Brain Tumor Segmentation and Detection using Soft Computing Technique

Abstract

Brain tumor is most severe disease; most of populations in world affected due to brain tumor. Now day death rate because brain tumor gradually increases. For that consideration, most prominent method implemented for brain tumor detection and segmentation. When most normal cells grow, old cells die or damaged and new cells take their place. Sometimes this process goes wrong. New cells form when the body does not need them, and old or damaged cell do not die as they should .The buildup of extras cells often forms a mass of tissue called a growth or tumor. Earlier detection, diagnosis and proper treatment of brain tumor are essential to prevent human death. An effective brain tumor detection and segmentation using MR image is an essential task in medical field. A number of research papers related to medical image segmentation methods are studied. Segmentation and detection plays an important role in the processing of medical images. There are various segmentation methods implemented for brain tumor detection. These methods include k-means clustering with watershed segmentation algorithm; optimized k-means clustering with genetic algorithm and optimized c-means clustering with genetic algorithm. Traditional k-means algorithm is sensitive to the initial cluster centers. Genetic c-means and kmeans clustering techniques used to detect tumor in MRI of brain images etc. The proposed work deals with the use of firefly algorithm (FA) for brain tumor detection and segmentation using MRI images. The FA gives more improved parameters like time delay, % of tumor and FPR will be under consideration.