AI Health Spark Seminar Series: Machine learning for preclinical behavioral phenotyping and TBI clinical workflows
Professor Tim Dunn, PhD. will present recent work from two different projects applying machine learning and computer vision to understand and promote brain health. Body movement is closely linked to brain health and can, in principle, provide rich quantitative metrics for brain disorders and treatments. Nevertheless, there has been a notable lack of tools for precise movement quantification, especially in preclinical animal studies (but also in the clinic). To bridge this gap, we have built computer vision tools for 3D movement (pose) quantification in individuals and social groups. Prof. Dunn will summarize how, in lab rodents, we have used these 3D behavioral measurements to improve the sensitivity and throughout of preclinical drug and disease phenotyping. Given the clinical focus of the audience, he will also present his progress towards building brain CT image processing systems for traumatic brain injury clinical workflows.
This session is a part of the monthly seminar series organized by Spark: AI Health Initiative for Medical Imaging. The seminar will highlight outstanding work in medical imaging at Duke and beyond. The seminar recordings will be publicly available.
The Spark initiative focuses on development, validation, and clinical implementation of artificial intelligence algorithms for broadly understood medical imaging by bringing together the technical and clinical expertise across Duke campus. For more information please contact Dr. Maciej Mazurowski (firstname.lastname@example.org).