The consideration of changes or dynamics is fundamental for all aspects of brain activity – perception, cognition, and mental health – because the main feature of brain function is the continuous change of the underlying brain states even in a constant environment. The changes are driven by the continuous blood flow in the tissue and electrical activity of neurons that are subject-specific and dynamically evolving. In this talk, I will discuss our recent work on artificial intelligence to understand, characterize, and predict brain hemodynamics and electrical dynamics that focus on reducing patient risk, identifying treatment responders, and optimizing therapeutic outcomes.
Dr. Ruogu Fang is an Assistant Professor who teaches and conducts research on the convergence of machine learning and medical image analysis in the J Crayton Pruitt Family Department of Biomedical Engineering, where she directs the Smart Medical Informatics Learning and Evaluation (SMILE) Lab. Dr. Fang’s research focuses primarily on developing and applying machine learning and image analysis algorithms to understand, model, and predict brain imaging dynamics. Her research work has included auto-ML for low-dose CT perfusion image restoration, multimodal neuroimaging spatio-temporal super-resolution, precision dosing in tDCS treatment response for cognitive decline, early diagnosis and biomarker discovery for Alzheimer’s and Parkinson’s through retinal imaging, automated neuroimaging differentiation of Parkinsonism, mining neuron morphological data, personalized short- and long-term treatment outcome prediction in spinal cord stimulation, and physiological wound hemoglobin map analysis. Dr. Fang earned her PhD in Electrical and Computer Engineering from Cornell University in 2014. Prior joining the University of Florida, she was a tenure-track faculty in Computer Science at the Florida International University. To learn more about Dr Fang, visit her website at https://www.bme.ufl.edu/labs/fang/ruogu/.