同步辐射纳米CT图像超分辨率重建及其应用研究

彭真; 汪澳; 汪俊; 陶芬; 张玲; 杜国浩; 邓彪

doi:10.3724/j.0253-3219.2026.hjs.49.250034

您当前的位置：

首页 >

文章列表页 >

同步辐射纳米CT图像超分辨率重建及其应用研究

同步辐射技术及应用 | 更新时间：2026-01-19

- 同步辐射纳米CT图像超分辨率重建及其应用研究
- Super-resolution reconstruction of synchrotron radiation nano-CT images and its applications
- 核技术 2026年49卷第1期文章编号：010101
- 作者机构：
  
  1.上海大学上海 200444
  2.上海理工大学上海 200093
  3.中国科学院上海高等研究院上海光源中心上海 201204
- 作者简介：
  
  彭真，男，2000年出生，2022年毕业于德州学院，现为硕士研究生，研究领域为CT图像处理
  邓彪，E-mail：dengb@sari.ac.cn
- 基金信息：
  
  国家重点研发计划(2021YFA1600700;2021YFA1601001);国家自然科学基金(12275343)
- DOI：10.3724/j.0253-3219.2026.hjs.49.250034
  中图分类号： TP391;TL99
- 收稿：2025-01-21，
  
  修回：2025-03-19，
  
  纸质出版：2026-01-15
- 稿件说明：
移动端阅览
彭真,汪澳,汪俊等.同步辐射纳米CT图像超分辨率重建及其应用研究[J].核技术,2026,49(01):010101.

PENG Zhen,WANG Ao,WANG Jun,et al.Super-resolution reconstruction of synchrotron radiation nano-CT images and its applications[J].NUCLEAR TECHNIQUES,2026,49(01):010101.
彭真,汪澳,汪俊等.同步辐射纳米CT图像超分辨率重建及其应用研究[J].核技术,2026,49(01):010101. DOI： 10.3724/j.0253-3219.2026.hjs.49.250034. CSTR： 32193.14.hjs.CN31-1342/TL.2026.49.250034.

PENG Zhen,WANG Ao,WANG Jun,et al.Super-resolution reconstruction of synchrotron radiation nano-CT images and its applications[J].NUCLEAR TECHNIQUES,2026,49(01):010101. DOI： 10.3724/j.0253-3219.2026.hjs.49.250034. CSTR： 32193.14.hjs.CN31-1342/TL.2026.49.250034.

摘要

同步辐射纳米CT（Nano-Computed Tomography）技术因其能够在纳米尺度上提供高分辨率三维结构信息，在材料科学、能源、地质学等多个学科领域发挥着重要作用。然而，环境干扰、设备精度限制及光源强度波动等因素导致纳米CT图像信噪比降低、模糊和细节丢失，影响定量分析的准确性。针对这一挑战，本研究在缺少纳米CT数据集的情况下，提出了一种基于Transformer的图像超分辨率（Super-resolution，SR）网络，专门用于提高纳米CT图像的质量，还探究其对裂纹分割等后续分析任务的优化效果。该网络采用U型对称结构，融合了双卷积前馈网络和分组式多尺度窗口自注意力机制，以实现高效的纳米CT图像超分辨率重建。实验结果表明，该网络在计算效率和多个评价指标上均优于SwinIR和Real-ESRGAN模型。在裂纹分割中任务中，经该网络处理后的图像裂纹分割准确率达到99.3%，召回率提升了24.5%，验证了图像超分辨率重建技术在裂纹分割预处理中的有效性。

Abstract

Background

Synchrotron radiation nano-computed tomography (nano-CT) is widely applied in materials science

energy research

and geology due to its capability to provide high-resolution three-dimensional structural information at the nanoscale. However

environmental interference

equipment limitations

and light source fluctuations often degrade image quality

leading to reduced signal-to-noise ratio

blurring

and loss of critical details

which severely impact quantitative analysis and segmentation accuracy for microstructures such as cracks and pores. While existing super-resolution (SR) techniques for natural images have significant advantages

their adaptation to nano-CT remains challenged by dataset scarcity and stringent reconstruction accuracy requirements.

