Seed-Growing Heart Segmentation in Human Angiograms

Segmentation, Unsupervised clustering, Mean shift, Cardiac images, Human heart, Left ventricle. In this paper an image segmentation scheme that is based on combinations of a nonparametric technique and a seed based clustering algorithm is reported. The method has been applied to clinical unsubtracted angiograms of the human heart. The first step of the method consists in applying a mean shiftbased filter in order to improve the left ventricle cavity information in angiographic images. Second, the initial seed is semi automatically generated from the aortic valve manual localization by a specialist. Third, each angiographic image is segmented using a clustering algorithm that begins with the seed which is grown until image pixels associated to the left ventricle cavity are clustered. A validation is performed by comparing the estimated contours with respect to contours manually traced by a cardiologists. From this validation stage the maximum of the average contour error considering six angiographic sequences (a total of 178 images) is 7.30 %.