Understanding Biases and Disparities in Radiology AI Datasets: A Review.

Journal: Journal of the American College of Radiology : JACR
Published Date: Jul 16, 2023

Abstract

Artificial intelligence (AI) continues to show great potential in disease detection and diagnosis on medical imaging with increasingly high accuracy. An important component of AI model creation is dataset development for training, validation, and testing. Diverse and high-quality datasets are critical to ensure robust and unbiased AI models that maintain validity, especially in traditionally underserved populations globally. Yet publicly available datasets demonstrate problems with quality and inclusivity. In this literature review, the authors evaluate publicly available medical imaging datasets for demographic, geographic, genetic, and disease representation or lack thereof and call for an increase emphasis on dataset development to maximize the impact of AI models.

Authors

  • Satvik Tripathi
    Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA; Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, MA, USA.
  • Kyla Gabriel
    Department of Biomedical Informatics, Harvard Medical School, Boston, Massachusetts.
  • Suhani Dheer
    Department of Psychiatry, Brigham and Women's Hospital, Boston, MA, United States; Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, MA, United States; Harvard Medical School, Boston, MA, United States.
  • Aastha Parajuli
    Department of Radiology, Kathmandu University of School of Medical Sciences, Dhulikhel, Nepal.
  • Alisha Isabelle Augustin
    College of Engineering, Drexel University, Philadelphia, Pennsylvania.
  • Ameena Elahi
    From RAD-AID International, 8004 Ellingson Dr, Chevy Chase, MD 20815 (D.J.M., M.P.C., E.P., G.B., J.R.S., V.L.M., A.E., A.S., F.D.); Department of Radiology and Medical Imaging, Denver Health and Hospital Authority, Denver, Colo (E.P.); Departments of Radiology and Global Health, University of Washington, Seattle, Wash (J.R.S.); Fred Hutchinson Cancer Research Center, Seattle, Wash (J.R.S.); Department of Radiology, Memorial Sloan-Kettering Cancer Center, New York, NY (V.L.M.); Department of Radiology, University of Pennsylvania Health System, Philadelphia, Pa (A.E.); and Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, Md (F.D.).
  • Omar Awan
    Department of Radiology, University of Maryland School of Medicine, Baltimore, Maryland.
  • Farouk Dako
    Department of Radiology, Hospital of the University of Pennsylvania, Philadelphia, PA, USA.

Keywords

External Resources

Popular Topics
Recent Journals