Detection of Plaque in Coronary Artery in CMRI Images and 3D Visualization of Blood Flow

Detection of blocks in coronary arteries is becoming crucial interest for early detection of heart attacks. In this paper we propose a framework for detection of plaque in coronary arteries from cardio vascular magnetic resonance imaging(CMRI). It is a quantitative tool for the assessment of cardiovascular diseases. First, select a region of interest and segment the region of coronary artery using enhanced region based active contour (ERAC). Secondly the centreline extraction and lumen segmentation are integrated to extract the artery centreline using geometric moments and the vessel direction using Hessian matrix and segment the vessel lumen in each slice using ERAC. A boundary searching method is adapted to fine tune the segmented surface in each slice of CMRI image. Third, the soft plaques in the coronary artery are extracted by thresholding the segmented region. Finally a 3D visualization of blood flow in coronary artery is presented and the volume of blood flow is calculated. In the experiments we have employed 22 datasets of CMRI images. The experimental results show an average accuracy of 97.6% and with a mean and standard deviation of false discovery rate of 2.48 ± 0.002.