Single-participant structural connectivity matrices lead to greater accuracy in classification of participants than function in autism in MRI

TL;DR

This study introduces a method to derive symmetric structural connectivity matrices from grey-matter volume histograms in MRI, demonstrating improved autism classification accuracy over functional connectivity and univariate measures using CNNs.

Contribution

The paper presents a novel technique for extracting structural connectivity features from MRI data and validates its effectiveness in autism classification with large datasets.

Findings

Structural connectivity alone achieves 69.71% accuracy in autism classification.

Combining structural and functional connectivity improves accuracy to 69.40%.

Graph analysis identifies localized differences in brain regions related to autism.

Abstract

In this work, we introduce a technique of deriving symmetric connectivity matrices from regional histograms of grey-matter volume estimated from T1-weighted MRIs. We then validated the technique by inputting the connectivity matrices into a convolutional neural network (CNN) to classify between participants with autism and age-, motion-, and intracranial-volume-matched controls from six different databases (29,288 total connectomes, mean age = 30.72, range 0.42-78.00, including 1555 subjects with autism). We compared this method to similar classifications of the same participants using fMRI connectivity matrices as well as univariate estimates of grey-matter volumes. We further applied graph-theoretical metrics on output class activation maps to identify areas of the matrices that the CNN preferentially used to make the classification, focusing particularly on hubs. Our results gave AUROCs of 0.7298 (69.71% accuracy) when classifying by only structural connectivity, 0.6964 (67.72% accuracy) when classifying by only functional connectivity, and 0.7037 (66.43% accuracy) when classifying by univariate grey matter volumes. Combining structural and functional connectivities gave an AUROC of 0.7354 (69.40% accuracy). Graph analysis of class activation maps revealed no distinguishable network patterns for functional inputs, but did reveal localized differences between groups in bilateral Heschl's gyrus and upper vermis for structural connectivity. This work provides a simple means of feature extraction for inputting large numbers of structural MRIs into machine learning models.