-id>
          <pub-id pub-id-type="pmcid">PMC11720653</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref26">
        <label>26</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Chen</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Guo</surname>
              <given-names>W</given-names>
            </name>
            <name name-style="western">
              <surname>Li</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Lin</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Dong</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Qi</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Pu</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Li</surname>
              <given-names>W</given-names>
            </name>
            <name name-style="western">
              <surname>Sun</surname>
              <given-names>B</given-names>
            </name>
          </person-group>
          <article-title>Differentiation of glioblastoma and solitary brain metastasis using brain-tumor interface radiomics features based on MR images: a multicenter study</article-title>
          <source>Acad Radiol</source>
          <year>2025</year>
          <month>07</month>
          <volume>32</volume>
          <issue>7</issue>
          <fpage>4164</fpage>
          <lpage>76</lpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://linkinghub.elsevier.com/retrieve/pii/S1076-6332(25)00308-3"/>
          </comment>
          <pub-id pub-id-type="doi">10.1016/j.acra.2025.04.008</pub-id>
          <pub-id pub-id-type="medline">40280830</pub-id>
          <pub-id pub-id-type="pii">S1076-6332(25)00308-3</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref27">
        <label>27</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Ouyang</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Su</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Yang</surname>
              <given-names>W</given-names>
            </name>
            <name name-style="western">
              <surname>Huang</surname>
              <given-names>B</given-names>
            </name>
          </person-group>
          <article-title>Glioblastoma and solitary brain metastasis: differentiation by integrating demographic-MRI and deep-learning radiomics signatures</article-title>
          <source>J Magn Reson Imaging</source>
          <year>2024</year>
          <month>09</month>
          <volume>60</volume>
          <issue>3</issue>
          <fpage>909</fpage>
          <lpage>20</lpage>
          <pub-id pub-id-type="doi">10.1002/jmri.29123</pub-id>
          <pub-id pub-id-type="medline">37955154</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref28">
        <label>28</label>
        <nlm-citation citation-type="book">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Russo</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Maresca</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Marinelli</surname>
              <given-names>A</given-names>
            </name>
          </person-group>
          <article-title>A cognitive computing tool for identification and classification of brain tumors</article-title>
          <source>2024 IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI)</source>
          <year>2024</year>
          <publisher-loc>New York, NY</publisher-loc>
          <publisher-name>IEEE</publisher-name>
          <fpage>402</fpage>
          <lpage>407</lpage>
        </nlm-citation>
      </ref>
      <ref id="ref29">
        <label>29</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Park</surname>
              <given-names>YW</given-names>
            </name>
            <name name-style="western">
              <surname>Eom</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Kim</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Lim</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Park</surname>
              <given-names>JE</given-names>
            </name>
            <name name-style="western">
              <surname>Kim</surname>
              <given-names>HS</given-names>
            </name>
            <name name-style="western">
              <surname>You</surname>
              <given-names>SC</given-names>
            </name>
            <name name-style="western">
              <surname>Ahn</surname>
              <given-names>SS</given-names>
            </name>
            <name name-style="western">
              <surname>Lee</surname>
              <given-names>SK</given-names>
            </name>
          </person-group>
          <article-title>Differentiation of glioblastoma from solitary brain metastasis using deep ensembles: empirical estimation of uncertainty for clinical reliability</article-title>
          <source>Comput Methods Programs Biomed</source>
          <year>2024</year>
          <month>09</month>
          <volume>254</volume>
          <fpage>108288</fpage>
          <pub-id pub-id-type="doi">10.1016/j.cmpb.2024.108288</pub-id>
          <pub-id pub-id-type="medline">38941861</pub-id>
          <pub-id pub-id-type="pii">S0169-2607(24)00283-9</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref30">
        <label>30</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>J</given-names>
            </name>
          </person-group>
          <article-title>Aided diagnosis model based on deep learning for glioblastoma, solitary brain metastases, and primary central nervous system lymphoma with multi-modal MRI</article-title>
          <source>Biology (Basel)</source>
          <year>2024</year>
          <month>02</month>
          <day>05</day>
          <volume>13</volume>
          <issue>2</issue>
          <fpage>99</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://www.mdpi.com/resolver?pii=biology13020099"/>
          </comment>
          <pub-id pub-id-type="doi">10.3390/biology13020099</pub-id>
          <pub-id pub-id-type="medline">38392317</pub-id>
          <pub-id pub-id-type="pii">biology13020099</pub-id>
          <pub-id pub-id-type="pmcid">PMC10887006</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref31">
        <label>31</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Garcia-Ruiz</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Pons-Escoda</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Grussu</surname>
              <given-names>F</given-names>
            </name>
            <name name-style="western">
              <surname>Naval-Baudin</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Monreal-Aguero</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Hermann</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Karunamuni</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Ligero</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Lopez-Rueda</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Oleaga</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Berbís</surname>
              <given-names>MÁ</given-names>
            </name>
            <name name-style="western">
              <surname>Cabrera-Zubizarreta</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Martin-Noguerol</surname>
              <given-names>T</given-names>
            </name>
            <name name-style="western">
              <surname>Luna</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Seibert</surname>
              <given-names>TM</given-names>
            </name>
            <name name-style="western">
              <surname>Majos</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Perez-Lopez</surname>
              <given-names>R</given-names>
            </name>
          </person-group>
          <article-title>An accessible deep learning tool for voxel-wise classification of brain malignancies from perfusion MRI</article-title>
          <source>Cell Rep Med</source>
          <year>2024</year>
          <month>03</month>
          <day>19</day>
          <volume>5</volume>
          <issue>3</issue>
          <fpage>101464</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://linkinghub.elsevier.com/retrieve/pii/S2666-3791(24)00108-3"/>
          </comment>
          <pub-id pub-id-type="doi">10.1016/j.xcrm.2024.101464</pub-id>
          <pub-id pub-id-type="medline">38471504</pub-id>
          <pub-id pub-id-type="pii">S2666-3791(24)00108-3</pub-id>
          <pub-id pub-id-type="pmcid">PMC10983037</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref32">
        <label>32</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Gao</surname>
              <given-names>E</given-names>
            </name>
            <name name-style="western">
              <surname>Wang</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Bai</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Ma</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Gao</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Qi</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Zhao</surname>
              <given-names>K</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Yan</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Yang</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Zhao</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Cheng</surname>
              <given-names>J</given-names>
            </name>
          </person-group>
          <article-title>Radiomics analysis of diffusion kurtosis imaging: distinguishing between glioblastoma and single brain metastasis</article-title>
          <source>Acad Radiol</source>
