AI RESEARCH

Anatomy-Aware Unsupervised Detection and Localization of Retinal Abnormalities in Optical Coherence Tomography

arXiv CS.LG

ArXi:2604.22139v1 Announce Type: cross Reliable automated analysis of Optical Coherence Tomography (OCT) imaging is crucial for diagnosing retinal disorders but faces a critical barrier: the need for expensive, labor-intensive expert annotations. Supervised deep learning models struggle to generalize across diverse pathologies, imaging devices, and patient populations due to their restricted vocabulary of annotated abnormalities.