Spatial-Temporal Convolutional Attention for Mapping Functional Brain Networks
This work addresses the lack of dynamic analysis in brain network mapping for neuroscience researchers, though it appears incremental as it builds on existing attention mechanisms.
The authors tackled the problem of mapping dynamic functional brain networks (FBNs) from fMRI data by proposing a Spatial-Temporal Convolutional Attention (STCA) model, which achieved higher spatial similarity with templates compared to classical methods.
Using functional magnetic resonance imaging (fMRI) and deep learning to explore functional brain networks (FBNs) has attracted many researchers. However, most of these studies are still based on the temporal correlation between the sources and voxel signals, and lack of researches on the dynamics of brain function. Due to the widespread local correlations in the volumes, FBNs can be generated directly in the spatial domain in a self-supervised manner by using spatial-wise attention (SA), and the resulting FBNs has a higher spatial similarity with templates compared to the classical method. Therefore, we proposed a novel Spatial-Temporal Convolutional Attention (STCA) model to discover the dynamic FBNs by using the sliding windows. To validate the performance of the proposed method, we evaluate the approach on HCP-rest dataset. The results indicate that STCA can be used to discover FBNs in a dynamic way which provide a novel approach to better understand human brain.