DECT-MULTRA: Dual-Energy CT Image Decomposition With Learned Mixed Material Models and Efficient Clustering
Abstract
Dual-energy computed tomography (DECT) imaging plays an important role in advanced imaging applications due to its material decomposition capability. Image-domain decomposition operates directly on CT images using linear matrix inversion, but the decomposed material images can be severely degraded by noise and artifacts. This paper proposes a new method dubbed DECT-MULTRA for image-domain DECT material decomposition that combines conventional penalized weighted-least squares (PWLS) estimation with regularization based on a mixed union of learned transforms (MULTRA) model. Our proposed approach pre-learns a union of common-material sparsifying transforms from patches extracted from all the basis materials, and a union of cross-material sparsifying transforms from multi-material patches. The common-material transforms capture the common properties among different material images, while the cross-material transforms capture the cross-dependencies. The proposed PWLS formulation is optimized efficiently by alternating between an image update step and a sparse coding and clustering step, with both of these steps having closed-form solutions. The effectiveness of our method is validated with both XCAT phantom and clinical head data. The results demonstrate that our proposed method provides superior material image quality and decomposition accuracy compared to other competing methods.
- Authors:
-
- Univ. of Michigan, Ann Arbor, MI (United States); Shanghai Jiao Tong Univ. (China)
- Michigan State Univ., East Lansing, MI (United States)
- Univ. of Michigan, Ann Arbor, MI (United States)
- Publication Date:
- Research Org.:
- Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1768537
- Report Number(s):
- LA-UR-18-31890
Journal ID: ISSN 0278-0062
- Grant/Contract Number:
- 89233218CNA000001
- Resource Type:
- Accepted Manuscript
- Journal Name:
- IEEE Transactions on Medical Imaging
- Additional Journal Information:
- Journal Volume: 39; Journal Issue: 4; Journal ID: ISSN 0278-0062
- Publisher:
- IEEE
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 47 OTHER INSTRUMENTATION; Computer Science; Mathematics
Citation Formats
Li, Zhipeng, Ravishankar, Saiprasad, Long, Yong, and Fessler, Jeffrey A. DECT-MULTRA: Dual-Energy CT Image Decomposition With Learned Mixed Material Models and Efficient Clustering. United States: N. p., 2020.
Web. doi:10.1109/tmi.2019.2946177.
Li, Zhipeng, Ravishankar, Saiprasad, Long, Yong, & Fessler, Jeffrey A. DECT-MULTRA: Dual-Energy CT Image Decomposition With Learned Mixed Material Models and Efficient Clustering. United States. https://doi.org/10.1109/tmi.2019.2946177
Li, Zhipeng, Ravishankar, Saiprasad, Long, Yong, and Fessler, Jeffrey A. Wed .
"DECT-MULTRA: Dual-Energy CT Image Decomposition With Learned Mixed Material Models and Efficient Clustering". United States. https://doi.org/10.1109/tmi.2019.2946177. https://www.osti.gov/servlets/purl/1768537.
@article{osti_1768537,
title = {DECT-MULTRA: Dual-Energy CT Image Decomposition With Learned Mixed Material Models and Efficient Clustering},
author = {Li, Zhipeng and Ravishankar, Saiprasad and Long, Yong and Fessler, Jeffrey A.},
abstractNote = {Dual-energy computed tomography (DECT) imaging plays an important role in advanced imaging applications due to its material decomposition capability. Image-domain decomposition operates directly on CT images using linear matrix inversion, but the decomposed material images can be severely degraded by noise and artifacts. This paper proposes a new method dubbed DECT-MULTRA for image-domain DECT material decomposition that combines conventional penalized weighted-least squares (PWLS) estimation with regularization based on a mixed union of learned transforms (MULTRA) model. Our proposed approach pre-learns a union of common-material sparsifying transforms from patches extracted from all the basis materials, and a union of cross-material sparsifying transforms from multi-material patches. The common-material transforms capture the common properties among different material images, while the cross-material transforms capture the cross-dependencies. The proposed PWLS formulation is optimized efficiently by alternating between an image update step and a sparse coding and clustering step, with both of these steps having closed-form solutions. The effectiveness of our method is validated with both XCAT phantom and clinical head data. The results demonstrate that our proposed method provides superior material image quality and decomposition accuracy compared to other competing methods.},
doi = {10.1109/tmi.2019.2946177},
journal = {IEEE Transactions on Medical Imaging},
number = 4,
volume = 39,
place = {United States},
year = {Wed Apr 01 00:00:00 EDT 2020},
month = {Wed Apr 01 00:00:00 EDT 2020}
}
Works referenced in this record:
Nonlocal low-rank and sparse matrix decomposition for spectral CT reconstruction
journal, January 2018
- Niu, Shanzhou; Yu, Gaohang; Ma, Jianhua
- Inverse Problems, Vol. 34, Issue 2
Realistic CT simulation using the 4D XCAT phantom
journal, July 2008
- Segars, W. P.; Mahesh, M.; Beck, T. J.
