Supervised method for blood vessel segmentation from coronary angiogram images using 7-D feature vector

Abstract

With the recent advancement in medical image processing field and sophisticated simulation tools it has been possible to acquire useful information from raw images for different parts of the body. Coronary artery segmentation is the fundamental component which extract significant features from angiogram images. Cardiac catheterization is an invasive diagnostic procedure that provides important information about the structure and function of heart. The procedure usually involves X-ray images of heart, arteries using coronary angiography. The resultant images (coronary angiogram) are considered as best of way to diagnose cardiac heart disease. The main focus of coronary angiography is to find the blockage in major blood vessels, however if the blockage is not found in large blood vessels and patient persists to have pain (angina) then it is concluded that the patient is having micro vascular disease (MVD). MVD is caused by blockage or narrowing of small blood vessels in heart, unfortunately there is no specific test to diagnose MVD but it is common in people having diabetes and blood pressure. This paper proposes an automated method of vessel segmentation from coronary angiogram images using radial basis function and moment invariant-based features to extract the small blood vessel for diagnosis of MVD. Experimental results show that the proposed method is capable of extracting small blood vessels from coronary artery and can be a basis to identify key characteristics for MVD. The dataset of angiogram images have been provided by ISRA University Hospital and MATLAB is used for implementing the proposed method.