Implementation Of Power Law Transform For Indication Of...

Implementation of Power Law Transform for Indication of Multi-Modal Brain Tumors Giritharan Ravichandran and A G Ramakrishnan Giritharan Ravichandran is with the E.G.S. Pillay Engineering College, Nagapattinam, TN 611001 India (corresponding author to provide phone: +91 9715589763; e-mail: rvenkkatprabu@gmail.com). A G Ramakrishnan is with Indian Institute of Science, Bangalore, KA 560012 India. (e-mail: agrkrish@gmail.com). ABSTRACT In this paper , the problem of identification of masses or tumors in the Magnetic Resonance Image (MRI) of Brain . Here a novel method of Power Law Transformation is introduced on the Brain Image. The gamma value for the Brain Image is fixed as 1.5 and thresholding is done. Thus the resulting binary image clearly separates any kind of tumors or a mass present in the brain images, and makes the identification process easier. By exhaustive experimentations it is found that the proposed algorithm is performs well than the literature. The experimentations is done with the Virtual Skeleton Database (VSD) which is a brain tumor image dataset obtained from Challenge on Multimodal Brain Tumor Segmentation with are the outcomes of BRATS2012 and BRATS2013. It is reported that the tumor in the brain is identified correctly in majority of cases and the efficiency of the proposed algorithm is 90% in case of normal images and 82.51% in case of multimodal images. Keywords: CT Images, Brain Image, Power law transform, Binarization, Tumor,