- Medical Physics, Vol. 35, Issue 8
Model-Based Iterative Reconstruction for Dual-Energy X-Ray CT Using a Joint Quadratic Likelihood Model
journal, January 2014
- Zhang, Ruoqiao; Thibault, Jean-Baptiste; Bouman, Charles A.
- IEEE Transactions on Medical Imaging, Vol. 33, Issue 1, p. 117-134
Structured Overcomplete Sparsifying Transform Learning with Convergence Guarantees and Applications
journal, October 2014
- Wen, Bihan; Ravishankar, Saiprasad; Bresler, Yoram
- International Journal of Computer Vision, Vol. 114, Issue 2-3
Iterative image-domain decomposition for dual-energy CT
journal, March 2014
- Niu, Tianye; Dong, Xue; Petrongolo, Michael
- Medical Physics, Vol. 41, Issue 4
$rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
journal, November 2006
- Aharon, M.; Elad, M.; Bruckstein, A.
- IEEE Transactions on Signal Processing, Vol. 54, Issue 11
Multienergy element-resolved cone beam CT (MEER-CBCT) realized on a conventional CBCT platform
journal, September 2018
- Shen, Chenyang; Li, Bin; Lou, Yifei
- Medical Physics, Vol. 45, Issue 10
Multi-Material Decomposition Using Statistical Image Reconstruction for Spectral CT
journal, August 2014
- Long, Yong; Fessler, Jeffrey A.
- IEEE Transactions on Medical Imaging, Vol. 33, Issue 8
Statistical Sinogram Restoration in Dual-Energy CT for PET Attenuation Correction
journal, November 2009
- Joonki Noh, ; Fessler, J. A.; Kinahan, P. E.
- IEEE Transactions on Medical Imaging, Vol. 28, Issue 11
Statistical image-domain multimaterial decomposition for dual-energy CT
journal, February 2017
- Xue, Yi; Ruan, Ruoshui; Hu, Xiuhua
- Medical Physics, Vol. 44, Issue 3
Accuracies of the synthesized monochromatic CT numbers and effective atomic numbers obtained with a rapid kVp switching dual energy CT scanner
journal, March 2011
- Goodsitt, Mitchell M.; Christodoulou, Emmanuel G.; Larson, Sandra C.
- Medical Physics, Vol. 38, Issue 4
Spectral prior image constrained compressed sensing (spectral PICCS) for photon-counting computed tomography
journal, August 2016
- Yu, Zhicong; Leng, Shuai; Li, Zhoubo
- Physics in Medicine and Biology, Vol. 61, Issue 18
Dual-energy CT reconstruction based on dictionary learning and total variation constraint
conference, October 2012
- Li, Liang; Chen, Zhiqiang; Jiao, Pengfei
- 2012 IEEE Nuclear Science Symposium and Medical Imaging Conference Record (NSS/MIC)
Dual-dictionary learning-based iterative image reconstruction for spectral computed tomography application
journal, November 2012
- Zhao, Bo; Ding, Huanjun; Lu, Yang
- Physics in Medicine and Biology, Vol. 57, Issue 24
Image domain dual material decomposition for dual‐energyCT using butterfly network
journal, April 2019
- Zhang, Wenkun; Zhang, Hanming; Wang, Linyuan
- Medical Physics, Vol. 46, Issue 5
Iodine Quantification With Dual-Energy CT: Phantom Study and Preliminary Experience With Renal Masses
journal, June 2011
- Chandarana, Hersh; Megibow, Alec J.; Cohen, Benjamin A.
