Clinical Evaluation of a Multiparametric Deep Learning Model for Glioblastoma Segmentation Using Heterogeneous Magnetic Resonance Imaging Data From Clinical Routine.

Journal: Investigative radiology
Published Date: Nov 1, 2018

Abstract

OBJECTIVES: The aims of this study were, first, to evaluate a deep learning-based, automatic glioblastoma (GB) tumor segmentation algorithm on clinical routine data from multiple centers and compare the results to a ground truth, manual expert segmentation, and second, to evaluate the quality of the segmentation results across heterogeneous acquisition protocols of routinely acquired clinical magnetic resonance imaging (MRI) examinations from multiple centers.

Authors

  • Michael Perkuhn
    Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Cologne, Germany.
  • Pantelis Stavrinou
    Department of Neurosurgery, University Hospital Cologne, Cologne, Germany.
  • Frank Thiele
    Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Cologne, Germany.
  • Georgy Shakirin
    Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Cologne, Germany.
  • Manoj Mohan
    Data Science, Philips Healthcare, Bangalore, India.
  • Dionysios Garmpis
  • Christoph Kabbasch
  • Jan Borggrefe
    Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Cologne, Germany. jan.borggrefe@uk-koeln.de.

Keywords

External Resources

Popular Topics
Recent Journals