Liver lesion localisation and classification with convolutional neural networks: a comparison between conventional and spectral computed tomography.

Journal: Biomedical physics & engineering express
Published Date:

Abstract

PURPOSE: To evaluate the benefit of the additional available information present in spectral CT datasets, as compared to conventional CT datasets, when utilizing convolutional neural networks for fully automatic localisation and classification of liver lesions in CT images.

Authors

  • Nadav Shapira
    Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, United States of America.
  • Julia Fokuhl
  • Manuel Schultheiß
  • Stefanie Beck
  • Felix K Kopp
    Department of Diagnostic and Interventional Radiology, Technische Universität München, Munich, 81675, Germany.
  • Daniela Pfeiffer
    Department of Diagnostic and Interventional Radiology, Technische Universität München, Munich, 81675, Germany.
  • Julia Dangelmaier
  • Gregor Pahn
  • Andreas P Sauter
  • Bernhard Renger
  • Alexander A Fingerle
    Department of Diagnostic and Interventional Radiology, Technische Universität München, Munich, 81675, Germany.
  • Ernst J Rummeny
    Department of Diagnostic and Interventional Radiology, Technische Universität München, Munich, 81675, Germany.
  • Shadi Albarqouni
  • Nassir Navab
    Chair for Computer Aided Medical Procedures & Augmented Reality, TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Germany.
  • Peter B Noël
    Department of Diagnostic and Interventional Radiology, Technische Universität München, Munich, 81675, Germany.