267
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: not found

      The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

      research-article
      , , , , , , , , , , , , , , , , , , , , , , , ,   , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,
      IEEE transactions on medical imaging
      MRI, Brain, Oncology/tumor, Image segmentation, Benchmark
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) organized in conjunction with the MICCAI 2012 and 2013 conferences. Twenty state-of-the-art tumor segmentation algorithms were applied to a set of 65 multi-contrast MR scans of low- and high-grade glioma patients—manually annotated by up to four raters—and to 65 comparable scans generated using tumor image simulation software. Quantitative evaluations revealed considerable disagreement between the human raters in segmenting various tumor sub-regions (Dice scores in the range 74%–85%), illustrating the difficulty of this task. We found that different algorithms worked best for different sub-regions (reaching performance comparable to human inter-rater variability), but that no single algorithm ranked in the top for all sub-regions simultaneously. Fusing several good algorithms using a hierarchical majority vote yielded segmentations that consistently ranked above all individual algorithms, indicating remaining opportunities for further methodological improvements. The BRATS image data and manual annotations continue to be publicly available through an online evaluation system as an ongoing benchmarking resource.

          Related collections

          Author and article information

          Contributors
          Journal
          8310780
          20511
          IEEE Trans Med Imaging
          IEEE Trans Med Imaging
          IEEE transactions on medical imaging
          0278-0062
          1558-254X
          9 April 2016
          04 December 2014
          October 2015
          01 October 2016
          : 34
          : 10
          : 1993-2024
          Affiliations
          Institute for Advanced Study and Department of Computer Science, Technische Universität München, Munich, Germany, and with the Computer Vision Laboratory, ETH, Zürich, Switzerland, and with the Asclepios Project, Inria, Sophia-Antipolis, France, and also with the Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA 02139 USA
          Computer Vision Laboratory, ETH, Zürich, Switzerland, and also with the University of Debrecen, Debrecen, Hungary
          Institute for Surgical Technology and Biomechanics, University of Bern, Switzerland, and also with the Support Center for Advanced Neuroimaging (SCAN), Institute for Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, Switzerland
          Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston MA, USA
          Cancer Imaging Program, National Cancer Institute, National Institutes of Health, Bethesda MD, USA
          Cancer Imaging Program, National Cancer Institute, National Institutes of Health, Bethesda MD, USA
          Support Center for Advanced Neuroimaging (SCAN), Institute for Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, Switzerland
          Support Center for Advanced Neuroimaging (SCAN), Institute for Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, Switzerland
          Support Center for Advanced Neuroimaging (SCAN), Institute for Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, Switzerland
          Support Center for Advanced Neuroimaging (SCAN), Institute for Diagnostic and Interventional Neuroradiology, Inselspital, Bern University Hospital, Switzerland
          University of Debrecen, Debrecen, Hungary
          Department of Neuro-oncology, Massachusetts General Hosptial, Harvard Medical School, Boston MA, USA
          Diagnostic and Interventional Radiology, University Hospital, Heidelberg, Germany
          Centre for Intelligent Machines, McGill University, Canada
          Penn Image Computing and Science Lab, Department of Radiology, University of Pennsylvania, Philadelphia PA, USA
          Asclepios Project, INRIA, Sophia-Antipolis, France
          INFOTECH Soft, Inc., Miami FL, USA
          McConnell Brain Imaging Centre, McGill University, Canada
          Asclepios Project, INRIA, Sophia-Antipolis, France
          Computer Science and Engineering, SUNY, Buffalo NY, USA
          Microsoft Research, Cambridge, U.K.
          Cambridge University Hospitals, Cambridge, U.K.
