The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) - Archive ouverte HAL Access content directly
Journal Articles IEEE Transactions on Medical Imaging Year : 2014

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

1 ASCLEPIOS - Analysis and Simulation of Biomedical Images
2 CIR lab - Computational Image Analysis and Radiology
3 ISTB - Institute for Surgical Technology and Biomechanics [Bern]
4 Massachusetts General Hospital [Boston]
5 Department of Health and Human Services
6 Inselspital Bern
7 University of Debrecen Egyetem [Debrecen]
8 Division of Medical Physics in Radiology [Heidelberg]
9 Diagnostic and Interventional Radiology [Heidelberg]
10 CIM - Centre for Intelligent Machines
11 PICSL - Penn Image Computing & Science Lab [Philadelphia]
13 MNI - McConnell Brain Imaging Centre
14 SUNY - State University of New York
15 Microsoft - Microsoft Research [Cambridge]
16 CUH - Cambridge University Hospitals - NHS
17 Computer Science Department [Stanford]
18 Department of radiology and medical imaging [Charlottesville]
19 GIN - [GIN] Grenoble Institut des Neurosciences
20 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
21 Universidade do Minho = University of Minho [Braga]
22 CSAIL - Computer Science and Artificial Intelligence Laboratory [Cambridge]
23 Columbia University [New York]
24 Sabanci University - Faculty of Engineering and Natural Sciences
25 ODU - Old Dominion University [Norfolk]
26 Addenbrooke's Hospital
27 Bangor University
28 Department of Surgery
29 McGill University = Université McGill [Montréal, Canada]
30 Bristol Glaciology Centre
31 Molecular Carcinogenesis [Sutton]
32 CNC - Center for Neuroscience and Cell Biology (CNC)
33 Computer Vision Laboratory - ETHZ [Zurich]
34 Department of Radiology [San Francisco]
35 Purdue University [West Lafayette]
36 Department of Computer Science [New York]
37 SCI Institute - Scientific Computing and Imaging Institute
38 Massachusetts General Hospital - Department of radiology
Yuliya Burren
  • Function : Author
Nicole Porz
  • Function : Author
Roland Wiest
  • Function : Author
Patricia Buendia
  • Function : Author
Michel Dojat
Ezequiel Geremia
  • Function : Author
  • PersonId : 764717
  • IdRef : 170040232
Ben Glocker
Raj Jena
  • Function : Author
Nigel John
  • Function : Author
Michael Ryan
  • Function : Author
Thomas Taylor
  • Function : Author
Owen Thomas
  • Function : Author


In this paper we report the set-up and results of the Multimodal Brain Tumor Image Segmentation (BRATS) benchmark 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 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 subregions 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.
Fichier principal
Vignette du fichier
menze_brats.pdf (4.33 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00935640 , version 1 (27-01-2014)
hal-00935640 , version 2 (29-11-2014)



Bjoern Menze, Andras Jakab, Stefan Bauer, Jayashree Kalpathy-Cramer, Keyvan Farahani, et al.. The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS). IEEE Transactions on Medical Imaging, 2014, 34 (10), pp.1993-2024. ⟨10.1109/TMI.2014.2377694⟩. ⟨hal-00935640v2⟩
7829 View
6202 Download



Gmail Facebook X LinkedIn More