PREDICTION OF GLIOMA USING GENETIC OPTIMIZED NEURAL NETWORK

Abstract

Neural networks are a computational paradigm model of the human brain that has become popular in recent years. We have tried to address the problem of Glioma by creating a more accurate classifier which can act as an expert assistant to medical practitioners. Brain stem gliomas are now recognized as a heterogenous group of tumors. In this study proposed a prediction of Glioma in MR images using weight optimized neural network. Magnetic Resonance (MR) images are affected by rician noise which limits the accuracy of any quantitative measurements from the data. A recently proposed filter for rician noise removal is analyzed and adapted to reduce this noise in MR images. This parametric filter, named Non-Local Means (NLM), is highly dependent on setting its parameters. Experimental results reveal the efficacy of the adduced methodology as compared to the related work.