- American Journal of Roentgenology, Vol. 196, Issue 6
Iodine quantification with dual-energy CT: phantom study and preliminary experience with VX2 residual tumour in rabbits after radiofrequency ablation
journal, September 2013
- Li, Y.; Shi, G.; Wang, S.
- The British Journal of Radiology, Vol. 86, Issue 1029
Virtual monochromatic imaging in dual-source dual-energy CT: Radiation dose and image quality
journal, November 2011
- Yu, Lifeng; Christner, Jodie A.; Leng, Shuai
- Medical Physics, Vol. 38, Issue 12
Image-domain material decomposition using data-driven sparsity models for dual-energy CT
conference, April 2018
- Li, Zhipeng; Ravishankar, Saiprasad; Long, Yong
- 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)
Noninvasive Differentiation of Uric Acid versus Non–Uric Acid Kidney Stones Using Dual-Energy CT
journal, December 2007
- Primak, Andrew N.; Fletcher, Joel G.; Vrtiska, Terri J.
- Academic Radiology, Vol. 14, Issue 12
A general method to derive tissue parameters for Monte Carlo dose calculation with multi-energy CT
journal, October 2016
- Lalonde, Arthur; Bouchard, Hugo
- Physics in Medicine and Biology, Vol. 61, Issue 22
Dual- and Multi-Energy CT: Principles, Technical Approaches, and Clinical Applications
journal, September 2015
- McCollough, Cynthia H.; Leng, Shuai; Yu, Lifeng
- Radiology, Vol. 276, Issue 3
Material elemental decomposition in dual and multi-energy CT via a sparsity-dictionary approach for proton stopping power ratio calculation
journal, February 2018
- Shen, Chenyang; Li, Bin; Chen, Liyuan
- Medical Physics, Vol. 45, Issue 4
A Flexible Method for Multi-Material Decomposition of Dual-Energy CT Images
journal, January 2014
- Mendonca, Paulo R. S.; Lamb, Peter; Sahani, Dushyant V.
- IEEE Transactions on Medical Imaging, Vol. 33, Issue 1
Tensor-Based Dictionary Learning for Spectral CT Reconstruction
journal, January 2017
- Zhang, Yanbo; Mou, Xuanqin; Wang, Ge
- IEEE Transactions on Medical Imaging, Vol. 36, Issue 1
Sparsifying Transform Learning With Efficient Optimal Updates and Convergence Guarantees
journal, May 2015
- Ravishankar, Saiprasad; Bresler, Yoram
- IEEE Transactions on Signal Processing, Vol. 63, Issue 9
Low-dose spectral CT reconstruction using image gradient ℓ0–norm and tensor dictionary
journal, November 2018
- Wu, Weiwen; Zhang, Yanbo; Wang, Qian
- Applied Mathematical Modelling, Vol. 63
Low dose CT image reconstruction with learned sparsifying transform
conference, July 2016
- Zheng, Xuehang; Lu, Zening; Ravishankar, Saiprasad
- 2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP)
Learning Sparsifying Transforms
journal, March 2013
- Ravishankar, Saiprasad; Bresler, Yoram
- IEEE Transactions on Signal Processing, Vol. 61, Issue 5
PWLS-ULTRA: An Efficient Clustering and Learning-Based Approach for Low-Dose 3D CT Image Reconstruction
journal, June 2018
- Zheng, Xuehang; Ravishankar, Saiprasad; Long, Yong
- IEEE Transactions on Medical Imaging, Vol. 37, Issue 6
Learning overcomplete sparsifying transforms for signal processing
conference, May 2013
- Ravishankar, Saiprasad; Bresler, Yoram
- 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
Data-Driven Learning of a Union of Sparsifying Transforms Model for Blind Compressed Sensing
journal, September 2016
- Ravishankar, Saiprasad; Bresler, Yoram
- IEEE Transactions on Computational Imaging, Vol. 2, Issue 3