Noise Reduction in Medical Images using an Unbiased Non-local Means Method

Abstract: Medical ultrasound also known as diagnostic sonography or ultrasonogrophy is a diagnostic imaging technique based on the application of ultrasound. Since the speckle intensity has a signal dependent nature, filters based on the standard additive Gaussian noise model are inadequate. The main objective of the system is to remove the noise present in the image using UNLM Filter. The proposed unbiased NLM speckle filter based on Gamma statistics has mainly two phases. In the first phase the shape and scale parameters, ? and �, of the Gamma distribution are computed. In the second phase, an Unbiased Non-Local Means Method (UNLM) method was applied. Experiments were carried out on synthetic, B- mode US, CT scan, MRI images to validate the performance of the proposed method. Quantitative analysis based on PSNR with various noise levels shows that the proposed method is more effective in denoising.

Keywords: Denoising, ultrasound, MRI, CT scan images, NLM.