Deep Learning–Based Automated Segmentation and Quantification of Ellipsoid Zone and RPE–Bruch's Membrane Complex in Healthy Subjects and Geographic Atrophy

We present a deep-learning framework for automated segmentation and quantification of the ellipsoid zone (EZ) and the RPE–Bruch’s membrane complex from OCT volumes, evaluated in both healthy subjects and patients with geographic atrophy. The method enables reproducible, high-throughput measurement of FDA-relevant structural biomarkers for drug discovery and disease monitoring. N. Hasan and A. Gadari contributed equally to this work.

In Preprints, 2026. doi:10.20944/preprints202604.1517.v1