Studies On Medical Image Segmentation Based On Deformation Model

Medical-image analysis is the main applied domain in image processing. Deformable model is playing a more and more important role in image segmentation owing to its unique advantages. This article is the work around the deformation model in the medical image segmentation of the initiated. According to the characteristics of medical images, this paper proposed a Mumford-Shah based Approach for image segmentation with multi-index flexible energy in carding on the basis of knowledge.Firstly, This article introduced the parametric active contour models. Currently, the active contour method models have become an important tool of 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.Secondly, Level set methods were discussed in detail, which is the basic of geometric deformable models. 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 superiority 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, to 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.Finally, Level Set methods based on Mumford-Shah model are the excellent and impartant methods based on deformable model. Because of depending on global information of homogeneous regions in the image, they segment the image quickly and precisely. Mumford-Shah model can realize simultaneously segment and restore the image, Where the segmentation is performed on a set smooth images thus simplify the segmentation. But it needs computing all the data of the image constantly during the iterative course, so it is hard to used to real-time application for its low efficiency.The Mumford-Shah functionality model is more and more important for image processing. Chan and Vese proposed a Level Set method based on the simplified Mumford-Shah model for image segmentation. This paper improved C-V's model in two points: First, construct new inner and outer energy with flexibility, and use them instead traditional rigid energy, this step decrease the phenomena of numerical oscillation and deeper segmentation; Second, construct inner and outer energy based on multi image information to improve the segmentation ability and precision of C-V's model. Finally, this paper proposed a Mumford-Shah based Approach for image segmentation with multi-index flexible energy via above two points. New model can deal with the image in high noise polluted and inner gray variety. The experiments on synthesized, MRI(Magnetic Resonance Image) and real world images showed the capability of this method, and it is faster convergence and robust.