          Asclepios Project, INRIA, Sophia-Antipolis, France
          Computer Science Department, Stanford University, Stanford CA, USA
          Department of Radiology and Medical Imaging, University of Virginia, Charlottesville VA USA
          INRIA Rhône-Alpes, Grenoble, France, and also with the INSERM, U836, Grenoble, France
          INRIA Rhône-Alpes, Grenoble, France, and also with the INSERM, U836, Grenoble, France
          Department of Electronics, University Minho, Portugal
          INRIA Rhône-Alpes, Grenoble, France, and also with the INSERM, U836, Grenoble, France
          Asclepios Project, INRIA, Sophia-Antipolis, France
          BioMedIA Group, Imperial College, London, U.K.
          Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge MA USA
          Department of Radiology, Columbia University, New York, NY USA
          Faculty of Engineering and Natural Sciences, Sabanci University, Istanbul, Turkey
          Vision Lab, Department of Electrical and Computer Engineering, Old Dominion University, Norfolk, VA USA
          Cambridge University Hospitals, Cambridge, U.K.
          INFOTECH Soft, Inc., Miami, FL USA, and also with the Department of Electrical and Computer Engineering, University of Miami, Coral Gables FL USA
          Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital and Harvard Medical School, Boston MA USA
          Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge MA USA
          Life and Health Science Research Institute (ICVS), School of Health Sciences, University of Minho, Braga, Portugal, and also with the ICVS/3B's—PT Government Associate Laboratory, Braga/Guimaraes, Portugal
          Institute for Surgical Technology and Biomechanics, University of Bern, 3014 Bern, Switzerland
          Department of Electronics, University Minho, Portugal
          School of Computer Science, McGill University, Canada. and also with the Electrical and Computer Engineering Department, Ben-Gurion University, Beer-Sheva, Israel
          Cambridge University Hospitals, Cambridge, U.K.
          Vision Lab, Department of Electrical and Computer Engineering, Old Dominion University, Norfolk, VA USA
          INFOTECH Soft, Inc., Miami FL, USA
          Computer Science and Engineering, SUNY, Buffalo NY, USA
          Department of Radiology, Columbia University, New York, NY USA
          Sutton, U.K.
          Microsoft Research, Cambridge, U.K.
          Department of Electronics, University Minho, Portugal
          Life and Health Science Research Institute (ICVS), School of Health Sciences, University of Minho, Braga, Portugal, and also with the ICVS/3B's—PT Government Associate Laboratory, Braga/Guimaraes, Portugal
          Centre for Intelligent Machines, McGill University, Canada
          Computer Vision Laboratory, ETH, Zürich, Switzerland
          INFOTECH Soft, Inc., Miami FL, USA
          Cambridge University Hospitals, Cambridge, U.K.
          Department of Radiology and Medical Imaging, University of Virginia, Charlottesville VA USA
          Faculty of Engineering and Natural Sciences, Sabanci University, Istanbul, Turkey
          INRIA Rhône-Alpes, Grenoble, France, and also with the INSERM, U836, Grenoble, France
          Department of Radiology and Medical Imaging, University of Virginia, Charlottesville VA USA
          Electrical and Computer Engineering Department, Purdue University, USA
          Computer Science and Engineering, SUNY, Buffalo NY, USA
          Department of Radiology, Columbia University, New York, NY USA
          Microsoft Research, Cambridge, U.K.
          GE Global Research, Niskayuna NY, USA
          Institute for Surgical Technology and Biomechanics, University of Bern, 3014 Bern, Switzerland
          Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02129 USA, and with the Technical University of Denmark, Denmark, and also with Aalto University, Finland
          Author notes

          M. Reyes and K. Van Leemput contributed equally.

          Article
          PMC4833122 PMC4833122 4833122 nihpa775317
          10.1109/TMI.2014.2377694
          4833122
          25494501
          246c6ca7-0ef2-4e1c-baaa-d3e5f36b62f1
          History
          Categories
          Article

          Benchmark,MRI,Brain,Oncology/tumor,Image segmentation
          Benchmark, MRI, Brain, Oncology/tumor, Image segmentation

          Comments

          Comment on this article