Artificial intelligence (AI) approach to the analysis of computed tomography (CT) images of human brain with abnormalities is proposed in this thesis. Segmenting of CT image is achieved by a system composed of three sequential stages and as follows: First stage includes implementation of unsupervised fuzzy clustering algorithm in order to outlines the regions in the input CT brain image. Extracted regions are spatially localized and have uniform brightness. The second stage involves separation of different tissues of the human brain; it consists of three steps and based on threshold technique. In the third stage, the different tissues of the human brain are assigned into one of the following regions: Brain region, calcification regions, background region, skull region, and intercerebral brain hemorrhages (ICH) regions. Third stage includes implementation of several images processing technique such as image enhancement, edge detection, and hole filling operations that are based on morphology process. This stage consists of sequential steps and each step depends on previous step. As a result of this stage, the images that contain abnormality calcification, ICH) have been obtained. These images may be of benefit for a doctor since the other tissues (normal) have been separated from calcification and ICH, so this lead to be more diagnosis of the abnormalities to study it and more analysis of the normal tissues. The system has been applied to a number of real CT brain images and shown satisfactory results.