Understanding Graph Isomorphism Network for rs-fMRI Functional Connectivity Analysis
This work addresses the interpretability challenge in applying GNNs to fMRI analysis for neuroscientists, though it is incremental as it adapts existing techniques to a specific domain.
The authors tackled the problem of explaining graph neural network (GNN) classification results in fMRI data by developing a framework using Graph Isomorphism Network (GIN) and adapting CNN-based saliency map techniques to visualize important brain regions. They validated the framework on large-scale rs-fMRI data for sex classification, showing that the saliency maps aligned with known neuroimaging evidence on sex differences.
Graph neural networks (GNN) rely on graph operations that include neural network training for various graph related tasks. Recently, several attempts have been made to apply the GNNs to functional magnetic resonance image (fMRI) data. Despite recent progresses, a common limitation is its difficulty to explain the classification results in a neuroscientifically explainable way. Here, we develop a framework for analyzing the fMRI data using the Graph Isomorphism Network (GIN), which was recently proposed as a powerful GNN for graph classification. One of the important contributions of this paper is the observation that the GIN is a dual representation of convolutional neural network (CNN) in the graph space where the shift operation is defined using the adjacency matrix. This understanding enables us to exploit CNN-based saliency map techniques for the GNN, which we tailor to the proposed GIN with one-hot encoding, to visualize the important regions of the brain. We validate our proposed framework using large-scale resting-state fMRI (rs-fMRI) data for classifying the sex of the subject based on the graph structure of the brain. The experiment was consistent with our expectation such that the obtained saliency map show high correspondence with previous neuroimaging evidences related to sex differences.