Single-image super-resolution of gamma-ray imaging system using deep denoiser prior based on plug-and-play framework

Li Guo-Guang; Sheng Liang; Duan Bao-Jun; Li Yang; Song Yan; Zhu Zi-Jian; Yan Wei-Peng; Hei Dong-Wei; Xing Qing-Zi

doi:10.1063/5.0236541

Volume 10 Issue 2

Mar. 2025

Turn off MathJax

Article Contents

Article Navigation > Matter and Radiation at Extremes > 2025 > 10(2): 027402

Li Guo-Guang, Sheng Liang, Duan Bao-Jun, Li Yang, Song Yan, Zhu Zi-Jian, Yan Wei-Peng, Hei Dong-Wei, Xing Qing-Zi. Single-image super-resolution of gamma-ray imaging system using deep denoiser prior based on plug-and-play framework[J]. Matter and Radiation at Extremes, 2025, 10(2): 027402. doi: 10.1063/5.0236541

Citation:

Li Guo-Guang, Sheng Liang, Duan Bao-Jun, Li Yang, Song Yan, Zhu Zi-Jian, Yan Wei-Peng, Hei Dong-Wei, Xing Qing-Zi. Single-image super-resolution of gamma-ray imaging system using deep denoiser prior based on plug-and-play framework[J]. Matter and Radiation at Extremes, 2025, 10(2): 027402. doi: 10.1063/5.0236541

Citation:

Li Guo-Guang, Sheng Liang, Duan Bao-Jun, Li Yang, Song Yan, Zhu Zi-Jian, Yan Wei-Peng, Hei Dong-Wei, Xing Qing-Zi. Single-image super-resolution of gamma-ray imaging system using deep denoiser prior based on plug-and-play framework[J]. Matter and Radiation at Extremes, 2025, 10(2): 027402. doi: 10.1063/5.0236541

PDF( 18099 KB)

Single-image super-resolution of gamma-ray imaging system using deep denoiser prior based on plug-and-play framework

doi: 10.1063/5.0236541

Li Guo-Guang^{1, 2, 3
,},
Sheng Liang^{4
,
,
,},
Duan Bao-Jun^4
,,
Li Yang⁴,
Song Yan⁴,
Zhu Zi-Jian⁴,
Yan Wei-Peng⁴,
Hei Dong-Wei⁴,
Xing Qing-Zi^{1, 2, 3
,
,
,}

1.
Key Laboratory of Particle and Radiation Imaging (Tsinghua University), Ministry of Education, Beijing 100084, China
2.
Laboratory for Advanced Radiation Sources and Application, Tsinghua University, Beijing 100084, China
3.
Department of Engineering Physics, Tsinghua University, Beijing 100084, China
4.
State Key Laboratory of Intense Pulsed Radiation Simulation and Effect, Northwest Institute of Nuclear Technology, Xi’an 710024, China

More Information

Corresponding author: a)Authors to whom correspondence should be addressed: shengliang@tsinghua.org.cn and xqz@tsinghua.edu.cn
Received Date: 2024-09-01
Accepted Date: 2024-12-18

Available Online: 2025-03-01

Publish Date: 2025-03-01

Abstract

Abstract

Gamma-ray imaging systems are powerful tools in radiographic diagnosis. However, the recorded images suffer from degradations such as noise, blurring, and downsampling, consequently failing to meet high-precision diagnostic requirements. In this paper, we propose a novel single-image super-resolution algorithm to enhance the spatial resolution of gamma-ray imaging systems. A mathematical model of the gamma-ray imaging system is established based on maximum a posteriori estimation. Within the plug-and-play framework, the half-quadratic splitting method is employed to decouple the data fidelity term and the regularization term. An image denoiser using convolutional neural networks is adopted as an implicit image prior, referred to as a deep denoiser prior, eliminating the need to explicitly design a regularization term. Furthermore, the impact of the image boundary condition on reconstruction results is considered, and a method for estimating image boundaries is introduced. The results show that the proposed algorithm can effectively addresses boundary artifacts. By increasing the pixel number of the reconstructed images, the proposed algorithm is capable of recovering more details. Notably, in both simulation and real experiments, the proposed algorithm is demonstrated to achieve subpixel resolution, surpassing the Nyquist sampling limit determined by the camera pixel size.

