Researching | Low-dose nano-CT reconstruction image denoising based on Swin Transformer and convolutional neural network

Opto-Electronic Engineering, Volume. 52, Issue 6, 240306(2025)

Low-dose nano-CT reconstruction image denoising based on Swin Transformer and convolutional neural network

Ao Wang^1,2,3, Zhen Peng^3,4, Jun Wang³, Fen Tao³, Ling Zhang³, Guohao Du³, Yi Liu^1、*, and Biao Deng^2,3、**

Author Affiliations

¹School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China

²Shanghai Institute of Applied Physics, Chinese Academy of Sciences, Shanghai 201800, China

³Shanghai Synchrotron Radiation Facility, Shanghai Advanced Research Institute, Chinese Academy of Sciences, Shanghai 201204, China

⁴School of Microelectronics, Shanghai University, Shanghai 200444, China

show less

Abstract Get PDF(in Chinese)

Figures&Tables (8)

References (32)

Paper Information

References(32)

[1] Su B, Tao F, Li K et al. Image alignment for synchrotron radiation based X-ray nano-CT[J]. Acta Phys Sin, 70, 160704(2021).

[2] Tao F, Zhang L, Su B et al. Design, development and commissioning of 3D nano image beamline at Shanghai synchrotron radiation facility[J]. Acta Opt Sin, 42, 2334001(2022).

[3] Xing Y J, Gao R Y, Zhang L et al. Background sequence prediction for TXM-XANES based on polynomial regression and linear interpolation[J]. Nucl Tech, 47, 030102(2024).

[4] Apeleo Zubiri B, Wirth J, Drobek D et al. Correlative laboratory nano-CT and 360° electron tomography of macropore structures in hierarchical zeolites[J]. Adv Mater Interfaces, 8, 2001154(2021).

[5] Da Silva J C, Mader K, Holler M et al. Assessment of the 3 D pore structure and individual components of preshaped catalyst bodies by X-ray imaging[J]. ChemCatChem, 7, 413-416(2015).

[6] Huang X Z, Li N, Wang D J et al. Quantitative three-dimensional analysis of poly (lactic-co-glycolic acid) microsphere using hard X-ray nano-tomography revealed correlation between structural parameters and drug burst release[J]. J Pharmaceut Biomed Anal, 112, 43-49(2015).

[7] Prass S, Hasanpour S, Sow P K et al. Microscale X-ray tomographic investigation of the interfacial morphology between the catalyst and micro porous layers in proton exchange membrane fuel cells[J]. J Power Sources, 319, 82-89(2016).

[8] Weber S, Zimmermann R T, Bremer J et al. Digitization in catalysis research: towards a holistic description of a Ni/Al2O3 reference catalyst for CO2 methanation[J]. ChemCatChem, 14, e202101878(2022).

[9] Ziesche R F, Heenan T M M, Kumari P et al. Multi-dimensional characterization of battery materials[J]. Adv Energy Mater, 13, 2300103(2023).

[10] Chen G H, Leng S, Mistretta C. A generalized projection-slice theorem for the divergent beam projections[J]. Proc SPIE, 5535, 301-309(2004).

[11] Qi Z W, Kong H H, Li J X et al. Overlapping group sparsity on hyper-Laplacian prior of sparse angle CT reconstruction[J]. Opto-Electron Eng, 50, 230167(2023).

[12] Gong Y X, Yu Z J, Wang J J. Application of X-ray 3D imaging in the field of battery materials research[J]. Chem Bull, 83, 349-355(2020).

[13] Liu Z, Lin Y T, Cao Y et al. Swin Transformer: hierarchical vision Transformer using shifted windows[C], 9992-10002(2021). https://doi.org/10.1109/ICCV48922.2021.00986

[14] Liang J Y, Cao J Z, Sun G L et al. SwinIR: image restoration using Swin Transformer[C], 1833-1844(2021). https://doi.org/10.1109/ICCVW54120.2021.00210

[15] Dabov K, Foi A, Katkovnik V et al. Image denoising by sparse 3-D transform-domain collaborative filtering[J]. IEEE Trans Image Process, 16, 2080-2095(2007).

