Tumor and Its Stages Detection in Brain MRI Using Template Based K-means and Fuzzy C-means Clustering Algorithm

Abstract

Segmentation is obligatory process in medical application for MRI image to detect brain tumour. This research work represents a robust segmentation method which is the integration of Template based K-means and modified Fuzzy C-means (TKFCM) clustering computed algorithm that, reduces the lack of operator performance, and error in equipment. In this method, the template is selected based on convolution between grey level intensity in small portion of brain image, and brain tumour image. K-means algorithm is to emphasized initial segmentation through the proper selection of template. Updated membership of FCM is obtained through distances from cluster centroid to cluster data points, until it reaches to its best. This Euclidian distance depends upon the different features i.e. intensity, entropy, contrast, dissimilarity and homogeneity of coarse image, which was depended only on similarity in conventional FCM. Then, on the basis of updated membership and automatic cluster selection, a sharp segmented image is obtained with red marked tumour from modified FCM technique. The small deviation of grey level intensity of normal and abnormal tissue is detected through TKFCM. For the tumor and its stages classification the linearization and region properties algorithm is needed to apply on detected tumor obtained from TKFCM, which provides the characteristics parameters like area, eccentricity, bounding box, perimeters and orientation. By these parameters the classified tumor and its stages are extracted. Besides the performances of TKFCM method is analyzed through neural network not only mathematically but also graphically. The resultant values give a better regression and least error compare to the other existing methods. This method will also help in detecting tumor in multiple intensity based brain MRI image.