UC Santa Cruz

Analysis and comparison of multiple time-varying connectomes is crucial for studying brain diseases such as Depression and Alzheimer’s Disease. Recently, many visualization techniques have been proposed to assist clinical psychiatrists in exploring complex connectome datasets but majority of them are focused on static connectome features. We develop two novel visualization applications: TempoCave and ConnectoVis, for analyzing dynamic brain networks, or connectomes. TempoCave and ConnectoVis provide a range of functionality to explore metrics related to the activity patterns of different regions in the brain. Analysis of temporal connectome is limited due to high dimensionality of the data. To address this problem, we introduce a new data analysis technique that is specifically designed for dynamic functional connectomes by combining a novel temporal graph neural network and a learnable mask mechanism. Our technique can classify remitted depression group vs control group with 98% accuracy and the mask is used to identify the significant brain regions that contribute to depression. Along with our visualization tools, we have a spatio-temporal connectome analysis pipeline. We demonstrate the effectiveness of our pipeline through three use cases.