          <year>2024</year>
          <month>03</month>
          <volume>31</volume>
          <issue>3</issue>
          <fpage>1036</fpage>
          <lpage>43</lpage>
          <pub-id pub-id-type="doi">10.1016/j.acra.2023.07.023</pub-id>
          <pub-id pub-id-type="medline">37690885</pub-id>
          <pub-id pub-id-type="pii">S1076-6332(23)00392-6</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref33">
        <label>33</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Bathla</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Dhruba</surname>
              <given-names>DD</given-names>
            </name>
            <name name-style="western">
              <surname>Soni</surname>
              <given-names>N</given-names>
            </name>
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Larson</surname>
              <given-names>NB</given-names>
            </name>
            <name name-style="western">
              <surname>Kassmeyer</surname>
              <given-names>BA</given-names>
            </name>
            <name name-style="western">
              <surname>Mohan</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Roberts-Wolfe</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Rathore</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Le</surname>
              <given-names>NH</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Sonka</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Priya</surname>
              <given-names>S</given-names>
            </name>
          </person-group>
          <article-title>AI-based classification of three common malignant tumors in neuro-oncology: a multi-institutional comparison of machine learning and deep learning methods</article-title>
          <source>J Neuroradiol</source>
          <year>2024</year>
          <month>05</month>
          <volume>51</volume>
          <issue>3</issue>
          <fpage>258</fpage>
          <lpage>64</lpage>
          <pub-id pub-id-type="doi">10.1016/j.neurad.2023.08.007</pub-id>
          <pub-id pub-id-type="medline">37652263</pub-id>
          <pub-id pub-id-type="pii">S0150-9861(23)00237-7</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref34">
        <label>34</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Bathla</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Dhruba</surname>
              <given-names>DD</given-names>
            </name>
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Le</surname>
              <given-names>NH</given-names>
            </name>
            <name name-style="western">
              <surname>Soni</surname>
              <given-names>N</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Mohan</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Roberts-Wolfe</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Rathore</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Sonka</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Priya</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Agarwal</surname>
              <given-names>A</given-names>
            </name>
          </person-group>
          <article-title>Differentiation between glioblastoma and metastatic disease on conventional MRI imaging using 3D-convolutional neural networks: model development and validation</article-title>
          <source>Acad Radiol</source>
          <year>2024</year>
          <month>05</month>
          <volume>31</volume>
          <issue>5</issue>
          <fpage>2041</fpage>
          <lpage>9</lpage>
          <pub-id pub-id-type="doi">10.1016/j.acra.2023.10.044</pub-id>
          <pub-id pub-id-type="medline">37977889</pub-id>
          <pub-id pub-id-type="pii">S1076-6332(23)00598-6</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref35">
        <label>35</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Bai</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>He</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Gao</surname>
              <given-names>E</given-names>
            </name>
            <name name-style="western">
              <surname>Yang</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Yang</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Dong</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Ma</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Gao</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Yan</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Cheng</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Zhao</surname>
              <given-names>G</given-names>
            </name>
          </person-group>
          <article-title>High-performance presurgical differentiation of glioblastoma and metastasis by means of multiparametric neurite orientation dispersion and density imaging (NODDI) radiomics</article-title>
          <source>Eur Radiol</source>
          <year>2024</year>
          <month>10</month>
          <volume>34</volume>
          <issue>10</issue>
          <fpage>6616</fpage>
          <lpage>28</lpage>
          <pub-id pub-id-type="doi">10.1007/s00330-024-10686-8</pub-id>
          <pub-id pub-id-type="medline">38485749</pub-id>
          <pub-id pub-id-type="pii">10.1007/s00330-024-10686-8</pub-id>
          <pub-id pub-id-type="pmcid">PMC11399163</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref36">
        <label>36</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Tariciotti</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Caccavella</surname>
              <given-names>VM</given-names>
            </name>
            <name name-style="western">
              <surname>Fiore</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Schisano</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Carrabba</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Borsa</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Giordano</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Palmisciano</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Remoli</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Remore</surname>
              <given-names>LG</given-names>
            </name>
            <name name-style="western">
              <surname>Pluderi</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Caroli</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Conte</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Triulzi</surname>
              <given-names>F</given-names>
            </name>
            <name name-style="western">
              <surname>Locatelli</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Bertani</surname>
              <given-names>G</given-names>
            </name>
          </person-group>
          <article-title>A deep learning model for preoperative differentiation of glioblastoma, brain metastasis and primary central nervous system lymphoma: a pilot study</article-title>
          <source>Front Oncol</source>
          <year>2022</year>
          <month>02</month>
          <day>24</day>
          <volume>12</volume>
          <fpage>816638</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://air.unimi.it/handle/2434/917016"/>
          </comment>
          <pub-id pub-id-type="doi">10.3389/fonc.2022.816638</pub-id>
          <pub-id pub-id-type="medline">35280801</pub-id>
          <pub-id pub-id-type="pmcid">PMC8907851</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref37">
        <label>37</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Joo</surname>
              <given-names>B</given-names>
            </name>
            <name name-style="western">
              <surname>Ahn</surname>
              <given-names>SS</given-names>
            </name>
            <name name-style="western">
              <surname>An</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Han</surname>
              <given-names>K</given-names>
            </name>
            <name name-style="western">
              <surname>Choi</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Kim</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Park</surname>
              <given-names>JE</given-names>
            </name>
            <name name-style="western">
              <surname>Kim</surname>
              <given-names>HS</given-names>
            </name>
            <name name-style="western">
              <surname>Lee</surname>
              <given-names>SK</given-names>
            </name>
          </person-group>
          <article-title>Fully automated radiomics-based machine learning models for multiclass classification of single brain tumors: glioblastoma, lymphoma, and metastasis</article-title>
          <source>J Neuroradiol</source>
          <year>2023</year>
          <month>06</month>
          <volume>50</volume>
          <issue>4</issue>
          <fpage>388</fpage>
          <lpage>95</lpage>
          <pub-id pub-id-type="doi">10.1016/j.neurad.2022.11.001</pub-id>
          <pub-id pub-id-type="medline">36370829</pub-id>
          <pub-id pub-id-type="pii">S0150-9861(22)00166-3</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref38">
        <label>38</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Biggs</surname>
              <given-names>ML</given-names>
            </name>
            <name name-style="western">
              <surname>Wang</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Soni</surname>
              <given-names>N</given-names>
            </name>
