An analysis of the effects of limited training data in distributed learning scenarios for brain age prediction.

Journal: Journal of the American Medical Informatics Association : JAMIA
Published Date:

Abstract

OBJECTIVE: Distributed learning avoids problems associated with central data collection by training models locally at each site. This can be achieved by federated learning (FL) aggregating multiple models that were trained in parallel or training a single model visiting sites sequentially, the traveling model (TM). While both approaches have been applied to medical imaging tasks, their performance in limited local data scenarios remains unknown. In this study, we specifically analyze FL and TM performances when very small sample sizes are available per site.

Authors

  • Raissa Souza
    Department of Radiology, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada.
  • Pauline Mouches
    Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada.
  • Matthias Wilms
    Department of Radiology, University of Calgary, Calgary, AB, Canada.
  • Anup Tuladhar
    Department of Radiology, University of Calgary, Calgary, Alberta, Canada; Hotchkiss Brain Institute, University of Calgary, Calgary, Alberta, Canada. Electronic address: anup.tuladhar@ucalgary.ca.
  • Sönke Langner
    Institute for Diagnostic Radiology and Neuroradiology, Rostock University Medical Center, Rostock, Germany.
  • Nils D Forkert
    Department of Radiology, University of Calgary, Calgary, Canada. nils.forkert@ucalgary.ca.