An efficient brain tumor detection by integrating modified texture based region growing and cellular automata edge detection

Brain tumor is one of the most life-threatening diseases and hence its detection should be fast and accurate. This can be achieved by the execution of automated tumor detection techniques on medical images. Many automated techniques which use image segmentation have been proposed. Here we propose an automated and efficient brain tumor detection technique implementing on Magnetic Resonance Imaging (MRI) images, which integrates two image segmentation methods such as modified texture based region growing and cellular automata edge detection. Simulation of the proposed work is done in MATLAB. Even though the modified texture based region growing and cellular automata edge detection are efficient techniques, incorporation of both enhances the efficiency of brain tumor detection. The performance of the proposed technique is analyzed by making different comparisons. Results show that the proposed method is more efficient than modified texture based segmentation and cellular automata edge detection. From the results, it is evident that the detection by the proposed method is closer to that of the manual segmentation when it is taken as the ground truth and more dependable compared to manual segmentation. It is also understood that the modified texture based segmentation integrated with the cellular automata edge detection is better when compared to the one with the incorporation of classical edge detection methods. All these advantages make the proposed method efficient in treatment of brain tumors and also in surgical removal of tumors, if needed.