Semiautomatic Segmentation of CT Cardiac Images

In order to complete the semi auto-segmentation of dual-source CT image of heart and extract the structure of heart accurately, propose a novel segmentation method of CT images based on graph cuts based active contour and anisotropies spreads algorithms. The method combines image characteristics with high-level segmentation model, Due to effectively used heart anatomical structure, the noise and fuzzy boundary have less effect on the segmentation results. It is used to quickly and accurately segment ventricle, atria and coronary artery. After the pre-segmentation of the DSCT images, the ventricular and atrium are fast and accurately segmented through minimize the energy function. The segmentation method can effectively process cardiac medical image of DSCT. It provides new methods for clinical doctors to get more information of cardiac images.