A New Meta Heuristic Based Segmentation for MRI Image
An automated brain tumor segmentation and detection have huge importance in the diagnostics of medical field as it renders information about functional structures in addition to the probable abnormal tissue required for surgical planning. However, it is still a problem due to low contrast and poorly-specified boundaries and accuracy issue. Hence, Refined Migrating Birds Optimization (RMBO) algorithm is introduced for automatic tumor segmentation that gets over the disadvantage of classical metaheuristic segmentation techniques. The RMBO helps in improving both migration and position update steps which includes three phases. First phase starts from Preprocessing, film artifacts and unnecessary areas (skull) of MRI images are eliminated with the help of enhanced tracking algorithm. Next and second phase being the procedure of eliminating the noises employing Anisotropic Filtering and contrast enhancement is carried out with the help of histogram equalization. Finally segmentation is performed employing RMBO. The novel algorithm operates on the image pixels information along with regions/neighborhood map to generate a contextual area where the merging is possible. With the RMBO algorithm, MRI of brain images are segmented and the results are analyzed through the comparison of the existing techniques viz., Particle Swarm Optimization (PSO), Genetic algorithms.