TractEM, a fast protocol for whole brain tractography. In this project, we proposed to create a resource of manually labelled white matter atlases that is driven by state-of-the-art diffusion tractography, and can be manually created in less than 6 hours. More information can be found at https://my.vanderbilt.edu/tractem/.
Deep learning tractography. In this project, we are using the tractEM dataset, and asking the question, if we can learn patterns of tracts from non-expert annotated training data and apply the model to unseen data to predict accurate tracts.
Reinforcement tractography. How we can formulate the tractography problem for reinforcement learning. This project is in its idea-stage and I would like to collaborate with people who might have ideas and suggestions.