Segmenting brain tumors from FLAIR MRI using fully convolutional neural networks.

Journal: Computer methods and programs in biomedicine
Published Date:

Abstract

BACKGROUND AND OBJECTIVE: Magnetic resonance imaging (MRI) is an indispensable tool in diagnosing brain-tumor patients. Automated tumor segmentation is being widely researched to accelerate the MRI analysis and allow clinicians to precisely plan treatment-accurate delineation of brain tumors is a critical step in assessing their volume, shape, boundaries, and other characteristics. However, it is still a very challenging task due to inherent MR data characteristics and high variability, e.g., in tumor sizes or shapes. We present a new deep learning approach for accurate brain tumor segmentation which can be trained from small and heterogeneous datasets annotated by a human reader (providing high-quality ground-truth segmentation is very costly in practice).

Authors

  • Pablo Ribalta Lorenzo
    Future Processing, Bojkowska 37A, 44-100 Gliwice, Poland. Electronic address: pribalta@ieee.org.
  • Jakub Nalepa
    Future Processing, Bojkowska 37A, 44-100 Gliwice, Poland; Institute of Informatics, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland. Electronic address: jakub.nalepa@polsl.pl.
  • Barbara Bobek-Billewicz
    Maria Sklodowska-Curie Memorial Cancer Center and Institute of Oncology, Wybrzeze Armii Krajowej 15, 44-102 Gliwice, Poland. Electronic address: bbillewicz@io.gliwice.pl.
  • Pawel Wawrzyniak
    Maria Sklodowska-Curie Memorial Cancer Center and Institute of Oncology, Wybrzeze Armii Krajowej 15, 44-102 Gliwice, Poland. Electronic address: pawel.wawrzyniak@io.gliwice.pl.
  • Grzegorz Mrukwa
    Future Processing, Bojkowska 37A, 44-100 Gliwice, Poland. Electronic address: grukwa@future-processing.com.
  • Michal Kawulok
    Future Processing, Bojkowska 37A, 44-100 Gliwice, Poland; Institute of Informatics, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland. Electronic address: michal.kawulok@polsl.pl.
  • Pawel Ulrych
    Maria Sklodowska-Curie Memorial Cancer Center and Institute of Oncology, Wybrzeze Armii Krajowej 15, 44-102 Gliwice, Poland. Electronic address: pawel.ulrych@io.gliwice.pl.
  • Michael P Hayball
    Feedback Medical Ltd., Broadway, Bourn, Cambridge CB23 2TA, UK. Electronic address: mike.hayball@fbkmed.com.