Purpose

This study aims to develop a dedicated super-resolution reconstruction network for synchrotron radiation nano-CT images to enhance the clarity and detail restoration of low-quality CT images and investigate its efficacy in optimizing downstream tasks such as crack segmentation.

Methods

Firstly

a Transformer-based U-shaped symmetric network for SR (UTSR) was proposed

integrating a Double Convolutional Feedforward Network (DCFFN) and a Grouped Multi-scale Window Self-Attention (GMSA) mechanism to achieve efficient reconstruction through multi-level feature extraction and hierarchical processing. Then

a transfer learning strategy was adopted

leveraging natural image datasets for pre-training and fine-tuning the model with nano-CT data from the Shanghai Synchrotron Radiation Facility (SSRF) to address dataset scarcity. Finally

a Sobel edge loss function was introduced to prioritize texture preservation

and a two-stage training framework (general image pre-training and nano-CT fine-tuning) was implemented to optimize model performances in terms of Natural Image Quality Evaluator (NIQE)

Learned Perceptual Image Patch Similarity (LPIPS)

Deep Image Structure and Texture Similarity (DISTS)

Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM).

Results

Comparison results show that UTSR demonstrates superior performance on both simulated and nano-CT datasets: it achieves lower NIQE (9.38) and LPIPS (0.312) scores compared to SwinIR and Real-ESRGAN

alongside reduced computational complexity (45.72G FLOPs). When applied to crack segmentation

UTSR-processed images attain an accuracy of 99.3%

with a 24.5% improvement in recall and a 19.1% increase in F1 Score over original images. Ablation experiments confirm the effectiveness of the DCFFN module

where its combination with GMSA further reduces NIQE to 10.99.

Conclusions

The UTSR network effectively addresses the challenges of low-quality synchrotron radiation nano-CT images and scarce datasets through its innovative architecture and transfer learning strategy

providing a robust preprocessing solution for microstructural analysis

hence expands the application of deep learning-based super-resolution in scientific imaging

offering substantial academic and engineering value.

关键词

Keywords

references

袁清习 , 邓彪 , 关勇 , 等 . 同步辐射纳米成像技术的发展与应用 [J ] . 物理 , 2019 , 48 ( 4 ): 205 – 218 . DOI: 10.7693/wl20190401 http://dx.doi.org/10.7693/wl20190401 .

YUAN Qingxi , DENG Biao , GUAN Yong , et al . Novel developments and applications of nanoscale synchrotron radiation microscopy [J ] . Physics , 2019 , 48 ( 4 ): 205 – 218 . DOI: 10.7693/wl20190401 http://dx.doi.org/10.7693/wl20190401 .

邢彦军 , 高若阳 , 张玲 , 等 . 基于多项式回归与线性插值的全场纳米谱学成像背景序列预测 [J ] . 核技术 , 2024 , 47 ( 3 ): 030102 . DOI: 10.11889/j.0253-3219.2024.hjs.47.030102 http://dx.doi.org/10.11889/j.0253-3219.2024.hjs.47.030102 .

XING Yanjun , GAO Ruoyang , ZHANG Ling , et al . Background sequence prediction for TXM-XANES based on polynomial regression and linear interpolation [J ] . Nuclear Techniques , 2024 , 47 ( 3 ): 030102 . DOI: 10.11889/j.0253-3219.2024.hjs.47.030102 http://dx.doi.org/10.11889/j.0253-3219.2024.hjs.47.030102 .

谢红兰 , 邓彪 , 杜国浩 , 等 . 上海光源X射线成像及其在材料科学上的应用研究进展 [J ] . 失效分析与预防 , 2021 , 16 ( 1 ): 46 – 59+69 . DOI: 10.3969/j.issn.1673-6214.2021.01.005 http://dx.doi.org/10.3969/j.issn.1673-6214.2021.01.005 .

