Abstract: In this paper, I present a fast and robust practical tool for segmentation of solid tumors with minimal user interaction to assist clinicians and researchers in radio surgery planning and assessment of the response to the therapy. K Means based seeded tumor segmentation method on contrast enhanced T1 weighted magnetic resonance (MR) images, which standardizes the volume of interest (VOI) and seed selection, is proposed. And the result is compared against Cellular automata based tumor segmentation method. Seed points are selected as the intersection of maximum white points row wise and column wise . First the seed pixels of tumor and background are fed to the algorithm. Using this seeds, the algorithm finds the strength maps for both tumor and background image .This maps are then combined to get the tumor probability map. Comparison studies on both clinical and synthetic brain tumor datasets for both this methods demonstrate 80%–90% overlap performance of the proposed algorithm( K Means)in terms of, its efficiency and accuracy.