Radiomics for glioblastoma survival analysis in pre-operative MRI: exploring feature robustness, class boundaries, and machine learning techniques.

Journal: Cancer imaging : the official publication of the International Cancer Imaging Society
Published Date: Aug 5, 2020

Abstract

BACKGROUND: This study aims to identify robust radiomic features for Magnetic Resonance Imaging (MRI), assess feature selection and machine learning methods for overall survival classification of Glioblastoma multiforme patients, and to robustify models trained on single-center data when applied to multi-center data.

Authors

  • Yannick Suter
    ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland. yannick.suter@artorg.unibe.ch.
  • Urspeter Knecht
    Institute for Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, and University of Bern, Bern, Switzerland.
  • Mariana Alão
    ARTORG Center for Biomedical Engineering Research, University of Bern, Bern, Switzerland.
  • Waldo Valenzuela
    Insel Data Science Center, Inselspital, Bern University Hospital, Murtenstrasse 42, CH-3008, Bern, Switzerland.
  • Ekkehard Hewer
    Institute of Pathology, University of Bern, Bern, Switzerland.
  • Philippe Schucht
    Department of Neurosurgery, Inselspital, Bern University Hospital, Bern, Switzerland.
  • Roland Wiest
    Institute for Diagnostic and Interventional Neuroradiology, University of Bern, Bern, Switzerland.
  • Mauricio Reyes
    Center for Artificial Intelligence in Medicine, University of Bern, Bern, Switzerland.

Keywords

External Resources

Popular Topics
Recent Journals