Investigative Ophthalmology & Visual Science Cover Image for Volume 59, Issue 9
July 2018
Volume 59, Issue 9
Open Access
ARVO Annual Meeting Abstract  |   July 2018
Predicting refractive error from retinal fundus images using deep learning
Author Affiliations & Notes
  • Ryan Poplin
    Google Research, Google, Inc., Mountain View, California, United States
  • Avinash Varadarajan
    Google Research, Google, Inc., Mountain View, California, United States
  • Katy Blumer
    Google Research, Google, Inc., Mountain View, California, United States
  • Christof Angermueller
    Google Research, Google, Inc., Mountain View, California, United States
  • Joe Ledsam
    Google DeepMind, Google, Inc., London, United Kingdom
  • Reena Chopra
    NIHR Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology, London, United Kingdom
  • Pearse Keane
    Google DeepMind, Google, Inc., London, United Kingdom
    NIHR Biomedical Research Centre for Ophthalmology, Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology, London, United Kingdom
  • Greg Corrado
    Google Research, Google, Inc., Mountain View, California, United States
  • Lily Peng
    Google Research, Google, Inc., Mountain View, California, United States
  • Dale Webster
    Google Research, Google, Inc., Mountain View, California, United States
  • Footnotes
    Commercial Relationships   Ryan Poplin, Google, Inc. (E), Google, Inc. (P); Avinash Varadarajan, Google, Inc. (E), Google, Inc. (P); Katy Blumer, Google, Inc. (E), Google, Inc. (P); Christof Angermueller, Google, Inc. (E), Google, Inc. (P); Joe Ledsam, Google, Inc. (E), Google, Inc. (P); Reena Chopra, None; Pearse Keane, Allergan (R), Bayer (R), Google, Inc. (C), Haag-Streit (R), Heidelberg Engineering (R), Novartis (R), Topcon (R), Zeiss (R); Greg Corrado, Google, Inc. (E), Google, Inc. (P); Lily Peng, Google, Inc. (E), Google, Inc. (P); Dale Webster, Google, Inc. (E), Google, Inc. (P)
  • Footnotes
    Support  None
Investigative Ophthalmology & Visual Science July 2018, Vol.59, 1729. doi:
  • Views
  • Share
  • Tools
    • Alerts
      ×
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Ryan Poplin, Avinash Varadarajan, Katy Blumer, Christof Angermueller, Joe Ledsam, Reena Chopra, Pearse Keane, Greg Corrado, Lily Peng, Dale Webster; Predicting refractive error from retinal fundus images using deep learning. Invest. Ophthalmol. Vis. Sci. 2018;59(9):1729.

      Download citation file:


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

      ×
  • Supplements
Abstract

Purpose : Deep learning has show great promise in diagnosis and interpretation of retinal imaging with the potential to identify new image features to augment current medical practice. In this study we demonstrate this by training a model to estimate spherical equivalent refractive error from fundus photographs.

Methods : A deep convolutional neural network was trained to predict spherical equivalent refractive error from retinal fundus photographs from the UK Biobank (autorefraction) and AREDS (subjective refraction) clinical trial cohorts. Prediction accuracy was tested against documented refractive error measurements. We use soft-attention to identify image features that contributed most to model predictions.

Results : The resulting algorithm had a mean average error (MAE) of 0.56 diopters (95% CI: 0.55-0.56) for estimating spherical equivalent on the UK Biobank dataset and 0.91 diopters (95% CI: 0.89-0.92) for the AREDS dataset. The baseline expected MAE (obtained by predicting the mean of this population) is 1.81 diopters (95% CI: 1.79-1.84) for UK Biobank and 1.63 (95% CI: 1.60-1.67) for AREDS. Attention maps suggest that the foveal region is one of the most important areas that is used by the algorithm to make this prediction, though other regions also contribute to the prediction.

Conclusions : The ability to estimate refractive error with high accuracy from retinal fundus photos has not been previously known and demonstrates that deep learning can be applied to make novel predictions from medical images. In addition recent advances in obtaining retinal fundus photographs using mobile phones and inexpensive attachments suggest this work may be particularly relevant in regions of the world where autorefractors may not be readily available.

This is an abstract that was submitted for the 2018 ARVO Annual Meeting, held in Honolulu, Hawaii, April 29 - May 3, 2018.

×
×

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.

×