Improved Automated Detection of Diabetic Retinopathy on a Publicly Available Dataset Through Integration of Deep Learning.

Journal: Investigative ophthalmology & visual science
Published Date:

Abstract

PURPOSE: To compare performance of a deep-learning enhanced algorithm for automated detection of diabetic retinopathy (DR), to the previously published performance of that algorithm, the Iowa Detection Program (IDP)-without deep learning components-on the same publicly available set of fundus images and previously reported consensus reference standard set, by three US Board certified retinal specialists.

Authors

  • Michael David Abràmoff
    Department of Ophthalmology and Visual Sciences, University of Iowa Hospitals and Clinics, Iowa City, Iowa, United States 2Iowa City Veterans Affairs Medical Center, Iowa City, Iowa, United States 3IDx LLC, Iowa City, Iowa, United States.
  • Yiyue Lou
    Department of Biostatistics, College of Public Health, University of Iowa, Iowa City, Iowa, United States.
  • Ali Erginay
    Service d' Ophtalmologie, Hôpital Lariboisière, APHP, Paris, France.
  • Warren Clarida
    IDx LLC, Iowa City, Iowa, United States.
  • Ryan Amelon
    IDx LLC, Iowa City, Iowa, United States.
  • James C Folk
    1Department of Ophthalmology and Visual Sciences, University of Iowa, Iowa City, IA 52242 USA.
  • Meindert Niemeijer
    IDx LLC, Iowa City, Iowa, United States.