Multi-class classification of central and non-central geographic atrophy using Optical Coherence Tomography

Purpose To develop and validate deep learning (DL)-based models for classifying geographic atrophy (GA) subtypes using Optical Coherence Tomography (OCT) scans across four clinical classification tasks. Design Retrospective comparative study evaluating three DL architectures on OCT data with two experimental approaches. Subjects 455 OCT volumes (258 Central GA [CGA], 74 Non-Central GA [NCGA], 123 no GA [NGA]) from 104 patients at Atrium Health Wake Forest Baptist. For GA versus age-related macular degeneration (AMD) classification, we supplemented our dataset with AMD cases from four public repositories.

We implemented ResNet50, MobileNetV2, and Vision Transformer (ViT-B/16) architectures using two approaches: (1) utilizing all B-scans within each OCT volume and (2) selectively using B-scans containing foveal regions. Models were trained using transfer learning, standardized data augmentation, and patient-level data splitting (70:15:15 ratio) for training, validation, and testing. Main Outcome Measures Area under the receiver operating characteristic curve (AUC-ROC), F1 score, and accuracy for each classification task (CGA vs. NCGA, CGA vs. NCGA vs. NGA, GA vs. NGA, and GA vs. other forms of AMD).

ViT-B/16 consistently outperformed other architectures across all classification tasks. For CGA versus NCGA classification, ViT-B/16 achieved an AUC-ROC of 0.728±0.083 and accuracy of 0.831±0.006 using selective B-scans. In GA versus NGA classification, ViT-B/16 attained an AUC-ROC of 0.950±0.002 and accuracy of 0.873±0.012 with selective B-scans. All models demonstrated exceptional performance in distinguishing GA from other AMD forms (AUC-ROC>0.998). For multi-class classification, ViT-B/16 achieved an AUC-ROC of 0.873±0.003 and accuracy of 0.751±0.002 using selective B-scans.

Our DL approach successfully classifies GA subtypes with clinically relevant accuracy. ViT-B/16 demonstrates superior performance due to its ability to capture spatial relationships between atrophic regions and the foveal center. Focusing on B-scans containing foveal regions improved diagnostic accuracy while reducing computational requirements, better aligning with clinical practice workflows. Competing Interest Statement The authors have declared no competing interest. Funding Statement The study was funded by NEI R21EY035271 (MNA), R15EY035804 (MNA); and UNC Charlotte Faculty Research Grant (MNA). Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: Institutional Review Board of Atrium Health Wake Forest Baptist gave ethical approval for this work I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes Footnotes Financial Support: Supported by NEI R21EY035271 (MNA), R15EY035804 (MNA); and UNC Charlotte Faculty Research Grant (MNA). Conflict of Interests: The author(s) declared no potential conflicts of interest with respect to the research, authorship and/or publication of this article. Data Availability All data produced in the present study are available upon reasonable request to the authors Abbreviations - AI - Artificial Intelligence - AMD - Age-related Macular Degeneration - AUC-ROC - Area Under the Receiver Operating Characteristic Curve - BCVA - Best Corrected Visual Acuity - CAM - Classification of Atrophy Meetings - GA - Geographic Atrophy - CGA - Central Geographic Atrophy - CRVO - Central Retinal Vein Occlusion - DL - Deep Learning - DME - Diabetic Macular Edema - DS1–DS4 - Public OCT Datasets 1 through 4 - FAF - Fundus Autofluorescence - GA - Geographic Atrophy - Grad-CAM - Gradient-weighted Class Activation Mapping - LogMAR - Logarithm of the Minimum Angle of Resolution - NCGA - Non-Central Geographic Atrophy - NGA - No Geographic Atrophy - OCT - Optical Coherence Tomography - OD - Oculus Dexter (Right Eye) - OS - Oculus Sinister (Left Eye) - PRs - Photoreceptors - RPE - Retinal Pigment Epithelium