Denoising 3D magnetic resonance images based on weighted tensor nuclear norm minimization using balanced nonlocal patch tensors. (April 2022)

• Record Type: Journal Article
• Authors: He, Jingfei; Gao, Peng; Zheng, Xunan; Zhou, Yatong; He, Hao
• Is Part Of: Biomedical signal processing and control. Volume 74(2022)
• Publication Date: 2022-04
• Subjects: MR image Denoising -- Nonlocal Patch Tensors -- Adaptive Clustering -- Weighted Tensor Nuclear Norm; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.103524
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A new 3D MR image denoising method based on the T -SVD framework using balanced nonlocal patch tensors was proposed. Adaptive clustering was developed to construct nonlocal patch tensors exhibiting low-rank characteristics. The local noise level information of the nonlocal patch tensor was considered when imposing the low rank constraint. Abstract: The denoising of magnetic resonance (MR) images is important to improve the accuracy of organ tissue information recognition in the process of medical diagnosis. This paper proposes a 3D MR image denoising method based on weighted tensor nuclear norm minimization using balanced nonlocal patch tensors. In order to make utilization of the nonlocal self-similarity in high-dimensional images and the correlation among different dimensions, a high-dimensional adaptive clustering technology is developed to construct highly correlated 3D MR image patches into nonlocal patch tensors. Since the generated tensor exhibits low-rank characteristics, a low-rank tensor approximation technique based on the tensor singular value decomposition framework can be used to denoise the MR data. To improve the denoising accuracy, the local noise level information of different nonlocal patch tensors is considered. Besides, a method for constructing more balanced 3D nonlocal patch tensors is proposed to exploit the effectiveness of the tensor singular value decomposition. Experimental results show that the proposed method has a greater improvement over the existing MR image denoising methods in terms of objective measurement and subjective visual quality on simulated and real 3D MR images with different categories and noise levels.