Before starting this systematic review and meta-analysis, we registered a protocol on the PROSPERO website. This review adhered to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) and PRISMA-DTA (PRISMA of Diagnostic Test Accuracy) checklists [19,20].

We included studies using AI algorithms to detect, classify, identify, segment, quantify, or predict GA secondary to AMD from CFP, OCT, OCT angiography, FAF, or NIR. The data were from participants, with or without symptoms, who were diagnosed with GA (or cRORA) secondary to nonexudative AMD. Study designs were not restricted; multicenter or single-center, prospective or retrospective, post hoc analysis, clinical study, or model development studies were all accepted. Eyes with neovascular complications or macular atrophy from causes other than AMD, any previous anti-vascular endothelial growth factor treatment, any confounding retinopathy, or poor image quality were excluded.

Two consecutive searches were conducted on PubMed, Embase, Web of Science, Scopus, Cochrane Library, and CINAHL. Because this review required the extraction of baseline data and items, considering the completeness of the data, we did not conduct any in press or print source searches and excluded conference proceedings and similar materials. The initial search was completed from the date of entry to December 1, 2024; the updated search, from December 1, 2024, to October 5, 2025. We used a search strategy for patient (GA) and index tests (AI and retinal images) that had been used in previous Cochrane Review without any search peer review process [21]. There were no restrictions on the date of publication. The language was limited to English. In Multimedia Appendix 1, detailed search strategies for each database are provided. During this process, no filters were used. During the search process, we adhered to the PRISMA-S (Preferred Reporting Items for Systematic reviews and Meta-Analyses literature search extension) reporting guidelines [22].

All relevant literature was imported into EndNote (version 20; Clarivate Analytics) software, and literature screening was conducted independently by 2 researchers (NS and JL) who specialize in ophthalmology. Duplicates were removed from the software, and the titles and abstracts of the literature were reviewed to identify those relevant to the topic. Finally, the full texts were downloaded and examined, leading to the selection of literature that met the inclusion criteria. In cases of inconsistencies in the final inclusion decisions made by the 2 researchers, a third professional (LL) was consulted to resolve the dispute.

Using standardized data items, the data were extracted independently from the included studies by 2 researchers (NS and JL). A third review author (LL) confirmed or adjudicated any discrepancies through group discussion. We retrieved the following data items: (1) study characteristics (author, year, study design, region, and theme), (2) dataset characteristics (databases, source of databases, training/validation/testing ratio, patient number, number of images or volumes, scan number, mean age, clinical registration number, and model evaluation method), (3) image and algorithm characteristics (devices, metrics, image modality, image resolution, and AI algorithms), (4) performance metrics (outcomes, performance of models, ground truth, and performance of the ophthalmologists), and (5) main results. All the information was retrieved from the main text and the tables provided in Multimedia Appendix 2. Therefore, we did not seek additional data by contacting the authors or experts. In some studies, the authors reported multiple sets of performance data based on a subset of a single dataset. For example, they may have reported results such as sensitivity, specificity, accuracy, and so forth, conducted on the cross-validation set, the test set, or the development set. We referred to the relevant literature to select the optimal set of test performance results [21]. However, when the primary study provided performance results based on a single test, the development dataset was used to train the AI model, and an external validation set ultimately was used to determine the performance of the optimal model. We extracted the external validation set performance data [23].

We worked in pairs to assess the risk of bias and the applicability of the studies, which involved detection, classification, identification, segmentation, and quantification using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS)-AI [24] and the modified QUADAS-2 tool [25], while predictive studies used the Prediction Model Risk of Bias Assessment Tool (PROBAST) [26].

In the current context, QUADAS-AI has not yet established a complete specification of items. Therefore, we referenced the examples provided by QUASAS-AI and the published literature to compile the revised QUADAS-AI items, which included 4 domains and 9 leading questions (Table S4 in Multimedia Appendix 2). The PROBAST tool comprises participants, predictors, outcomes, and analysis, containing 20 signaling questions across 4 domains (Table S5 in Multimedia Appendix 2). We also evaluated the applicability of the study based on the leading or signaling questions in the first 3 domains. A study with “yes” answers to all index questions was considered to have a low risk of bias. If the answer to any of the informational questions was “no,” there was a potential for bias, leading the authors to rate the risk of bias as high. “Indeterminate” grades were applied when detailed content was not provided in the literature, making it difficult for the evaluator to reach a judgment. They were used only when the reported data were insufficient. Throughout the process, disagreements between the 2 reviewers (NS and JL) were resolved by consulting the senior reviewer (LL).

