JSE_V7_N1_RP1 Kailash Sinha G.R. Sinha Journal on Software Engineering 2230 – 7168 7 1 6 11 Magnetic Resonance Imaging, MRI, Brain Tumor, Segmentation, Clustering, K-Means, Watershed In medical image processing, brain tumor extraction is one of the challenging tasks; since brain image are complicated and tumor can be analyzed only by expert physicians. The location of tumors in the brain is one of the factors that determine how a brain tumor effects an individual’s functioning and what symptoms the tumor causes. We have proposed a methodology in this paper that integrates k-means clustering and watershed algorithm for tumor extraction from 2D MRI (magnetic resonance imaging) images. The use of the conservative watershed algorithm for medical image analysis is pervasive because of its advantages, such as always being able to construct an entire division of the image. On the other hand, its disadvantages include over segmentation and sensitivity to false edges. The k-means clustering algorithm is used to produce a primary segmentation of the image before we apply watershed segmentation algorithm to it; which is an unsupervised learning algorithm, while watershed segmentation algorithm makes use of automated thresholding on the gradient magnitude map. It can be observed that the method can successfully detect the brain tumor size and region. July - September 2012 Copyright © 2012 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=1956