Combining convolutional neural networks and star convex cuts for fast whole spine vertebra segmentation in MRI.

Journal: Computer methods and programs in biomedicine
Published Date:

Abstract

BACKGROUND AND OBJECTIVE: We propose an automatic approach for fast vertebral body segmentation in three-dimensional magnetic resonance images of the whole spine. Previous works are limited to the lower thoracolumbar section and often take minutes to compute, which is problematic in clinical routine, for study data sets with numerous subjects or when the cervical or upper thoracic spine is to be analyzed.

Authors

  • Marko Rak
  • Johannes Steffen
  • Anneke Meyer
    Department of Simulation and Graphics, University of Magdeburg Universitätsplatz 2, Magdeburg, 39106 Germany.
  • Christian Hansen
    Department of Simulation and Graphics, University of Magdeburg Universitätsplatz 2, Magdeburg, 39106 Germany.
  • Klaus-Dietz Tönnies
    Department of Simulation and Graphics, University of Magdeburg Universitätsplatz 2, Magdeburg, 39106 Germany.