Convolutional neural networks for head and neck tumor segmentation on 7-channel multiparametric MRI: a leave-one-out analysis.

Journal: Radiation oncology (London, England)
Published Date: Jul 29, 2020

Abstract

BACKGROUND: Automatic tumor segmentation based on Convolutional Neural Networks (CNNs) has shown to be a valuable tool in treatment planning and clinical decision making. We investigate the influence of 7 MRI input channels of a CNN with respect to the segmentation performance of head&neck cancer.

Authors

  • Lars Bielak
    Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany. lars.bielak@uniklinik-freiburg.de.
  • Nicole Wiedenmann
    German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany.
  • Arnie Berlin
    MathWorks, Inc, Novi, MI, USA.
  • Nils Henrik Nicolay
    German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany.
  • Deepa Darshini Gunashekar
    Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany.
  • Leonard Hägele
    Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany.
  • Thomas Lottner
    Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany.
  • Anca-Ligia Grosu
    German Cancer Consortium (DKTK), Partner Site Freiburg, Freiburg, Germany.
  • Michael Bock
    Department of Radiology, Medical Physics, Medical Center University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany.

Keywords

External Resources

Popular Topics
Recent Journals