Review

Review of a diffusion-based generative global tractography model. It uses VAEs to globally encode the dMRI signal into an informative single tensor that is used to inform the denoising process of batches of streamlines.

Review of the original technique which is widely used today for LLM alignment. It’s the foundation to many other alignment techinques proposed in the recent litterature.

Particle filtering tractography is used to optimize tractography parameters in terms of connectivity and to understand the benefits of a relaxed stopping criterion using partial volume estimation maps.

Théberge et al reviews what’s been done to this day in tractography using reinforcement learning, listing what works best and what doesn’t work.