Comparative Survey of Multigraph Integration Methods for Holistic Brain Connectivity Mapping

TL;DR

This paper reviews methods for creating a unified brain connectivity map called the connectional brain template (CBT) by integrating heterogeneous neuroimaging data, highlighting the superior performance of the deep graph normalizer (DGN) method.

Contribution

It provides a comprehensive comparison of single-view and multi-view CBT estimation methods and demonstrates the effectiveness of DGN in producing more representative brain connectivity maps.

Findings

DGN outperforms other methods in centeredness and reproducibility.

Multi-graph integration improves topological trait preservation.

DGN achieves higher biomarker reproducibility across datasets.

Abstract

One of the greatest scientific challenges in network neuroscience is to create a representative map of a population of heterogeneous brain networks, which acts as a connectional fingerprint. The connectional brain template (CBT), also named network atlas, presents a powerful tool for capturing the most representative and discriminative traits of a given population while preserving its topological patterns. The idea of a CBT is to integrate a population of heterogeneous brain connectivity networks, derived from different neuroimaging modalities or brain views (e.g., structural and functional), into a unified holistic representation. Here we review current state-of-the-art methods designed to estimate well-centered and representative CBT for populations of single-view and multi-view brain networks. We start by reviewing each CBT learning method, then we introduce the evaluation measures to compare CBT representativeness of populations generated by single-view and multigraph integration methods, separately, based on the following criteria: centeredness, biomarker-reproducibility, node-level similarity, global-level similarity, and distance-based similarity. We demonstrate that the deep graph normalizer (DGN) method significantly outperforms other multi-graph and all single-view integration methods for estimating CBTs using a variety of healthy and disordered datasets in terms of centeredness, reproducibility (i.e., graph-derived biomarkers reproducibility that disentangle the typical from the atypical connectivity variability), and preserving the topological traits at both local and global graph-levels.