Studies On Cardiac MR Image Segmentation Based On Variational Method

The application of magnetic resonance imaging, with the characteristics of no intervention, not harmful, seldom effected by the motions of objection, has been used in taking pictures of medical images. Medical image segmentation plays an important role in biomedical research and clinical applications such as study of anatomical structure, quantification of tissue volumes, localization of pathology, diagnosis, treatment planning, and computer aided surgery, etc. As a result, accurate segmentation method is crucial to the follow-up analysis.According to different image analysis task, medical image segmentation aims at partition the original image into several meaningful regions or isolating the region of interesting (ROI). Variational method could naturally convert complex segmentation into a variational functional optimization problem. In this thesis, variarional method-based medical image segmentation for specific tasks is extensively explored, and efficient numerical algorithms are discussed.Currently, the active contour models have become an important tool of the medical image analysis. When segmenting images, the classical parametric active contour models suffer from a strong sensitivity to its initial position, have little space to catch, can not move into the area, where is depressed, easy to fall into local minima, can not deal with topological changes, the curves will shrink to a point when the outer force is little, the curves will pass through the weak edges, and there are no academic directions to confirm the parameters. Because of the complexity of anatomical structures and abnormity of parenchyma, the quality of the image is not good enough. In this paper, we present an image segmentation method of Sanke model based on the GAs (genetic algorithms) to prevent the model falling into local minima, and give an image segmentation method of Dual-T-Sankes model based on the Gas. By making use of the Dual-T-Snakes model, it inherits the capability of changing the topology of the T-Snake, reduces the valid search space for the GAs to remedy its limitations. The solution of the Dual-T-Snake consists of two curves enclosing each object boundary, and it composed the valid search space of the GAs. The optimal object boundary can be obtained through the operation of selection, crossover, and mutation. The new model can accelerate the convergence rate while inheriting the capability of changing the topology of the T-Snake, avoid local minima from Snakes model, and maintain the global optimal ability of the GAs, then obtain more precise segmentation. Better results are achieved in application of this method on segmentation of cardiac magnetic resonance images.Aiming at the disability of changing the topology, the Level set model emerges. The model has been driving the studies of none parameterized geometrical models. One of the greatest virtue of geometrical model is that it can change the topology freely. But with the affect of the weak edges, classical level set model, using the information of edges, be effected by the noise and weak edges, can not get the right edges. And if the initial curves cross the edge, the model can not get the results. To do with this problem, we give a D-Level Set Method. In this new method, it can segment the object quickly. Level Set Method can not get the true segmentation when it segments an image with strong noise or week boundary. For it only use edge information to construct the speed function. In this...