AI in Medical Imaging: The Present and Future – Erickson, Bradley

Bio : Bradley J. Erickson, M.D., Ph.D., is Professor of Radiology, with joint appointments in the Department of Quantitative Health Sciences and the Department of Biomedical Engineering and Physiology. He is a practicing neuroradiologist at Mayo Clinic. He also runs a lab with 17 post-doctoral fellows that focus on the application of artificial intelligence and deep learning to medical imaging. This research includes the development and validation of algorithms that can detect progression, regression or risk of disease, and the prediction of molecular markers from medical images. His work has been funded by the National Institute of Diabetes and Digestive and Kidney Disease; National Institute of General Medical Sciences; National Institute of Neurological Disorders and Stroke; and National Cancer Institute. He has developed numerous computer-based tools that have been put into clinical practice, including the clinical image viewer that has been used for more than 25 years. He also founded Teramedica which was one of the first vendor-neutral archive companies, and more recently FlowSIGMA, which applies intelligent process automation to clinical practice. He also has several AI-based tools that have been put into clinical practice.

Date & Time : 7th December at 9:30 AM

Abstract : The presentation will focus on how AI is being applied to medical imaging and where it is likely to be further developed. In particular, some of the technical challenges and recent advances will be highlighted to help frame the likely trajectory. Some of the applications described will be for image segmentation, classification with particular attention to multi-modal AI, and applications for image reconstruction and improvement. Finally, considerations and options for clinical implementation will be discussed.