XIE Honglan , DENG Biao , DU Guohao , et al . Development of X-ray imaging methodology and its applications on material science at Shanghai Synchrotron Radiation Facility [J ] . Failure Analysis and Prevention , 2021 , 16 ( 1 ): 46 – 59+69 . DOI: 10.3969/j.issn.1673-6214.2021.01.005 http://dx.doi.org/10.3969/j.issn.1673-6214.2021.01.005 .

仇正杰 , 李可 , 谢红兰 , 等 . 20 Hz高时空分辨X射线单色光动态显微CT研究 [J ] . 核技术 , 2023 , 46 ( 7 ): 070101 . DOI: 10.11889/j.0253-3219.2023.hjs.46.070101 http://dx.doi.org/10.11889/j.0253-3219.2023.hjs.46.070101 .

QIU Zhengjie , LI Ke , XIE Honglan , et al . Study of 20 Hz high spatial-temporal resolution monochromatic X-ray dynamic micro-CT [J ] . Nuclear Techniques , 2023 , 46 ( 7 ): 070101 . DOI: 10.11889/j.0253-3219.2023.hjs.46.070101 http://dx.doi.org/10.11889/j.0253-3219.2023.hjs.46.070101 .

许明伟 , 薛艳玲 , 陈荣昌 , 等 . 基于相位衬度成像的X射线生物特征识别仪 [J ] . 核技术 , 2021 , 44 ( 8 ): 080202 . DOI: 10.11889/j.0253-3219.2021.hjs.44.080202 http://dx.doi.org/10.11889/j.0253-3219.2021.hjs.44.080202 .

XU Mingwei , XUE Yanling , CHEN Rongchang , et al . A biometrics recognition instrument using X-ray phase contrast imaging for biosafety inspection [J ] . Nuclear Techniques , 2021 , 44 ( 8 ): 080202 . DOI: 10.11889/j.0253-3219.2021.hjs.44.080202 http://dx.doi.org/10.11889/j.0253-3219.2021.hjs.44.080202 .

苏博 , 陶芬 , 李可 , 等 . 同步辐射纳米CT图像配准方法研究 [J ] . 物理学报 , 2021 , 70 ( 16 ): 53 – 67 . DOI: 10.7498/aps.70.20210156 http://dx.doi.org/10.7498/aps.70.20210156 .

SU Bo , TAO Fen , LI Ke , et al . Image alignment for synchrotron radiation based X-ray nano-CT [J ] . Acta Physica Sinica , 2021 , 70 ( 16 ): 53 – 67 . DOI: 10.7498/aps.70.20210156 http://dx.doi.org/10.7498/aps.70.20210156 .

Dong C , Loy C C , He K M , et al . Learning a deep convolutional network for image super-resolution [C ] . Computer Vision – ECCV 2014. Cham : Springer International Publishing , 2014 : 184 – 199 . DOI: 10.1007/978-3-319-10593-2_13 http://dx.doi.org/10.1007/978-3-319-10593-2_13 .

Kim J , Lee J K , Lee K M . Accurate image super-resolution using very deep convolutional networks [C ] . Las Vegas, NV, USA : 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2016 : 1646 – 1654 . DOI: 10.1109/CVPR.2016.182 http://dx.doi.org/10.1109/CVPR.2016.182 .

Lim B , Son S , Kim H , et al . Enhanced deep residual networks for single image super-resolution [C ] . Honolulu, HI, USA : 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) , 2017 : 1132 – 1140 . DOI: 10.1109/CVPRW.2017.151 http://dx.doi.org/10.1109/CVPRW.2017.151 .

Kim J , Lee J K , Lee K M . Deeply-recursive convolutional network for image super-resolution [C ] . Las Vegas, NV, USA : 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27- 30 , 2016. IEEE , 2016: 1637 – 1645 . DOI: 10.1109/CVPR.2016.181 http://dx.doi.org/10.1109/CVPR.2016.181 .

Tai Y , Yang J , Liu X M . Image super-resolution via deep recursive residual network [C ] . Honolulu, HI, USA : 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2017 : 2790 – 2798 . DOI: 10.1109/CVPR.2017.298 http://dx.doi.org/10.1109/CVPR.2017.298 .