            <name name-style="western">
              <surname>Priya</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Bathla</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Canahuate</surname>
              <given-names>G</given-names>
            </name>
          </person-group>
          <article-title>Evaluating autoencoders for dimensionality reduction of MRI-derived radiomics and classification of malignant brain tumors</article-title>
          <source>Sci Stat Database Manag</source>
          <year>2023</year>
          <month>07</month>
          <volume>2023</volume>
          <fpage>1</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/38344216"/>
          </comment>
          <pub-id pub-id-type="doi">10.1145/3603719.3603737</pub-id>
          <pub-id pub-id-type="medline">38344216</pub-id>
          <pub-id pub-id-type="pii">1</pub-id>
          <pub-id pub-id-type="pmcid">PMC10853989</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref39">
        <label>39</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Bai</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>He</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Gao</surname>
              <given-names>E</given-names>
            </name>
            <name name-style="western">
              <surname>Yang</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Yang</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Dong</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Ma</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Gao</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Yan</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Cheng</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Zhao</surname>
              <given-names>G</given-names>
            </name>
          </person-group>
          <article-title>Radiomic texture analysis based on neurite orientation dispersion and density imaging to differentiate glioblastoma from solitary brain metastasis</article-title>
          <source>BMC Cancer</source>
          <year>2023</year>
          <month>12</month>
          <day>14</day>
          <volume>23</volume>
          <issue>1</issue>
          <fpage>1231</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://bmccancer.biomedcentral.com/articles/10.1186/s12885-023-11718-0"/>
          </comment>
          <pub-id pub-id-type="doi">10.1186/s12885-023-11718-0</pub-id>
          <pub-id pub-id-type="medline">38098041</pub-id>
          <pub-id pub-id-type="pii">10.1186/s12885-023-11718-0</pub-id>
          <pub-id pub-id-type="pmcid">PMC10722697</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref40">
        <label>40</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Chen</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Ge</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Hu</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Yang</surname>
              <given-names>K</given-names>
            </name>
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Hu</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Luo</surname>
              <given-names>B</given-names>
            </name>
            <name name-style="western">
              <surname>Yan</surname>
              <given-names>Z</given-names>
            </name>
            <name name-style="western">
              <surname>Song</surname>
              <given-names>K</given-names>
            </name>
            <name name-style="western">
              <surname>Xiao</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Zou</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>W</given-names>
            </name>
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>H</given-names>
            </name>
          </person-group>
          <article-title>Differentiation of malignant brain tumor types using intratumoral and peritumoral radiomic features</article-title>
          <source>Front Oncol</source>
          <year>2022</year>
          <month>07</month>
          <day>28</day>
          <volume>12</volume>
          <fpage>848846</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/35965511"/>
          </comment>
          <pub-id pub-id-type="doi">10.3389/fonc.2022.848846</pub-id>
          <pub-id pub-id-type="medline">35965511</pub-id>
          <pub-id pub-id-type="pmcid">PMC9366472</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref41">
        <label>41</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Yao</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Gao</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Tan</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Yang</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Wen</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Wang</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Xie</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Liao</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Tang</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Chen</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Li</surname>
              <given-names>Y</given-names>
            </name>
          </person-group>
          <article-title>An integrated radiomics model incorporating diffusion-weighted imaging and 18F-FDG PET imaging improves the performance of differentiating glioblastoma from solitary brain metastases</article-title>
          <source>Front Oncol</source>
          <year>2021</year>
          <month>08</month>
          <day>30</day>
          <volume>11</volume>
          <fpage>732704</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/34527594"/>
          </comment>
          <pub-id pub-id-type="doi">10.3389/fonc.2021.732704</pub-id>
          <pub-id pub-id-type="medline">34527594</pub-id>
          <pub-id pub-id-type="pmcid">PMC8435895</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref42">
        <label>42</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Wu</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Liang</surname>
              <given-names>F</given-names>
            </name>
            <name name-style="western">
              <surname>Wei</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Lai</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Lv</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Luo</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Wu</surname>
              <given-names>Z</given-names>
            </name>
            <name name-style="western">
              <surname>Chen</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>W</given-names>
            </name>
            <name name-style="western">
              <surname>Zeng</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Ye</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Wu</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Wei</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Jiang</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Zhen</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Yang</surname>
              <given-names>R</given-names>
            </name>
          </person-group>
          <article-title>A multiparametric MR-based radiofusionomics model with robust capabilities of differentiating glioblastoma multiforme from solitary brain metastasis</article-title>
          <source>Cancers (Basel)</source>
          <year>2021</year>
          <month>11</month>
          <day>18</day>
          <volume>13</volume>
          <issue>22</issue>
          <fpage>5793</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://www.mdpi.com/resolver?pii=cancers13225793"/>
          </comment>
          <pub-id pub-id-type="doi">10.3390/cancers13225793</pub-id>
          <pub-id pub-id-type="medline">34830943</pub-id>
          <pub-id pub-id-type="pii">cancers13225793</pub-id>
          <pub-id pub-id-type="pmcid">PMC8616314</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref43">
        <label>43</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Shin</surname>
              <given-names>I</given-names>
            </name>
            <name name-style="western">
              <surname>Kim</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Ahn</surname>
              <given-names>SS</given-names>
            </name>
            <name name-style="western">
              <surname>Sohn</surname>
              <given-names>B</given-names>
            </name>
            <name name-style="western">
              <surname>Bae</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Park</surname>
              <given-names>JE</given-names>
            </name>
            <name name-style="western">
              <surname>Kim</surname>
              <given-names>HS</given-names>
            </name>
            <name name-style="western">
              <surname>Lee</surname>
              <given-names>SK</given-names>
            </name>
          </person-group>
          <article-title>Development and validation of a deep learning-based model to distinguish glioblastoma from solitary brain metastasis using conventional MR images</article-title>
          <source>AJNR Am J Neuroradiol</source>
          <year>2021</year>
          <month>05</month>
          <volume>42</volume>
          <issue>5</issue>
          <fpage>838</fpage>
          <lpage>44</lpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="http://www.ajnr.org/cgi/pmidlookup?view=long&amp;pmid=33737268"/>
          </comment>
