Brain-MGF: Multimodal Graph Fusion Network for EEG-fMRI Brain Connectivity Analysis Under Psilocybin
This provides an interpretable framework for neuroscientists studying psychedelic effects on brain networks, though it is incremental as it builds on existing multimodal fusion techniques.
The paper tackled the problem of analyzing brain connectivity changes under psilocybin using EEG and fMRI data, and the result was that their adaptive graph fusion method improved classification accuracy to 74.0% and F1 score to 76.5% for meditation conditions, and 76.0% accuracy with 85.8% ROC-AUC for rest conditions.
Psychedelics, such as psilocybin, reorganise large-scale brain connectivity, yet how these changes are reflected across electrophysiological (electroencephalogram, EEG) and haemodynamic (functional magnetic resonance imaging, fMRI) networks remains unclear. We present Brain-MGF, a multimodal graph fusion network for joint EEG-fMRI connectivity analysis. For each modality, we construct graphs with partial-correlation edges and Pearson-profile node features, and learn subject-level embeddings via graph convolution. An adaptive softmax gate then fuses modalities with sample-specific weights to capture context-dependent contributions. Using the world's largest single-site psilocybin dataset, PsiConnect, Brain-MGF distinguishes psilocybin from no-psilocybin conditions in meditation and rest. Fusion improves over unimodal and non-adaptive variants, achieving 74.0% accuracy and 76.5% F1 score on meditation, and 76.0% accuracy with 85.8% ROC-AUC on rest. UMAP visualisations reveal clearer class separation for fused embeddings. These results indicate that adaptive graph fusion effectively integrates complementary EEG-fMRI information, providing an interpretable framework for characterising psilocybin-induced alterations in large-scale neural organisation.