June 2022
Volume 63, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2022
Detecting Cataract from Color Fundus Photographs Using Explainable Deep Learning
Author Affiliations & Notes
  • Amr Elsawy
    National Center of Biotechnology Information, National Library of Medicine, Bethesda, Maryland, United States
  • Tiarnan D L Keenan
    Division of Epidemiology and Clinical Applications, National Eye Institute, Bethesda, Maryland, United States
  • Qingyu Chen
    National Center of Biotechnology Information, National Library of Medicine, Bethesda, Maryland, United States
  • Alisa T Thavikulwat
    Division of Epidemiology and Clinical Applications, National Eye Institute, Bethesda, Maryland, United States
  • Sanjeeb Bhandari
    Division of Epidemiology and Clinical Applications, National Eye Institute, Bethesda, Maryland, United States
  • Emily Y Chew
    Division of Epidemiology and Clinical Applications, National Eye Institute, Bethesda, Maryland, United States
  • Zhiyong Lu
    National Center of Biotechnology Information, National Library of Medicine, Bethesda, Maryland, United States
  • Footnotes
    Commercial Relationships   Amr Elsawy None; Tiarnan Keenan None; Qingyu Chen None; Alisa T Thavikulwat None; Sanjeeb Bhandari None; Emily Chew None; Zhiyong Lu None
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science June 2022, Vol.63, 217 – F0064. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Amr Elsawy, Tiarnan D L Keenan, Qingyu Chen, Alisa T Thavikulwat, Sanjeeb Bhandari, Emily Y Chew, Zhiyong Lu; Detecting Cataract from Color Fundus Photographs Using Explainable Deep Learning. Invest. Ophthalmol. Vis. Sci. 2022;63(7):217 – F0064.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Diagnosing cataract usually requires in-person evaluation by an ophthalmologist. However, many individuals undergo color fundus photography (CFP) outside ophthalmology clinics, which represents an opportunity towards more accessible diagnosis by developing automated cataract detection methods. Therefore, the purpose of this study was to develop an explainable deep learning network that can detect cataract from color fundus photographs (CFPs) obtained from the Age-Related Eye Diseases Study 2 (AREDS2).

Methods : A dataset of 17, 514 CFPs was obtained from 2,573 AREDS2 participants. The dataset comprised 8,681 CFPs from eyes with cataract and 8,833 CFPs from eyes without cataract. The ground truth labels were transferred from slit lamp exams of nuclear cataracts conducted by ophthalmologists and from reading center gradings of the anterior segment photos (red reflex photos) for evaluating cortical and posterior subcapsular cataracts. The dataset was divided into training, validation, and testing datasets (70%, 20%, and 10% participants, respectively). A deep learning network was developed using separable convolutions and residual connections. The network performance was compared to that of three ophthalmologists. The network was visualized using Gradient Class Activation Maps (Grad-CAMs) where areas of high signal correspond to the CFP pixels that contributed most to the network decision.

Results : The network achieved performance scores (with 95% CI) of 0.6683 (0.6531, 0.6838), 0.6691 (0.6536, 0.685), 0.6686 (0.6533, 0.6842), 0.6686 (0.6533, 0.6842) compared to that of the combined ophthalmologists of 0.6025 (0.5100, 0.7000), 0.6119 (0.5085, 0.7123), 0.5988 (0.5074, 0.6895), and 0.5988 (0.5074, 0.6895) for accuracy, precision, recall, and AUC, respectively. Qualitative analysis of the Grad-CAMs, of correctly graded CFPs, showed that areas of high signal in CFPs without cataract and areas of low signal in CFPs with cataract corresponded to retinal blood vessels, as shown in Fig. 1.

Conclusions : The proposed network outperformed three ophthalmologists in the detection of cataract from CFP, which may increase the accessibility of cataract diagnosis. The detections were generally explainable where the retinal blood vessels seemed to be an important diagnostic feature.

This abstract was presented at the 2022 ARVO Annual Meeting, held in Denver, CO, May 1-4, 2022, and virtually.

 

Fig. 1: Examples of Grad-CAMs of correctly diagnosed CFPs (a) without and (b) with cataract.

Fig. 1: Examples of Grad-CAMs of correctly diagnosed CFPs (a) without and (b) with cataract.

×
×

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.

×