New medical image sequences segmentation based on level set method

Image segmentation is one of the key problems in medical image processing. The level set method based on curves evolving theory and partial differential equation theory is widely applied in the segmentation of medical image. The level set method can handle topology changes effectively. In this paper, a penalized energy is added into the geodesic active contour (GAC) model and the C_V model respectively to eliminate the re-initialization procedure completely. Then, a term of boundary information is added into the C_V model to incorporate regional and gradient information together for better segmentation. The segmentation for medical image sequence which is implemented in this paper is the necessary preparation for 3D reconstruction later on. The obtained results have shown desirable segmentation performance.