July 2019
Volume 60, Issue 9
Free
ARVO Annual Meeting Abstract  |   July 2019
Deep neural network and human evaluation of referral-warranted diabetic retinopathy using smartphone-based retinal photographs
Author Affiliations & Notes
  • Michael Aaberg
    Ophthalmology and Visual Sciences, University of Michigan, Ann Arbor, Michigan, United States
  • Tyson Kim
    Ophthalmology and Visual Sciences, University of Michigan, Ann Arbor, Michigan, United States
  • Patrick Li
    Ophthalmology and Visual Sciences, University of Michigan, Ann Arbor, Michigan, United States
  • Leslie Niziol
    Ophthalmology and Visual Sciences, University of Michigan, Ann Arbor, Michigan, United States
  • Malavika Bhaskaranand
    Eyenuk Inc., California, United States
  • Sandeep Bhat
    Eyenuk Inc., California, United States
  • Chaithanya Ramachandra
    Eyenuk Inc., California, United States
  • Kaushal Solanki
    Eyenuk Inc., California, United States
  • Jose Davila
    Ophthalmology and Visual Sciences, University of Michigan, Ann Arbor, Michigan, United States
  • Frankie Myers
    Department of Bioengineering, University of California Berkeley, California, United States
  • Clay Reber
    Department of Bioengineering, University of California Berkeley, California, United States
  • David C Musch
    Ophthalmology and Visual Sciences, University of Michigan, Ann Arbor, Michigan, United States
  • Todd Margolis
    Department of Ophthalmology and Visual Sciences, Washington University School of Medicine, Montana, United States
  • Daniel Fletcher
    Department of Bioengineering, University of California Berkeley, California, United States
  • Yannis Mantas Paulus
    Ophthalmology and Visual Sciences, University of Michigan, Ann Arbor, Michigan, United States
    Department of Biomedical Engineering, University of Michigan, Ann Arbor, Michigan, United States
  • Footnotes
    Commercial Relationships   Michael Aaberg, None; Tyson Kim, Retinal CellScope Apparatus (P); Patrick Li, None; Leslie Niziol, None; Malavika Bhaskaranand, Eyenuk Inc. (E); Sandeep Bhat, Eyenuk Inc. (E); Chaithanya Ramachandra, Eyenuk Inc. (E); Kaushal Solanki, Eyenuk Inc. (E); Jose Davila, None; Frankie Myers, None; Clay Reber, Eyenuk Inc. (E); David Musch, None; Todd Margolis, None; Daniel Fletcher, CellScope (I), CellScope (E); Yannis Paulus, None
  • Footnotes
    Support  Knights Templar Eye Foundation Career-Starter Research Grant, University of Michigan Translational Research and Commercialization for Life Sciences, University of Michigan Center for Entrepreneurship Dean’s Engineering Translational Prototype Research Fund, QB3 Bridging the Gap Award from the Rogers Family Foundation, Bakar Fellows Award, Chan-Zuckerberg Biohub Investigator award, National Eye Institute grant 1K08EY027458 and 4K12EY022299, University of Michigan Department of Ophthalmology and Visual Sciences, and unrestricted departmental support from Research to Prevent Blindness
Investigative Ophthalmology & Visual Science July 2019, Vol.60, 1444. doi:https://doi.org/
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Michael Aaberg, Tyson Kim, Patrick Li, Leslie Niziol, Malavika Bhaskaranand, Sandeep Bhat, Chaithanya Ramachandra, Kaushal Solanki, Jose Davila, Frankie Myers, Clay Reber, David C Musch, Todd Margolis, Daniel Fletcher, Yannis Mantas Paulus; Deep neural network and human evaluation of referral-warranted diabetic retinopathy using smartphone-based retinal photographs. Invest. Ophthalmol. Vis. Sci. 2019;60(9):1444. doi: https://doi.org/.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Diabetic retinopathy remains a leading cause of vision loss in working-age adults due to low screening rates. Smartphone-based retinal photography has emerged as a portable tool capable of accessing greater patient populations and increasing screening rates. The aim of this study is to investigate the efficacy of a mobile platform that combines high-quality, smartphone-based retinal imaging with automated grading for determining the presence of referral-warranted diabetic retinopathy (RWDR).

Methods : Adult patients were recruited at the University of Michigan Kellogg Eye Center Retina Clinic. A smartphone-based camera (RetinaScope) was used to image the retina of patients with diabetes with no significant media opacity. Images were analyzed with the Eyenuk EyeArtTM software, which generates referral recommendations based on presence of moderate or worse diabetic retinopathy (DR) or markers for clinically significant macular edema (CSME) through autonomous, cloud based, deep neural network software. Images were then independently evaluated by two masked readers and similarly categorized as RWDR or non-RWDR. The sensitivity and specificity of the masked graders and automated interpretation were determined by comparing the results to the treating clinician’s dilated slit-lamp fundus examination.

Results : A total of 119 eyes from 69 patients were included for analysis. By slit-lamp examination, RWDR was present in 86 eyes (72.3%). At the eye-level, automated interpretation had a sensitivity of 77.9% and specificity of 69.7%; grader 1 had a sensitivity of 94.2% and specificity of 51.5%; grader 2 had a sensitivity of 89.3% and specificity of 63.6%. At the patient-level, RWDR was present in 53 subjects (76.8%). Automated interpretation had a sensitivity of 86.8% and specificity of 73.3%; grader 1 had a sensitivity of 96.2% and specificity of 40.0%; grader 2 had a sensitivity of 92.3% and specificity of 46.7%.

Conclusions : Smartphone-based retinal photography combined with autonomous, deep neural network software is an effective screening tool for RWDR and, at the patient level, it achieves a slightly higher specificity but lower sensitivity than trained human graders. Future studies following more patients in randomized, community-based cohorts of undifferentiated diabetic patients are needed.

This abstract was presented at the 2019 ARVO Annual Meeting, held in Vancouver, Canada, April 28 - May 2, 2019.

×
×

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.

×