Realistic fundus photograph generation for improving automated disease classification.

Journal: The British journal of ophthalmology
Published Date: Jun 23, 2025

Abstract

AIMS: This study aims to investigate whether denoising diffusion probabilistic models (DDPMs) could generate realistic retinal images, and if they could be used to improve the performance of a deep convolutional neural network (CNN) ensemble for multiple retinal disease classification, which was previously shown to outperform human experts.

Authors

  • Prashant U Pandey
    School of Biomedical Engineering, University of British Columbia, Vancouver, Canada. prashant@ece.ubc.ca.
  • Jonathan A Micieli
    Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, ON.
  • Stephan Ong Tone
    Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada.
  • Kenneth T Eng
    Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, Ontario, Canada.
  • Peter J Kertes
    Department of Ophthalmology and Vision Sciences, University of Toronto, Toronto, ON, Canada.
  • 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