Generalisability and performance of an OCT-based deep learning classifier for community-based and hospital-based detection of gonioscopic angle closure. Issue 4 (20th October 2021)

• Record Type: Journal Article
• Authors: Randhawa, Jasmeen; Chiang, Michael; Porporato, Natalia; Pardeshi, Anmol A; Dredge, Justin; Apolo Aroca, Galo; Tun, Tin A; Quah, Joanne HuiMin; Tan, Marcus; Higashita, Risa; Aung, Tin; Varma, Rohit; Xu, Benjamin Y
• Is Part Of: British journal of ophthalmology. Volume 107:Issue 4(2023)
• Page Start: 511
• Page End: 517
• Publication Date: 2021-10-20
• Subjects: glaucoma -- anterior chamber -- diagnostic tests/investigation -- imaging; Ophthalmology -- Periodicals; 617.7
• DOI: 10.1136/bjophthalmol-2021-319470
• Languages: English
• ISSNs: 0007-1161

Abstract

Abstract : Purpose: To assess the generalisability and performance of a deep learning classifier for automated detection of gonioscopic angle closure in anterior segment optical coherence tomography (AS-OCT) images. Methods: A convolutional neural network (CNN) model developed using data from the Chinese American Eye Study (CHES) was used to detect gonioscopic angle closure in AS-OCT images with reference gonioscopy grades provided by trained ophthalmologists. Independent test data were derived from the population-based CHES, a community-based clinic in Singapore, and a hospital-based clinic at the University of Southern California (USC). Classifier performance was evaluated with receiver operating characteristic curve and area under the receiver operating characteristic curve (AUC) metrics. Interexaminer agreement between the classifier and two human examiners at USC was calculated using Cohen's kappa coefficients. Results: The classifier was tested using 640 images (311 open and 329 closed) from 127 Chinese Americans, 10 165 images (9595 open and 570 closed) from 1318 predominantly Chinese Singaporeans and 300 images (234 open and 66 closed) from 40 multiethnic USC patients. The classifier achieved similar performance in the CHES (AUC=0.917), Singapore (AUC=0.894) and USC (AUC=0.922) cohorts. Standardising the distribution of gonioscopy grades across cohorts produced similar AUC metrics (range 0.890–0.932). The agreement between the CNN classifier and two human examiners (Ҡ=0.700 and 0.704) approximated interexaminer agreement (Ҡ=0.693) in the USC cohort. Conclusion: An OCT-based deep learning classifier demonstrated consistent performance detecting gonioscopic angle closure across three independent patient populations. This automated method could aid ophthalmologists in the assessment of angle status in diverse patient populations.