Connectivity analysis quantifies the relationship between brain regions.For example, anatomical connectivity informs us about neural pathways, or the internal wiring of the brain. In contrast, functional connectivity assesses neural synchrony, which relates to patterns of communication. These interactions are crucial to developing a comprehensive understanding of the brain. In this talk I will present a generative framework that combines anatomical and functional connectivity information to identify patterns associated with a neurological disorder.
My framework relies on a latent structure, which captures hidden interactions within the brain. This includes the relationship between anatomy and function and the propagation of disease. The latent variables are complemented by an intuitive likelihood model for the observed neuroimaging data. The resulting algorithm produces clinically meaningful results by simultaneously localizing the centers of abnormal activity and the network of disrupted connectivity. I demonstrate that the model learns stable differences between a control and a schizophrenia population. I will also highlight some very recent work in presurgical planning for epilepsy.