Blood vessel segmentation in coronary angiogram image

Coronary heart disease has been one of the main threats to human health. Coronary angiography is taken as the gold standard for the assessment of coronary artery disease. However, sometimes the images are difficult to visually interpret because of the crossing and overlapping of vessels in the angiogram. Also due to the low contrast of the image between the backdrop and the small blood vessels, the blurred and fuzzy background of coronary artery image, a new blood vessel segmentation method using morphology is presented in this paper. Firstly the original angiogram image is preprocessed using Top hat operator which enhances the contrast of image. Then morphological close operation is used for vessel segmentation. After thresholding the blood vessels of coronary angiogram are extracted. Using this method, both the coronary artery trees and most of smaller distal vessels could be extracted clearly. Index Terms coronary angiogram, vessel segmentation, morphology. ________________________________________________________________________________________________________