June 2021
Volume 62, Issue 8
Open Access
ARVO Annual Meeting Abstract  |   June 2021
Deep learning for detecting glaucoma in the Ocular Hypertension Treatment Study: Implications for clinical trial endpoints
Author Affiliations & Notes
  • Rui Fan
    Hamilton Glaucoma Center, Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California San Diego, La Jolla, California, United States
    Department of Computer Science and Engineering, University of California San Diego, La Jolla, California, United States
  • Christopher Bowd
    Hamilton Glaucoma Center, Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California San Diego, La Jolla, California, United States
  • Mark Christopher
    Hamilton Glaucoma Center, Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California San Diego, La Jolla, California, United States
  • Nicole Brye
    Hamilton Glaucoma Center, Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California San Diego, La Jolla, California, United States
  • James A Proudfoot
    Hamilton Glaucoma Center, Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California San Diego, La Jolla, California, United States
  • Jasmin Rezapour
    Hamilton Glaucoma Center, Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California San Diego, La Jolla, California, United States
    Department of Ophthalmology, Universitatsmedizin der Johannes Gutenberg-Universitat Mainz, Mainz, Rheinland-Pfalz, Germany
  • Akram Belghith
    Hamilton Glaucoma Center, Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California San Diego, La Jolla, California, United States
  • Robert N Weinreb
    Hamilton Glaucoma Center, Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California San Diego, La Jolla, California, United States
  • David Kriegman
    Department of Computer Science and Engineering, University of California San Diego, La Jolla, California, United States
  • Linda M Zangwill
    Hamilton Glaucoma Center, Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California San Diego, La Jolla, California, United States
  • Footnotes
    Commercial Relationships   Rui Fan, None; Christopher Bowd, None; Mark Christopher, None; Nicole Brye, None; James Proudfoot, None; Jasmin Rezapour, None; Akram Belghith, None; Robert Weinreb, Aerie Pharmaceuticals (C), Allergan (C), Bausch&Lomb (C), Bausch&Lomb (F), Carl Zeiss Meditec (F), Centervue (F), Eyenovia. Unity (C), Genentech (F), Heidelberg Engineering (F), Konan Medical (F), Meditec-Zeiss (P), Optos (F), Optovue (F), Toromedes (P); David Kriegman, None; Linda Zangwill, Carl Zeiss Meditec Inc. (F), Heidelberg Engineering GmbH (F), National Eye Institute (F), Optovue Inc. (F), Topcon Medical Systems Inc. (F), Zeiss Meditec (P)
  • Footnotes
    Support  Supported in part by National Eye Institute R01EY029058, R21EY027945, K99EY030942, R01EY011008, R01EY19869, R01EY027510, P30EY022589, R01EY026574, German Research Foundation research fellowship grant (RE 4155/1-1) and German Ophthalmological Society Grant and an unrestricted grant from Research to Prevent Blindness, New York
Investigative Ophthalmology & Visual Science June 2021, Vol.62, 1006. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Rui Fan, Christopher Bowd, Mark Christopher, Nicole Brye, James A Proudfoot, Jasmin Rezapour, Akram Belghith, Robert N Weinreb, David Kriegman, Linda M Zangwill; Deep learning for detecting glaucoma in the Ocular Hypertension Treatment Study: Implications for clinical trial endpoints. Invest. Ophthalmol. Vis. Sci. 2021;62(8):1006.

      Download citation file:


      © ARVO (1962-2015); The Authors (2016-present)

      ×
  • Supplements
Abstract

Purpose : To investigate the diagnostic accuracy of deep learning (DL) algorithms to detect primary open angle glaucoma (POAG) trained on fundus photographs from the Ocular Hypertension Treatment Study (OHTS).

Methods : 74,678 photographs from 3,272 eyes of 1,636 OHTS participants with a mean follow-up (range) of 10.7 (0.0, 14.3) years were used to train a ResNet-50 deep learning model to detect the OHTS I and II Endpoint Committee POAG determination based on optic disc (n=287 eyes, 3,502 photographs) and /or visual field (n=198 eyes, 2,300 visual fields) changes. OHTS training, validation and testing sets were randomly determined using an 85-5-10 percentage split by subject. Three independent test sets (1: UCSD Diagnostic Innovations in Glaucoma Study (DIGS), 2: ACRIMA (Spain) and 3: Large-scale Attention-based Glaucoma (LAG, China) were used to estimate the generalizability of the model. Areas under the receiver operating characteristic curve (AUROC) and sensitivities at fixed specificities were used to compare model performance. Evaluation of false positive rates at a fixed specificity of 90% was used to determine whether the DL model detected glaucoma before the Endpoint Committee determination.

Results : For the OHTS test set, the DL model achieved an AUROC (95% CI) of 0.87 (0.80, 0.91) for the overall OHTS POAG endpoint. For the OHTS endpoints based on optic disc changes or visual field changes, AUROCs were 0.90 (0.87, 0.93) and 0.87 (0.80, 0.91), respectively. False positive rates (at 90% specificity) were higher in earlier photographs of hypertensive eyes that later developed POAG by disc or visual field (19.1%), compared to hypertensive eyes that did not develop POAG (7.3%) during their OHTS follow-up. The diagnostic accuracy of the DL model developed based on the OHTS optic disc endpoint on the 3 independent datasets was lower with AUROC for DIGS of 0.74 (0.69, 0.79), ACRIMA of 0.74 (0.70, 0.77) and LAG of 0.79 (0.78, 0.81).

Conclusions : The high diagnostic accuracy of the current DL model suggests that DL can be used to automate the determination of POAG for clinical trials and management. In addition, the higher false positive rate in early photographs of eyes that later developed POAG suggests that DL models detected POAG in some eyes earlier than the OHTS POAG Endpoint Committee.

This is a 2021 ARVO Annual Meeting abstract.

×
×

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.

×