The goal of the IronTract challenge is to provide an objective assessment of the accuracy of brain pathways as reconstructed with diffusion MRI tractography, by direct comparison to chemical tracing in the same brain.
Round 1 (completed)
The winners of the first round were announced at MICCAI 2019, for two challenge tracks:
- Overall winner: In this track, participants were allowed to use the q-space sampling scheme (single-shell, multi-shell, Cartesian grid, etc.) that worked best for their tractography method. The goal was to find the method that achieves the highest accuracy possible today, regardless of acquisition scheme.
- HCP winner: In this track, participants used the two-shell acquisition scheme that is deployed by both lifespan studies and disease studies of the Human Connectome Project (HCP). The goal was to find the method that is best suited for analyzing the 6500+ data sets that are being collected across these studies and that will soon be available publicly.
Read more about Round 1 in the September 2019 issue of Computer Vision News >
Round 2 (completed)
In Round 2, all teams (both returning and new) used the same pre- and post-processing strategies as the two highest-scoring teams from Round 1. Thus this second round focused on comparing orientation reconstruction and tractography methods.
Read more about Round 2 in this press release >
See the results of Round 2 in our ISMRM 2021 abstract>
See detailed results from Round 2 in the final ranking table >