As very few studies reported the number of true positives, true negatives, false positives, and false negatives, we restricted the quantitative analysis to determine the diagnostic accuracy of AI as a triaging tool for GA secondary to nonexudative AMD. However, a meta-analysis was not performed due to significant methodological heterogeneity across studies, arising from diverse AI architectures, imaging modalities, outcome metrics, and validation protocols. Instead, a systematic review was performed to qualitatively summarize performance trends. This approach allowed for a comprehensive evaluation of the AI capabilities in the detection and management of GA via noninvasive images.

A total of 979 records related to the topic of this systematic review were searched across 6 different databases using a combination of subject terms and free-text terms. After removing duplicates, 335 records remained and were examined for titles and abstracts. Excluding studies not relevant to the research topic resulted in 200 reports. The full texts were then downloaded and reviewed in detail based on the eligibility criteria for the studies. In the final qualitative analysis, 41 studies were included. Of these, 10 focusing on GA diagnosis, 20 on GA assessment and progression, and 11 on GA prediction. Figure 1 presents the detailed flow diagram of the literature selection.

Ten of the 41 included studies focused on AI-based detection of GA using noninvasive retinal images (Table S1 in Multimedia Appendix 2). As listed in Table 1, the studies were published from 2018 to 2025. Four of the studies [27-30] focused on model development, 3 [31-33] were retrospective studies, and 3 [34-36] were prospective studies (1 multicenter cohort study, 1 multicenter and low-interventional clinical study, and 1 clinical study). Geographically, half were from the United States, with others from Israel, Italy, Switzerland, Germany, and a multicenter European collaboration. The studies addressed several detection-related tasks: 5 focused solely on GA detection [27-29,34,35], 2 covered detection and classification [30,33], and others integrated detection with quantification or segmentation [31,32,36].

Dataset configurations varied: 6 studies used training, validation, and test sets [30-33,35,36]; 3 used only training and test sets [27,28,34]; and 1 included a tuning set [29]. Collectively, these studies involved at least 7132 participants, with ages ranging from 50 to 85 years. Three studies were registered with ClinicalTrials.gov (NCT00734487, NCT01790802, and NCT03349801) [28,29,36]. Cross-validation methods included 5-fold (40% of studies) [27,29,32,34], 10-fold (20%) [28,33], and triple-fold (10%) [31]; 30% did not report validation details.

Spectral-domain (SD)–OCT was the most frequently used imaging modality (6/10 of studies) [27-29,31,32,36], followed by CFP (2/10) [34,35], and FAF or NIR (2/10 each) [30,33]. Most studies applied image preprocessing techniques—such as size standardization, orientation adjustment, intensity normalization, and noise reduction—to improve model performance. DL-based algorithms for GA detection have been developed for multiple image modalities. For example, Derradji et al [32] trained a convolutional neural networks (CNNs), U-Net, to predict atrophic signs in the retina, based on the EfficientNet-b3 architecture. Kalra et al [31] and de Vente et al [36] also trained a DL model based on U-Net. Yao et al [29] applied 3D OCT scans with ResNet18 pretrained on the ImageNet dataset, and Chiang et al [27] developed CNN (ResNet18) to improve computational efficiency. Elsawy et al [28] proposed Deep-GA-Net, a 3D backbone CNN with a 3D loss-based attention layer, and evaluated the effectiveness of using attention layers. Sarao et al [35] used a deep CNN, the EfficientNet_b2 model, which was pretrained on the ImageNet dataset and is well-known for its high efficiency and small size. Keenan et al [34] established their model using Inception v3, while Treder et al [30] performed a deep CNN, a self-learning algorithm, processing input data with FAF images.