The authors have no conflicts to disclose.
Conflict of Interest
Guo-Guang Li: Conceptualization (equal); Investigation (equal); Methodology (equal); Software (equal); Writing – original draft (equal). Liang Sheng: Conceptualization (equal); Funding acquisition (equal); Resources (equal); Supervision (equal); Writing – review & editing (equal). Bao-Jun Duan: Methodology (equal); Project administration (equal); Resources (equal); Validation (equal). Yang Li: Project administration (equal); Resources (equal); Validation (equal). Yan Song: Project administration (equal); Resources (equal); Validation (equal). Zi-Jian Zhu: Methodology (equal); Resources (equal); Validation (equal). Wei-Peng Yan: Methodology (equal); Resources (equal); Validation (equal). Dong-Wei Hei: Funding acquisition (equal); Resources (equal); Supervision (equal). Qing-Zi Xing: Resources (equal); Supervision (equal); Writing – review & editing (equal).
Author Contributions
The data that support the findings of this study are available within the article, and additional data are available from the corresponding authors upon reasonable request.

FullText(HTML)

References(64)

References

[1]	H. O. Anger, “Use of a gamma-ray pinhole camera for in vivo studies,” Nature 170, 200–201 (1952).10.1038/170200b0
[2]	G. Li, L. Sheng, B. Duan, Y. Li, D. Hei et al., “Monte Carlo simulation of spatial resolution of lens-coupled LYSO scintillator for intense pulsed gamma-ray imaging system with large field of view,” Nucl. Eng. Technol. 56, 2650–2658 (2024).10.1016/j.net.2024.02.024
[3]	J. Zhang, Q. Yi, L. Li, F. Zhang, D. Chen et al., “Simulation and experimental study of the angle-dependent sensitivity of the thick pinhole used for gamma imaging,” Nucl. Instrum. Methods Phys. Res., Sect. A 915, 24–30 (2019).10.1016/j.nima.2018.10.163
[4]	Z. Wang, A. F. T. Leong, A. Dragone, A. E. Gleason, R. Ballabriga et al., “Ultrafast radiographic imaging and tracking: An overview of instruments, methods, data, and applications,” Nucl. Instrum. Methods Phys. Res., Sect. A 1057, 168690 (2023).10.1016/j.nima.2023.168690
[5]	P. Knoblauch, V. Raspa, F. D. Lorenzo, A. Clausse, and C. Moreno, “Hard X-ray dosimetry of a plasma focus suitable for industrial radiography,” Radiat. Phys. Chem. 145, 39–42 (2018).10.1016/j.radphyschem.2017.12.014
[6]	H. B. Barber, B. A. Apotovsky, F. L. Augustine, H. H. Barrett, E. L. Dereniak et al., “Semiconductor pixel detectors for gamma-ray imaging in nuclear medicine,” Nucl. Instrum. Methods Phys. Res., Sect. A 395, 421–428 (1997).10.1016/s0168-9002(97)00615-3
[7]	A. M. Alyassin, H. A. Maqsoud, A. M. Mashat, A.-S. Al-Mohr, and S. Abdulwajid, “Feasibility study of gamma-ray medical radiography,” Appl. Radiat. Isot. 72, 16–29 (2013).10.1016/j.apradiso.2012.11.001
[8]	G. Petringa, G. A. P. Cirrone, C. Caliri, G. Cuttone, L. Giuffrida et al., “Study of gamma-ray emission by proton beam interaction with injected Boron atoms for future medical imaging applications,” J. Instrum. 12, C03049 (2017).10.1088/1748-0221/12/03/c03049
[9]	D. N. Fittinghoff, N. Birge, and V. Geppert-Kleinrath, “Neutron imaging of inertial confinement fusion implosions,” Rev. Sci. Instrum. 94, 021101 (2023).10.1063/5.0124074
