Journal
IEEE TRANSACTIONS ON MEDICAL IMAGING
Volume 34, Issue 10, Pages 1993-2024Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMI.2014.2377694
Keywords
MRI; Brain; Oncology/tumor; Image segmentation; Benchmark
Categories
Funding
- NIH NCRR [P41-RR14075]
- NIH NIBIB [R01EB013565]
- Academy of Finland [133611]
- TEKES (ComBrain)
- Lundbeck Foundation [R141-2013-13117]
- Swiss Cancer League
- Swiss Institute for Computer Assisted Surgery (SICAS)
- NIH NIBIB NAMIC [U54-EB005149]
- NIH NCRR NAC [P41-RR13218]
- NIH NIBIB NAC [P41-EB-015902]
- NIH NCI [R15CA115464]
- European Research Council through ERC [MedYMA 2011-291080]
- FCT
- COMPETE [FCOM-01-0124-FEDER-022674]
- MICAT Project (EU) [PIRG-GA-2008-231052]
- European Union [600841]
- Swiss NSF project Computer Aided and Image Guided Medical Interventions (NCCR CO-ME)
- Technische Universitat Munchen-Institute for Advanced Study - German Excellence Initiative
- Technische Universitat Munchen-Institute for Advanced Study - European Union [291763]
- Marie Curie COFUND program of the European Union
- Academy of Finland (AKA) [133611, 133611] Funding Source: Academy of Finland (AKA)
- Lundbeck Foundation [R141-2013-13117] Funding Source: researchfish
- National Institute for Health Research [NIHR/CS/009/011] Funding Source: researchfish
Ask authors/readers for more resources
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available