PhD defense of Majd Zreik

On Tuesday 14 January, Majd Zreik will defend his thesis entitled: “Machine learning for coronary artery disease analysis in cardiac CT.”

Abstract

Cardiovascular diseases (CVD) are diseases that affect the heart and the blood vessels, such as myocardial infarction and stroke. Obstructive coronary artery disease (CAD) is the most common type of CVD. Obstructive CAD develops when atherosclerotic plaque builds up in the wall of the coronary arteries, narrowing the coronary artery lumen. This is defined as coronary stenosis, which could potentially limit blood supply to the heart and lead to ischemia and irreversible damage to the myocardium (heart muscle). Only functionally significant stenosis, i.e. those which significantly limit blood flow and cause ischemia, need to be invasively intervened in order to reduce CAD morbidity. Moreover, various types of atherosclerotic plaque and varying anatomical grades (degree of narrowing) of stenosis could lead to differences in management of patients with coronary artery disease. Therefore, to manage patient treatment and to guide invasive interventions, it is crucial to assess the functional and the anatomical significance of a coronary artery disease, as well as to classify the type of coronary artery plaque.

Cardiac CT angiography (CCTA) images of patients with suspected obstructive CAD are typically used to visually characterize coronary artery plaque and stenosis, as well as to serve as the gatekeeper for referral to invasive coronary angiography (ICA), where the fractional flow reserve (FFR) is measured to identify functionally significant stenosis. This thesis describes different machine learning-based methods for automatic noninvasive identification of patients with functionally significant stenosis, and for automatic detection and characterization of coronary artery plaque and stenosis in CCTA images.