Left Ventricle Segmentation Technology based on CV Level Set Methods

This paper presents an improved contour extraction method based on CT images of the left ventricle. It provides the basis for three-dimensional and four-dimensional reconstruction of post-cardiac imaging. In this method, original CT image will be segmented by CV level set methods after the pre-treatment of the image firstly, and we derive boundary point set from energy function minimization information; then we gain the global contour lines dataset which contains multiple contours. Finally, we accurately extract the outline of the left ventricle based on the determinant conditions of area and so on after excluding one-point outline. Experimental results show that this method can effectively extract the left ventricle smooth continuous contour in the environment of fuzzy boundary information and topology changing.