Extended Pillars K-Means Clustering for Automatic Brain Tumor Technique

Conference: Third International Conference on Recent Trends in Power, Control and Instrumentation Engineering
Author(s): K. Sudharani, T.C. Sarma, K. Satya Prasad Year: 2015
Grenze ID: 02.PCIE.2015.3.505 Page: 9-15

Abstract

Tumor is an uncontrolled growth of tissue in any part of the body. This paper is to implement of simple Algorithm for detection of range and shape of tumor in brain MR Images. Performance of K-means algorithm which depends highly on initial starting points can be trapped in local minima and led to incorrect clustering results. The lack of K-means algorithm that generates the initial centroids randomly does not consider the placement of them spreading in the feature space. In this paper a new approach to optimize K-means with morphological segmentation techniques is presented. Statistical parameters like sensitivity, specificity, similarity index, accuracy of the proposed algorithm is presented along with the area calculations of the defective part of the brain. Comparative study is made between k-means and proposed k-means methodologies.

<< BACK

PCIE - 2015