All the data are kindly provided by the Cardiff University Brain Research Imaging Centre (CUBRIC).
The training data will be provided by the organisers. Participants will not be restricted to use solely such data, as they will be free to exploit other data at their hand for the training. However, all teams will be asked to perform at least one submission using only the training data provided by the organisers, in order to ensure one fair comparison among all algorithms.
The training data provided will consist of multi-vendor diffusion-weighted (DW) scans from 10 healthy subjects, in the form of raw DW magnitude images (i.e. without any form of preprocessing). For each brain data set, 5 sets of DW images will be provided, as listed below.
A) Standard Protocol, scanner 1: 3T General Electric Excite-HD, isotropic resolution of 2.4 mm, TE = 89 ms, TR = 12 s, 30 directions @ b = 1200 s/mm2;
B) Standard Protocol, scanner 2: 3T Siemens Prisma, isotropic resolution of 2.4 mm, TE = 89 ms, TR = 7.2 s, 30 directions @ b = 1200 s/mm2;
C) Standard Protocol, scanner 3: 3T Siemens Connectom, isotropic resolution of 2.4 mm, TE = 89 ms, TR = 7.2 s, 30 directions @ b = 1200 s/mm2;
D) State-of-the-art protocol, scanner 2: 3T Siemens Prisma, isotropic resolution of 1.5 mm, TE = 80 ms, TR = 7.2 s, 60 directions at 1200 s/mm2 (b = 0 images with same TE and TR as B are also provided);
E) State-of-the-art protocol, scanner 3: Siemens Connetcom, isotropic resolution of 1.2 mm, TE = 68 ms, TR = 5.4 s, 60 directions at 1200 s/mm2 (b = 0 images with same TE and TR as C are also provided).
In addition, routine structural scans will be acquired with each MRI scanner for anatomical depiction. The data is available from 16 June 2017.
The test data will consist of scans from 4 additional healthy volunteers who were not included within the training set. Training and test data will be allocated at random from the overall set of DW scans available to the organisers from 14 healthy controls.
The test data will consist of DW data sets acquired with scanner 1 (3T General Electric Excite-HD) according to the standard protocol (protocol A listed above), alongside the anatomical scans acquired with the same scanner. The test data is available from mid July 2017.
Tasks for teams
From the data set A (the only protocol that will be given for the test data), teams submitting to the challenge will predict data sets (i.e. raw DW images) B, C, D and E. Specifically, teams will face two tasks:
- predict data acquired with the same protocol: predict protocols B and C given protocol A;
- enhance spatial and angular resolution: predict protocols D and E given protocol A.
Important information regarding submissions:
- teams will submit the predicted DW images, given the diffusion encoding protocol, within a given brain mask that excludes the cerebellum;
- no co-registration is required, as the final release of the data includes pre-processing that warps scans to a subject-specific reference space;
- submissions will be in NIFTI format (the same format will be used for all training and test data);
- teams can enter the challenge with various submissions; however, at least one submission should be obtained using soley the data provided by the organisers for traning.
The data from protocols B, C, D and E of the test set will be available to the organisers to evaluate quantitatively the goodness of the submissions.
The challenge has been re-opened with final deadline for submissions set on Tuesday, January 09th 2018 23:59 GMT.
The reference that will be used for the challenge will consist of the scans comprising data sets B, C, D and E, mentioned above. Such scans will not be released to the public within the test data and will act as a gold standard.
The goal of the challenge will be the prediction of data B, C, D and E from the standard protocol (A), given the set of examples (i.e. the training data). Teams will predict the DW data within a brain mask provided by the organisers, which does not include the cerebellum.
The metrics for the evaulation will assess accuracy and precision of the predictions, and will be evaluated within 3D sliding windows and within different brain regions-of-interest. The evaluation will NOT include the edges of the brain and will NOT include the cerebellum.
Practically, accuracy and precisions will be evaluated looking at the residuals of clinically relevant metrics such as Fractional Anisotropy (FA) and Mean Diffusivity (MD) from Diffusion Tensor Imaging (Basser PJ et al, Biophysical Journal 1994). Additionally, the Rotation Invariant Spherical Harmonic (RISH) features (Mirzaalian H et al, NeuroImage 2016) of the raw DW signal residuals will also be calcualted. FA, MD and RISH will be calculated by the organisers from the DW images submitted by the teams.
Submissions will be ranked according to the the quality-of-the-prediction for FA, MD, and RISH features in turn.