Joint reconstruction and classification of tumor cells and cell interactions in melanoma tissue sections with synthesized training data.

Journal: International journal of computer assisted radiology and surgery
Published Date:

Abstract

PURPOSE: Cancers are almost always diagnosed by morphologic features in tissue sections. In this context, machine learning tools provide new opportunities to describe tumor immune cell interactions within the tumor microenvironment and thus provide phenotypic information that might be predictive for the response to immunotherapy.

Authors

  • Alexander Effland
    Institute for Numerical Simulation, University of Bonn, Bonn, Germany. alexander.effland@ins.uni-bonn.de.
  • Erich Kobler
    Institute of Computer Graphics and Vision, Graz University of Technology, Graz, Austria.
  • Anne Brandenburg
    Department of Dermatology and Allergy, University of Bonn, Bonn, Germany.
  • Teresa Klatzer
    Institute of Computer Graphics and Vision, Graz University of Technology, Graz, Austria.
  • Leonie Neuhäuser
    Institute for Numerical Simulation, University of Bonn, Bonn, Germany.
  • Michael Hölzel
    Institute of Clinical Chemistry and Clinical Pharmacology, University of Bonn, Bonn, Germany.
  • Jennifer Landsberg
    Department of Dermatology and Allergy, University of Bonn, Bonn, Germany.
  • Thomas Pock
    Institute of Computer Graphics and Vision, Graz University of Technology, Graz, Austria.
  • Martin Rumpf
    Institute for Numerical Simulation, University of Bonn, Bonn, Germany.