Unsupervised abnormalities extraction and brain segmentation

In this paper, we propose a methodology consists of several unsupervised clustering techniques to acquire a satisfactory segmentation of computed tomography (CT) brain images. The ultimate goal of segmentation is to obtain three segmented images, which are the abnormalities, cerebrospinal fluid (CSF) and brain matter respectively. The proposed approach contains of two phase-segmentation methods. In the first phase segmentation, the combination of k-means and fuzzy c-means (FCM) methods is implemented to partition the images into the binary images. From the binary images, a decision tree is then utilized to annotate the connected component into normal and abnormal regions. For the second phase segmentation, the obtained experimental results have shown that modified FCM with population-diameter independent(PDI) segmentation is more feasible and yield satisfactory results.