25th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Singapore, Singapore, 18 - 22 September 2022, vol.13431, pp.305-314
A connectional brain template (CBT) is a normalized representation of a population of brain multigraphs, where two anatomical regions of interests (ROIs) are connected by multiple edges. Each edge captures a particular type of interaction between pairs of ROIs (e.g., structural/functional). Learning a well-centered and representative CBT of a particular brain multigraph population (e.g., healthy or atypical) is a means of modeling complex and varying ROI interactions in a holistic manner. Existing methods generate CBTs by locally integrating heterogeneous multi-edge attributes (e.g., weights and features). However, such methods are agnostic to brain network modularity as they ignore the hierarchical structure of neural interactions. Furthermore, they only perform node-level integration at the individual level without learning the multigraph representation at the group level in a layer-wise manner. To address these limitations, we propose Dual Hierarchical Integration Network (Dual-HINet) for connectional brain template estimation, which simultaneously learns the node-level and cluster-level integration processes using a dual graph neural network architecture. We also propose a novel loss objective to jointly learn the clustering assignment across different edge types and the centered CBT representation of the population multigraphs. Our Dual-HINet significantly outperforms state-of-the-art methods for learning CBTs on a large-scale multigraph connectomic datasets. Our source code can be found at https://github.com/basiralab/Dual-HINet.