Abstract
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. METHODS: 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). RESULTS: 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. CONCLUSIONS: 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.