[16] Mao X J, Shen C H, Yang Y B. Image restoration using convolutional auto-encoders with symmetric skip connections[Z](2016). https://arxiv.org/abs/1606.08921

[17] Zhang K, Zuo W M, Chen Y J et al. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising[J]. IEEE Trans Image Process, 26, 3142-3155(2017).

[18] Lehtinen J, Munkberg J, Hasselgren J et al. Noise2Noise: learning image restoration without clean data[C], 2965-2974.(2018).

[19] Guo S, Yan Z F, Zhang K et al. Toward convolutional blind denoising of real photographs[C], 1712-1722(2019). https://doi.org/10.1109/CVPR.2019.00181

[20] Chen H T, Wang Y H, Guo T Y et al. Pre-trained image processing transformer[C], 12294-12305(2021). https://doi.org/10.1109/CVPR46437.2021.01212

[21] Wang Z D, Cun X D, Bao J M et al. Uformer: a general U-shaped Transformer for image restoration[C], 17662-17672(2022). https://doi.org/10.1109/CVPR52688.2022.01716

[22] Chen H, Zhang Y, Zhang W H et al. Low-dose CT via convolutional neural network[J]. Biomed Opt Express, 8, 679-694(2017).

[23] Pelt D M, Batenburg K J, Sethian J A. Improving tomographic reconstruction from limited data using mixed-scale dense convolutional neural networks[J]. J Imaging, 4, 128(2018).

[24] Liu Z C, Bicer T, Kettimuthu R et al. TomoGAN: low-dose synchrotron X-ray tomography with generative adversarial networks: discussion[J]. J Opt Soc Am A, 37, 422-434(2020).

[25] Agustsson E, Timofte R. NTIRE 2017 challenge on single image super-resolution: dataset and study[C], 1122-1131(2017). https://doi.org/10.1109/CVPRW.2017.150

[26] Zhang K, Liang J Y, Van Gool L et al. Designing a practical degradation model for deep blind image super-resolution[C], 4771-4780(2021). https://doi.org/10.1109/ICCV48922.2021.00475

[27] Tao F, Wang J, Du G H et al. Full-field hard X-ray nano-tomography at SSRF[J]. J Synchrotron Radiat, 30, 815-821(2023). https://doi.org/10.1107/S1600577523003168

[28] Zhang L, Tao F, Wang J et al. The 3D nanoimaging beamline at SSRF[J]. Nucl Sci Tech, 34, 201(2023).

[29] Wang S Y, Yao Z Y, Zhang Y R et al. A multilayer linear fusion algorithm for endoscopic image enhancement[J]. Opto-Electron Eng, 51, 240063(2024).

[30] Mittal A, Soundararajan R, Bovik A C. Making a "completely blind" image quality analyzer[J]. IEEE Signal Process Lett, 20, 209-212(2013).

[31] Mittal A, Moorthy A K, Bovik A C. No-reference image quality assessment in the spatial domain[J]. IEEE Trans Image Process, 21, 4695-4708(2012).

[32] Liang T F, Jin Y, Li Y D et al. EDCNN: edge enhancement-based densely connected network with compound loss for low-dose CT denoising[C], 193-198(2020). https://doi.org/10.1109/ICSP48669.2020.9320928

Tools

Get Citation

Copy Citation Text

Ao Wang, Zhen Peng, Jun Wang, Fen Tao, Ling Zhang, Guohao Du, Yi Liu, Biao Deng. Low-dose nano-CT reconstruction image denoising based on Swin Transformer and convolutional neural network[J]. Opto-Electronic Engineering, 2025, 52(6): 240306

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Article

Received: Dec. 25, 2024

Accepted: Apr. 28, 2025

Published Online: Sep. 3, 2025

The Author Email: Yi Liu (刘一), Biao Deng (邓彪)

DOI:10.12086/oee.2025.240306

Topics

laser devices and laser physics

Lasers and Laser Optics

laser manufacturing

Instrumentation, Measurement and Metrology