          <pub-id pub-id-type="doi">10.3174/ajnr.A7003</pub-id>
          <pub-id pub-id-type="medline">33737268</pub-id>
          <pub-id pub-id-type="pii">ajnr.A7003</pub-id>
          <pub-id pub-id-type="pmcid">PMC8115383</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref44">
        <label>44</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Samani</surname>
              <given-names>ZR</given-names>
            </name>
            <name name-style="western">
              <surname>Parker</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Wolf</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Hodges</surname>
              <given-names>W</given-names>
            </name>
            <name name-style="western">
              <surname>Brem</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Verma</surname>
              <given-names>R</given-names>
            </name>
          </person-group>
          <article-title>Distinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases</article-title>
          <source>Sci Rep</source>
          <year>2021</year>
          <month>07</month>
          <day>14</day>
          <volume>11</volume>
          <issue>1</issue>
          <fpage>14469</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://doi.org/10.1038/s41598-021-93804-6"/>
          </comment>
          <pub-id pub-id-type="doi">10.1038/s41598-021-93804-6</pub-id>
          <pub-id pub-id-type="medline">34262079</pub-id>
          <pub-id pub-id-type="pii">10.1038/s41598-021-93804-6</pub-id>
          <pub-id pub-id-type="pmcid">PMC8280204</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref45">
        <label>45</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Priya</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Ward</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Le</surname>
              <given-names>NH</given-names>
            </name>
            <name name-style="western">
              <surname>Soni</surname>
              <given-names>N</given-names>
            </name>
            <name name-style="western">
              <surname>Pillenahalli Maheshwarappa</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Monga</surname>
              <given-names>V</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Sonka</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Bathla</surname>
              <given-names>G</given-names>
            </name>
          </person-group>
          <article-title>Radiomic based machine learning performance for a three class problem in neuro-oncology: time to test the waters?</article-title>
          <source>Cancers (Basel)</source>
          <year>2021</year>
          <month>05</month>
          <day>24</day>
          <volume>13</volume>
          <issue>11</issue>
          <fpage>2568</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://www.mdpi.com/resolver?pii=cancers13112568"/>
          </comment>
          <pub-id pub-id-type="doi">10.3390/cancers13112568</pub-id>
          <pub-id pub-id-type="medline">34073840</pub-id>
          <pub-id pub-id-type="pii">cancers13112568</pub-id>
          <pub-id pub-id-type="pmcid">PMC8197204</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref46">
        <label>46</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>Z</given-names>
            </name>
            <name name-style="western">
              <surname>Jiang</surname>
              <given-names>Z</given-names>
            </name>
            <name name-style="western">
              <surname>Meng</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Yang</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Peng</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Li</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Xiao</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>Z</given-names>
            </name>
            <name name-style="western">
              <surname>Zhou</surname>
              <given-names>R</given-names>
            </name>
          </person-group>
          <article-title>Handcrafted and deep learning-based radiomic models can distinguish GBM from brain metastasis</article-title>
          <source>J Oncol</source>
          <year>2021</year>
          <month>06</month>
          <day>03</day>
          <volume>2021</volume>
          <fpage>5518717</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/34188680"/>
          </comment>
          <pub-id pub-id-type="doi">10.1155/2021/5518717</pub-id>
          <pub-id pub-id-type="medline">34188680</pub-id>
          <pub-id pub-id-type="pmcid">PMC8195660</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref47">
        <label>47</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Han</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Niu</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Chen</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Yang</surname>
              <given-names>B</given-names>
            </name>
            <name name-style="western">
              <surname>Chen</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Zheng</surname>
              <given-names>F</given-names>
            </name>
            <name name-style="western">
              <surname>Zang</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Xin</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Chen</surname>
              <given-names>X</given-names>
            </name>
          </person-group>
          <article-title>Differentiation between glioblastoma multiforme and metastasis from the lungs and other sites using combined clinical/routine MRI radiomics</article-title>
          <source>Front Cell Dev Biol</source>
          <year>2021</year>
          <month>08</month>
          <day>26</day>
          <volume>9</volume>
          <fpage>710461</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/34513840"/>
          </comment>
          <pub-id pub-id-type="doi">10.3389/fcell.2021.710461</pub-id>
          <pub-id pub-id-type="medline">34513840</pub-id>
          <pub-id pub-id-type="pmcid">PMC8427511</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref48">
        <label>48</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Demirel</surname>
              <given-names>E</given-names>
            </name>
            <name name-style="western">
              <surname>Gokaslan</surname>
              <given-names>CO</given-names>
            </name>
            <name name-style="western">
              <surname>Dilek</surname>
              <given-names>O</given-names>
            </name>
            <name name-style="western">
              <surname>Ozdemir</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Boyaci</surname>
              <given-names>MG</given-names>
            </name>
            <name name-style="western">
              <surname>Korkmaz</surname>
              <given-names>S</given-names>
            </name>
          </person-group>
          <article-title>Differential diagnosis of glioblastoma and solitary brain metastasis – the success of artificial intelligence models created with radiomics data obtained by automatic segmentation from conventional MRI sequences</article-title>
          <source>Cesk Slov Neurol N</source>
          <year>2021</year>
          <volume>84</volume>
          <issue>6</issue>
          <fpage>541</fpage>
          <lpage>6</lpage>
          <pub-id pub-id-type="doi">10.48095/cccsnn2021541</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref49">
        <label>49</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>de Causans</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Carré</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Roux</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Tauziède-Espariat</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Ammari</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Dezamis</surname>
              <given-names>E</given-names>
            </name>
            <name name-style="western">
              <surname>Dhermain</surname>
              <given-names>F</given-names>
            </name>
            <name name-style="western">
              <surname>Reuzé</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Deutsch</surname>
              <given-names>E</given-names>
            </name>
            <name name-style="western">
              <surname>Oppenheim</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Varlet</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Pallud</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Edjlali</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Robert</surname>
              <given-names>C</given-names>
            </name>
          </person-group>
          <article-title>Development of a machine learning classifier based on radiomic features extracted from post-contrast 3D T1-weighted MR images to distinguish glioblastoma from solitary brain metastasis</article-title>
          <source>Front Oncol</source>
          <year>2021</year>
          <month>07</month>
          <day>13</day>
          <volume>11</volume>
          <fpage>638262</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/34327133"/>
          </comment>
          <pub-id pub-id-type="doi">10.3389/fonc.2021.638262</pub-id>
          <pub-id pub-id-type="medline">34327133</pub-id>
          <pub-id pub-id-type="pmcid">PMC8315001</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref50">
