Spatiotemporal Learning of Brain Dynamics from fMRI Using Frequency-Specific Multi-Band Attention for Cognitive and Psychiatric Applications
This work addresses the problem of improving biomarker accuracy and interpretability for cognitive and psychiatric disorders, offering a novel framework that could advance precision psychiatry and developmental neuroscience, though it builds incrementally on existing transformer and frequency-based methods.
The authors tackled the challenge of modeling the brain's complex nonlinear dynamics from fMRI data by introducing MBBN, a transformer-based framework that integrates frequency decomposition with multi-band self-attention, achieving up to 52.5% higher AUROC in predicting psychiatric and cognitive outcomes like depression, ADHD, and ASD across large-scale cohorts.
Understanding how the brain's complex nonlinear dynamics give rise to cognitive function remains a central challenge in neuroscience. While brain functional dynamics exhibits scale-free and multifractal properties across temporal scales, conventional neuroimaging analytics assume linearity and stationarity, failing to capture frequency-specific neural computations. Here, we introduce Multi-Band Brain Net (MBBN), the first transformer-based framework to explicitly model frequency-specific spatiotemporal brain dynamics from fMRI. MBBN integrates biologically-grounded frequency decomposition with multi-band self-attention mechanisms, enabling discovery of previously undetectable frequency-dependent network interactions. Trained on 49,673 individuals across three large-scale cohorts (UK Biobank, ABCD, ABIDE), MBBN sets a new state-of-the-art in predicting psychiatric and cognitive outcomes (depression, ADHD, ASD), showing particular strength in classification tasks with up to 52.5\% higher AUROC and provides a novel framework for predicting cognitive intelligence scores. Frequency-resolved analyses uncover disorder-specific signatures: in ADHD, high-frequency fronto-sensorimotor connectivity is attenuated and opercular somatosensory nodes emerge as dynamic hubs; in ASD, orbitofrontal-somatosensory circuits show focal high-frequency disruption together with enhanced ultra-low-frequency coupling between the temporo-parietal junction and prefrontal cortex. By integrating scale-aware neural dynamics with deep learning, MBBN delivers more accurate and interpretable biomarkers, opening avenues for precision psychiatry and developmental neuroscience.