Analysis of Cardiac CT Scan Images for Detection of Vessel Blockage (P-0088) (MFN 4661)

Abstract

Cardiac Arrest is a medical condition caused due to the blockage of heart arteries. It is caused due to plaque or narrowing of the arteries and may cause death. The aim of this project is to design and implement computer aided diagnostic system for automated detection of blood clot in heart vessels. This helps in diagnosis of the clot which is not visible through naked eye thus preventing complications or any disease. Our proposed system consists of three stages; i.e. Preprocessing, Feature Extraction and finally the Fusion Process. In Preprocessing, CT images are enhanced using different techniques. First images are sharpened for better results. After noise is removed and contrast is improved. Second stage extract all possible details using Morphological Operations. Gabor wavelet and thresholding is applied for vessel segmentation. Last part consists of fusion of Thallium and CT images. Thallium images are smoothen using morphological operation and transparency images are obtained. Scaling and image equalization is applied. Finally using point to point transversal Thallium images are fused on CT images. It is clear by the experimental results that high accuracy is obtained by the proposed system. Validity of the proposed system is also proven by the results.