A NOVEL APPROACH FOR FINDING BRAIN ABNORMALITIES USING FCM

Abstract

MRI brain image processing is a vast area of research, several methods and approaches have been used to segment these images (thresholding, region, contour, clustering). In the proposed methodology, we propose a novel segmentation approach, which is based on fuzzy c-means clustering and morphological operation. Clustering approach is widely used in biomedical applications particularly for brain tumour detection in abnormal magnetic resonance (MRI) images. Fuzzy clustering using fuzzy C-means (FCM) algorithm proved to be superior over the other clustering approaches in terms of segmentation efficiency. Also the enhancement methods proposed here improved the contrast of the input images drastically and also midrange stretch enhancement improves the image quality for segmentation. To validate the proposed methodology, it is tested successfully on several datasets of approximately 400 MRI images.