TractGraphCNN: anatomically informed graph CNN for classification using diffusion MRI tractography

TL;DR

This paper introduces TractGraphCNN, a graph CNN that incorporates neuroanatomical information from diffusion MRI tractography to improve brain phenotype prediction, demonstrating superior performance and interpretability.

Contribution

The paper presents a novel anatomically informed graph CNN framework that leverages white matter geometry for improved brain phenotype classification.

Findings

TractGraphCNN outperforms baseline models in sex prediction tasks.

Graphs based on white matter geometry yield higher accuracy than gray matter connectivity graphs.

Key predictive tracts include the bilateral cingulum and left middle longitudinal fasciculus.

Abstract

The structure and variability of the brain's connections can be investigated via prediction of non-imaging phenotypes using neural networks. However, known neuroanatomical relationships between input features are generally ignored in network design. We propose TractGraphCNN, a novel, anatomically informed graph CNN framework for machine learning tasks using diffusion MRI tractography. An EdgeConv module aggregates features from anatomically similar white matter connections indicated by graph edges, and an attention module enables interpretation of predictive white matter tracts. Results in a sex prediction testbed task demonstrate strong performance of TractGraphCNN in two large datasets (HCP and ABCD). Graphs informed by white matter geometry demonstrate higher performance than graphs informed by gray matter connectivity. Overall, the bilateral cingulum and left middle longitudinal fasciculus are consistently highly predictive of sex. This work shows the potential of incorporating anatomical information, especially known anatomical similarities between input features, to guide convolutions in neural networks.