Analysis of a Dedicated Pixel Tracking Method for Intravascular Ultrasound Images

Abstract

Atherosclerosis is a major cause of acute coronary events. The development of methods capable of identifying and classifying the mechanical properties of atherosclerotic plaques is of great interest in the medical field. In order to properly identify the plaques, it is first necessary to accurately track its deformation under different pressures. The aim of this study is to, first, propose a pixel tracking methodology for application in intravascular ultrasound images, and second, evaluate the pixel tracking method through a novel automated method. The framework proposed utilizes a numerical phantom of the artery and mechanically deforms an atherosclerotic plaque by applying different intraluminal pressures, providing a known position map of control points on the plaque throughout the deformation of the tissue. We track the position of the control points through two subsequential frames that correspond to diastolic and systolic intraluminal pressures. We evaluate the accuracy of the pixel tracking method by comparing the tracked positions of the control points with the known positions of the control points through statistical analysis. This study has the potential to provide a new metrics for evaluating distinct pixel tracking parameters and methods, contributing to provide a safer, more accurate method of evaluating atherosclerotic plaques.