Zhang Y L , Li K P , Li K , et al . Image super-resolution using very deep residual channel attention networks [C ] . Cham : Springer International Publishing: Computer Vision – ECCV , 2018 : 294 – 310 . DOI: 10.1007/978-3-030-01234-2_18 http://dx.doi.org/10.1007/978-3-030-01234-2_18 .

Lai W S , Huang J B , Ahuja N , et al . Deep Laplacian pyramid networks for fast and accurate super-resolution [C ] . Honolulu, HI, USA : 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2017 : 5835 – 5843 . DOI: 10.1109/CVPR.2017.618 http://dx.doi.org/10.1109/CVPR.2017.618 .

Haris M , Shakhnarovich G , Ukita N . Deep back-projection networks for super-resolution [C ] . Salt Lake City, UT, USA : 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18- 23 , 2018 : 1664 – 1673 . DOI: 10.1109/CVPR.2018.00179 http://dx.doi.org/10.1109/CVPR.2018.00179 .

Chen H T , Wang Y H , Guo T Y , et al . Pre-trained image processing transformer [C ] . Nashville, TN, USA : 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2021 : 12294 – 12305 . DOI: 10.1109/cvpr46437.2021.01212 http://dx.doi.org/10.1109/cvpr46437.2021.01212 .

Liang J Y , Cao J Z , Sun G L , et al . SwinIR: image restoration using swin transformer [C ] . Montreal, BC, Canada : 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) , 2021 : 1833 – 1844 . DOI: 10.1109/ICCVW54120.2021.00210 http://dx.doi.org/10.1109/ICCVW54120.2021.00210 .

Chen X Y , Wang X T , Zhou J T , et al . Activating more pixels in image super-resolution transformer [C ] . Vancouver, BC, Canada : 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2023 : 22367 – 22377 . DOI: 10.1109/CVPR52729.2023.02142 http://dx.doi.org/10.1109/CVPR52729.2023.02142 .

Chen Z , Zhang Y L , Gu J J , et al . Dual aggregation transformer for image super-resolution [C ] . Paris, France : 2023 IEEE/CVF International Conference on Computer Vision (ICCV) , 2023 : 12278 – 12287 . DOI: 10.1109/ICCV51070.2023.01131 http://dx.doi.org/10.1109/ICCV51070.2023.01131 .

Umehara K , Ota J , Ishida T . Application of super-resolution convolutional neural network for enhancing image resolution in chest CT [J ] . Journal of Digital Imaging , 2018 , 31 ( 4 ): 441 – 450 . DOI: 10.1007/s10278-017-0033-z http://dx.doi.org/10.1007/s10278-017-0033-z .

Zhao B C , Saxena N , Hofmann R , et al . Enhancing resolution of micro-CT images of reservoir rocks using super resolution [J ] . Computers & Geosciences , 2023 , 170 : 105265 . DOI: 10.1016/j.cageo.2022.105265 http://dx.doi.org/10.1016/j.cageo.2022.105265 .

Ahuja V R , Gupta U , Rapole S R , et al . Siamese-SR: a Siamese super-resolution model for boosting resolution of digital rock images for improved petrophysical property estimation [J ] . IEEE Transactions on Image Processing , 2022 , 31 : 3479 – 3493 . DOI: 10.1109/TIP.2022.3172211 http://dx.doi.org/10.1109/TIP.2022.3172211 .

Guan Y , Zhang S , Wang H W , et al . Multifunctional GAN-based optimization for X-ray tomography under different conditions [J ] . Optics Express , 2024 , 32 ( 23 ): 4 0767– 40782 . DOI: 10.1364/OE.527366 http://dx.doi.org/10.1364/OE.527366 .

Shi W Z , Caballero J , Huszár F , et al . Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network [C ] . Las Vegas, NV, USA : 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2016 : 1874 – 1883 . DOI: 10.1109/CVPR.2016.207 http://dx.doi.org/10.1109/CVPR.2016.207 .

