Addressing Artificial Intelligence Bias in Retinal Diagnostics.

Journal: Translational vision science & technology
Published Date: Feb 5, 2021

Abstract

PURPOSE: This study evaluated generative methods to potentially mitigate artificial intelligence (AI) bias when diagnosing diabetic retinopathy (DR) resulting from training data imbalance or domain generalization, which occurs when deep learning systems (DLSs) face concepts at test/inference time they were not initially trained on.

Authors

  • Philippe Burlina
    Applied Physics Laboratory, Johns Hopkins University, Laurel, Maryland, United States of America.
  • Neil Joshi
    Applied Physics Laboratory, Johns Hopkins University, Laurel, Maryland, United States of America.
  • William Paul
    Applied Physics Laboratory, The Johns Hopkins University, Baltimore, Maryland.
  • Katia D Pacheco
    Retina Division, Brazilian Center of Vision Eye Hospital, DF, Brazil.
  • Neil M Bressler
    Wilmer Eye Institute, Johns Hopkins University, Baltimore, Maryland4Editor, JAMA Ophthalmology.

Keywords

External Resources

Popular Topics
Recent Journals