        <label>50</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Baazaoui</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Hubertus</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Maros</surname>
              <given-names>ME</given-names>
            </name>
            <name name-style="western">
              <surname>Mohamed</surname>
              <given-names>SA</given-names>
            </name>
            <name name-style="western">
              <surname>Förster</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Schad</surname>
              <given-names>LR</given-names>
            </name>
            <name name-style="western">
              <surname>Wenz</surname>
              <given-names>H</given-names>
            </name>
          </person-group>
          <article-title>Artificial neural network-derived cerebral metabolic rate of oxygen for differentiating glioblastoma and brain metastasis in MRI: a feasibility study</article-title>
          <source>Appl Sci</source>
          <year>2021</year>
          <month>10</month>
          <day>24</day>
          <volume>11</volume>
          <issue>21</issue>
          <fpage>9928</fpage>
          <pub-id pub-id-type="doi">10.3390/app11219928</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref51">
        <label>51</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Park</surname>
              <given-names>JE</given-names>
            </name>
            <name name-style="western">
              <surname>Kim</surname>
              <given-names>HS</given-names>
            </name>
            <name name-style="western">
              <surname>Lee</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Cheong</surname>
              <given-names>EN</given-names>
            </name>
            <name name-style="western">
              <surname>Shin</surname>
              <given-names>I</given-names>
            </name>
            <name name-style="western">
              <surname>Ahn</surname>
              <given-names>SS</given-names>
            </name>
            <name name-style="western">
              <surname>Shim</surname>
              <given-names>WH</given-names>
            </name>
          </person-group>
          <article-title>Deep-learned time-signal intensity pattern analysis using an autoencoder captures magnetic resonance perfusion heterogeneity for brain tumor differentiation</article-title>
          <source>Sci Rep</source>
          <year>2020</year>
          <month>12</month>
          <day>08</day>
          <volume>10</volume>
          <issue>1</issue>
          <fpage>21485</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://doi.org/10.1038/s41598-020-78485-x"/>
          </comment>
          <pub-id pub-id-type="doi">10.1038/s41598-020-78485-x</pub-id>
          <pub-id pub-id-type="medline">33293590</pub-id>
          <pub-id pub-id-type="pii">10.1038/s41598-020-78485-x</pub-id>
          <pub-id pub-id-type="pmcid">PMC7723041</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref52">
        <label>52</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Ortiz-Ramón</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Ruiz-España</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Mollá-Olmos</surname>
              <given-names>E</given-names>
            </name>
            <name name-style="western">
              <surname>Moratal</surname>
              <given-names>D</given-names>
            </name>
          </person-group>
          <article-title>Glioblastomas and brain metastases differentiation following an MRI texture analysis-based radiomics approach</article-title>
          <source>Phys Med</source>
          <year>2020</year>
          <month>08</month>
          <volume>76</volume>
          <fpage>44</fpage>
          <lpage>54</lpage>
          <pub-id pub-id-type="doi">10.1016/j.ejmp.2020.06.016</pub-id>
          <pub-id pub-id-type="medline">32593138</pub-id>
          <pub-id pub-id-type="pii">S1120-1797(20)30149-6</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref53">
        <label>53</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Dong</surname>
              <given-names>F</given-names>
            </name>
            <name name-style="western">
              <surname>Li</surname>
              <given-names>Q</given-names>
            </name>
            <name name-style="western">
              <surname>Jiang</surname>
              <given-names>B</given-names>
            </name>
            <name name-style="western">
              <surname>Zhu</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Zeng</surname>
              <given-names>Q</given-names>
            </name>
            <name name-style="western">
              <surname>Huang</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Chen</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>M</given-names>
            </name>
          </person-group>
          <article-title>Differentiation of supratentorial single brain metastasis and glioblastoma by using peri-enhancing oedema region-derived radiomic features and multiple classifiers</article-title>
          <source>Eur Radiol</source>
          <year>2020</year>
          <month>05</month>
          <volume>30</volume>
          <issue>5</issue>
          <fpage>3015</fpage>
          <lpage>22</lpage>
          <pub-id pub-id-type="doi">10.1007/s00330-019-06460-w</pub-id>
          <pub-id pub-id-type="medline">32006166</pub-id>
          <pub-id pub-id-type="pii">10.1007/s00330-019-06460-w</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref54">
        <label>54</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Bae</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>An</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Ahn</surname>
              <given-names>SS</given-names>
            </name>
            <name name-style="western">
              <surname>Kim</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Han</surname>
              <given-names>K</given-names>
            </name>
            <name name-style="western">
              <surname>Kim</surname>
              <given-names>SW</given-names>
            </name>
            <name name-style="western">
              <surname>Park</surname>
              <given-names>JE</given-names>
            </name>
            <name name-style="western">
              <surname>Kim</surname>
              <given-names>HS</given-names>
            </name>
            <name name-style="western">
              <surname>Lee</surname>
              <given-names>SK</given-names>
            </name>
          </person-group>
          <article-title>Robust performance of deep learning for distinguishing glioblastoma from single brain metastasis using radiomic features: model development and validation</article-title>
          <source>Sci Rep</source>
          <year>2020</year>
          <month>07</month>
          <day>21</day>
          <volume>10</volume>
          <issue>1</issue>
          <fpage>12110</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://doi.org/10.1038/s41598-020-68980-6"/>
          </comment>
          <pub-id pub-id-type="doi">10.1038/s41598-020-68980-6</pub-id>
          <pub-id pub-id-type="medline">32694637</pub-id>
          <pub-id pub-id-type="pii">10.1038/s41598-020-68980-6</pub-id>
          <pub-id pub-id-type="pmcid">PMC7374174</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref55">
        <label>55</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Qin</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Li</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Liang</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Yao</surname>
              <given-names>W</given-names>
            </name>
          </person-group>
          <article-title>Histogram analysis of absolute cerebral blood volume map can distinguish glioblastoma from solitary brain metastasis</article-title>
          <source>Medicine (Baltimore)</source>
          <year>2019</year>
          <month>10</month>
          <volume>98</volume>
          <issue>42</issue>
          <fpage>e17515</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/31626111"/>
          </comment>
          <pub-id pub-id-type="doi">10.1097/MD.0000000000017515</pub-id>
          <pub-id pub-id-type="medline">31626111</pub-id>
          <pub-id pub-id-type="pii">00005792-201910180-00033</pub-id>
          <pub-id pub-id-type="pmcid">PMC6824738</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref56">
        <label>56</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Qian</surname>
              <given-names>Z</given-names>
            </name>
            <name name-style="western">
              <surname>Li</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Wang</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Li</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Li</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Wang</surname>
              <given-names>K</given-names>
            </name>
            <name name-style="western">
              <surname>Li</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Tang</surname>
              <given-names>K</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Fan</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Chen</surname>
              <given-names>B</given-names>
            </name>
            <name name-style="western">
