Search for: All records

In this paper, we propose a supervised graph representation learning method to model the relationship between brain functional connectivity (FC) and structural connectivity (SC) through a graph encoder-decoder system. The graph convolutional network (GCN) model is leveraged in the encoder to learn lower-dimensional node representations (i.e. node embeddings) integrating information from both node attributes and network topology. In doing so, the encoder manages to capture both direct and indirect interactions between brain regions in the node embeddings which later help reconstruct empirical FC networks. From node embeddings, graph representations are learnt to embed the entire graphs into a vector space. Our end-to-end model utilizes a multi-objective loss function to simultaneously learn node representations for FC network reconstruction and graph representations for subject classification. The experiment on a large population of non-drinkers and heavy drinkers shows that our model can provide a characterization of the population pattern in the SC-FC relationship, while also learning features that capture individual uniqueness for subject classification. The identified key brain subnetworks show significant between-group difference and support the promising prospect of GCN-based graph representation learning on brain networks to model human brain activity and function. 

In this paper, the relationship between functional and structural brain networks is investigated by training a graph encoder-decoder system to learn the mapping from brain structural connectivity (SC) to functional connectivity (FC). Our work leverages a graph convolutional network (GCN) model in the encoder which integrates both nodal attributes and the network topology information to generate new graph representations in lower dimensions. Using brain SC graphs as inputs, the novel GCN-based encoder-decoder system manages to account for both direct and indirect interactions between brain regions to reconstruct the empirical FC networks. In doing so, the latent variables within the system (i.e., the learnt low-dimensional embeddings) capture important information regarding the relation between functional and structural networks. By decomposing the reconstructed functional networks in terms of the output of each graph convolution filter, we can extract those brain regions which contribute most to the generation of FC networks from their SC counterparts. Experiments on a large population of healthy subjects from the Human Connectome Project show our model can learn a generalizable and interpretable SC-FC relationship. Overall, results here support the promising prospect of using GCNs to discover more about the complex nature of human brain activity and function.