Iterator-Net: sinogram-based CT image reconstruction

Limin Ma; Yudong Yao; Yueyang Teng; Limin Ma; Yudong Yao; Yueyang Teng

doi:10.3934/mbe.2022609

Mathematical Biosciences and Engineering

2022, Volume 19, Issue 12: 13050-13061. doi: 10.3934/mbe.2022609

Previous Article Next Article

Research article Special Issues

Iterator-Net: sinogram-based CT image reconstruction

1.
College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110004, China
2.
Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ, United States

Academic Editor: Biswajeet Pradhan

Received: 10 June 2022 Revised: 12 August 2022 Accepted: 26 August 2022 Published: 06 September 2022

Image reconstruction is extremely important for computed tomography (CT) imaging, so it is significant to be continuously improved. The unfolding dynamics method combines a deep learning model with a traditional iterative algorithm. It is interpretable and has a fast reconstruction speed, but the essence of the algorithm is to replace the approximation operator in the optimization objective with a learning operator in the form of a convolutional neural network. In this paper, we firstly design a new iterator network (iNet), which is based on the universal approximation theorem and tries to simulate the functional relationship between the former and the latter in the maximum-likelihood expectation maximization (MLEM) algorithm. To evaluate the effectiveness of the method, we conduct experiments on a CT dataset, and the results show that our iNet method improves the quality of reconstructed images.
- computed tomography (CT),
- image reconstruction,
- maximum-likelihood expectation maximization (MLEM)
Citation: Limin Ma, Yudong Yao, Yueyang Teng. Iterator-Net: sinogram-based CT image reconstruction[J]. Mathematical Biosciences and Engineering, 2022, 19(12): 13050-13061. doi: 10.3934/mbe.2022609

Related Papers:

Abstract

Image reconstruction is extremely important for computed tomography (CT) imaging, so it is significant to be continuously improved. The unfolding dynamics method combines a deep learning model with a traditional iterative algorithm. It is interpretable and has a fast reconstruction speed, but the essence of the algorithm is to replace the approximation operator in the optimization objective with a learning operator in the form of a convolutional neural network. In this paper, we firstly design a new iterator network (iNet), which is based on the universal approximation theorem and tries to simulate the functional relationship between the former and the latter in the maximum-likelihood expectation maximization (MLEM) algorithm. To evaluate the effectiveness of the method, we conduct experiments on a CT dataset, and the results show that our iNet method improves the quality of reconstructed images.

References

[1]	H. Zhang, B. Liu, H. Yu, B. Dong, MetaInv-Net: meta inversion network for sparse view CT image reconstruction, IEEE Trans. Med. Imaging, 40 (2020), 621–634. https://doi.org/10.1109/TMI.2020.3033541 doi: 10.1109/TMI.2020.3033541
[2]	Y. Wei, M. Zhao, M. Zhao, M. Lei, ADMM-based decoder for binary linear codes aided by deep learning, IEEE Commun. Lett., 24 (2020), 1028–1032. https://doi.org/10.1109/LCOMM.2020.2974199 doi: 10.1109/LCOMM.2020.2974199
[3]	Y. Yang, J. Sun, H. Li, Z. Xu, Deep ADMM-Net for compressive sensing MRI, Adv. Neural Inf. Process. Syst., 29 (2016), 10–18. https://dl.acm.org/doi/10.5555/3157096.3157098
[4]	Y. Yang, J. Sun, H. Li, Z. Xu, ADMM-CSNet: a deep learning approach for image compressive sensing, IEEE Trans. Pattern Anal. Mach. Intell., 42 (2018), 521–538. https://doi.org/10.1109/TPAMI.2018.2883941 doi: 10.1109/TPAMI.2018.2883941
[5]	L. Yang, H. Wang, H. Qian, An ADMM-ResNet for data recovery in wireless sensor networks with guaranteed convergence, Digital Signal Process., 111 (2021), 102956. https://doi.org/10.1016/j.dsp.2020.102956 doi: 10.1016/j.dsp.2020.102956
[6]	J. M. Ramirez, J. I. Martínez-Torre, H. Arguello, LADMM-Net: an unrolled deep network for spectral image fusion from compressive data, Signal Process., 189 (2021), 108239. https://doi.org/10.1016/j.sigpro.2021.108239 doi: 10.1016/j.sigpro.2021.108239
[7]	K. Gong, D. Wu, K. Kim, Y. Yang, G. EI Fakhri, Y. Seo, et al., EMnet: an unrolled deep neural network for PET image reconstruction, Med. Imaging 2019: Phys. Med. Imaging, 10948 (2019), 1203–1208. https://doi.org/10.1117/12.2513096 doi: 10.1117/12.2513096
[8]	Y. Liu, Q. Liu, M. Zhang, Q. Yang, S. Wang, D. Liang, IFR-Net: iterative feature refinement network for compressed sensing MRI, IEEE Trans. Comput. Imaging, 6 (2019), 434–446. https://doi.org/10.1109/TCI.2019.2956877 doi: 10.1109/TCI.2019.2956877
[9]	J. Zhang, B. Ghanem, STA-Net: interpretable optimization-inspired deep network for image compressive sensing, in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018 (2018), 1828–1837. https://doi.org/10.1109/CVPR.2018.00196
[10]	K. Jin, M. T. McCann, E. Froustey, M. Unser, Deep convolutional neural network for inverse problems in imaging, IEEE Trans. Image Process., 26 (2017), 4509–4522. https://doi.org/10.1109/TIP.2017.2713099 doi: 10.1109/TIP.2017.2713099
[11]	H. Chen, Y. Zhang, Y. Chen, J. Zhang, W. Zhang, H. Sun, et al., LEARN: learned experts' assessment-based reconstruction network for sparse-data CT, IEEE Trans. Med Imaging, 37 (2018), 1333–1347. https://doi.org/10.1109/TMI.2018.2805692 doi: 10.1109/TMI.2018.2805692
[12]	G. Cybenko, Approximation by superpositions of a sigmoidal function, Math. Control, Signals Syst., 2 (1989), 303–314. https://doi.org/10.1007/BF02551274 doi: 10.1007/BF02551274
[13]	K. Hornik, M. Stinchcombe, H. White, Multilayer feedforward networks are universal approximators, Neural Networks, 2 (1989), 359–366. https://doi.org/10.1016/0893-6080(89)90020-8 doi: 10.1016/0893-6080(89)90020-8
[14]	T. Chen, H. Chen, Approximations of continuous functionals by neural networks with application to dynamic systems, IEEE Trans. Neural Networks, 4 (1993), 910–918. https://doi.org/10.1109/72.286886 doi: 10.1109/72.286886
[15]	H. Mhaskar, N. Hahm, Neural networks for functional approximation and system identification, Neural Comput., 9 (1997), 143–159. https://doi.org/10.1162/neco.1997.9.1.143 doi: 10.1162/neco.1997.9.1.143
[16]	F. Rossi, B. Conan-Guez, Functional multi-layer perceptron: a non-linear tool for functional data analysis, Neural Networks, 18 (2005), 45–60. https://doi.org/10.1016/j.neunet.2004.07.001 doi: 10.1016/j.neunet.2004.07.001
[17]	D. P. Kingma, J. Ba, Adam: a method for stochastic optimization, preprint, arXiv: 1412.6980.

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)