The Kernel Two-Sample Test for Brain Networks

TL;DR

This paper introduces the kernel two-sample test (KTST) as an efficient alternative to classifiers for comparing brain network populations, especially effective with small samples and requiring less computation.

Contribution

It demonstrates that KTST can directly compare brain network populations with comparable or better accuracy and lower computational cost than traditional classification methods.

Findings

KTST performs similarly to classifiers in distinguishing brain networks.

KTST requires less computational resources.

KTST has lower Type II error in low sample size regimes.

Abstract

In clinical and neuroscientific studies, systematic differences between two populations of brain networks are investigated in order to characterize mental diseases or processes. Those networks are usually represented as graphs built from neuroimaging data and studied by means of graph analysis methods. The typical machine learning approach to study these brain graphs creates a classifier and tests its ability to discriminate the two populations. In contrast to this approach, in this work we propose to directly test whether two populations of graphs are different or not, by using the kernel two-sample test (KTST), without creating the intermediate classifier. We claim that, in general, the two approaches provides similar results and that the KTST requires much less computation. Additionally, in the regime of low sample size, we claim that the KTST has lower frequency of Type II error than the classification approach. Besides providing algorithmic considerations to support these claims, we show strong evidence through experiments and one simulation.