[10]	C. Tian, M. Yu, L. Shan, F. Wu, B. Bi et al., “Diagnosis of indirectly driven double shell targets with point-projection hard x-ray radiography,” Matter Radiat. Extremes 9, 027602 (2024).10.1063/5.0045112
[11]	V. Geppert-Kleinrath, N. Hoffman, N. Birge, A. DeYoung, D. Fittinghoff et al., “Gamma-ray imaging of inertial confinement fusion implosions reveals remaining ablator carbon distribution,” Phys. Plasmas 30, 022703 (2023).10.1063/5.0122938
[12]	Z. Gong, K. Z. Hatsagortsyan, and C. H. Keitel, “Deciphering in situ electron dynamics of ultrarelativistic plasma via polarization pattern of emitted γ-photons,” Phys. Rev. Res. 4, L022024 (2022).10.1103/physrevresearch.4.l022024
[13]	Z. Gong, X. Shen, K. Z. Hatsagortsyan, and C. H. Keitel, “Electron slingshot acceleration in relativistic preturbulent shocks explored via emitted photon polarization,” Phys. Rev. Lett. 131, 225101 (2023).10.1103/physrevlett.131.225101
[14]	T. Da, J. Ma, B. Duan, C. Han, W. Gu et al., “Pulsed radiation image restoration based on unsupervised deep learning,” Nucl. Instrum. Methods Phys. Res., Sect. A 1061, 169128 (2024).10.1016/j.nima.2024.169128
[15]	C. A. Barrera, E. C. Morse, and M. J. Moran, “Image reconstruction algorithms for inertial confinement fusion neutron imaging,” Rev. Sci. Instrum. 77, 10E716 (2006).10.1063/1.2220042
[16]	R. A. Lerche, D. Ress, R. J. Ellis, S. M. Lane, and K. A. Nugent, “Neutron penumbral imaging of laser-fusion targets,” Laser Part. Beams 9, 99–118 (1991).10.1017/s0263034600002366
[17]	W. H. Richardson, “Bayesian-based iterative method of image restoration,” J. Opt. Soc. Am. 62, 55–59 (1972).10.1364/josa.62.000055
[18]	R. Noumeir, G. E. Mailloux, and R. Lemieux, “An expectation maximization reconstruction algorithm for emission tomography with non-uniform entropy prior,” Int. J. Biomed. Comput. 39, 299–310 (1995).10.1016/0020-7101(95)01111-q
[19]	Y. Park, L. Reichel, G. Rodriguez, and X. Yu, “Parameter determination for Tikhonov regularization problems in general form,” J. Comput. Appl. Math. 343, 12–25 (2018).10.1016/j.cam.2018.04.049
[20]	L. I. Rudin, S. Osher, and E. Fatemi, “Nonlinear total variation based noise removal algorithms,” Physica D 60, 259–268 (1992).10.1016/0167-2789(92)90242-f
[21]	D. Wang, H. Hu, F. Zhang, and Q. Jia, “Source reconstruction for neutron coded-aperture imaging: A sparse method,” Rev. Sci. Instrum. 88, 083502 (2017).10.1063/1.4996193
[22]	Q. Li, Y. Yan, F. Wang, and J. He, “Combination algorithms applied to source reconstruction for neutron coded images and restoration for incomplete coded images,” Rev. Sci. Instrum. 94, 053301 (2023).10.1063/5.0138742
[23]	M. Yan, H. Hu, G. Hu, Z. Liu, C. He et al., “Comparison of heuristic and deterministic algorithms in neutron coded imaging reconstruction,” Nucl. Instrum. Methods Phys. Res., Sect. A 985, 164704 (2021).10.1016/j.nima.2020.164704
[24]	P. S. Cheol, P. M. Kyu, and K. M. Gi, “Super-resolution image reconstruction: A technical overview,” IEEE Signal Process. Mag. 20, 21–36 (2003).10.1109/msp.2003.1203207
[25]	J. Tian and K.-K. Ma, “A survey on super-resolution imaging,” Signal, Image Video Process. 5, 329–342 (2011).10.1007/s11760-010-0204-6