A total of 14 performance sets were extracted from the 10 studies. Key metrics included sensitivity, specificity, accuracy, positive predictive value, negative predictive value, intersection over union, area under the receiver operating characteristic curve, area under the precision-recall curve, F₁-score, precision, recall, Kappa, and dice similarity coefficient. Six OCT-based studies showed that DL models could detect GA with high accuracy, comparable to human graders [27-29,31,32,36]. Two studies using CFP also reported strong performance [34,35], while FAF- and NIR-based approaches demonstrated excellent repeatability and reliability [30,33].

We conducted a thorough evaluation of the 10 diagnostic studies’ methodological quality for the “participant selection,” “index test,” “reference standard,” and “flow and timing” domains at the study level (Table 2). None of the studies had an overall low or unclear risk of bias; instead, every study had a high risk of bias in at least 1 of the 4 domains. Regarding “patient selection,” only 4 studies [29,32,33,36] described the eligibility criteria; the rest did not report them. One study [30] used an open dataset (ImageNet) and did not include a test set. The small sample size of 4 studies [32,33,35,36] may have resulted in overfitting. In addition, 3 studies [29,30,32] did not report image formats and resolutions. Five studies [30,31,34-36] had a high risk of bias in participant selection because the included participants were not only GA secondary to dry AMD but also had other unrelated diseases. Regarding the “Index test,” only 1 algorithm was externally validated using a different dataset [27]; all other items were evaluated as low risk.

Twenty studies explored AI for GA assessment and progression using noninvasive imaging, published between 2019 and 2025 (Table S2 in Multimedia Appendix 2). As shown in Table 3, these studies covered 11 segmentation [5,11,37-45], 2 algorithm optimization [46,47], 3 AMD progression classification [48-50], and 3 combined tasks such as identification, segmentation, and quantification [51-53]. One study focused solely on GA quantification [54]. Retrospective analyses accounted for 9 studies [5,40,41,43,44,47,48,50,51], while 7 were model development [11,37-39,45,49,53], and the remainder were prospective [52,54], comparative [46], or cross-sectional [42]. Geographically, contributions came from China (6/20), the United States (7/20), the United Kingdom (2/20), Australia (2/20), France (1/20), Israel (1/20), and Austria (1/20).

Dataset configurations varied: 9 out of 20 studies used training, validation, and test sets [40,41,43-46,50-52]; 11 studies used training and test sets [5,11,37-39,49]; 2 studies used training and validation sets [42,48]; 1 study comprised training, tuning, and internal validation sets [53]; and 2 studies did not specify [47,54]. Across studies, at least 14,064 participants provided image data for analysis. Less than half of the studies (9/20, 45%) provided demographic information, with the average age of participants ranging from 55 to 94 years. Six studies were registered with ClinicalTrials.gov (NCT01342926, NCT02503332, NCT02479386, NCT02399072, and NCT04469140 [5,40,41,46,47,53]). To assess the generalization ability of the DL model, cross-validation methods included 5-fold (8/20 studies [5,38,41,43-46,48]), 4-fold (1/20 study [51]), 3-fold (1/20 study [49]), and other approaches (1/20 study [39]). Nine studies did not report validation specifics.

Multiple imaging modalities supported GA assessment: spectral domain optical coherence tomography (SD-OCT) was most common, followed by swept-source OCT (SS-OCT), 3D-OCT, FAF, and NIR. Preprocessing techniques were widely applied to standardize images and improve model performance. Algorithm architectures varied, with U-Net being the most frequently used. Other approaches included custom CNNs, self-learning algorithms, weakly supervised models, and multimodal networks. For example, Hu et al [48] trained the DL models (ResNet-50, Xception, DenseNet169, and EfficientNetV2), evaluating them on a single fold of the validation dataset, with all F₁-scores exceeding 90%. Yang [49] proposed an ensemble DL architecture that integrated 4 different CNNs, including ResNet50, EfficientNetB4, MobileNetV3, and Xception, to classify dry AMD progression stages. GA lesions on FAF were automatically segmented using multimodal DL networks (U-Net and Y-Net) fed with FAF and NIR images [40]. In contrast to the multimodal algorithms mentioned above (ie, the examples of DL models), Safai [46] investigated 3 distinct segmentation architectures along with 4 commonly used encoders, resulting in 12 different AI model combinations to determine the optimal AI framework for GA segmentation on FAF images.

