Motion-Invariant Variational Auto-Encoding of Brain Structural Connectomes

TL;DR

This paper introduces a motion-invariant variational auto-encoder that improves the accuracy of brain connectome analysis by removing motion artifacts, leading to better understanding of brain-cognition relationships.

Contribution

The paper presents a novel generative model that learns low-dimensional, motion-invariant representations of brain connectomes, enhancing analysis accuracy and interpretability.

Findings

Motion-invariant connectomes are more strongly associated with cognitive traits.

The proposed model outperforms competitors in connectome reconstruction.

Motion adjustment improves the link between brain networks and cognition.

Abstract

Mapping of human brain structural connectomes via diffusion MRI offers a unique opportunity to understand brain structural connectivity and relate it to various human traits, such as cognition. However, head displacement during image acquisition can compromise the accuracy of connectome reconstructions and subsequent inference results. We develop a generative model to learn low-dimensional representations of structural connectomes invariant to motion-induced artifacts, so that we can link brain networks and human traits more accurately, and generate motion-adjusted connectomes. We apply the proposed model to data from the Adolescent Brain Cognitive Development (ABCD) study and the Human Connectome Project (HCP) to investigate how our motion-invariant connectomes facilitate understanding of the brain network and its relationship with cognition. Empirical results demonstrate that the proposed motion-invariant variational auto-encoder (inv-VAE) outperforms its competitors in various aspects. In particular, motion-adjusted structural connectomes are more strongly associated with a wide array of cognition-related traits than other approaches without motion adjustment.