              <surname>Li</surname>
              <given-names>W</given-names>
            </name>
          </person-group>
          <article-title>Differentiation of glioblastoma from solitary brain metastases using radiomic machine-learning classifiers</article-title>
          <source>Cancer Lett</source>
          <year>2019</year>
          <month>06</month>
          <day>01</day>
          <volume>451</volume>
          <fpage>128</fpage>
          <lpage>35</lpage>
          <pub-id pub-id-type="doi">10.1016/j.canlet.2019.02.054</pub-id>
          <pub-id pub-id-type="medline">30878526</pub-id>
          <pub-id pub-id-type="pii">S0304-3835(19)30154-5</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref57">
        <label>57</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Artzi</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Bressler</surname>
              <given-names>I</given-names>
            </name>
            <name name-style="western">
              <surname>Ben Bashat</surname>
              <given-names>D</given-names>
            </name>
          </person-group>
          <article-title>Differentiation between glioblastoma, brain metastasis and subtypes using radiomics analysis</article-title>
          <source>J Magn Reson Imaging</source>
          <year>2019</year>
          <month>08</month>
          <volume>50</volume>
          <issue>2</issue>
          <fpage>519</fpage>
          <lpage>28</lpage>
          <pub-id pub-id-type="doi">10.1002/jmri.26643</pub-id>
          <pub-id pub-id-type="medline">30635952</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref58">
        <label>58</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Lambin</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Woodruff</surname>
              <given-names>HC</given-names>
            </name>
            <name name-style="western">
              <surname>Mali</surname>
              <given-names>SA</given-names>
            </name>
            <name name-style="western">
              <surname>Zhong</surname>
              <given-names>X</given-names>
            </name>
            <name name-style="western">
              <surname>Kuang</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Lavrova</surname>
              <given-names>E</given-names>
            </name>
            <name name-style="western">
              <surname>Khan</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Lekadir</surname>
              <given-names>K</given-names>
            </name>
            <name name-style="western">
              <surname>Zwanenburg</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Deasy</surname>
              <given-names>J</given-names>
            </name>
            <name name-style="western">
              <surname>Bobowicz</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Marti-Bonmati</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Maidment</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Dumontier</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Kinahan</surname>
              <given-names>PE</given-names>
            </name>
            <name name-style="western">
              <surname>Nobel</surname>
              <given-names>JM</given-names>
            </name>
            <name name-style="western">
              <surname>Amirrajab</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Salahuddin</surname>
              <given-names>Z</given-names>
            </name>
          </person-group>
          <article-title>Radiomics Quality Score 2.0: towards radiomics readiness levels and clinical translation for personalized medicine</article-title>
          <source>Nat Rev Clin Oncol</source>
          <year>2025</year>
          <month>11</month>
          <volume>22</volume>
          <issue>11</issue>
          <fpage>831</fpage>
          <lpage>46</lpage>
          <pub-id pub-id-type="doi">10.1038/s41571-025-01067-1</pub-id>
          <pub-id pub-id-type="medline">40903523</pub-id>
          <pub-id pub-id-type="pii">10.1038/s41571-025-01067-1</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref59">
        <label>59</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Reitsma</surname>
              <given-names>JB</given-names>
            </name>
            <name name-style="western">
              <surname>Glas</surname>
              <given-names>AS</given-names>
            </name>
            <name name-style="western">
              <surname>Rutjes</surname>
              <given-names>AW</given-names>
            </name>
            <name name-style="western">
              <surname>Scholten</surname>
              <given-names>RJ</given-names>
            </name>
            <name name-style="western">
              <surname>Bossuyt</surname>
              <given-names>PM</given-names>
            </name>
            <name name-style="western">
              <surname>Zwinderman</surname>
              <given-names>AH</given-names>
            </name>
          </person-group>
          <article-title>Bivariate analysis of sensitivity and specificity produces informative summary measures in diagnostic reviews</article-title>
          <source>J Clin Epidemiol</source>
          <year>2005</year>
          <month>10</month>
          <volume>58</volume>
          <issue>10</issue>
          <fpage>982</fpage>
          <lpage>90</lpage>
          <pub-id pub-id-type="doi">10.1016/j.jclinepi.2005.02.022</pub-id>
          <pub-id pub-id-type="medline">16168343</pub-id>
          <pub-id pub-id-type="pii">S0895-4356(05)00162-9</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref60">
        <label>60</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Fagan</surname>
              <given-names>TJ</given-names>
            </name>
          </person-group>
          <article-title>Letter: nomogram for Bayes's theorem</article-title>
          <source>N Engl J Med</source>
          <year>1975</year>
          <month>07</month>
          <day>31</day>
          <volume>293</volume>
          <issue>5</issue>
          <fpage>257</fpage>
          <pub-id pub-id-type="doi">10.1056/NEJM197507312930513</pub-id>
          <pub-id pub-id-type="medline">1143310</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref61">
        <label>61</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Deeks</surname>
              <given-names>JJ</given-names>
            </name>
            <name name-style="western">
              <surname>Macaskill</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Irwig</surname>
              <given-names>L</given-names>
            </name>
          </person-group>
          <article-title>The performance of tests of publication bias and other sample size effects in systematic reviews of diagnostic test accuracy was assessed</article-title>
          <source>J Clin Epidemiol</source>
          <year>2005</year>
          <month>09</month>
          <volume>58</volume>
          <issue>9</issue>
          <fpage>882</fpage>
          <lpage>93</lpage>
          <pub-id pub-id-type="doi">10.1016/j.jclinepi.2005.01.016</pub-id>
          <pub-id pub-id-type="medline">16085191</pub-id>
          <pub-id pub-id-type="pii">S0895-4356(05)00142-3</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref62">
        <label>62</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Lin</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Chu</surname>
              <given-names>H</given-names>
            </name>
          </person-group>
          <article-title>Meta-analysis of proportions using generalized linear mixed models</article-title>
          <source>Epidemiology</source>
          <year>2020</year>
          <month>09</month>
          <volume>31</volume>
          <issue>5</issue>
          <fpage>713</fpage>
          <lpage>7</lpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/32657954"/>
          </comment>
          <pub-id pub-id-type="doi">10.1097/EDE.0000000000001232</pub-id>
          <pub-id pub-id-type="medline">32657954</pub-id>
          <pub-id pub-id-type="pii">00001648-202009000-00016</pub-id>
          <pub-id pub-id-type="pmcid">PMC7398826</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref63">
        <label>63</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Cepeda</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>García-García</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Arrese</surname>
              <given-names>I</given-names>
            </name>
            <name name-style="western">
              <surname>Fernández-Pérez</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Velasco-Casares</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Fajardo-Puentes</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Zamora</surname>
              <given-names>T</given-names>
            </name>
            <name name-style="western">
              <surname>Sarabia</surname>
              <given-names>R</given-names>
            </name>
          </person-group>
          <article-title>Comparison of intraoperative ultrasound B-mode and strain elastography for the differentiation of glioblastomas from solitary brain metastases. An automated deep learning approach for image analysis</article-title>
          <source>Front Oncol</source>
          <year>2020</year>
          <volume>10</volume>
          <fpage>590756</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/33604286"/>
