AIMI-IBIIS Seminar with Tessa Cook, MD, PhD - Deploying AI in the Clinical Radiology Workflow: Challenges, Opportunities, and Examples

About:
Dr. Cook is an Assistant Professor of Radiology at the Perelman School of Medicine at the University of Pennsylvania in Philadelphia. She has a strong background in imaging informatics, having done her doctoral work in quantitative image processing in the Penn Image Computing and Science Laboratory (PICSL) of Dr. James Gee. During her residency, Dr. Cook became heavily involved in clinical imaging informatics research and completed a dedicated year of research as part of her residency. She is the developer of RADIANCE, an open-source software pipeline for CT radiation exposure which was the second available tool worldwide upon its release in 2010. Dr. Cook is an active member of multiple radiology societies, including the RSNA, ACR, SIIM, and AUR. She was one of the two recipients of the 2011 E. Stephen Amis, Jr. Fellowship in Quality and Safety offered annually by the American College of Radiology. In 2013 she was named one of the four AUR GERRAF fellows for 2013-2015. Dr. Cook currently enjoys an academic appointment in radiology that enables her to continue her clinical work and research in imaging informatics. She is the director of the Imaging Informatics Fellowship in the Department of Radiology, as well as the clinical director of the department's 3-D and Advanced Imaging Laboratory. She is also the Co-Director of the Center for Practice Transformation. Dr. Cook’s current research sits squarely at the intersection of imaging informatics and health services. She and her team were awarded one of the first grants from the Penn Center for Healthcare Innovation, in order to develop and study an automated radiology recommendation-tracking engine. In her various roles, she is pursuing innovative methods to improve radiologists' workflow, as well as enhance the delivery of longitudinal patient care in radiology.

Abstract:

Although many radiology AI efforts are focused on pixel-based tasks, there is great potential for AI to impact radiology care delivery and workflow when applied to reports, EMR data, and workflow data. Radiology-pathology correlation, identification of follow-up recommendations, and report segmentation can be used to increase meaningful feedback to radiologists as well as to automate tasks that are currently manual and time-consuming. When deploying AI within the clinical workflow, there are many challenges that may slow down or otherwise affect the integration. Careful consideration of the way in which radiologists may expect to interact with AI results should be undertaken to meaningfully deploy radiology AI in a safe and effective way.

Join via Zoom: https://stanford.zoom.us/j/344651804