July 2020
Volume 61, Issue 9
Free
ARVO Imaging in the Eye Conference Abstract  |   July 2020
Detecting pre-perimetric and perimetic glaucoma from fundus photographs using deep learning
Author Affiliations & Notes
  • Siamak Yousefi
    Ophthalmology, University of Tennessee Health Science Center, Memphis, Tennessee, United States
  • Anshul Thakur
    School of Computing and Electrical Engineering, Indian Institute of Technology, Mandi, India
  • Michael Goldbaum
    Ophthalmology, University of California San Diego, San Diego, California, United States
  • Footnotes
    Commercial Relationships   Siamak Yousefi, None; Anshul Thakur, None; Michael Goldbaum, None
  • Footnotes
    Support  NH Grant EY030142
Investigative Ophthalmology & Visual Science July 2020, Vol.61, PP0011. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Siamak Yousefi, Anshul Thakur, Michael Goldbaum; Detecting pre-perimetric and perimetic glaucoma from fundus photographs using deep learning. Invest. Ophthalmol. Vis. Sci. 2020;61(9):PP0011.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To assess the accuracy of deep learning models to detect pre-perimetric and perimetric glaucoma from fundus photographs.

Methods : We included 3,272 eyes of 1,636 subjects that had participated in the ocular hypertension treatment study (OHTS). A total of 66,721 fundus photographs and visual fields were previously examined by independent readers from the optic disc and visual field reading centers of the OHTS and glaucoma development was further confirmed by an endpoint committee. We included 45,379 reliable fundus photographs from OHTS participants; 41,298 fundus photographs of eyes without glaucomatous optic neuropathy (GON) and normal visual field, as defined by the OHTS study, and 4,081 fundus photographs of eyes with either apparent glaucomatous optic neuropathy (GON) without visual field abnormality (pre-perimetric glaucoma) or visual field abnormality (perimetric glaucoma). We then trained and validated a MobileNetV2 deep learning architecture using 85% of the fundus photographs and further re-tested the models using 15% held-out fundus photographs.

Results : The area under the receiver operating characteristic curve (AUC) of the deep learning model in detecting glaucoma was 0.95 (95% confidence interval 0.93 - 0.96). The AUC was improved to 0.97 (0.96, 0.98) on re-testing fundus photographs of only pre-perimetric eyes (eyes with apparent GON). However, the AUC decreased to 0.88 (0.86, 0.89) when we tested the deep learning model using the fundus photographs of only perimetric eyes (eyes with abnormal visual field but without apparent GON).

Conclusions : Deep learning models can detect pre-perimetric and perimetric glaucoma from fundus photographs with a high accuracy. Perimetric eyes without apparent GON had a higher tendency to be missed by the deep learning algorithms compared to eyes with apparent GON.

This is a 2020 Imaging in the Eye Conference abstract.

 

Figure 1. The eye is labeled as glaucoma based on glaucomatous optic neuropathy (GON) or visual field abnormality further confirmed by an endpoint committee. Only fundus photographs collected on or after glaucoma onset were used.

Figure 1. The eye is labeled as glaucoma based on glaucomatous optic neuropathy (GON) or visual field abnormality further confirmed by an endpoint committee. Only fundus photographs collected on or after glaucoma onset were used.

 

Figure 2. Regions that are most promising for the deep learning model in decision making. Fundus photographs of normal eyes with their corresponding activation maps shown in the first and second rows. Fundus photographs of glaucoma eyes with their corresponding activation maps presented in the third and fourth rows.

Figure 2. Regions that are most promising for the deep learning model in decision making. Fundus photographs of normal eyes with their corresponding activation maps shown in the first and second rows. Fundus photographs of glaucoma eyes with their corresponding activation maps presented in the third and fourth rows.

×
×

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.

×