Cargando…
Low-dose CT reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares
BACKGROUND: In order to reduce the radiation dose of CT (computed tomography), compressed sensing theory has been a hot topic since it provides the possibility of a high quality recovery from the sparse sampling data. Recently, the algorithm based on DL (dictionary learning) was developed to deal wi...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
BioMed Central
2016
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4912768/ https://www.ncbi.nlm.nih.gov/pubmed/27316680 http://dx.doi.org/10.1186/s12938-016-0193-y |
_version_ | 1782438322085298176 |
---|---|
author | Zhang, Cheng Zhang, Tao Li, Ming Peng, Chengtao Liu, Zhaobang Zheng, Jian |
author_facet | Zhang, Cheng Zhang, Tao Li, Ming Peng, Chengtao Liu, Zhaobang Zheng, Jian |
author_sort | Zhang, Cheng |
collection | PubMed |
description | BACKGROUND: In order to reduce the radiation dose of CT (computed tomography), compressed sensing theory has been a hot topic since it provides the possibility of a high quality recovery from the sparse sampling data. Recently, the algorithm based on DL (dictionary learning) was developed to deal with the sparse CT reconstruction problem. However, the existing DL algorithm focuses on the minimization problem with the L(2)-norm regularization term, which leads to reconstruction quality deteriorating while the sampling rate declines further. Therefore, it is essential to improve the DL method to meet the demand of more dose reduction. METHODS: In this paper, we replaced the L(2)-norm regularization term with the L(1)-norm one. It is expected that the proposed L(1)-DL method could alleviate the over-smoothing effect of the L(2)-minimization and reserve more image details. The proposed algorithm solves the L(1)-minimization problem by a weighting strategy, solving the new weighted L(2)-minimization problem based on IRLS (iteratively reweighted least squares). RESULTS: Through the numerical simulation, the proposed algorithm is compared with the existing DL method (adaptive dictionary based statistical iterative reconstruction, ADSIR) and other two typical compressed sensing algorithms. It is revealed that the proposed algorithm is more accurate than the other algorithms especially when further reducing the sampling rate or increasing the noise. CONCLUSION: The proposed L(1)-DL algorithm can utilize more prior information of image sparsity than ADSIR. By transforming the L(2)-norm regularization term of ADSIR with the L(1)-norm one and solving the L(1)-minimization problem by IRLS strategy, L(1)-DL could reconstruct the image more exactly. |
format | Online Article Text |
id | pubmed-4912768 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2016 |
publisher | BioMed Central |
record_format | MEDLINE/PubMed |
spelling | pubmed-49127682016-06-19 Low-dose CT reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares Zhang, Cheng Zhang, Tao Li, Ming Peng, Chengtao Liu, Zhaobang Zheng, Jian Biomed Eng Online Research BACKGROUND: In order to reduce the radiation dose of CT (computed tomography), compressed sensing theory has been a hot topic since it provides the possibility of a high quality recovery from the sparse sampling data. Recently, the algorithm based on DL (dictionary learning) was developed to deal with the sparse CT reconstruction problem. However, the existing DL algorithm focuses on the minimization problem with the L(2)-norm regularization term, which leads to reconstruction quality deteriorating while the sampling rate declines further. Therefore, it is essential to improve the DL method to meet the demand of more dose reduction. METHODS: In this paper, we replaced the L(2)-norm regularization term with the L(1)-norm one. It is expected that the proposed L(1)-DL method could alleviate the over-smoothing effect of the L(2)-minimization and reserve more image details. The proposed algorithm solves the L(1)-minimization problem by a weighting strategy, solving the new weighted L(2)-minimization problem based on IRLS (iteratively reweighted least squares). RESULTS: Through the numerical simulation, the proposed algorithm is compared with the existing DL method (adaptive dictionary based statistical iterative reconstruction, ADSIR) and other two typical compressed sensing algorithms. It is revealed that the proposed algorithm is more accurate than the other algorithms especially when further reducing the sampling rate or increasing the noise. CONCLUSION: The proposed L(1)-DL algorithm can utilize more prior information of image sparsity than ADSIR. By transforming the L(2)-norm regularization term of ADSIR with the L(1)-norm one and solving the L(1)-minimization problem by IRLS strategy, L(1)-DL could reconstruct the image more exactly. BioMed Central 2016-06-18 /pmc/articles/PMC4912768/ /pubmed/27316680 http://dx.doi.org/10.1186/s12938-016-0193-y Text en © The Author(s) 2016 Open AccessThis article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated. |
spellingShingle | Research Zhang, Cheng Zhang, Tao Li, Ming Peng, Chengtao Liu, Zhaobang Zheng, Jian Low-dose CT reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares |
title | Low-dose CT reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares |
title_full | Low-dose CT reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares |
title_fullStr | Low-dose CT reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares |
title_full_unstemmed | Low-dose CT reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares |
title_short | Low-dose CT reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares |
title_sort | low-dose ct reconstruction via l1 dictionary learning regularization using iteratively reweighted least-squares |
topic | Research |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4912768/ https://www.ncbi.nlm.nih.gov/pubmed/27316680 http://dx.doi.org/10.1186/s12938-016-0193-y |
work_keys_str_mv | AT zhangcheng lowdosectreconstructionvial1dictionarylearningregularizationusingiterativelyreweightedleastsquares AT zhangtao lowdosectreconstructionvial1dictionarylearningregularizationusingiterativelyreweightedleastsquares AT liming lowdosectreconstructionvial1dictionarylearningregularizationusingiterativelyreweightedleastsquares AT pengchengtao lowdosectreconstructionvial1dictionarylearningregularizationusingiterativelyreweightedleastsquares AT liuzhaobang lowdosectreconstructionvial1dictionarylearningregularizationusingiterativelyreweightedleastsquares AT zhengjian lowdosectreconstructionvial1dictionarylearningregularizationusingiterativelyreweightedleastsquares |