Graph neural networks for fMRI functional brain networks: A survey.

Abstract

With the rapid advancement of neuroimaging technologies, the development of deep learning-based models for the analysis of mental disorders has become an emerging consensus. Graphs, as a data and relationship representative, can abstract complex brain data, enabling us to systematically and precisely reveal key issues related to brain structure and function with the support of neuroimaging techniques. Graph neural networks (GNNs) provide new tools and methods for brain network analysis, allowing for a deeper exploration of the relationships between functional regions of the brain and potential functional patterns. Therefore, GNN-based methods for brain network analysis are gaining increasing attention. However, there is currently a lack of a comprehensive summary of the latest research approaches in this field from the perspective of computer science. This survey covers functional brain network analysis methods from different dimensions. In addition, for each method, we discuss the corresponding open challenges and unmet needs to identify the limitations and future directions of these methods in brain network research. Finally, to facilitate researchers in selecting and applying appropriate brain network datasets for experimentation and validation, we summarize the characteristics and sources of various brain network analysis datasets.