News

The MRBrainS18 challenge is now closed and the data has been published on DataVerseNL: https://doi.org/10.34894/E0U32Q

Welcome to the Grand Challenge on MR Brain Segmentation 2018.

Aim

The purpose of this challenge is to directly compare methods for segmentation of gray matter, white matter, cerebrospinal fluid, and other structures on 3T MRI scans of the brain, and to assess the effect of (large) pathologies on segmentation and volumetry.

Outline

To participate in the challenge, interested teams can register on this website. After registration, training data can be downloaded. This data consists of 7 sets of brain MR images (T1, T1 inversion recovery, and T2-FLAIR) with manual segmentations of ten brain structures. These manual segmentations have been made by experts in brain segmentation. Unlike the MRBrainS13 challenge, the training- and test-data now also include images with (large) pathologies.

Participants can train their methods on the available data and submit the resulting method for evaluation by the organizers. A brief description (1-2 pages) of the method should be included. Test data will not be released, but consists of 23 sets of brain MR images and manual segmentations.

Details can be found here.

Results & journal publication (on-site challenge)

After the deadline (15 August), all submitted methods will be evaluated by the organizers. During the challenge session at the MICCAI 2018, participants will present their methods. The final results will be presented by the organizers. All results will be summarized in a journal publication and each participating team who presented their method at the challenge session is allowed two co-authorships.

Extended versions of the 1-2 page descriptions can optionally be submitted for publication in LNCS, as part of the BrainLes 2018 post-proceedings.