          </comment>
          <pub-id pub-id-type="doi">10.3389/fonc.2020.590756</pub-id>
          <pub-id pub-id-type="medline">33604286</pub-id>
          <pub-id pub-id-type="pmcid">PMC7884775</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref64">
        <label>64</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Meier</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Pahud de Mortanges</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Wiest</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Knecht</surname>
              <given-names>U</given-names>
            </name>
          </person-group>
          <article-title>Exploratory analysis of qualitative MR imaging features for the differentiation of glioblastoma and brain metastases</article-title>
          <source>Front Oncol</source>
          <year>2020</year>
          <volume>10</volume>
          <fpage>581037</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/33425734"/>
          </comment>
          <pub-id pub-id-type="doi">10.3389/fonc.2020.581037</pub-id>
          <pub-id pub-id-type="medline">33425734</pub-id>
          <pub-id pub-id-type="pmcid">PMC7793795</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref65">
        <label>65</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Pomohaci</surname>
              <given-names>D</given-names>
            </name>
            <name name-style="western">
              <surname>Marciuc</surname>
              <given-names>EA</given-names>
            </name>
            <name name-style="western">
              <surname>Dobrovăț</surname>
              <given-names>BI</given-names>
            </name>
            <name name-style="western">
              <surname>Popescu</surname>
              <given-names>MR</given-names>
            </name>
            <name name-style="western">
              <surname>Istrate</surname>
              <given-names>AC</given-names>
            </name>
            <name name-style="western">
              <surname>Onicescu Oniciuc</surname>
              <given-names>OM</given-names>
            </name>
            <name name-style="western">
              <surname>Chirica</surname>
              <given-names>SI</given-names>
            </name>
            <name name-style="western">
              <surname>Chirica</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Haba</surname>
              <given-names>D</given-names>
            </name>
          </person-group>
          <article-title>Artificial intelligence-based MRI segmentation for the differential diagnosis of single brain metastasis and glioblastoma</article-title>
          <source>Diagnostics (Basel)</source>
          <year>2025</year>
          <month>09</month>
          <day>05</day>
          <volume>15</volume>
          <issue>17</issue>
          <fpage>2248</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://www.mdpi.com/resolver?pii=diagnostics15172248"/>
          </comment>
          <pub-id pub-id-type="doi">10.3390/diagnostics15172248</pub-id>
          <pub-id pub-id-type="medline">40941735</pub-id>
          <pub-id pub-id-type="pii">diagnostics15172248</pub-id>
          <pub-id pub-id-type="pmcid">PMC12428284</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref66">
        <label>66</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Bijari</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Jahanbakhshi</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Hajishafiezahramini</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Abdolmaleki</surname>
              <given-names>P</given-names>
            </name>
          </person-group>
          <article-title>Differentiating glioblastoma multiforme from brain metastases using multidimensional radiomics features derived from MRI and multiple machine learning models</article-title>
          <source>Biomed Res Int</source>
          <year>2022</year>
          <volume>2022</volume>
          <fpage>2016006</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/36212721"/>
          </comment>
          <pub-id pub-id-type="doi">10.1155/2022/2016006</pub-id>
          <pub-id pub-id-type="medline">36212721</pub-id>
          <pub-id pub-id-type="pmcid">PMC9534611</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref67">
        <label>67</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Tateishi</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Nakaura</surname>
              <given-names>T</given-names>
            </name>
            <name name-style="western">
              <surname>Kitajima</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Uetani</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Nakagawa</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Inoue</surname>
              <given-names>T</given-names>
            </name>
            <name name-style="western">
              <surname>Kuroda</surname>
              <given-names>JI</given-names>
            </name>
            <name name-style="western">
              <surname>Mukasa</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Yamashita</surname>
              <given-names>Y</given-names>
            </name>
          </person-group>
          <article-title>An initial experience of machine learning based on multi-sequence texture parameters in magnetic resonance imaging to differentiate glioblastoma from brain metastases</article-title>
          <source>J Neurol Sci</source>
          <year>2020</year>
          <month>03</month>
          <day>15</day>
          <volume>410</volume>
          <fpage>116514</fpage>
          <pub-id pub-id-type="doi">10.1016/j.jns.2019.116514</pub-id>
          <pub-id pub-id-type="medline">31869660</pub-id>
          <pub-id pub-id-type="pii">S0022-510X(19)30446-0</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref68">
        <label>68</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>An</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Park</surname>
              <given-names>YW</given-names>
            </name>
            <name name-style="western">
              <surname>Ahn</surname>
              <given-names>SS</given-names>
            </name>
            <name name-style="western">
              <surname>Han</surname>
              <given-names>K</given-names>
            </name>
            <name name-style="western">
              <surname>Kim</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Lee</surname>
              <given-names>SK</given-names>
            </name>
          </person-group>
          <article-title>Radiomics machine learning study with a small sample size: single random training-test set split may lead to unreliable results</article-title>
          <source>PLoS One</source>
          <year>2021</year>
          <volume>16</volume>
          <issue>8</issue>
          <fpage>e0256152</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://dx.plos.org/10.1371/journal.pone.0256152"/>
          </comment>
          <pub-id pub-id-type="doi">10.1371/journal.pone.0256152</pub-id>
          <pub-id pub-id-type="medline">34383858</pub-id>
          <pub-id pub-id-type="pii">PONE-D-21-06656</pub-id>
          <pub-id pub-id-type="pmcid">PMC8360533</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref69">
        <label>69</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Bathla</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Zamboni</surname>
              <given-names>CG</given-names>
            </name>
            <name name-style="western">
              <surname>Larson</surname>
              <given-names>N</given-names>
            </name>
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Zhang</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Lee</surname>
              <given-names>NH</given-names>
            </name>
            <name name-style="western">
              <surname>Agarwal</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Soni</surname>
              <given-names>N</given-names>
            </name>
            <name name-style="western">
              <surname>Sonka</surname>
              <given-names>M</given-names>
            </name>
          </person-group>
          <article-title>Radiomics-based differentiation of glioblastoma and metastatic disease: impact of different T1-contrast-enhanced sequences on radiomics features and model performance</article-title>
          <source>AJNR Am J Neuroradiol</source>
          <year>2025</year>
          <month>02</month>
          <day>03</day>
          <volume>46</volume>
          <issue>2</issue>
          <fpage>321</fpage>
          <lpage>9</lpage>
          <pub-id pub-id-type="doi">10.3174/ajnr.A8470</pub-id>
          <pub-id pub-id-type="medline">39179298</pub-id>
          <pub-id pub-id-type="pii">ajnr.A8470</pub-id>
          <pub-id pub-id-type="pmcid">PMC11878985</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref70">
        <label>70</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Parvaze</surname>
              <given-names>PS</given-names>
            </name>
            <name name-style="western">
              <surname>Bhattacharjee</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Verma</surname>
              <given-names>YK</given-names>
            </name>
            <name name-style="western">
              <surname>Singh</surname>
              <given-names>RK</given-names>
            </name>
