MS segmentation challenge using a data management and processing infrastructure

Data and format

53 datasets from 4 different sites and 4 different MRI scanners will be used. The provided MR sequences will include:
  • 3D FLAIR
  • 3D T1-w
  • 3D T1-w GADO
  • 2D DP/T2

The provided data are split into two sets (15 training data and 38 testing data) as shown in the following table. All 53 datasets include raw data in Nifti format.

 

# exams

Training

Testing

GE Discovery 3T

0

8

Philips Ingenia 3T

5

10

Siemens Aera 1.5T

5

10

Siemens Verio 3T

5

10

Total

15

38

 

Since April 8, we have made available the 15 training datasets, allowing the teams to train their algorithms and tune their parameters, as two packages (zip files): 
 
  • one package with unprocessed datasets and manual lesion delineations from seven independent experts
  • one package with pre-processed datasets (denoised, registered, brain extracted, bias field corrected) using state-of-the-art pre-processing algorithms
 
To access these dataset, please register first your participating team on the website (Subscribe link on the overview page): the links to the two zip files appear at the bottom of this page once logged in. More details on the pre-processing and data are available in a README file inside each zip file. These zip files will be accessible to any registered user to the MS SEG challenge, subject to the following constraints until the challenge date has passed (conditions will change once the challenge is finished): 
 
  • these files shall not be used outside of the scope of the MS SEG challenge
  • these files shall not be distributed to third-parties