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

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.

💡 Research Summary

The paper introduces a novel way to represent task‑fMRI data as graphs whose edge weights encode evidence for a particular cognitive state. For each pair of brain regions, a set of simple time‑series features (e.g., mean, variance, correlation) is extracted and fed into a lightweight probabilistic classifier (logistic regression, naïve Bayes, etc.). The classifier outputs posterior probabilities for the two experimental conditions; the edge weight is defined as the difference between these probabilities (P(state = 2) − P(state = 1)). Consequently, each weight lies in the interval