Font Size: a A A

Active Contour Model Applied Research In Nuclear Magnetic Resonance Image Processing

Posted on:2006-07-26Degree:MasterType:Thesis
Country:ChinaCandidate:Y J ChenFull Text:PDF
GTID:2208360152483200Subject:Applied Mathematics
Abstract/Summary:PDF Full Text Request
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 deformable 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 a new image force. With this force the Snake modal can do well in segmenting the noising image, and give an image segmentation method of Sanke model based on the Gas (genetic algorithms) to prevent the model falling into local minima, 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 virtues 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 affected 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.After compared the virtues of Snake model and Level set model, this paper presents a new active contour model-S-L model, which combines the virtues of Snake model and Level Set model. The new model use the energy equation of Snake model to evolve the curve and use a symbol table, which is based on the soul of level set model , to change the topology of the curve. To reduce the effect of the noise, the new model constructs a new outer force, which based on the region information. With the new outer force, the initial curve can be made in a large space. For using the region information, the new model can find the edges powerfully, even if it has complex topology, avoid local minima from Snake model. The experiments to segment cardiac magnetic resonance images show that the new model can get the similarresults with level-set in an efficient way.Munford-Shah(M-S) model is a coupled variational model that can simultaneously segment and restore the image, where the segmentation is performed on 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. Aiming at this disability, by using the characteristic of the MRI, a fast method of solving the M-S model is improved based on the histogram method. This method first construct a signed table, which can be used to distinguish the area inside or outside of the edges, and use the histogram method to get the rough results, then use t...
Keywords/Search Tags:Image segmentation, Variational method, Parametric active contour model, Geometric active contour model, Coupled segmentation and enhancement
PDF Full Text Request
Related items