Self-Supervised Feature Learning and Phenotyping for Assessing Age-Related Macular Degeneration Using Retinal Fundus Images.

Journal: Ophthalmology. Retina
Published Date: Jul 2, 2021

Abstract

OBJECTIVE: Diseases such as age-related macular degeneration (AMD) are classified based on human rubrics that are prone to bias. Supervised neural networks trained using human-generated labels require labor-intensive annotations and are restricted to specific trained tasks. Here, we trained a self-supervised deep learning network using unlabeled fundus images, enabling data-driven feature classification of AMD severity and discovery of ocular phenotypes.

Authors

  • Baladitya Yellapragada
    Department of Vision Science, University of California, Berkeley, Berkeley, California; International Computer Science Institute, Berkeley, California; Department of Ophthalmology & Vision Science, University of California, Davis, Sacramento, California.
  • Sascha Hornauer
    International Computer Science Institute, Berkeley, California.
  • Kiersten Snyder
    Department of Ophthalmology & Vision Science, University of California, Davis, Sacramento, California.
  • Stella Yu
    Department of Vision Science, University of California, Berkeley, Berkeley, California; International Computer Science Institute, Berkeley, California.
  • Glenn Yiu
    Department of Ophthalmology & Vision Science, University of California, Davis, Sacramento, California. Electronic address: gyiu@ucdavis.edu.

Keywords

External Resources

Popular Topics
Recent Journals