Perelman School of Medicine at the University of Pennsylvania

Section for Biomedical Image Analysis (SBIA)

Multimodal Brain Tumor Segmentation Challenge 2017

• Scope • RelevanceTasksDataEvaluationParticipation SummaryRegistrationPrevious BraTSPeople


Scope

BraTS has always been focusing on the evaluation of state-of-the-art methods for the segmentation of brain tumors in magnetic resonance imaging (MRI) scans. BraTS 2017 utilizes multi-institutional pre-operative MRI scans and focuses on the segmentation of intrinsically heterogeneous (in appearance, shape, and histology) brain tumors, namely gliomas. Furthemore, this year, in order to pinpoint the clinical relevance of this segmentation task, BraTS’17 also focuses on the prediction of patient overall survival, via integrative analyses of radiomic features and machine learning algorithms.

  IMPORTANT DATES:
5 May
30 Jun
Extended: 24 Jul
Extended: 1-27 Aug
31 Aug
14 Sep
10 Nov

Release of training datasets. — (Registration is now closed)
Release of validation datasets. — (Released)   View the Leaderboard
Submission of short papers, reporting proposed method & preliminary results.
Release of testing datasets (& performance evaluation).
Contacting top performing methods for preparing slides for oral presentation.
Challenge at MICCAI (Quebec City) - Announcing results.
Extended LNCS paper submission deadline.

BraTS 2017 runs in conjunction with the MICCAI 2017 conference, on Sep.14, as part of the full-day BrainLes Workshop.
Feel free to send any communication related to the BraTS challenge in brats@miccai2017.org


Fig.1: Glioma sub-regions. Shown are image patches with the tumor sub-regions that are annotated in the different modalities (top left) and the final labels for the whole dataset (right). The image patches show from left to right: the whole tumor (yellow) visible in T2-FLAIR (Fig.A), the tumor core (red) visible in T2 (Fig.B), the enhancing tumor structures (light blue) visible in T1Gd, surrounding the cystic/necrotic components of the core (green) (Fig. C). The segmentations are combined to generate the final labels of the tumor sub-regions (Fig.D): edema (yellow), non-enhancing solid core (red), necrotic/cystic core (green), enhancing core (blue). (Figure taken from the BraTS IEEE TMI paper.)