News
The MRBrainS13 challenge is now closed and the data has been published on DataVerseNL: https://doi.org/10.34894/645ZIN
Welcome to the MRBrainS website. On September 26th, 2013 we organized the Grand Challenge on MR Brain Image Segmentation workshop at the MICCAI in Nagoya, Japan, where we launched this evaluation framework. The aim of the MRBrainS evaluation framework is to compare (semi-)automatic algorithms for segmentation of grey matter, white matter and cerebrospinal fluid on multi-sequence (T1-weighted, T1-weighted inversion recovery and FLAIR) 3 Tesla MRI scans of the brain. More information about the workshop and the results of the workshop challenge can be found here.
Evaluation framework: The Challenge Continues – until 2024
The MRBrainS website will remain open as an online evaluation framework for new segmentation algorithms or new versions of already applied algorithms. So feel free to register, download the training and test data and submit your results. Any team, whether from academia or industry, can join! You are welcome to submit your new unpublished method, but we would also like to encourage teams with well established published methods to register and submit their results. In this way, the MRBrainS challenge will present an overview of the performance of a wide variety of available brain structure segmentation methods.
How does it work?
The organisation of this challenge is similar to that of previous challenges described on Grand Challenges in Medical Image Analysis. Five datasets (MRI scans with manual segmentations) are provided for training and fifteen datasets (only MRI scans) are provided for testing. Teams can register on this website, sign the confidentiality agreement, and download the data. They can train their segmentation algorithm on the training data, apply it to the test data and submit the obtained results as well as a description of their algorithm. Each submission will be evaluated against the reference standard (manual segmentations) and the evaluation results will be sent to the team contact person by e-mail and published in the results section of this website.
More information can be found on the details page.
News: MRBrainS journal paper accepted for publication
If you use the MRBrainS evaluation framework or data, please cite the following paper: