Novel Algorithms Of Brain Magnetic Resonance Image Segmentation Based On Fuzzy C-Means

The main purpose of the medical image segmentation is to distinguish between different objects in a given and to label each pixel with its underlying class. Image segmentation is very important to image preprocessing and patter recognition, such as feature quantification, image registration 3D reconstruction and etc. In this thesis, the brain magnetic resonance (MR) image segmentation is researched. There are three purposes for the segmentation of brain MR images: the first one is to extract brain tissue from brain MR images. The second one is to segment brain MR images into different tissue classes, namely, gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF). The third one is to extract the focal region of interesting (ROI) from other tissues. The research on the paper focuses on the problem of classing the normal brain tissues.In general an ideal MR image is assumed to be piecewise constant, unfortunately, the property is destroyed by electron and structured noises, intensive inhomogeneity and partial volume effect (PVE), etc. Because of the individual differences in the tissue anatomy and the slow calculating speed and inaccuracy, the current segmentation algorithms fail to satisfy the need of clinical practice. Fuzzy C-means (FCM) algorithm has been widely used in brain MR image segmentation. However, the conventional FCM algorithm is used for image segmentation, no spatial information is taken into account, leading to the FCM algorithm get the unexpected results of segmentation when dealing with the images corrupted by noises. 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.Chapter 2 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 3, 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 4, 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 5, we present a modified kernel-based FCM clustering algorithm for image segmentation. The algorithm by using kernel method the original Euclidean distance in the FCM is replaced by a kernel-induced distance. Then, a spatial penalty term is added to the objective function to compensate the influence of the neighboring pixels on the center pixel. The new algorithm which is applied to both synthetic images and simulation MR images is shown to be more accurate in comparison with others. Especially, it is more robust to 'salt & pepper' noise than other FCM-based methods.