Ensemble-based graph representation of fMRI data for cognitive brain state classification

TL;DR

This paper introduces an ensemble-based graph representation for fMRI data that improves brain state classification accuracy and interpretability over traditional correlation graphs, demonstrating high performance across multiple cognitive tasks.

Contribution

The study presents a novel ensemble-based graph encoding method for fMRI data that enhances decoding accuracy and interpretability compared to conventional correlation-based graphs.

Findings

Achieved 97.07-99.74% accuracy in binary brain state classification.

Ensemble graphs outperform correlation graphs in classification accuracy.

Edge weights provide probabilistic, interpretable insights into brain connectivity.

Abstract

fMRI is a non-invasive technique for investigating brain activity, offering high-resolution insights into neural processes. Understanding and decoding cognitive brain states from fMRI depends on how functional interactions are represented. We propose an ensemble-based graph representation in which each edge weight encodes state evidence as the difference between posterior probabilities of two states, estimated by an ensemble of edge-wise probabilistic classifiers from simple pairwise time-series features. We evaluate the method on seven task-fMRI paradigms from the Human Connectome Project, performing binary classification within each paradigm. Using compact node summaries (mean incident edge weights) and logistic regression, we obtain average accuracies of 97.07-99.74 %. We further compare ensemble graphs with conventional correlation graphs using the same graph neural network classifier; ensemble graphs consistently yield higher accuracy (88.00-99.42 % vs 61.86-97.94 % across tasks). Because edge weights have a probabilistic, state-oriented interpretation, the representation supports connection- and region-level interpretability and can be extended to multiclass decoding, regression, other neuroimaging modalities, and clinical classification.