June 2020
Volume 61, Issue 7
Open Access
ARVO Annual Meeting Abstract  |   June 2020
Deep learning automated detection of reticular pseudodrusen from fundus autofluorescence images and color fundus photographs in the Age-Related Eye Disease Study 2 (AREDS2)
Author Affiliations & Notes
  • Tiarnan D L Keenan
    Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, Maryland, United States
  • Qingyu Chen
    National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, Maryland, United States
  • Yifan Peng
    National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, Maryland, United States
  • Amitha Domalpally
    Fundus Photographic Reading Center, University of Wisconsin, Bethesda, Maryland, United States
  • Elvira Agron
    Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, Maryland, United States
  • Christopher K Hwang
    Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, Maryland, United States
  • Alisa Therese Thavikulwat
    Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, Maryland, United States
  • Debora Hana Lee
    Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, Maryland, United States
  • Daniel Li
    National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, Maryland, United States
  • Wai T. Wong
    Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, Maryland, United States
    Section on Neuron-Glia Interactions in Retinal Disease, National Eye Institute, National Institutes of Health, Bethesda, Maryland, United States
  • Zhiyong Lu
    National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health, Bethesda, Maryland, United States
  • Emily Chew
    Division of Epidemiology and Clinical Applications, National Eye Institute, National Institutes of Health, Bethesda, Maryland, United States
  • Footnotes
    Commercial Relationships   Tiarnan Keenan, None; Qingyu Chen, None; Yifan Peng, None; Amitha Domalpally, None; Elvira Agron, None; Christopher Hwang, None; Alisa Thavikulwat, None; Debora Lee, None; Daniel Li, None; Wai Wong, None; Zhiyong Lu, None; Emily Chew, None
  • Footnotes
    Support  Supported by the intramural program funds and contracts from the National Center for Biotechnology Information/National Library of Medicine/National Institutes of Health, the National Eye Institute/National Institutes of Health, Department of Health and Human Services, Bethesda Maryland (contract HHS-N-260-2005-00007-C; ADB contract NO1-EY-5-0007; grant K99LM013001). Funds were generously contributed to these contracts by the following NIH institutes: Office of Dietary Supplements, National Center for Complementary and Alternative Medicine; National Institute on Aging; National Heart, Lung, and Blood Institute, and National Institute of Neurological Disorders and Stroke. The sponsor and funding organization participated in the design and conduct of the study; data collection, management, analysis, and interpretation; and the preparation, review and approval of the manuscript. We also acknowledge the financial support of The Heed Ophthalmic Foundation (CKH) and the NIH Medical Research Scholars Program (DHL), a public-private partnership supported jointly by the NIH and contributions to the Foundation for the NIH from the Doris Duke Charitable Foundation (DDCF Grant #2014194), the American Association for Dental Research, the Colgate-Palmolive Company, Genentech, Elsevier, and other private donors.
Investigative Ophthalmology & Visual Science June 2020, Vol.61, 1644. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Tiarnan D L Keenan, Qingyu Chen, Yifan Peng, Amitha Domalpally, Elvira Agron, Christopher K Hwang, Alisa Therese Thavikulwat, Debora Hana Lee, Daniel Li, Wai T. Wong, Zhiyong Lu, Emily Chew; Deep learning automated detection of reticular pseudodrusen from fundus autofluorescence images and color fundus photographs in the Age-Related Eye Disease Study 2 (AREDS2). Invest. Ophthalmol. Vis. Sci. 2020;61(7):1644.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : To develop and evaluate deep learning (DL) models for detecting reticular pseudodrusen (RPD) using fundus autofluorescence (FAF) images. Second, using the novel technique of label transfer, to develop models for RPD detection using color fundus photographs (CFP). The latter is important because RPD are detected by human graders at much lower sensitivity on CFP than on FAF.

Methods : The AREDS2 dataset was used, comprising 11,535 FAF images of 2,450 participants with age-related macular degeneration (AMD), and 11,535 corresponding CFP. Ground truth labels were from reading center grading of the FAF images; these were transferred to corresponding CFP images. A FAF DL model was trained to detect RPD from FAF images. Using label transfer, a CFP DL model was trained to detect RPD from CFP. The main outcome measure was area under curve (AUC). Additionally, model performance was compared with grading of a subset of FAF and CFP images by four retinal specialists in a clinical setting.

Results : The FAF model had AUC 0.939 (95% CI 0.927-0.950), accuracy 0.899 (0.887-0.911), F1-score 0.783 (0.755-0.809), and kappa 0.718 (0.685-0.751) (Figure A). The CFP model had values of 0.832 (0.812-0.851), 0.809 (0.793-0.825), 0.593 (0.557-0.627), and 0.470 (0.426-0.511), respectively (Figure B). Performance measures for the FAF model were generally superior to those of the four retinal specialist graders; they exceeded the mean and matched the highest scores of the four specialists (Table). Performance measures for the CFP model were substantially superior to those of the four retinal specialist graders (Table).

Conclusions : DL-enabled automated detection of RPD presence can be achieved at high accuracy from FAF images, with equal or superior performance to that of retinal specialists. DL detection from CFP images also has relatively high accuracy, with substantially superior performance to retinal specialists. DL models can assist, and even augment, the detection of this clinically important, AMD-associated lesion.

This is a 2020 ARVO Annual Meeting abstract.

 


Figure. ROC curves for RPD detection by deep learning models from (A) FAF images and (B) corresponding CFP images. Human retinal specialist performance is shown (green dots).


Figure. ROC curves for RPD detection by deep learning models from (A) FAF images and (B) corresponding CFP images. Human retinal specialist performance is shown (green dots).

 

Table. Performance of the deep learning models and four retinal specialists for RPD detection. For each metric, the highest result is highlighted in bold.

Table. Performance of the deep learning models and four retinal specialists for RPD detection. For each metric, the highest result is highlighted in bold.

×
×

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.

×