Contrast Media Reduction in Computed Tomography With Deep Learning Using a Generative Adversarial Network in an Experimental Animal Study.

Journal: Investigative radiology
PMID: 35438659

Abstract

OBJECTIVE: This feasibility study aimed to use optimized virtual contrast enhancement through generative adversarial networks (GAN) to reduce the dose of iodine-based contrast medium (CM) during abdominal computed tomography (CT) in a large animal model.

Authors

  • Johannes Haubold
    Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147, Essen, Germany. Johannes.haubold@uk-essen.de.
  • Gregor Jost
    MR and CT Contrast Media Research, Bayer AG, Berlin.
  • Jens Matthias Theysohn
    From the Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Essen.
  • Johannes Maximilian Ludwig
    From the Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Essen.
  • Yan Li
    Interdisciplinary Research Center for Biology and Chemistry, Liaoning Normal University, Dalian, China.
  • Jens Kleesiek
    AG Computational Radiology, Abteilung Radiologie, Deutsches Krebsforschungszentrum (DKFZ), Im Neuenheimer Feld 280, 69120, Heidelberg, Deutschland. j.kleesiek@dkfz-heidelberg.de.
  • Benedikt Michael Schaarschmidt
    University Dusseldorf, Medical Faculty, Department of Diagnostic and Interventional Radiology, Germany. Electronic address: Benedikt.Schaarschmidt@med.uni-duesseldorf.de.
  • Michael Forsting
    Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Hufelandstraße 55, 45147, Essen, Germany.
  • Felix Nensa
    Institute for AI in Medicine (IKIM), University Hospital Essen, 45131 Essen, Germany.
  • Hubertus Pietsch
    MR and CT Contrast Media Research, Bayer AG, Berlin.
  • René Hosch
    Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Germany.

Keywords

External Resources

Popular Topics
Recent Journals