The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

Research output: Contribution to journalJournal article – Annual report year: 2015Researchpeer-review

  • Author: Menze, Bjoern H.

    Massachusetts Institute of Technology, United States

  • Author: Jakab, Andras

    Swiss Federal Institute of Technology Zurich, Switzerland

  • Author: Bauer, Stefan

    University of Bern, Switzerland

  • Author: Kalpathy-Cramer, Jayashree

    Harvard Medical School, United States

  • Author: Farahani, Keyvan

    US National Institute of Health, United States

  • Author: Kirby, Justin

    US National Institute of Health, United States

  • Author: Burren, Yuliya

    Bern University Hospital, Switzerland

  • Author: Porz, Nicole

    Bern University Hospital, Switzerland

  • Author: Slotboom, Johannes

    Bern University Hospital, Switzerland

  • Author: Wiest, Roland

    Bern University Hospital, Switzerland

  • Author: Van Leemput, Koen

    Harvard Medical School

    Image Analysis & Computer Graphics, Department of Applied Mathematics and Computer Science , Technical University of Denmark, Denmark

View graph of relations

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 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.
Original languageEnglish
JournalI E E E Transactions on Medical Imaging
Volume34
Issue number10
Pages (from-to)1993 - 2024
Number of pages33
ISSN0278-0062
DOIs
Publication statusPublished - 2015
CitationsWeb of Science® Times Cited: No match on DOI

Download statistics

No data available

ID: 110362726