Abstract: Tumour is a mass of tissue that grows out of control of the normal forces that regulates growth. Brain tumour is abnormal and uncontrolled proliferations of cells. Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) are the two most common tests undertake to confirm the presence of brain tumour and to identify its location for selected specialist treatment options. Brain tumour in MRI has been recent area of research in the field of automated medical diagnosis as the death rate is higher among humans due to brain tumour. In automated medical diagnostic systems magnetic resonance images (MRI) gives better results than computed tomography (CT) as magnetic resonance imaging provides greater contrast between different soft tissues in our human body. Therefore MRI is much efficient in brain and cancer imaging. There is number of methods already presented for brain tumour segmentation. But these methods have so many disadvantages on the SNR ratio and efficiency. The method of brain tumour segmentation is nothing but the differentiation of different tumour area from Magnetic Resonance (MR) images. There are number of methods already presented for segmentation of brain tumour efficiently. However it’s still critical to identify the brain tumour from MR images. The algorithm proposed here for segmentation is focuses to segment the image depth wise usually colour segmentation. The density can be calculated by considering the area of the tumour.

Keywords: depth estimation; markovian segmentation; k means clustering; density estimation.