Research On Algorithms Based On Fuzzy Theory For Magnetic Resonance Brain Image Segmentation

There are two purposes for the segmentation of MR brain images. The first one is to segment MR brain images into different tissue classes, especially gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF), which is crucial to the image registration, 3D reconstruction and medical image visualization. The second one is to extract the focal region of interesting (ROI) from other tissues in order to assist physicians in making right diagnosis, and working out the therapeutic strategy.The research on MR brain image segmentation has been an important field in medical image processing and analysis. There are a number of factors that cause current segmentation algorithms fail to satisfy the need of clinical practice, including 1) the individual differences in the tissue anatomy; 2) slow calculating speed and inaccuracy; and 3) poor image quality affected by noise, intensive inhomogeneity and partial volume effect (PVE), etc.Medical images behave fuzziness duo to PVE artifacts and the uncertainty in some focal regions. The idea of using membership function associated with fuzzy-set theory to represent partial volume proportions of each "pure" tissue has been a quite popular and widely used model, in which Fuzzy c-means (FCM) clustering algorithm is the well-established approach to the implementation of the image segmentation. However, the conventional FCM fails to incorporate the spatial information of the image leading to aberrant consequences in the case of dealing with low signal-to-noise ratio (SNR) MR images. In the thesis, two improved models of FCM algorithms are proposed. The performance of these algorithms is remarkably superior to the conventional ones in terms of accuracy and robustness.we investigate the segmentation of MS lesions—an inflammatory demyelinating disease that would damage central nervous system. There is a growing attention to this area for the conventional segmentation algorithms are not working well due to the effects of noises, intensive inhomogeneities, the behavior of MS lesions etc. The testing results for T2-weighted MR brain images show the proposed algorithm is robust and accurate enough for clinical use.Chapter 1 provides an overview of image segmentation methods. We describe the wide variety of medical image segmentation methods and applications. The thesis is devoted to general study of medical image segmentation, including the theory, the classification and the method of segmentation.In chapter 2, we present many improved methods of the FCM algorithm in recent years in the lecture. There are generally classed into three kinds: the first one, the constraints on membership function is changed, the second one, the term of spatial information is introduced, the third one, the kernel method is introduced. Finally, the typical ones of these algorithms are analysed and appraised simply.The main emphasis is on chapter 3, we develop a modified FCM clustering for brain MR image segmentation based on multiple objective programming, considering the intensities of ideal MR image which is piecewise constant. The proposed algorithm can reasonably use the spatial of image and improve the accuracy of segmentation. The new mathematical programming formula can thus be solved by the Lagrange multiplier. The results obtained by testing both simulated and clinical data, show that the proposed algorithm is more robust to noise and other artifacts than the conventional fuzzy image segmentation algorithms.Another main emphasis is on chapter 4, when the conventional fuzzy clustering algorithm is used for image segmentation, the algorithm strictly depending on the current pixels, works only on images with less noise. In the paper, we presented a modified fuzzy kernel clustering algorithm for MR images segmentation. The new algorithm incorporates a kernel-induced distance mertric and a penalty term that controls the neighborhood effect to the objective function. Experiment results on both synthetic images and simulation MR images show that the proposed algorithm more robust to noise than the standard fuzzy image segmentation algorithms.A novel approach to the segmentation of multiple sclerosis (MS) lesions in T2-weighted magnetic resonance (MR) images is presented in Chap5. According to the characteristic of MS lesions show the same high brightness with cerebrospinal fluid (CSF) in T2-weighted images, combining the strengths of the kernel fuzzy c-means algorithm and morphology characteristics of MS lesion tissues we present the segmentation of MS lesions based on kernel fuzzy c-means algorithm. The modified kernel fuzzy c-means algorithm is used to basic segmentation. Then the MS lesions are extracted by morphological method. The MS segmentation in simulated T2-weighted MR images show that the proposed algorithm can provide a powerful segmentation.In Chap6, we develop a MRF-based algorithm for DT-MRI image segmentation. As a new technology which can reflect the direction of molecule diffusion, DTI can show the information of the structure of the tissues and the exchanges of water molecule with each tissues in pathology. It has great advantages on showing the distribution of white matter fiber pathway and its three-dimensional structures because of the distinct anisotropy of the diffusion in water molecule of the brain white matter. Without any other methods can measure the character of the live white matter presently, DTI has great significance for the study of the anatomization of the brain and the diagnosis of the diseases of white matter. In this chapter, using the priori knowledge of the spatial correlations of the image and a new tensor distance, applied Gibbs random field and MAP method to the segmentation problem can achieve a novel segmentation of DT-MRI. The results obtained by testing clinical DT-MRI datasets show that MRF can segment them more accurately than FCM.