Diffusion MRI spherical mean improves deep cerebellar nuclei segmentation

Motivation: Structural MRI data enables cerebellar nuclei delineation, but small errors in registration to diffusion MRI data can hinder cerebellar brain connectivity analysis. Goal(s): Our goal is to provide an accurate deep cerebellar nuclei segmentation method employing diffusion MRI data. Approach: We employ several MRI contrasts to train a deep neural network to segment the deep cerebellar nuclei and assess their performance. Results: Diffusion MRI spherical mean data enable to segment the deep cerebellar nuclei with improved precision. Impact: Diffusion MRI spherical mean should be considered as a relevant image contrast for cerebellar structure segmentation using deep neural networks towards an increasingly accurate connectivity analysis.