OCT‐A Biomarker Analysis of Retinal Vein Occlusion Using a Deep Neural Network

Purpose To develop a deep learning (DL) model for the automatic detection of retinal vein occlusion (RVO) biomarkers in optical coherence tomography angiography (OCT‐A) images using retrospective data. Methods OCT‐A images from 254 patients were used to train and test an artificial intelligence (AI) model. Scans of the superficial, deep, en face, choriocapillaris, and outer retina to choriocapillaris (ORCC) layers were manually annotated with four biomarkers: perifoveal capillary plexus disruption, nonperfusion areas (NPAs), vascular tortuosity, and cystoid spaces. Deep convolutional neural networks (CNNs) were trained to segment and identify these biomarkers. The detection rate and Jaccard index were the primary outcome measures. Results The DL model achieved detection rates of 93% for perifoveal capillary plexus disruption, 92% for NPAs, 91% for vascular tortuosity, and 84% for cystoid spaces. The corresponding Jaccard index values were 0.85, 0.77, 0.72, and 0.73, respectively. Conclusion The proposed DL model achieves outstanding performance in identifying key biomarkers of RVO in OCT‐A images, supporting its potential role in automated disease assessment.