Kernel weighted FCM based MR image segmentation for brain tumor detection

Abstract

The paper presents MRI brain diagnosis support system for structure segmentation and its analysis using kernel weighted segmentation. The Proposed method has been used to segment normal tissues and abnormal tissue like tumor part of MR image automatically. MR images are often corrupted by Intensity in homogeneity and artifacts. This may affect the performance of image processing techniques used for brain image analysis. Due to this type of artifacts and noises unknowingly some normal tissue in MRI may be misclassified as other type of normal tissue and it leads to error during diagnosis process. The proposed system remove noise from the given images using a method called spectral subtraction de noising (SSD) and Kernel Weighted Fuzzy C Means (KWFCM) has been used for segmentation. This method incorporates spatial information and the membership weighting of every cluster has been altered after the cluster distribution in the neighborhood is considered. The paper results will be presented as segmented tissues with various parameter evaluations to show algorithm efficiency.