October 30th CTE Virtual Seminar
Title: Brain-machine-interfaces, closed-loop neuroscience, and neurorehabilitation:
Harnessing the potential of machine learning-based real-time fMRI
Presenter: Dr. Stephen LaConte
Associate Professor
Department of Biomedical Engineering and Mechanics
Fralin Biomedical Research Institute at
Virginia Tech Carilion School of Medicine
Dr. LaConte’s lab has developed real-time functional magnetic resonance (rtfMRI) that uses supervised learning models to continuously predict a subject’s sensory/behavioral/psychological states during ongoing brain imaging. This talk will present a brief description of machine learning-based real-time fMRI and present experiments that highlight its potential for basic science discovery as well as neurofeedback-based therapy. As specific examples, it will discuss how rtfMRI can be used to study the neural effects of brain machine interfaces and potentially improve their performance. It will also share the lab’s recent work to elucidate the functional roles of so-called resting-state networks. Originally thought to be noise, spontaneous brain activity is now known to arise as spatially distributed network coherence patterns. These networks are broadly implicated in healthy cognition and across the entire spectrum of brain health issues. Thus the talk will also show preliminary data from depression, attention deficit, and TBI participants that indicate that real-time fMRI might be able to characterize and ultimately help rehabilitate neurological and psychiatric illness.