Modeling the Shape of the Brain Connectome via Deep Neural Networks

TL;DR

This paper introduces a neural network-based approach to model brain connectomes as Riemannian manifolds, enabling accurate fiber tractography and overcoming limitations of previous methods in resolving crossing fibers.

Contribution

It proposes a novel method using convolutional encoder-decoder neural networks to estimate Riemannian metrics from DWI data, improving fiber tractography accuracy.

Findings

High fidelity in recovering crossing fibers

Effective alignment of geodesics with white matter pathways

Addresses longstanding issues in geodesic tractography

Abstract

The goal of diffusion-weighted magnetic resonance imaging (DWI) is to infer the structural connectivity of an individual subject's brain in vivo. To statistically study the variability and differences between normal and abnormal brain connectomes, a mathematical model of the neural connections is required. In this paper, we represent the brain connectome as a Riemannian manifold, which allows us to model neural connections as geodesics. This leads to the challenging problem of estimating a Riemannian metric that is compatible with the DWI data, i.e., a metric such that the geodesic curves represent individual fiber tracts of the connectomics. We reduce this problem to that of solving a highly nonlinear set of partial differential equations (PDEs) and study the applicability of convolutional encoder-decoder neural networks (CEDNNs) for solving this geometrically motivated PDE. Our method achieves excellent performance in the alignment of geodesics with white matter pathways and tackles a long-standing issue in previous geodesic tractography methods: the inability to recover crossing fibers with high fidelity.