From 20 studies, 42 performance sets were collected. Common metrics included correlation coefficient, mean absolute error, Spearman correlation coefficient, intraclass coefficient, overlap ratio, Pearson correlation coefficient (r²), Kappa, specificity (SPE), sensitivity (SEN), accuracy, positive predictive value (PPV), F₁-score, P, R, intersection over union, and dice similarity coefficient (DSC). Regarding the segmentation, classification, identification, and quantification of GA in SD-OCT, 12 studies demonstrated performance comparable to that of clinical experts [11,37,38,44,45,47-51,53,54]. AI was also capable of efficiently detecting, segmenting, and measuring GA in SS-OCT, 3D-OCT, and FAF images, according to 4 studies [5,41,42,52]. AI for GA segmentation in FAF and NIR images, with clinical data showing good segmentation performance [39,40,43].

We performed a comprehensive assessment of the methodological quality of 16 GA assessment and progression studies encompassing 4 domains (Table 4). Only 8 studies detailed the eligibility criteria in the “patient selection” category, while the others had not been published. Three of the studies [47-49] lacked complete datasets, and 3 others [37,39,54] had small datasets or limited volumes of data. In addition, 3 studies [48,49,54] failed to provide information on image formats or resolutions. Two studies [48,49] were ranked as high risk regarding patient selection since the participants included other types of dry AMD (drusen, nascent GA). In terms of applicability, 18 studies were classified as low risk, while 2 were deemed high risk concerning patient selection. Concerning the “Index test,” only 3 algorithms underwent external validation with a different dataset [40,46,53]. All other items were evaluated as low risk.

Eleven studies used AI for predicting GA lesion growth and progression using noninvasive imaging (Table S3 in Multimedia Appendix 2). These studies were published between 2021 and 2025, with some information provided in Table 5. The study designs consisted of 6 retrospective studies [55-60], 2 model development studies [61,62], 2 post hoc analyses [63,64], and 1 clinical evaluation of a DL algorithm [65]. Participants or images came from various regions: 6 studies were based in the United States [55,57-60,62], 3 in Australia [63-65], 1 in Switzerland [56], and another involving multiple centers in China and the United States [61]. Research aims focused on GA growth prediction [55,56,59-61,63,65], combined prediction and evaluation of lesion features [57], treatment response assessment [58], and integrated segmentation-prediction tasks [62,64].

Dataset structures varied: 3 out of 11 studies used training-validation-test splits [59,62,64]; 2 out of 11 studies used training-test sets [56,61]; 3 out of 11 studies used training-validation sets [55,63,65]; and the rest adopted development–holdout [57,60] or development-holdout-independent test configurations [58]. In total, 6706 participants were included across studies. Fewer than half of the studies (4/11, 36.4%) reported demographic information, with mean age ranges spanning from 74 to 83 years [55,58,64,65]. Six studies [57-60,63,64] were ethically approved and registered on ClinicalTrials.gov under the following identifiers: NCT02503332, NCT02247479, NCT02247531, NCT02479386, NCT01229215, and NCT02399072. The DL model’s generalizability was assessed using leave-one-out cross-validation in 1 study [61], 5-fold cross-validation in 7 studies [55,57,58,60,63-65], and 8-fold cross-validation in 1 study [62]. The remaining 2 studies [56,59] did not specify the cross-validation methodology.

Studies used 3D-OCT, SD-OCT, NIR, and FAF images, primarily sourced from Heidelberg, Zeiss, and Bioptigen devices. While most reported image metrics, 2 studies did not specify resolution details [63,65]. Commonly used DL architectures included Inception v3 [55,58], PSC-UNet [63,65], U-Net [59,62,64], EfficientNet-b3 [56], and VGG16 [57]. In addition, some studies introduced novel approaches, such as en-face intensity maps, SLIVER-net, 3D CNN, and a recurrent neural network, for improved GA progression forecasting.

