A Matrix Autoencoder Framework to Align the Functional and Structural Connectivity Manifolds as Guided by Behavioral Phenotypes

TL;DR

This paper introduces a matrix autoencoder that aligns functional and structural brain connectivity data using phenotypic information, enabling better prediction of behavioral traits and revealing interpretable brain biomarkers.

Contribution

The novel autoencoder framework jointly models functional and structural connectomes guided by phenotypes, improving connectivity mapping and behavioral prediction.

Findings

Successfully recovers structural connectivity patterns across individuals.

Robustly extracts predictive and interpretable brain biomarkers.

Outperforms baseline methods in behavioral phenotype prediction.

Abstract

We propose a novel matrix autoencoder to map functional connectomes from resting state fMRI (rs-fMRI) to structural connectomes from Diffusion Tensor Imaging (DTI), as guided by subject-level phenotypic measures. Our specialized autoencoder infers a low dimensional manifold embedding for the rs-fMRI correlation matrices that mimics a canonical outer-product decomposition. The embedding is simultaneously used to reconstruct DTI tractography matrices via a second manifold alignment decoder and to predict inter-subject phenotypic variability via an artificial neural network. We validate our framework on a dataset of 275 healthy individuals from the Human Connectome Project database and on a second clinical dataset consisting of 57 subjects with Autism Spectrum Disorder. We demonstrate that the model reliably recovers structural connectivity patterns across individuals, while robustly extracting predictive and interpretable brain biomarkers in a cross-validated setting. Finally, our framework outperforms several baselines at predicting behavioral phenotypes in both real-world datasets.