Denoising of low-dose CT images via low-rank tensor modeling and total variation regularization

• Published in: Artificial intelligence in medicine 2019-03, Vol.94, p.1-17
• Main Authors: Mohd Sagheer, Sameera V., George, Sudhish N.
• Format: Article
• Language: English
• Subjects: Algorithms; Computed tomography image; Denoising; Humans; Signal-To-Noise Ratio; Tensor low rank recovery; Tensor total variation; Tomography, X-Ray Computed - methods
• ISSN: 0933-3657; 1873-2860
• DOI: 10.1016/j.artmed.2018.12.006

•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. Low-dose Computed Tomography (CT) imaging is a most commonly used medical imaging modality. Though the reduction in dosage reduces the risk due to radiation, it leads to an increase in noise level. Hence, it is a mandatory requirement to include a noise reduction technique as a pre- and/or post-processing step for better disease diagnosis. The nuclear norm minimization has attracted a great deal of research interest in contemporary years. This paper proposes a low-rank approximation based approach for denoising of CT images by effectively utilizing the global spatial correlation and local smoothness properties. The tensor nuclear norm is used to describe the global properties and the tensor total variation is used to characterize the local smoothness as well as to improve global smoothness. The resulting optimization problem is solved by the Alternative Direction Method of Multipliers (ADMM) technique. Experimental results on simulated and real CT data prove that the proposed methods outperform the state-of-art works.