White Matter Modeling Challenge

Torben Schneider
University College London, UK

Uran Ferizi
University College London, UK

Benoit Scherrer
Boston Children’s Hospital, Harvard Medical School, USA



Challenge Abstract
The last decade has seen an emergence of many new diffusion MRI models to describe diffusion signal in neural tissue. However, competing models are rarely tested and compared on a common dataset. Furthermore, it is unclear how much the performance of a particular model depends on a specific set of diffusion encoding parameters and how well it generalizes to unseen data. Finding an accurate model that explains a large range of different diffusion MRI measurements is important, because it helps us identify the sensitivity of our models to capture the underlying tissue microstructure.

This challenge poses to find the best model in two different tissue configurations that are common in the brain: 1) fibers are approximately straight and parallel 2) more complex fiber configurations, such as fiber crossing, bending or fanning. For both configurations, we provide a broad set of measurements that covers the set of b-values and diffusion times as widely as possible. Challenge participants have access to three-quarters of the whole dataset; the winning model is the one that predicts the remaining ‘unseen’ quarter most closely.

About wpengine

This is the "wpengine" admin user that our staff uses to gain access to your admin area to provide support and troubleshooting. It can only be accessed by a button in our secure log that auto generates a password and dumps that password after the staff member has logged in. We have taken extreme measures to ensure that our own user is not going to be misused to harm any of our clients sites.