Artificial intelligence (AI) is showing promise in multiple medical imaging applications. Yet rigorous evaluation of these methods is important before they are introduced into clinical practice.
A multi-institutional and multiagency team led by researchers at Washington University in St. Louis is outlining a framework for objective task-based evaluation of AI-based methods and outlining the key role that physicians play in these evaluations. They also are providing techniques to conduct such evaluations, particularly in positron emission tomography (PET)… Continue reading.
Kyle Myers, a physicist with a Ph.D. in optical sciences, is a member of MDIC’s Computational Modeling and Simulation Steering Committee. She is Director of the Division of Imaging, Diagnostics, and Software Reliability in the U.S. Food and Drug Administration’s Center for Devices and Radiological Health (CDRH). In February, Myers was elected to membership in the National Academy of Engineers, one of the profession’s highest distinctions. The Academy recognized Myers’ development of analytical and regulatory science methods for accuracy and safety of medical imaging devices. Myers leads a team of scientists studying how next-generation screening and diagnostic devices using three-dimensional (3-D) imaging — like that used in video games and movies — can/may help detect and diagnose cancers, particularly early stage breast cancer.
MDIC: How do you view MDIC’S modeling and simulation work in terms of aligning with the FDA’s strategic priorities?
Myers: MDIC’s modeling and simulation project is completely aligned with the FDA’s priorities, particularly the science involved with assessing FDA-regulated products. Through MDIC, scientists from FDA/CDRH, industry and nonprofits are able to collaborate on developing new modeling and simulation tools and the design of new devices, as well as new approaches for the regulatory decision-making process. Of course, it’s the FDA’s responsibility to determine when a model or simulation technique is regulatory grade, but MDIC’s work will make modeling tools more widely available. This provides the FDA with valuable input on their applicability and reliability as evidence of device safety and effectiveness… Continue reading.