Analysis and implementation of MRI denoising methods using statistical filtering approach

Magnetic Resonance (MR) images are mostly corrupted with white Gaussian noise called as Rician noise. Due to its dependency on signal this noise is multiplicative in nature. Because of this noise contrast quality of MR images degrades significantly. That leads to lot of difficulties have to analysts in order to extract the useful information from images for proper diagnosis of disease. Various authors have proposed different statistical techniques for MR image denoising. Our main goal is to preserve such useful details like texture information, thin edges, and structural content of useful information when denoising. Methods are applied to the Rician noise corrupted images. In this work, we analyze the various statistical techniques like Average, Median and Gaussian filters. These techniques have ability to preserve the edges of fine structures and also to perform efficient denoising.