AI in motion: the impact of data augmentation strategies on mitigating MRI motion artifacts.

Journal: European radiology
Published Date:

Abstract

OBJECTIVES: Artifacts in clinical MRI can compromise the performance of AI models. This study evaluates how different data augmentation strategies affect an AI model's segmentation performance under variable artifact severity.

Authors

  • Simon D Westfechtel
    Department for Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany. swestfechtel@ukaachen.de.
  • Kristoffer Kußmann
    Department for Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany.
  • Cederic Aßmann
    Department for Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany.
  • Marc S Huppertz
    Department for Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany.
  • Robert M Siepmann
    Department for Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany.
  • Teresa Lemainque
    Department of Diagnostic and Interventional Radiology, Medical Faculty, RWTH Aachen University, 52074 Aachen, Germany. Electronic address: tlemainque@ukaachen.de.
  • Vera R Winter
    Department for Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany.
  • Alexandra Barabasch
    Department of Diagnostic and Interventional Radiology, Medical Faculty, RWTH Aachen University, 52074 Aachen, Germany.
  • Christiane K Kuhl
    Department of Diagnostic and Interventional Radiology, RWTH Aachen University Hospital, Pauwelsstraße 30, 52072, Aachen, Germany.
  • Daniel Truhn
    Department of Diagnostic and Interventional Radiology, University Hospital Düsseldorf, Düsseldorf, Germany (J.S., D.B.A., S.N.); Institute of Computer Vision and Imaging, RWTH University Aachen, Pauwelsstrasse 30, 52072 Aachen, Germany (J.S., D.M.); Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany (D.T., M.P., F.M., C.K., S.N.); and Faculty of Mathematics and Natural Sciences, Institute of Informatics, Heinrich Heine University Düsseldorf, Düsseldorf, Germany (S.C.).
  • Sven Nebelung
    Department of Diagnostic and Interventional Radiology, University Hospital Düsseldorf, Düsseldorf, Germany (J.S., D.B.A., S.N.); Institute of Computer Vision and Imaging, RWTH University Aachen, Pauwelsstrasse 30, 52072 Aachen, Germany (J.S., D.M.); Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany (D.T., M.P., F.M., C.K., S.N.); and Faculty of Mathematics and Natural Sciences, Institute of Informatics, Heinrich Heine University Düsseldorf, Düsseldorf, Germany (S.C.).

Keywords

No keywords available for this article.