            <name name-style="western">
              <surname>Yadav</surname>
              <given-names>V</given-names>
            </name>
            <name name-style="western">
              <surname>Singh</surname>
              <given-names>A</given-names>
            </name>
            <name name-style="western">
              <surname>Khanna</surname>
              <given-names>G</given-names>
            </name>
            <name name-style="western">
              <surname>Ahlawat</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Trivedi</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Patir</surname>
              <given-names>R</given-names>
            </name>
            <name name-style="western">
              <surname>Vaishya</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Shah</surname>
              <given-names>TJ</given-names>
            </name>
            <name name-style="western">
              <surname>Gupta</surname>
              <given-names>RK</given-names>
            </name>
          </person-group>
          <article-title>Quantification of radiomics features of peritumoral vasogenic edema extracted from fluid-attenuated inversion recovery images in glioblastoma and isolated brain metastasis, using T1-dynamic contrast-enhanced perfusion analysis</article-title>
          <source>NMR Biomed</source>
          <year>2023</year>
          <month>05</month>
          <volume>36</volume>
          <issue>5</issue>
          <fpage>e4884</fpage>
          <pub-id pub-id-type="doi">10.1002/nbm.4884</pub-id>
          <pub-id pub-id-type="medline">36453877</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref71">
        <label>71</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Csutak</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Ștefan</surname>
              <given-names>PA</given-names>
            </name>
            <name name-style="western">
              <surname>Lenghel</surname>
              <given-names>LM</given-names>
            </name>
            <name name-style="western">
              <surname>Moroșanu</surname>
              <given-names>CO</given-names>
            </name>
            <name name-style="western">
              <surname>Lupean</surname>
              <given-names>RA</given-names>
            </name>
            <name name-style="western">
              <surname>Șimonca</surname>
              <given-names>L</given-names>
            </name>
            <name name-style="western">
              <surname>Mihu</surname>
              <given-names>CM</given-names>
            </name>
            <name name-style="western">
              <surname>Lebovici</surname>
              <given-names>A</given-names>
            </name>
          </person-group>
          <article-title>Differentiating high-grade gliomas from brain metastases at magnetic resonance: the role of texture analysis of the peritumoral zone</article-title>
          <source>Brain Sci</source>
          <year>2020</year>
          <month>09</month>
          <day>16</day>
          <volume>10</volume>
          <issue>9</issue>
          <fpage>638</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://www.mdpi.com/resolver?pii=brainsci10090638"/>
          </comment>
          <pub-id pub-id-type="doi">10.3390/brainsci10090638</pub-id>
          <pub-id pub-id-type="medline">32947822</pub-id>
          <pub-id pub-id-type="pii">brainsci10090638</pub-id>
          <pub-id pub-id-type="pmcid">PMC7565295</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref72">
        <label>72</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Kopřivová</surname>
              <given-names>T</given-names>
            </name>
            <name name-style="western">
              <surname>Dostál</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Jůza</surname>
              <given-names>T</given-names>
            </name>
            <name name-style="western">
              <surname>Vybíhal</surname>
              <given-names>V</given-names>
            </name>
            <name name-style="western">
              <surname>Ovesná</surname>
              <given-names>P</given-names>
            </name>
            <name name-style="western">
              <surname>Kozubek</surname>
              <given-names>M</given-names>
            </name>
            <name name-style="western">
              <surname>Keřkovský</surname>
              <given-names>M</given-names>
            </name>
          </person-group>
          <article-title>Differentiating brain metastasis and high-grade glioma using multi-b value diffusion MRI and tumor volumetry</article-title>
          <source>J Neuroimaging</source>
          <year>2025</year>
          <volume>35</volume>
          <issue>6</issue>
          <fpage>e70103</fpage>
          <pub-id pub-id-type="doi">10.1111/jon.70103</pub-id>
          <pub-id pub-id-type="medline">41229073</pub-id>
          <pub-id pub-id-type="pmcid">PMC12612568</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref73">
        <label>73</label>
        <nlm-citation citation-type="book">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Hong</surname>
              <given-names>C</given-names>
            </name>
            <name name-style="western">
              <surname>Wang</surname>
              <given-names>H</given-names>
            </name>
            <name name-style="western">
              <surname>Wu</surname>
              <given-names>Z</given-names>
            </name>
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>Z</given-names>
            </name>
            <name name-style="western">
              <surname>Lv</surname>
              <given-names>J</given-names>
            </name>
          </person-group>
          <article-title>FoTNet: an effective deep learning model for preoperative differentiation of common malignant brain tumors</article-title>
          <source>2024 IEEE International Conference on Medical Artificial Intelligence (MedAI)</source>
          <year>2024</year>
          <publisher-loc>New York, NY</publisher-loc>
          <publisher-name>IEEE</publisher-name>
        </nlm-citation>
      </ref>
      <ref id="ref74">
        <label>74</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Huang</surname>
              <given-names>Y</given-names>
            </name>
            <name name-style="western">
              <surname>Huang</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Liu</surname>
              <given-names>Z</given-names>
            </name>
          </person-group>
          <article-title>Multi-task learning-based feature selection and classification models for glioblastoma and solitary brain metastases</article-title>
          <source>Front Oncol</source>
          <year>2022</year>
          <volume>12</volume>
          <fpage>1000471</fpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://europepmc.org/abstract/MED/36212457"/>
          </comment>
          <pub-id pub-id-type="doi">10.3389/fonc.2022.1000471</pub-id>
          <pub-id pub-id-type="medline">36212457</pub-id>
          <pub-id pub-id-type="pmcid">PMC9533336</pub-id>
        </nlm-citation>
      </ref>
      <ref id="ref75">
        <label>75</label>
        <nlm-citation citation-type="journal">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Whiting</surname>
              <given-names>PF</given-names>
            </name>
            <name name-style="western">
              <surname>Rutjes</surname>
              <given-names>AW</given-names>
            </name>
            <name name-style="western">
              <surname>Westwood</surname>
              <given-names>ME</given-names>
            </name>
            <name name-style="western">
              <surname>Mallett</surname>
              <given-names>S</given-names>
            </name>
            <name name-style="western">
              <surname>Deeks</surname>
              <given-names>JJ</given-names>
            </name>
            <name name-style="western">
              <surname>Reitsma</surname>
              <given-names>JB</given-names>
            </name>
            <name name-style="western">
              <surname>Leeflang</surname>
              <given-names>MM</given-names>
            </name>
            <name name-style="western">
              <surname>Sterne</surname>
              <given-names>JA</given-names>
            </name>
            <name name-style="western">
              <surname>Bossuyt</surname>
              <given-names>PM</given-names>
            </name>
          </person-group>
          <article-title>QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies</article-title>
          <source>Ann Intern Med</source>
          <year>2011</year>
          <month>10</month>
          <day>18</day>
          <volume>155</volume>
          <issue>8</issue>
          <fpage>529</fpage>
          <lpage>36</lpage>
          <comment>
            <ext-link ext-link-type="uri" xlink:type="simple" xlink:href="https://www.acpjournals.org/doi/10.7326/0003-4819-155-8-201110180-00009?url_ver=Z39.88-2003&amp;rfr_id=ori:rid:crossref.org&amp;rfr_dat=cr_pub  0pubmed"/>
          </comment>
          <pub-id pub-id-type="doi">10.7326/0003-4819-155-8-201110180-00009</pub-id>
          <pub-id pub-id-type="medline">22007046</pub-id>
          <pub-id pub-id-type="pii">155/8/529</pub-id>
        </nlm-citation>
      </ref>
    </ref-list>
  </back>
</article>
