Spectral Graph Neural Networks for Cognitive Task Classification in fMRI Connectomes

TL;DR

This paper introduces SpectralBrainGNN, a spectral graph neural network model that effectively classifies cognitive tasks from fMRI connectomes, achieving high accuracy by leveraging spectral graph convolutions based on brain network topology.

Contribution

The paper presents a novel spectral GNN framework for brain connectome analysis, demonstrating improved classification accuracy on the HCPTask dataset.

Findings

Achieved 96.25% classification accuracy on HCPTask dataset.

SpectralGNN outperforms conventional methods in cognitive task classification.

Model implementation is publicly available for reproducibility.

Abstract

Cognitive task classification using machine learning plays a central role in decoding brain states from neuroimaging data. By integrating machine learning with brain network analysis, complex connectivity patterns can be extracted from functional magnetic resonance imaging connectomes. This process transforms raw blood-oxygen-level-dependent (BOLD) signals into interpretable representations of cognitive processes. Graph neural networks (GNNs) further advance this paradigm by modeling brain regions as nodes and functional connections as edges, capturing topological dependencies and multi-scale interactions that are often missed by conventional approaches. Our proposed SpectralBrainGNN model, a spectral convolution framework based on graph Fourier transforms (GFT) computed via normalized Laplacian eigendecomposition. Experiments on the Human Connectome Project-Task (HCPTask) dataset demonstrate the effectiveness of the proposed approach, achieving a classification accuracy of 96.25\%. The implementation is publicly available at https://github.com/gnnplayground/SpectralBrainGNN to support reproducibility and future research.