08-06-2013, 02:23 PM
EFFECTIVE FUZZY CLUSTERING ALGORITHM FOR ABNORMAL MR BRAIN IMAGE SEGMENTATION
EFFECTIVE FUZZY CLUSTERING.docx (Size: 46.47 KB / Downloads: 22)
ABSTRACT
Image segmentation plays a major role in the field of biomedical applications. The segmentation technique is widely used by the radiologists to segment the input medical image into meaningful regions. The specific application of this technique is to detect the tumor region by segmenting the abnormal MR input image. The size of the tumor region can be tracked using these techniques which aid the radiologists in treatment planning the primitive techniques are based on manual segmentation which is a time consuming process besides being susceptible to human errors. Several automated techniques have been developed which removes the drawbacks of manual segmentation.
BACK GROUND
Clustering is one of the widely used image segmentation techniques which classify patterns in such a way that samples of the same group are more similar to one another than samples belonging to different groups. There has been considerable interest recently in the use of fuzzy clustering methods, which retain more information from the original image than hard clustering methods. Fuzzy C-means algorithm is widely preferred because of its additional flexibility which allows pixels to belong to multiple classes with varying degrees of membership. But the major operational complaint is that the FCM technique is time consuming. Several modifications have been done on the existing network to improve the performance
METHODOLOGY
Clustering approach is widely used in biomedical applications particularly for brain tumor detection in abnormal magnetic resonance (MR) images. Fuzzy clustering using fuzzy C-means algorithm proved to be superior over the other clustering approaches in terms of segmentation efficiency. But the major drawback of the FCM algorithm is the huge computational time required for convergence.
The effectiveness of the FCM algorithm in terms of computational rate is improved by modifying the cluster center and membership value updation criterion. In this project, the application of modified FCM algorithm for MR brain tumor detection is explored. Abnormal brain images from four tumor classes namely metastase, meningioma, glioma and Astrocytomas are used in this work. A comprehensive feature vector space is used for segmentation technique. Comparative analysis in segmentation efficiency and convergence rate is performed between the conventional FCM and the modified FCM. Experimental results show superior results for the modified FCM algorithm in terms of the performance measures.