چكيده به لاتين
Abstract:
In this thesis, a fully automatic level-set method for left ventricle segmentation from cardiac MRI, is proposed. Edge based Distance Regularized Level Sets Evolution(DRLSE) model is developed to a two-layer formulation with its 0-level an k-level representing endocardium and epicardium respectively. The extraction of endocardium and epicardium is obtained as a result of the interactive curve evolution of the 0 and k level sets derived from the proposed variational level set formulation. In addition, since the shape of LV throughout the apex-base axis is close to a ring shape, we propose a circle fitting term in the level set framework to detect the endocardium. The circle fitting term imposes a penalty on the evolving contour from its fitting circle, and thereby handles quite well with issues in LV segmentation, especially the presence of outflow track in basal slices and intensity overlap between TPM and the myocardium. The choice of initial contour is done automatically by using a novel method based on the difference of frames. Then preliminary segmentation is done by applying the original DRLSE model and its result is used as the initial level set function for distance regularized two-layer level sets model.
The proposed method is applied to data set from MICCAI 2009 challenge on left ventricle. The average values for average perpendicular distance and dice similarity coefficient for 30 subjects are equal to 1.95 mm and 0.89 for endocardium and 2.03 mm and 0.93 for epicardium respectively which are desirable. In addition, ejection fraction and left ventricular mass are close to manual values which shows the ability of this method in accurate delineation of these clinical parameters.
Keywords: fully automatic, segmentation, left ventricle, cardiac MRI, level sets method