According to various image modalities, datasets, and follow-up durations, we gathered 31 sets of performance data from 11 studies. The performance metrics included the Hausdorff distance, concordance index, overlap, SEN, SPE, accuracy, mean absolute error, Kappa, DSC, P, PPV, R, r², and negative predictive value. The findings for a single image modality (3D-OCT, SD-OCT, or FAF) demonstrated the development of DL algorithms to predict GA growth rate and progression with excellent performance characteristics comparable to trained experts [55-57,59-61]. Multimodal approaches combining FAF, NIR, and SD-OCT further showed feasibility for individualized lesion growth prediction and localization [58,62-65].

In this systematic review, we used the PROBAST tool to rigorously evaluate prediction models across 4 domains, addressing 20 signaling questions for each paper reviewed. Within the “participants” domain, all studies used appropriate data sources; however, only 6 studies [57-60,64,65] clearly outlined their inclusion and exclusion criteria for participants, leaving the others unclear. In terms of “predictors,” these were defined and evaluated similarly for all participants, having no connection to outcome data and being available at baseline. All studies evaluated “yes” to the questions on outcome measurement methods, definitions, interference factors, and measurement time intervals. Concerning “analysis,” Dow [55] and Zhang [61] applied a small dataset with an insufficient number of participants. While Zhang performed internal validation, the lack of external validation notably limits the model’s generalizability, which was constructed with bi-directional long-short term memory networks and CNN frameworks. Two studies by Salvi [59] and Yoshida [60] lacked independent and external validation. Gigon [56] failed to explicitly mention missing data handling, complex problems, and model overfitting. Conversely, all other items were evaluated as low risk, and the applications of the studies were universally ranked as low risk (Table S1 in Multimedia Appendix 3).

This systematic review evaluated the performance of AI, particularly DL algorithms, in detecting and managing GA secondary to dry AMD using noninvasive imaging modalities. Our findings demonstrate that AI models exhibit strong capabilities in accurately detecting, segmenting, quantifying, and predicting GA progression from OCT, FAF, CFP, and NIR imaging, achieving diagnostic accuracy comparable to that of human experts. However, this review also identified several methodological challenges, such as limited sample sizes, inconsistent annotation standards, and a general lack of external validation, which may hinder the clinical generalizability and practical application of these models. Despite these limitations, AI-based tools show significant potential for future use by both specialists and nonspecialists in primary and specialty care settings.

Ten studies published between 2018 and 2025 were included, involving at least 7132 participants aged 50 to 85 years. Half of the studies were conducted in the United States, while others originated from European countries. SD-OCT was the most frequently used imaging modality (6/10 studies), followed by CFP (2/10 studies), NIR (1/10 studies), and FAF (1/10 studies). Image preprocessing techniques, such as standardization of size, orientation, and intensity, as well as noise reduction, were consistently applied to enhance model stability and training efficiency. However, 3 studies did not report critical image parameters, such as resolution, potentially limiting reproducibility. DL-based algorithms, including CNNs, were the primary methodologies used for GA detection. Cross-validation techniques, such as 5-fold and 10-fold methods, were used in half of the studies to assess model robustness, though 3 studies did not report validation strategies. AI, particularly DL algorithms, holds significant promise for the detection of GA using noninvasive imaging modalities. OCT, CFP, NIR, and FAF each demonstrated robust diagnostic potential, with performance metrics rivaling or exceeding human expertise.

A total of 20 studies (14,064 participants) were published between 2019 and 2025, focusing on themes such as GA segmentation, classification, quantification, and progression prediction. The research designs and geographic regions are diverse. The studies included retrospective analysis (9/20), model development (7/20), and prospective, comparative, or cross-sectional studies (4/20). Significant contributions came from China (6/20) and the United States (7/20), with additional studies from the United Kingdom (2/20), Australia (2/20), France (1/20), Israel (1/20), and Austria (1/20). The studies used a variety of imaging modalities to assess GA, including SD-OCT, FAF, NIR, SS-OCT, and 3D-OCT. DL algorithms demonstrated remarkable performance in GA management tasks. U-Net was the most commonly used architecture. Multimodal approaches combined FAF and NIR images with DL networks to improve segmentation accuracy. Performance metrics, such as DSC, Kappa, SEN, SPE, and accuracy, consistently showed strong diagnostic accuracy, with several studies achieving performance comparable to clinical experts.

