events

executive

news

Image Processing Methods for Applications in Medical Imaging: Towards Translating Personalized Biomarkers into Clinical Care

Professor Eranga Ukwatta

Assistant Professor, Department of Systems and Computer Engineering, Carleton University, Ottawa, Canada

February 2, 2016 13:00 - 14:30

Canal Building Room 2104, Carleton University

Paid parking available on campus.

Registration not required.

abstract

Medical image segmentation, a process of partitioning an image into multiple meaningful regions, is an important step in clinical workflows designed to extract quantitative information from medical images for diagnosis and treatment of diseases. In this talk, I will describe several image segmentation algorithms based on 'convex max-flow formulations' that were developed for patient-specific analysis and modeling of cardiovascular structure and function. In particular, I will present a number of multi-region-based segmentation methods for generating morphological measurements of atherosclerotic plaque burden in the arteries using non-invasive imaging techniques. My current research work focuses on investigating more quantitative and accurate ways to estimate the infarcted regions of the heart for clinical prognosis of cardiac rhythm disorders. To this end, I have developed an image analysis pipeline for building personalized computational models of the heart for simulation of ventricular tachycardia. These virtual models can be non-invasively interrogated to gain mechanistic insights into electrical activity of the heart, and has potential to be utilized in the clinic for numerous applications, such as patient risk stratification and prediction of target locations for cardiac ablation. Finally, I will demonstrate several applications of image analysis algorithms in other clinical domains, including prostate and brain imaging.

biography

Eran Ukwatta is currently an assistant professor in Systems and Computer Engineering at Carleton. Prior to that, he was a multi-center postdoctoral fellow at Johns Hopkins University and Sunnybrook Research Institute. His primary research is driven by the emerging need for robust image analysis methodologies for patient-specific analysis and modeling of cardiovascular structure and function. He was a recipient of NSERC postdoctoral fellowship, JHU BME Centennial postdoctoral fellowship, and MITACS Elevate postdoctoral fellowship (declined).