Connectivity-Driven Brain Parcellation via Consensus Clustering

TL;DR

This paper introduces two methods for creating connectivity-based brain atlases using consensus clustering of individual connectomes, improving upon standard anatomical atlases in various assessments.

Contribution

The paper proposes a novel consensus clustering approach for deriving brain parcellations from individual connectomes, leveraging dense connectivity representations and hierarchical clustering.

Findings

The proposed parcellation outperforms standard anatomical atlases in divergence measures.

It achieves higher inter-hemispheric symmetry.

It improves biological sex classification accuracy.

Abstract

We present two related methods for deriving connectivity-based brain atlases from individual connectomes. The proposed methods exploit a previously proposed dense connectivity representation, termed continuous connectivity, by first performing graph-based hierarchical clustering of individual brains, and subsequently aggregating the individual parcellations into a consensus parcellation. The search for consensus minimizes the sum of cluster membership distances, effectively estimating a pseudo-Karcher mean of individual parcellations. We assess the quality of our parcellations using (1) Kullback-Liebler and Jensen-Shannon divergence with respect to the dense connectome representation, (2) inter-hemispheric symmetry, and (3) performance of the simplified connectome in a biological sex classification task. We find that the parcellation based-atlas computed using a greedy search at a hierarchical depth 3 outperforms all other parcellation-based atlases as well as the standard Dessikan-Killiany anatomical atlas in all three assessments.