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.
Archana Venkataraman is a postdoctoral associate in the Medical Vision Group at the Massachusetts Institute of Technology (MIT). Her research focuses on multimodal and clinical applications of medical imaging. Her objective is to use engineering principles, such as probabilistic modeling, signal processing and network theory, to improve the diagnosis and treatment of debilitating neurological illnesses. Archana completed her B.S., M.S. and Ph.D. in Electrical Engineering at MIT in 2006, 2007 and 2012, respectively. She is a recipient of the NIH Advanced Multimodal Neuroimaging Training Grant, the National Defense Science and Engineering Graduate Fellowship, the Siebel Scholarship and the MIT Provost Presidential Fellowship.
NOTE Location: E25-111
10:30 AM Pre-seminar reception
11:00 AM Seminar