[26]	W. Yang, X. Zhang, Y. Tian, W. Wang, J. H. Xue et al., “Deep learning for single image super-resolution: A brief review,” IEEE Trans. Multimedia 21, 3106–3121 (2019).10.1109/tmm.2019.2919431
[27]	Z. Wang, J. Chen, and S. C. H. Hoi, “Deep learning for image super-resolution: A survey,” IEEE Trans. Pattern Anal. Mach. Intell. 43, 3365–3387 (2021).10.1109/tpami.2020.2982166
[28]	W. Dong, L. Zhang, G. Shi, and X. Li, “Nonlocally centralized sparse representation for image restoration,” IEEE Trans. Image Process. 22, 1620–1630 (2013).10.1109/tip.2012.2235847
[29]	J. Zhang, D. Zhao, and W. Gao, “Group-based sparse representation for image restoration,” IEEE Trans. Image Process. 23, 3336–3351 (2014).10.1109/tip.2014.2323127
[30]	C. Ren, X. He, Q. Teng, Y. Wu, and T. Q. Nguyen, “Single image super-resolution using local geometric duality and non-local similarity,” IEEE Trans. Image Process. 25, 2168–2183 (2016).10.1109/tip.2016.2542442
[31]	C. Dong, C. C. Loy, K. He, and X. Tang, “Image super-resolution using deep convolutional networks,” IEEE Trans. Pattern Anal. Mach. Intell. 38, 295–307 (2016).10.1109/tpami.2015.2439281
[32]
[33]
[34]	S. Gao and X. Zhuang, “Bayesian image super-resolution with deep modeling of image statistics,” IEEE Trans. Pattern Anal. Mach. Intell. 45, 1405–1423 (2023).10.1109/tpami.2022.3163307
[35]	R. Zhang, P. Gong, X. Tang, P. Wang, C. Zhou et al., “Reconstruction method for gamma-ray coded-aperture imaging based on convolutional neural network,” Nucl. Instrum. Methods Phys. Res., Sect. A 934, 41–51 (2019).10.1016/j.nima.2019.04.055
[36]	C.-M. Wang, R. Shi, X.-G. Tuo, G. Yang, Z. Li et al., “Reconstruction of tomographic gamma scanning transmission image from sparse projections based on convolutional neural networks,” Nucl. Instrum. Methods Phys. Res., Sect. A 1039, 167110 (2022).10.1016/j.nima.2022.167110
[37]	H.-J. Choi, J. Jeong, H. Lee, S. G. Kim, J. J. Ahn et al., “Image reconstruction method of gamma emission tomography based on prior-aware information and machine learning for partial-defect detection of PWR-type spent nuclear fuel,” Nucl. Eng. Technol. 56, 4770–4781 (2024).10.1016/j.net.2024.06.040
[38]	J. Song, J. Zheng, Z. Chen, J. Chen, and F. Wang, “Neutron penumbral image reconstruction with a convolution neural network using fast Fourier transform,” Rev. Sci. Instrum. 95, 013509 (2024).10.1063/5.0175347
[39]
[40]	S. Boyd, N. Parikh, E. Chu, B. Peleato, and J. Eckstein, “Distributed optimization and statistical learning via the alternating direction method of multipliers,” Found. Trends Mach. Learn. 3(1), 1–122 (2011), available at https://web.stanford.edu/~boyd/papers/admm_distr_stats.html.
[41]	D. Geman and Y. Chengda, “Nonlinear image recovery with half-quadratic regularization,” IEEE Trans. Image Process. 4, 932–946 (1995).10.1109/83.392335
[42]	Y. Romano, M. Elad, and P. Milanfar, “The little engine that could: Regularization by denoising (RED),” SIAM J. Imaging Sci. 10, 1804–1844 (2017).10.1137/16m1102884
[43]	K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26, 3142–3155 (2017).10.1109/tip.2017.2662206
[44]	K. Zhang, W. Zuo, and L. Zhang, “FFDNet: Toward a fast and flexible solution for CNN-based image denoising,” IEEE Trans. Image Process. 27, 4608–4622 (2018).10.1109/tip.2018.2839891
