An improved variational model for denoising magnetic resonance images

This paper presents an improved variational model for denoising MR images degraded by Rician noise. An additional data-fidelity based on image gradient is introduced, which can retain more details and edges. In this model, an automatic estimation of standard deviation of Rician noise is designed to enhance the quality of denoised results. The alternating direction method of multipliers (ADMM) is adopted to implement numerical schedule, and gains the robust solution. Experimental results demonstrate that the proposed method is efficient, and has better denoising capability than the state-of-the-art models. (C) 2018 Elsevier Ltd. All rights reserved.