A magnetic resonance imaging denoising technique using non-local means and unsupervised learning

Abstract

We propose a new non-local mean (NLM) algorithm using unsupervised learning and k-means clustering for denoising magnetic resonance (MR) images. Our technique improves image processing speeds with enhanced denoising performance on multiple types of images. The calculation of similarity weights at the cluster level improves computational efficiency. We conducted experiments with brain MR images of various sizes, including three T1- and T2-weighted images. Three quality metrics show that our algorithm achieves moderate improvements in denoising accuracy with significant reductions in execution time. The proposed method processed the sample data in one-fifth of the time of the original NLM method. Compared to several state-of-the-art methods, our method offers improved peak signal-to-noise ratios (PSNRs) for samples with large amounts of noise.