Digital Gonioscopy based on Three-dimensional Anterior Segment Optical Coherence Tomography: an international multicenter study

Objective: To develop and evaluate the performance of a three-dimensional deep-learning based automated digital gonioscopy system (3D DGS) in detecting two major characteristics in eyes suspected to have primary angle closure glaucoma (PACG): 1) narrow iridocorneal angles (static gonioscopy, Task I) and; 2) peripheral anterior synechiae (PAS) (dynamic gonioscopy, Task II) on optical coherence tomography scans. Design: International cross-sectional multicentre study. Subjects: A total of 1.112 million images of 8694 volume scans (2294 patients) from three centers were included in this study (Task I: training/internal validation/external testing - 4515, 1101, 2222 volume scans respectively; Task II: training/internal ...