Quantitative analysis of Carotid atherosclerosis to predict the severity of stroke

Abstract

Stroke is the third leading cause of death in the World. It occurs usually when the blood supply to parts of the brain is suddenly interrupted due to the accumulation of blood cell, lipid, protein and cholesterol crystals (called as plaques) in the Carotid arteries which blocks the oxygen supply to the part of the brain cells, and these cells will eventually begin to die. A plaque characteristic on texture and ecogenicity helps to identify a vulnerable and non vulnerable plaque which aids the physician to provide required therapy. Carotid artery image is considered as an input. The high resolution carotid artery image is fed as an input to the feature extraction. The parameters calculated from the feature extraction are energy, standard deviation, correlation co-efficient, mean and entropy. Neural network classifier is used to compare the trained image and input image based on score value. Percentage of lumen area occupied by the arthromatous material (Degree of Stenosis) can be identified by measuring the thickness of the plaque. This enables us to predict the severity of the stroke.