Causal insights from clinical information in radiology: Enhancing future multimodal AI development.

Journal: Computer methods and programs in biomedicine
Published Date:

Abstract

PURPOSE: This study investigates the causal mechanisms underlying radiology report generation by analyzing how clinical information and prior imaging examinations contribute to annotation shifts. We systematically estimate why and how biases manifest, providing insights into the data generation process that influences radiology reporting.

Authors

  • Michael Jantscher
    Chiesi Farmaceutici S.p.A, Parma, Italy.
  • Felix Gunzer
    Diagnostic and interventional Radiology, University Hospital Zurich, Zurich, Switzerland; Department of Neuroradiology, University Hospital Zurich, Zurich, Switzerland.
  • Gernot Reishofer
    Department of Radiology, Medical University of Graz, Auenbruggerplatz 9, Graz, 8036, Austria.
  • Roman Kern
    Know-Center GmbH, Knowledge Discovery, Graz, Austria.