5 March 2018 A denoising algorithm for CT image using low-rank sparse coding
Author Affiliations +
We propose a denoising method of CT image based on low-rank sparse coding. The proposed method constructs an adaptive dictionary of image patches and estimates the sparse coding regularization parameters using the Bayesian interpretation. A low-rank approximation approach is used to simultaneously construct the dictionary and achieve sparse representation through clustering similar image patches. A variable-splitting scheme and a quadratic optimization are used to reconstruct CT image based on achieved sparse coefficients. We tested this denoising technology using phantom, brain and abdominal CT images. The experimental results showed that the proposed method delivers state-of-art denoising performance, both in terms of objective criteria and visual quality.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yang Lei, Yang Lei, Dong Xu, Dong Xu, Zhengyang Zhou, Zhengyang Zhou, Tonghe Wang, Tonghe Wang, Xue Dong, Xue Dong, Tian Liu, Tian Liu, Anees Dhabaan, Anees Dhabaan, Walter J. Curran, Walter J. Curran, Xiaofeng Yang, Xiaofeng Yang, } "A denoising algorithm for CT image using low-rank sparse coding", Proc. SPIE 10574, Medical Imaging 2018: Image Processing, 105741P (5 March 2018); doi: 10.1117/12.2292890; https://doi.org/10.1117/12.2292890


SAR Image despeckling via sparse representation
Proceedings of SPIE (November 19 2014)
Image denoising by principal basis analysis
Proceedings of SPIE (December 17 2015)
Automatic thoracic body region localization
Proceedings of SPIE (March 03 2017)
CT slice localization via instance-based regression
Proceedings of SPIE (March 12 2010)

Back to Top