You are here

  • Home
  • Archive
  • Volume 108, Issue 3
  • Ensemble of deep convolutional neural networks is more accurate and reliable than board-certified ophthalmologists at detecting multiple diseases in retinal fundus photographs

Article info

Article menu

Download PDFPDF

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

Authors

  • Prashant U Pandey School of Biomedical Engineering, The University of British Columbia, Vancouver, British Columbia, Canada PubMed articlesGoogle scholar articles
  • Brian G Ballios Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada Krembil Research Institute, University Health Network, Toronto, Ontario, Canada Kensington Vision and Research Centre and Kensington Research Institute, Toronto, Ontario, Canada PubMed articlesGoogle scholar articles
  • Panos G Christakis Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada Kensington Vision and Research Centre and Kensington Research Institute, Toronto, Ontario, Canada PubMed articlesGoogle scholar articles
  • Alexander J Kaplan Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada PubMed articlesGoogle scholar articles
  • David J Mathew Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada Krembil Research Institute, University Health Network, Toronto, Ontario, Canada Kensington Vision and Research Centre and Kensington Research Institute, Toronto, Ontario, Canada PubMed articlesGoogle scholar articles
  • Stephan Ong Tone Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada Sunnybrook Research Institute, Toronto, Ontario, Canada PubMed articlesGoogle scholar articles
  • Michael J Wan Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada PubMed articlesGoogle scholar articles
  • Jonathan A Micieli Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada Kensington Vision and Research Centre and Kensington Research Institute, Toronto, Ontario, Canada Department of Ophthalmology, St. Michael's Hospital, Unity Health, Toronto, Ontario, Canada PubMed articlesGoogle scholar articles
  • Jovi C Y Wong Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada PubMed articlesGoogle scholar articles
  1. Correspondence to Dr Jovi C Y Wong, Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Canada; jovi.wong{at}mail.utoronto.ca
View Full Text

Citation

Pandey PU, Ballios BG, Christakis PG, et al
Ensemble of deep convolutional neural networks is more accurate and reliable than board-certified ophthalmologists at detecting multiple diseases in retinal fundus photographs
British Journal of Ophthalmology 2024;108:417-423.

Publication history

  • Received July 7, 2022
  • Accepted January 11, 2023
  • First published January 31, 2023.
Online issue publication 
February 21, 2024

Request permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

Copyright information

© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ. http://creativecommons.org/licenses/by-nc/4.0/This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited, appropriate credit is given, any changes made indicated, and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/.