A systematic review on the use of explainability in deep learning systems for computer aided diagnosis in radiology: Limited use of explainable AI?

Journal: European journal of radiology
Published Date:

Abstract

OBJECTIVES: This study aims to contribute to an understanding of the explainability of computer aided diagnosis studies in radiology that use end-to-end deep learning by providing a quantitative overview of methodological choices and by discussing the implications of these choices for their explainability.

Authors

  • Arjan M Groen
    Department of Radiology and Nuclear Medicine, Amsterdam Movement Sciences, Amsterdam UMC Location AMC, Amsterdam, Netherlands. Electronic address: a.m.groen@amsterdamumc.nl.
  • Rik Kraan
    Department of Radiology and Nuclear Medicine, Amsterdam Movement Sciences, Amsterdam UMC Location AMC, Amsterdam, Netherlands.
  • Shahira F Amirkhan
    Department of Radiology and Nuclear Medicine, Amsterdam Movement Sciences, Amsterdam UMC Location AMC, Amsterdam, Netherlands.
  • Joost G Daams
    Medical Library, Amsterdam UMC Location AMC, Amsterdam, Netherlands.
  • Mario Maas
    Department of Radiology and Nuclear Medicine, Amsterdam University Medical Centers, The Netherlands.