Denoising of low-dose CT images via low-rank tensor modeling and total variation regularization
作者：
Highlights：
• A new denoising method for Computed tomography (CT) images based on low-rank approximation by modeling the global spatial correlation and local smoothness properties is proposed.
• The tensor nuclear norm is used to describe the global properties and the tensor total variation is used to characterize the local smoothness.
• An efficient algorithm for solving the resulting optimization problem based on the Alternative Direction Method of Multipliers (ADMM) is also developed.
• The experiments explain the applicability of proposed method for real medical CT images.
• The proposed algorithm is shown to have superior performance compared to the state-of-art works existing in the literature.
摘要
•A new denoising method for Computed tomography (CT) images based on low-rank approximation by modeling the global spatial correlation and local smoothness properties is proposed.•The tensor nuclear norm is used to describe the global properties and the tensor total variation is used to characterize the local smoothness.•An efficient algorithm for solving the resulting optimization problem based on the Alternative Direction Method of Multipliers (ADMM) is also developed.•The experiments explain the applicability of proposed method for real medical CT images.•The proposed algorithm is shown to have superior performance compared to the state-of-art works existing in the literature.
论文关键词：Computed tomography image,Denoising,Tensor low rank recovery,Tensor total variation
论文评审过程：Received 23 November 2017, Revised 24 December 2018, Accepted 27 December 2018, Available online 31 December 2018, Version of Record 20 February 2019.
论文官网地址：https://doi.org/10.1016/j.artmed.2018.12.006
