CLUSTER BASED MEDICAL IMAGE SEGMENTATION

Abstract

Medical image segmentation is a key task in many medical applications. There are lots of methods for automatic and semi automatic image segmentation, though, most of them fail in unknown noise, poor image contrast, and weak boundaries that are usual in medical images. Clustering is a process for classifying objects or patterns in such a way that samples of the same cluster are more similar to one another than samples belonging to different clusters. There are two main clustering strategies: the hard clustering scheme and the fuzzy clustering scheme. K-means is one of the hard clustering methods. Fuzzy .c-means (FCM) algorithm is the most popular method used in image segmentation because it has robust characteristics for ambiguity and can retain much more information than hard segmentation methods. Although the conventional FCM algorithm works well on most noise-free images, it is very sensitive to noise and other imaging artifacts, since it does not consider any information about spatial context. Several spatial corrected methods are proposed in the literature to overcome this disadvantage. Fuzzy c-means (FCM) algorithms with spatial constraints (FCM_S) have been proven effective for image segmentation. However, they still have the following disadvantages: (1) although the introduction of local spatial information to the corresponding objective functions enhances their insensitiveness to noise to some extent, they still lack enough robustness to noise and outliers, especially in absence of prior knowledge of the noise; (2) in their objective functions, there exists a crucial parameter a used to balance between robustness to noise and effectiveness of preserving the details of the image, it is selected generally through experience; and (3) the time of segmenting an image is dependent on the image size, and hence the larger the size of the image, the more the segmentation time. In this thesis, by incorporating local spatial and gray information together, a novel fast and robust FCM framework for image segmentation, i.e., fast generalized fuzzy c-means (FGFCM) clustering algorithms is implemented. FGFCM can mitigate the disadvantages of FCM_S and at the same time enhances the clustering performance. Furthermore we proposed a new FCM algorithm called KFGFCM by modifying the FGFCM algorithm using kernel functions.