NeuroLens: A Holistic Visual Analytics System for Exploring Brain Networks Across Scales

Identifying biomarkers from human brain networks is critical in early detection of neurological disorders and understanding disease mechanisms. Existing visual analytics approaches show a remarkable ability to assist experts in discovering and validating biomarkers through exploration. However, these approaches often focus only on the diffusion features of fiber bundles and evaluate individual bundles and regions separately. This may hinder their ability to accurately represent the complex brain network for investigation from various perspectives. In this paper, we present NeuroLens, a visual analytics system that integrates comprehensive information across multiple levels, including fiber bundles, local regions and entire brain networks. Specifically, to model the bundles more precisely, we enhance the features by incorporating the joint distribution of geometric features. The bundle information is further aggregated to form representations at the region and the brain level using an attention-based graph neural network. The region-level representation describes complex structures involving multiple bundles, and the brain-level representation enables comparisons between subjects and groups. The NeuroLens interface enables comparative exploration of this multi-level and multi-faceted information. To verify the findings during exploration, NeuroLens leverages the large language model to query related information from existing literature. We collaborate with domain experts to examine the effectiveness of NeuroLens. Their exploration, findings, and feedback are discussed.