PERFORMANCE ANALYSIS OF IMAGE SEGMENTATION TECHNIQUES IN MEDICAL IMAGES

Abstract

ABSTRACT Medical imaging is a technique that is extensively used to create images of human body for medical and research purposes. In recent years, Magnetic Resonance Imaging (MRI) is the most widely used imaging technology, because of widespread availability and ability to produce high resolution images. MR imaging is a powerful visualization tool that permits to acquire images of internal anatomy of human body to be acquired in a secure and non-invasive manner. MRI of brain has become one of the major areas of medical research in order to segment brain tumor. Early detection and accurate treatment based on truthful diagnosis are the major concern to cure brain tumor. The important task in the diagnosis of brain tumor is to determine the exact location, orientation and area of the abnormal tissues. Detection of anatomical brain structure plays a major role in the planning of treatment. This study involves comparative analysis of three image segmentation techniques for detection of brain tumor from sample MRI images of brain. The image segmentation techniques involve namely, K-Means Clustering, Fuzzy C-Means Clustering and Region Growing. A comparative analysis of the above mentioned image segmentation techniques, is done on the images taken from Rajiv Gandhi Cancer Institute & Research Centre, Delhi, India (RGCI&RC).