Where, why, and how is bias learned in medical image analysis models? A study of bias encoding within convolutional networks using synthetic data.

Journal: EBioMedicine
Published Date:

Abstract

BACKGROUND: Understanding the mechanisms of algorithmic bias is highly challenging due to the complexity and uncertainty of how various unknown sources of bias impact deep learning models trained with medical images. This study aims to bridge this knowledge gap by studying where, why, and how biases from medical images are encoded in these models.

Authors

  • Emma A M Stanley
    Biomedical Engineering Graduate Program, University of Calgary, Calgary, Alberta, T2N 1N4, Canada.
  • Raissa Souza
    Department of Radiology, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada.
  • Matthias Wilms
    Department of Radiology, University of Calgary, Calgary, AB, Canada.
  • Nils D Forkert
    Department of Radiology, University of Calgary, Calgary, Canada. nils.forkert@ucalgary.ca.