Abstract
PURPOSE: To test a cataract shadow projection theory and validate it by developing a deep learning algorithm that enables automatic and stable posterior polar cataract (PPC) screening using fundus images. SETTING: Department of Ophthalmology, Far Eastern Memorial Hospital, New Taipei, Taiwan. DESIGN: Retrospective chart review. METHODS: A deep learning algorithm to automatically detect PPC was developed based on the cataract shadow projection theory. Retrospective data (n = 546) with ultra-wide field fundus images were collected, and various model architectures and fields of view were tested for optimization. RESULTS: The final model achieved 80% overall accuracy, with 88.2% sensitivity and 93.4% specificity in PPC screening on a clinical validation dataset (n = 103). CONCLUSIONS: This study established a significant relationship between PPC and the projected shadow, which may help surgeons to identify potential PPC risks preoperatively and reduce the incidence of posterior capsular rupture during cataract surgery.