Deep multimodal saliency parcellation of cerebellar pathways: linking microstructure and individual function through explainable multitask learning

TL;DR

This paper introduces DeepMSP, a deep learning method that integrates microstructure, connectivity, and functional performance data to improve cerebellar pathway parcellation, revealing distinct structure-function relationships.

Contribution

It presents a novel multimodal, multitask deep learning approach for cerebellar pathway parcellation that considers both structural features and individual functional performance.

Findings

Identified multiple cerebellar pathway parcels with unique structure-function saliency patterns.

Demonstrated stability of parcellation results across training folds.

Showed feasibility of linking microstructure and function through explainable deep learning.

Abstract

Parcellation of human cerebellar pathways is essential for advancing our understanding of the human brain. Existing diffusion MRI tractography parcellation methods have been successful in defining major cerebellar fibre tracts, while relying solely on fibre tract structure. However, each fibre tract may relay information related to multiple cognitive and motor functions of the cerebellum. Hence, it may be beneficial for parcellation to consider the potential importance of the fibre tracts for individual motor and cognitive functional performance measures. In this work, we propose a multimodal data-driven method for cerebellar pathway parcellation, which incorporates both measures of microstructure and connectivity, and measures of individual functional performance. Our method involves first training a multitask deep network to predict various cognitive and motor measures from a set of fibre tract structural features. The importance of each structural feature for predicting each functional measure is then computed, resulting in a set of structure-function saliency values that are clustered to parcellate cerebellar pathways. We refer to our method as Deep Multimodal Saliency Parcellation (DeepMSP), as it computes the saliency of structural measures for predicting cognitive and motor functional performance, with these saliencies being applied to the task of parcellation. Applying DeepMSP we found that it was feasible to identify multiple cerebellar pathway parcels with unique structure-function saliency patterns that were stable across training folds.