Study Of Image Segmentation In Brain Magnetic Resonance Images

Medical image segmentation is an important application in the field of image segmentation. Medical image segmentation is a hard-tough problem in medical image processing and analysis. Among it, brain medical image segmentation is the research focus for its important values. Medical image segmentation plays an important role in biomedical research and clinical application such as study of anatomical structure, diagnosis, As a result, accurate segmentation method is crucial to the follow-up analysis.Medical image segmentation aims at partition the original image into several meaningful regions or isolating the region of interesting, The paper does the summary to the purpose and meaning that the medical image segmentation on the foundation of the existing research result; the classification and comparison to the existing medical image segmentation methods. The research work and innovation of this paper include:The thesis first makes a review of the related key techniques, including the basic concepts and principles of image segmentation and MRI. This thesis also summarizes the research statuses of Medical image segmentation. Moreover, some of the typical algorithms are detailedly introduced and deeply analyzed in this thesis.Then, Image segmentation based on Modified Fuzzy C-Means(FCM) clustering in brain MR images has been appeared, The classical FCM clustering algorithm is one of well-known Fuzzy clustering techniques. However, FCM clustering algorithm usually leads to local minimum results, and the FCM algorithm is noise sensitive because of not taking into account the spatial information. The paper proposes a new modified FCM algorithm. We propose a new algorithm to initialize the cluster. Then spatial information is present and the prior spatial constraint is incorporated based on Gibbs random field. The new fuzzy membership of the pixel is recounted with the obtained probability and adjust the distance matrix. The experimental results show that the proposed method can segment the image effectively and properly and has good performance of resisting noise.Image segmentation based on Gaussian Mixture Models brain MR images has been appeared, The finite mixture Gaussian model has been widely used in image segmentation of brain images. A brain image could be considered as the result from Gaussian mixer model. To the noise image of brain, the paper filter the brain image by a modified way of filter at first. Then, by its feature of global optimization, the particle swarm optimization algorithm is employed, and avoid to leads to local minimum results to calculate more accurate parameters of Gaussian mixture model, and segment the image effectively.