ENGLISH

Abstract

A tumor is a growth in the abnormal tissue which can be differentiated from the surrounding tissue by its structure.A tumor also may lead to cancer, which is a major leading cause of death and responsible for around 13% of all deaths world-wide. Cancer incidence rate is growing at an alarming rate in the world. Great knowledge and experience on radiology are required for accurate tumor detection in medical imaging. Automation of tumor detection is required because there might be a shortage of skilled radiologists at a time of great need. This paper reviews the processes and techniques used in detecting tumor based on medical imaging results such as mammograms, x-ray computed tomography (x-ray CT) and magnetic resonance imaging (MRI). MRI image which is the Magnetic Resonance Imaging is also could be used for diagnosisand discover which is the type of the human brain that has been tested is normal or abnormal. Moreover, the MRI images give an observation and useful information that will help the doctors and surgeries to avoid some mistakes that will happen during the testing and the diagnosis process. Also, MRI characteristics are used for avoiding human error in manual interpretation of medical content. One of the most popular and useful application that the medical system in need is the MRI brain image classification approach. In this paper, we proposed a new clustering algorithm which relies on the differences between the contrast level of the tumor in the MRI. We depend on new approach for image clustering which is based on the difference between the construct (which is the intensity level) between the tumor region and the whole MRI image. In contrast, other algorithms like k-means, Fuzzy c-means, or probabilistic c-means depend on typical approach which is based on the distance majority between each point (pixel) and its mean. Our work consists some preprocessing steps like smoothed and enhanced the MRI by using enhancement techniques such as Gaussian kernel, median filter, high-pass filter, and Morphological image operation. Mainly, the proposed clustering algorithm in this work uses for segmentation of the image to detect the suspicious region of the tumor in brain MRI image. In this paper feature our results have been compared with the traditional clustering algorithm such as k-means and watershed.