©2009 The Visualization Society of Japan Journal of Visualization, Vol. 12, No. 2 (2009) 131-138 Segmentation of CT Brain Images Using Unsupervised Clusterings Tong Hau Lee *1 , Mohammad Faizal Ahmad Fauzi *2 and Ryoichi Komiya *1 *1 Faculty of Information Technology, Multimedia University, Jalan Multimedia, 63100 Cyberjaya, Selangor, Malaysia. E-mail: hltong@mmu.edu.my *2 Faculty of Engineering, Multimedia University, Jalan Multimedia, 63100 Cyberjaya, Selangor, Malaysia. Received 23 May 2008 Revised 3 November 2008 Abstract: In this paper, we present non-identical unsupervised clustering techniques for the segmentation of CT brain images. Prior to segmentation, we enhance the visualization of the original image. Generally, for the presence of abnormal regions in the brain images, we partition them into 3 segments, which are the abnormal regions itself, the cerebrospinal fluid (CSF) and the brain matter. However, for the absence of abnormal regions in the brain images, the final segmented regions will consist of CSF and brain matter only. Therefore, our system is divided into two stages of clustering. The initial clustering technique is for the detection of the abnormal regions. The later clustering technique is for the segmentation of the CSF and brain matter. The system has been tested with a number of real CT head images and has achieved satisfactory results. Keywords: Medical images, Visualization enhancement, Image segmentation, Computed tomography, Unsupervised clustering. 1. Introduction Computed tomography (CT) images can be distinguished for different tissues according to their different gray levels. The images, if processed appropriately can offer a wealth of information which is significant to assist doctors in medical diagnosis. Image segmentation is the process of partitioning a digital image into sets of pixels. Accurate, fast and reproducible image segmentation technique is required in various applications. The results of the segmentation are significant for classification and analysis purposes. CT scans of internal organs, bone and soft tissue furnish greater clearness than conventional x-ray. On the other hand, Magnetic Resonance Imaging (MRI) scan produces clearer images and a greater resolution compared with CT scan with lower resolution which may cause some small lesions go undetected. The limitations for CT scanning of head images are due to partial volume effects which affect the edges, produce low brain tissue contrast and yield different objects within the same range of intensity. All these limitations have made the segmentation more difficult. Therefore, the challenges for automatic segmentation of the CT head images have raised many different approaches. The segmentation techniques developed so far include statistical pattern recognition techniques (e.g., Nathalie et al, 2007; Y. Zhang et al, 2001), morphological processing with thresholding (e.g., K. H. Hohne et al, 1992; Lemieux et al, 1999), clustering algorithm (e.g., Qingmao et al, 2005; N. A. Mohamed et al, 1999) and active contour (e.g., Albert et al, 2006; Ruzica et al, 2000). Wei et al, 2007 introduced the effective particle swarm optimization(PSO) algorithm to segment the brain images into CSF and suspicious abnormal regions but without the annotation of the abnormal regions. Regular Paper