BRAIN TUMOR DETECTION USING FUUZY CO-CLUSTERING FOR IMAGES ALGORITHM

Abstract

ABSTRACT Medical image processing is currently the most emerging and challenging area of research in the field of image processing. Magnetic Resonance Imaging (MRI) is one of the most widely used imaging technique for the diagnosis and planning the treatment of brain tumor patients. The mapping of tumor in MRI images is done manually in the clinical environment by the radiologist depending on their visual interpretation. This mapping is very time consuming and tedious task and error prone due to human dependency. To overcome the shortcomings of mapping the tumor manually, the researchers are keen to develop automatic tumor segmentation system. Automatic tumor segmentation system involves contouring the tumor part in the image and using various measures for its quantification. This study presents a fully automatic technique to detect brain tumor from sample MRI images. The proposed strategy makes use of fuzzy co-clustering for images (FCCI) algorithm for initial segmentation of MRI images. The result of the proposed approach corresponds well to the ground truth in tracking the total area of the tumor. The real time database is taken from Rajiv Gandhi Cancer Institute & Research Centre, Delhi, India (RGCI&RC) and results are validated by the radiologist.