Sequential Monte Carlo Graph Convolutional Network for Dynamic Brain Connectivity

TL;DR

This paper introduces SMC-GCN, a novel graph neural network based on particle filtering, for dynamic brain connectivity analysis that handles noisy, non-stationary data and improves brain disorder classification accuracy.

Contribution

The paper presents a new methodology combining particle filtering with graph neural networks to analyze dynamic brain connectivity without assuming stationarity.

Findings

Outperforms existing methods in brain disorder classification

Effectively handles noisy and partial observations

Limits spurious connections in dynamic brain graphs

Abstract

An increasingly important brain function analysis modality is functional connectivity analysis which regards connections as statistical codependency between the signals of different brain regions. Graph-based analysis of brain connectivity provides a new way of exploring the association between brain functional deficits and the structural disruption related to brain disorders, but the current implementations have limited capability due to the assumptions of noise-free data and stationary graph topology. We propose a new methodology based on the particle filtering algorithm, with proven success in tracking problems, which estimates the hidden states of a dynamic graph with only partial and noisy observations, without the assumptions of stationarity on connectivity. We enrich the particle filtering state equation with a graph Neural Network called Sequential Monte Carlo Graph Convolutional Network (SMC-GCN), which due to the nonlinear regression capability, can limit spurious connections in the graph. Experiment studies demonstrate that SMC-GCN achieves the superior performance of several methods in brain disorder classification.