Public Lecture

Machine Learning Assessment of Coronary Artery Disease Using X-Ray Angiography

Alberto Figueroa (University of Michigan)

 

 

Coronary artery disease (CAD) and coronary microvascular dysfunction (CMD) diagnosis relies on different tests. Percutaneous approaches have made it possible to assess epicardial and microcirculation disease states in a single procedure, although this approach is rarely utilized due to its invasiveness and complexity. Conversely, there are over 4 million cardiac catheterization procedures performed yearly in the USA and Europe alone, making it one of the most used diagnostic procedures, although with a recognized low diagnostic yield.

Given the high number of catheterization procedures and its low diagnostic yield, there is a pressing need to develop methods to extract diagnostic information for both CAD and CMD from coronary angiography data. Our group has developed a data-driven computational models and machine learning tools for anatomical and functional characterization of CAD and CMD using angiography. In this work, we provide an overview of these tools and several applications.

C. Alberto Figueroa, PhD
C. Alberto Figueroa, PhD

Dr. Figueroa received his PhD in Mechanical Engineering from Stanford University, where he developed fluid-structure interaction methods for blood flow analysis. He was Sr Lecturer in the Division of Biomedical Engineering and Imaging Sciences at King’s College London. Dr. Figueroa is currently the Edward B. Diethrich M.D. Professor of Biomedical Engineering and Vascular Surgery at the University of Michigan.

Dr. Figueroa’s laboratory develops tools for modeling of blood flow which combine imaging, machine learning, and computational methods of fluid and solid mechanics. His group develops the modeling software CRIMSON and is co-founder of AngioInsight, Inc. a company which develops AI tools for assessment of coronary artery disease using x-ray angiography.