Eleven studies with 6706 participants, published between 2021 and 2025, concentrated on the application of AI for predicting and segmenting GA lesions, as well as their growth and progression. The methodologies were diverse, including retrospective studies, model development studies, post hoc analyses, and clinical algorithm assessment. Participants or images were gathered from regions such as the United States, Australia, Switzerland, and various centers in China and the United States, ensuring broad geographic representation. Demographic information was reported in fewer than half of the studies, with a mean age ranging from 74 to 83 years. Imaging modalities, such as 3D-OCT, SD-OCT, NIR, and FAF, were obtained from devices including Bioptigen, Heidelberg Spectralis HRA+OCT, and Cirrus OCT. While the image preprocessing parameters were consistent across most studies, some did not specify image resolution. Multiview CNN architectures and advanced frameworks, such as the bi-directional long-short term memory networks, were used. DL algorithms exhibited excellent predictive capabilities, with multimodal approaches enabling individualized GA lesion growth prediction.

GA, a late-stage form of dry AMD, is marked by the irreversible loss of photoreceptors, RPE, and choriocapillaris [4,5]. The application of noninvasive imaging modalities has revolutionized the detection and management of GA. A comparative summary of AI performance across these modalities is provided in Table S2 in Multimedia Appendix 3. CFP serves as a standard initial assessment tool, useful for screening and early detection. It identifies GA lesions as visible underlying choroidal vessels and well-defined regions of RPE hypopigmentation [66]. FAF imaging using a blue excitation wavelength (488 nm) visualizes metabolic changes at the level of photoreceptor or RPE complex and is practical in assessing GA lesion size and progression with hypo-autofluorescence [67]. In contrast to nonatrophic areas, GA lesions on NIR (787-820 nm, longer than FAF) typically appear brighter and less harmful to the eye [68]. In addition, NIR can help detect the boundaries of foveal lesions, where image contrast is lower on FAF [68]. Recently, the Classification of Atrophy Meeting group recommended that atrophy in both patients with and those without neovascular AMD be defined based on specific drusen characteristics and other anatomical features, and it is most easily characterized by OCT [69,70]. OCT stands out as the gold standard for GA detection and classification, providing high-resolution, cross-sectional, and en face images of the retina and choroid. SD-OCT is widely used in research and clinical trials, offering precise measurement of GA area and growth rates, while SS-OCT and 3D-OCT offer superior structural insights and potential for AI-driven automation [41,71,72]. Despite the higher cost and technical complexity of advanced OCT technologies, their detailed GA assessment capabilities make them indispensable tools in both clinical practice and research. Furthermore, OCT provides volumetric (3D) structural data, unlike the 2D en face projections of FAF, CFP, and NIR. It allows AI to learn not just the surface appearance of atrophy but also the cross-sectional structure alterations that define and precede GA [3]. As technology advances, the integration of AI and further developments in imaging techniques are expected to enhance the utility of these modalities, overcoming current limitations and expanding their applications in ophthalmology.

AI addresses critical limitations of traditional GA monitoring, such as labor-intensive manual grading and intergrader variability [73]. Therefore, automated algorithms enable rapid, standardized analysis of large fundus image datasets, reducing clinician workload and enhancing reproducibility [74]. Furthermore, our review revealed a clear trend in the choice of model architectures tailored to specific clinical tasks. A critical analysis of these architectures is provided in Table S3 in Multimedia Appendix 3. Interestingly, with the advancement of AI algorithm architectures, numerous studies have emerged that use these technologies to identify atrophy caused by various retinal diseases and to evaluate treatment outcomes through image analysis. Miere et al [75] pretrained a DL-based classifier to automatically distinguish GA from atrophy secondary to inherited retinal diseases on FAF according to etiology, using 2 approaches (a trained and validated method and a 10-fold cross-validation method), achieving good accuracy and excellent area under the receiver operating characteristic (AUROC) values. In addition, a study examined the association between treatment and changes in photoreceptor lamina thickness in patients with GA secondary to AMD. The effect of pegcetacoplan on photoreceptors in OCT was supported by this post hoc analysis, which demonstrated that treatment with the drug was linked with reduced outer retinal thinning [76]. Similarly, DL-based OCT image analysis assessed the therapeutic effectiveness of complement component 3 inhibition in delaying GA progression, with findings indicating decreased photoreceptor thinning and loss [77]. Recent studies demonstrating the application of AI algorithms in imaging further validate their potential as reliable supplements to human expertise in the diagnosis and management of GA.

