A Dual-Attention Graph Network for fMRI Data Classification
This work addresses the challenge of accurately diagnosing ASD from fMRI data, which is an incremental improvement over existing methods by better modeling neural dynamics.
The paper tackles the problem of classifying fMRI data for Autism Spectrum Disorder diagnosis by proposing a dual-attention graph network that captures dynamic functional connectivity and spatio-temporal relationships, achieving 63.2% accuracy and 60.0 AUC on the ABIDE dataset, outperforming static graph-based methods like GCN at 51.8% accuracy.
Understanding the complex neural activity dynamics is crucial for the development of the field of neuroscience. Although current functional MRI classification approaches tend to be based on static functional connectivity or cannot capture spatio-temporal relationships comprehensively, we present a new framework that leverages dynamic graph creation and spatiotemporal attention mechanisms for Autism Spectrum Disorder(ASD) diagnosis. The approach used in this research dynamically infers functional brain connectivity in each time interval using transformer-based attention mechanisms, enabling the model to selectively focus on crucial brain regions and time segments. By constructing time-varying graphs that are then processed with Graph Convolutional Networks (GCNs) and transformers, our method successfully captures both localized interactions and global temporal dependencies. Evaluated on the subset of ABIDE dataset, our model achieves 63.2 accuracy and 60.0 AUC, outperforming static graph-based approaches (e.g., GCN:51.8). This validates the efficacy of joint modeling of dynamic connectivity and spatio-temporal context for fMRI classification. The core novelty arises from (1) attention-driven dynamic graph creation that learns temporal brain region interactions and (2) hierarchical spatio-temporal feature fusion through GCNtransformer fusion.