A Review on Automatic Brain Tumor Detection

Abstract

Detection and segmentation of brain tumor is very important because it provides anatomical information of normal and abnormal tissues which helps in treatment planning and patient follow up. Medical image segmentation is a method of extracting the desired parts and features from the input medical image data. Image segmentation locates objects and boundaries within images and the segmentation process is stopped when region of interest is separated from the input image. There are number of techniques for image segmentation. This paper emphasis on a comparison between two segmentation algorithms for segmenting brain tumors from MRI images. The tumor area is identified by using K-Means and Fuzzy C- Means algorithms and a comparative study of these methods is done using execution time and PSNR. Tumor classification is done using Feed Forward Neural Network. A GUI is developed to make the system more users interactive.