A Caltech Library Service

Glaucoma Expert-Level Detection of Angle Closure in Goniophotographs With Convolutional Neural Networks: The Chinese American Eye Study

Chiang, Michael and Guth, Daniel and Pardeshi, Anmol A. and Randhawa, Jasmeen and Shen, Alice and Shan, Meghan and Dredge, Justin and Nguyen, Annie and Gokoffski, Kimberly and Wong, Brandon J. and Song, Brian and Lin, Shan and Varma, Rohit and Xu, Benjamin Y. (2021) Glaucoma Expert-Level Detection of Angle Closure in Goniophotographs With Convolutional Neural Networks: The Chinese American Eye Study. American Journal of Ophthalmology, 226 . pp. 100-107. ISSN 0002-9394. doi:10.1016/j.ajo.2021.02.004.

[img] PDF - Accepted Version
See Usage Policy.

[img] MS Word - Supplemental Material
See Usage Policy.

[img] MS Word - Supplemental Material
See Usage Policy.

[img] MS Word - Supplemental Material
See Usage Policy.


Use this Persistent URL to link to this item:


Purpose: To compare the performance of a novel convolutional neural network (CNN) classifier and human graders in detecting angle closure in EyeCam (Clarity Medical Systems, Pleasanton, California, USA) goniophotographs. Design: Retrospective cross-sectional study. Methods: Subjects from the Chinese American Eye Study underwent EyeCam goniophotography in 4 angle quadrants. A CNN classifier based on the ResNet-50 architecture was trained to detect angle closure, defined as inability to visualize the pigmented trabecular meshwork, using reference labels by a single experienced glaucoma specialist. The performance of the CNN classifier was assessed using an independent test dataset and reference labels by the single glaucoma specialist or a panel of 3 glaucoma specialists. This performance was compared to that of 9 human graders with a range of clinical experience. Outcome measures included area under the receiver operating characteristic curve (AUC) metrics and Cohen kappa coefficients in the binary classification of open or closed angle. Results: The CNN classifier was developed using 29,706 open and 2,929 closed angle images. The independent test dataset was composed of 600 open and 400 closed angle images. The CNN classifier achieved excellent performance based on single-grader (AUC = 0.969) and consensus (AUC = 0.952) labels. The agreement between the CNN classifier and consensus labels (κ = 0.746) surpassed that of all non-reference human graders (κ = 0.578-0.702). Human grader agreement with consensus labels improved with clinical experience (P = 0.03). Conclusion: A CNN classifier can effectively detect angle closure in goniophotographs with performance comparable to that of an experienced glaucoma specialist. This provides an automated method to support remote detection of patients at risk for primary angle closure glaucoma.

Item Type:Article
Related URLs:
URLURL TypeDescription
Chiang, Michael0000-0002-9093-9702
Guth, Daniel0000-0003-0937-5282
Randhawa, Jasmeen0000-0002-9120-8901
Dredge, Justin0000-0002-6771-8522
Nguyen, Annie0000-0002-4777-843X
Wong, Brandon J.0000-0002-2894-4631
Song, Brian0000-0003-4226-3135
Xu, Benjamin Y.0000-0003-1573-988X
Alternate Title:Glaucoma Expert-level Detection of Angle Closure in Goniophotographs with Convolutional Neural Networks: The Chinese American Eye Study: Automated Angle Closure Detection in Goniophotographs
Additional Information:© 2021 Elsevier Inc. Received 5 October 2020, Revised 20 January 2021, Accepted 3 February 2021, Available online 9 February 2021. This work was supported by grants U10 EY017337, K23 EY029763, and P30 EY029220 from the National Eye Institute, National Institutes of Health, Bethesda, Maryland, USA; a Young Clinician Scientist Research Award from the American Glaucoma Society, San Francisco, California, USA; a Grant-in-Aid Research Award from Fight for Sight, New York, New York, USA; a Clinical and Community Research Award from the Southern California Clinical and Translational Science Institute, Los Angeles, California, USA; and an unrestricted grant to the Department of Ophthalmology from Research to Prevent Blindness, New York, New York, USA. Financial Disclosures: Rohit Varma is a consultant for Allegro Inc, Allergan, and Bausch Health Companies Inc. The other authors have no financial disclosures. All authors attest that they meet the current ICMJE criteria for authorship.
Funding AgencyGrant Number
NIHU10 EY017337
NIHK23 EY029763
NIHP30 EY029220
National Eye InstituteUNSPECIFIED
American Glaucoma SocietyUNSPECIFIED
Fight for SightUNSPECIFIED
Southern California Clinical and Translational Science InstituteUNSPECIFIED
Research to Prevent BlindnessUNSPECIFIED
Subject Keywords:Angle closure; primary angle closure glaucoma; artificial intelligence; goniophotography; gonioscopy
Record Number:CaltechAUTHORS:20210224-094620349
Persistent URL:
Official Citation:Michael Chiang, Daniel Guth, Anmol A. Pardeshi, Jasmeen Randhawa, Alice Shen, Meghan Shan, Justin Dredge, Annie Nguyen, Kimberly Gokoffski, Brandon J. Wong, Brian Song, Shan Lin, Rohit Varma, Benjamin Y. Xu, Glaucoma Expert-Level Detection of Angle Closure in Goniophotographs With Convolutional Neural Networks: The Chinese American Eye Study, American Journal of Ophthalmology, Volume 226, 2021, Pages 100-107, ISSN 0002-9394, (
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:108165
Deposited By: Tony Diaz
Deposited On:24 Feb 2021 19:42
Last Modified:29 Mar 2021 18:12

Repository Staff Only: item control page