Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI.

Journal: European radiology
Published Date: Jun 25, 2018

Abstract

OBJECTIVES: Magnetic resonance imaging (MRI) is the method of choice for imaging meningiomas. Volumetric assessment of meningiomas is highly relevant for therapy planning and monitoring. We used a multiparametric deep-learning model (DLM) on routine MRI data including images from diverse referring institutions to investigate DLM performance in automated detection and segmentation of meningiomas in comparison to manual segmentations.

Authors

  • Kai Roman Laukamp
    Institute for Diagnostic and Interventional Radiology, 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.
  • David Zopfs
    Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Cologne, Germany.
  • Andrea Faymonville
    Department of Neurosurgery, University Hospital Cologne, Cologne, Germany.
  • Marco Timmer
    Neurosurgery, Faculty of Medicine and University Hospital Cologne, University of Cologne.
  • David Maintz
    Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Cologne, Germany.
  • Michael Perkuhn
    Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Cologne, Germany.
  • 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