[45]	K. Zhang, Y. Li, W. Zuo, L. Zhang, L. Van Gool et al., “Plug-and-play image restoration with deep denoiser prior,” IEEE Trans. Pattern Anal. Mach. Intell. 44, 6360–6376 (2022).10.1109/tpami.2021.3088914
[46]	T. Liu, Q. Yin, J. Yang, Y. Wang, and W. An, “Combining deep denoiser and low-rank priors for infrared small target detection,” Pattern Recognit. 135, 109184 (2023).10.1016/j.patcog.2022.109184
[47]	Z. Lai, K. Wei, and Y. Fu, “Deep plug-and-play prior for hyperspectral image restoration,” Neurocomputing 481, 281–293 (2022).10.1016/j.neucom.2022.01.057
[48]	Y. Chen, X. Gui, J. Zeng, X. L. Zhao, and W. He, “Combining low-rank and deep plug-and-play priors for snapshot compressive imaging,” IEEE Trans. Neural Netw. Learn. Sys. 35(11), 16396–16408 (2023).10.1109/TNNLS.2023.3294262
[49]	B. Wan, F. Yang, D. Ding, S. Zhao, J. Xie et al., “Effects of yttrium content on intrinsic radioactivity energy spectra of LYSO:Ce crystals,” Nucl. Instrum. Methods Phys. Res., Sect. A 1001, 165263 (2021).10.1016/j.nima.2021.165263
[50]	S. i. Amari, “Backpropagation and stochastic gradient descent method,” Neurocomputing 5, 185–196 (1993).10.1016/0925-2312(93)90006-o
[51]	G. Li, L. Sheng, B. Duan, Y. Li, D. Hei, and Q. Xing, “Super-resolution image reconstruction of a neutron thick pinhole imaging system using image denoiser prior based on half quadratic splitting method,” Nucl. Instrum. Methods Phys. Res., Sect. A 1061, 169130 (2024).10.1016/j.nima.2024.169130
[52]	A. Buades, B. Coll, and J. M. Morel, “A non-local algorithm for image denoising,” in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (IEEE, 2005), Vol. 2, pp. 60–65.
[53]	K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, “Image denoising by sparse 3-D transform-domain collaborative filtering,” IEEE Trans. Image Process. 16, 2080–2095 (2007).10.1109/tip.2007.901238
[54]	O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015), Lecture Notes in Computer Science (Springer, 2015), Vol. 9351, pp. 234–241.10.1007/978-3-319-24574-4_28
[55]
[56]	Y. Chen and T. Pock, “Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration,” IEEE Trans. Pattern Anal. Mach. Intell. 39, 1256–1272 (2017).10.1109/tpami.2016.2596743
[57]
[58]
[59]
[60]	S. H. Chan, X. Wang, and O. A. Elgendy, “Plug-and-play ADMM for image restoration: Fixed-point convergence and applications,” IEEE Trans. Comput. Imaging 3(1), 84–98 (2017).10.1109/tci.2016.2629286
[61]	M. S. C. Almeida and M. Figueiredo, “Deconvolving images with unknown boundaries using the alternating direction method of multipliers,” IEEE Trans. Image Process. 22, 3074–3086 (2013).10.1109/tip.2013.2258354
[62]	A. Matakos, S. Ramani, and J. A. Fessler, “Accelerated edge-preserving image restoration without boundary artifacts,” IEEE Trans. Image Process. 22, 2019–2029 (2013).10.1109/tip.2013.2244218
[63]	C. C. Paige and M. A. Saunders, “LSQR: An algorithm for sparse linear equations and sparse least squares,” ACM Trans. Math. Software 8, 43–71 (1982).10.1145/355984.355989
[64]	P. Volegov, C. R. Danly, D. N. Fittinghoff, G. P. Grim, N. Guler et al., “Neutron source reconstruction from pinhole imaging at national ignition facility,” Rev. Sci. Instrum. 85, 023508 (2014).10.1063/1.4865456