Despite the promising advancements in AI for GA detection and management, several technical challenges and limitations persist. A significant limitation of OCT-based AI models is their difficulty in distinguishing GA secondary to AMD from other forms of retinal atrophy; thus, the findings may not generalize to broader AMD cases or other retinal diseases, which limits their clinical applicability. In addition, images from different OCT devices show significant variability and imprecision, not offering good enough data acquisition [74]. Another major challenge is the variability in algorithm performance caused by differences in training data, image acquisition protocols, and disease definitions. These differences reduce reproducibility and limit practical deployment. For instance, the absence of standardized reporting in AI studies can result in discrepancies when interpreting results and hinder comparisons between different models. Moreover, despite the high-performance metrics (eg, SEN, SPE, DSC>0.85, and AUROC>0.95) reported by many studies, methodological limitations remain. All diagnostic studies included in this review were assessed as high risk in at least 1 domain (10/10), only 1 GA assessment study (1/20) was evaluated as low risk across all domains, and several prediction studies (7/11) were ranked as high or unclear risk in at least 1 domain, primarily due to small or nonrepresentative datasets and a lack of detailed reporting on image preprocessing and external validation. These methodological shortcomings may lead to an overestimation of AI model performance and reduced overall robustness, thereby decreasing the generalizability of the findings and limiting confidence in their real-world applicability. Future studies should prioritize the use of larger, more diverse datasets and implement rigorous validation frameworks to enhance performance metrics (including detection, segmentation, quantification, and prediction accuracy) and conduct prospective, multicenter validation studies to improve clinical applicability and generalizability. Furthermore, adherence to established reporting guidelines for AI studies (such as the Standards for Reporting Diagnostic Accuracy-AI and Checklist for Artificial Intelligence in Medical Imaging [78,79]) would improve comprehension and transparency, allow for more meaningful comparisons between systems, and facilitate meta-analyses.

Overall, despite some limitations, AI is constantly evolving and holds great potential for transformation in the health care sector [80]. AI has the potential to accelerate existing forms of medical analysis; however, its algorithms require further testing to be fully trusted. Clinically, AI-based automated tools show strong potential to facilitate early detection, precise quantification, progression, and prediction of GA, thereby reducing the burden on retinal specialists and improving diagnostic consistency. Furthermore, DL algorithms have demonstrated effectiveness in identifying retinal image features associated with cognitive decline, dementia, Parkinson disease, and cardiovascular risk factors [81]. These findings indicate that AI-based retinal images hold promise for transforming primary care and systemic disease management. Although most AI applications remain in the validation phase, the integration of AI with multimodal imaging, novel biomarkers, and emerging therapeutics holds promise for transforming clinical management paradigms in GA and advancing personalized medicine. Future efforts should focus on developing standardized datasets, improving algorithmic generalizability, and conducting real-world validation studies to fully integrate AI into routine ophthalmic practice.

AI, especially DL-based algorithms, holds considerable promise for the detection and management of GA secondary to dry AMD, with performance comparable to trained experts. This systematic review synthesizes and critically appraises the current evidence, highlighting that AI’s capabilities extend across GA management—from initial detection and precise segmentation to the forecasting of lesion progression, which informs future research directions. Meanwhile, with the development of C5 inhibitors, AI-based noninvasive fundus image analysis is expected to detect, identify, and monitor GA at an early stage, thereby increasing the window of opportunity in the future. AI has strong potential to augment and streamline clinical workflows by offering automated, reproducible analysis that can assist clinicians in managing large volumes of imaging data; however, more studies are needed to further validate its effectiveness, repeatability, and accuracy.