Zhang X D , Zeng H , Guo S , et al . Efficient long-range attention network forImage super-resolution [C ] . Cham : Springer Nature Switzerland: Computer Vision – ECCV , 2022 : 649 – 667 . DOI: 10.1007/978-3-031-19790-1_39 http://dx.doi.org/10.1007/978-3-031-19790-1_39 .

Agustsson E , Timofte R . NTIRE 2017 challenge on single image super-resolution: dataset and study [C ] . Honolulu, HI, USA : 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) , 2017 : 1122 – 1131 . DOI: 10.1109/CVPRW.2017.150 http://dx.doi.org/10.1109/CVPRW.2017.150 .

Timofte R , Agustsson E , Van Gool L , et al . NTIRE 2017 challengeon single image super-resolution: methodsand results [C ] . Honolulu, HI, USA : Proceedings of the 2017 IEEE/CVF Conferenceon Computer Visionand Pattern Recognition Workshops (CVPRW). IEEE , 2017 : 1110 – 1121 . DOI: 10.1109/CVPRW.2017.149 http://dx.doi.org/10.1109/CVPRW.2017.149 .

Wang X T , Yu K , Dong C , et al . Recovering realistic texture in image super-resolution by deep spatial feature transform [C ] . Salt Lake City, UT, USA : 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2018 : 606 – 615 . DOI: 10.1109/CVPR.2018.00070 http://dx.doi.org/10.1109/CVPR.2018.00070 .

Zhang L , Tao F , Wang J , et al . The 3D nanoimaging beamline at SSRF [J ] . Nuclear Science and Techniques , 2023 , 34 ( 12 ): 201 . DOI: 10.1007/s41365-023-01347-4 http://dx.doi.org/10.1007/s41365-023-01347-4 .

Tao F , Wang J , Du G H , et al . Full-field hard X-ray nano-tomography at SSRF [J ] . Journal of Synchrotron Radiation , 2023 , 30 ( Pt 4 ): 815 – 821 . DOI: 10.1107/S1600577523003168 http://dx.doi.org/10.1107/S1600577523003168 .

Zhang L , Tao F , Du G H , et al . In-house design hard X-ray transmission microscope at SSRF [J ] . Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment , 2023 , 1057 : 168781 . DOI: 10.1016/j.nima.2023.168781 http://dx.doi.org/10.1016/j.nima.2023.168781 .

Zhang K , Liang J Y , Van Gool L , et al . Designing a practical degradation model for deep blind image super-resolution [C ] . Montreal, QC, Canada : 2021 IEEE/CVF International Conference on Computer Vision (ICCV), October 10- 17 , 2021 : 4771 – 4780 . DOI: 10.1109/ICCV48922.2021.00475 http://dx.doi.org/10.1109/ICCV48922.2021.00475 .

Mittal A , Soundararajan R , Bovik A C . Making a "completely blind" image quality analyzer [J ] . IEEE Signal Processing Letters , 2013 , 20 ( 3 ): 209 – 212 . DOI: 10.1109/LSP.2012.2227726 http://dx.doi.org/10.1109/LSP.2012.2227726 .

Zhang R , Isola P , Efros A A , et al . The unreasonable effectiveness of deep features as a perceptual metric [C ] . Salt Lake City, UT, USA : 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 18- 23 , 2018 : 586 – 595 . DOI: 10.1109/CVPR.2018.00068 http://dx.doi.org/10.1109/CVPR.2018.00068 .

Ding K Y , Ma K D , Wang S Q , et al . Image quality assessment: unifying structure and texture similarity [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2022 , 44 ( 5 ): 2567 – 2581 . DOI: 10.1109/TPAMI.2020.3045810 http://dx.doi.org/10.1109/TPAMI.2020.3045810 .

Czimmermann T , Ciuti G , Milazzo M , et al . Visual-based defect detection and classification approaches for industrial applications-a SURVEY [J ] . Sensors , 2020 , 20 ( 5 ): 1459 . DOI: 10.3390/s20051459 http://dx.doi.org/10.3390/s20051459 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

纳米CT样品漂移在线自动校正研究

用同步辐射X射线相反衬成像研究PM_2.5诱导的大鼠肺炎

快速冲击磁铁系统的研制