Multi-region competitive tractography via graph-based random walks

We propose a multi-region approach to tractography that not only allows for competition between seed regions, but also allows for the incorporation of knowledge beyond a local scale. By formulating tractography as a graph-based random walk, we are able to obtain a closed-form solution for connection probabilities. Results on synthetic data and thirty images from the MIDAS database show that the introduction of competition reduces erroneous connectivity to regions outside the seeded tracts.