Fusion Learning from Dynamic Functional Connectivity: Combining the Amplitude and Phase of fMRI Signals to Identify Brain Disorders

The study introduces a multi-scale fusion learning framework (MSFL) that integrates amplitude and phase information from resting-state fMRI signals to enhance the detection of brain disorders. By utilizing dynamic functional connectivity (dFC) features derived from sliding window correlation (SWC) and phase synchronization (PS), MSFL was evaluated on autism spectrum disorder and major depressive disorder datasets (ABIDE I and REST-meta-MDD), demonstrating superior classification performance compared to existing models. This approach highlights the importance of combining different dFC features for improved diagnostic accuracy in neuroimaging applications.