Analytical Aspects of MRI Denoising using Gaussian Blurred Intensity Averaging Method Disturbed by Random Noise

Feature extraction and object recognition are two important parameters for analyzing any MRI (magnetic resonance imaging), taken by various imaging modalities. These MRI always contain random noise so Feature extraction and object recognition becomes difficult. This noise affects randomly on pixels of MRI and will change the both amplitude and phase of pixels of MRI. This causes imperfect diagnostics of dieses and due to that we cannot start a correct treatment for a body. so MRI denoising is important exercise for making correct diagnostic. There are different approaches for noise reduction, each of which has its own advantages and limitation. MRI denoising is a difficult task as fine details in medical image should not be removed during denoising process because it contains diagnostic information. Here we are suggesting, an algorithm for MRI denoising. We are doing intensity averaging of pixels which provides kind of smoothing to the image. Intensity averaging is performed by iterations and Gaussian blurring. This will reconstruct noisy MR image. Performance matrices used to measure the quality of denoised MRI are PSNR(Peak signal to noise ration), MSE(Mean square error) and RMSE(Root mean square error) .The final result shows that this method is effectively removing the noise while preserving the edge and fine information in the images.