Ensemble of deep convolutional neural networks is more accurate and reliable than board-certified ophthalmologists at detecting multiple diseases in retinal fundus photographs.

Journal: The British journal of ophthalmology
Published Date: Feb 21, 2024

Abstract

AIMS: To develop an algorithm to classify multiple retinal pathologies accurately and reliably from fundus photographs and to validate its performance against human experts.

Authors

  • Prashant U Pandey
    School of Biomedical Engineering, University of British Columbia, Vancouver, Canada. prashant@ece.ubc.ca.
  • Brian G Ballios
    Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada.
  • Panos G Christakis
    Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada.
  • Alexander J Kaplan
    Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada.
  • David J Mathew
    Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada.
  • Stephan Ong Tone
    Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada.
  • Michael J Wan
    Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada.
  • Jonathan A Micieli
    Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, ON.
  • Jovi C Y Wong
    Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada jovi.wong@mail.utoronto.ca.

Keywords

External Resources

Popular Topics
Recent Journals