Skip to main content
SpringerLink
Log in

Unpaired low-dose CT denoising via an improved cycle-consistent adversarial network with attention ensemble

  • Original article
  • Published:
The Visual Computer Aims and scope Submit manuscript

Abstract

Many deep learning-based approaches have been authenticated well performed for low-dose computed tomography (LDCT) image postprocessing. Unfortunately, most of them highly depend on well-paired datasets, which are difficult to acquire in clinical practice. Therefore, we propose an improved cycle-consistent adversarial networks (CycleGAN) to improve the quality of LDCT images. We employ a UNet-based network with attention gates ensembled as the generator, which could adaptively stress salient features which is useful for the denoising task. By doing so, the proposed network could enable the decoder to acquire available semantic features from the encoder with emphasis, thereby improving its performance. Then, perceptual loss found on the visual geometry group (VGG) is drawn into the cycle consistency loss to elevate the visual effect of denoised images to that of standard-dose computed tomography images as far as possible. Moreover, we raise an ameliorative adversarial loss based on the least square loss. In particular, the Lipschitz constraint is added to the objective function of the discriminator, while total variation is added to that of the generator, to further enhance the denoising capability of the network. The proposed method is trained and tested on a public dataset named ‘Lung-PET-CT-Dx’ and a real clinical dataset. Results show that the proposed method outperforms the comparative methods and even performs comparably results to that of an approach based on paired datasets in terms of quantitative scores and visual sense.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

References

  1. Messerli-Odermatt, O., Serrallach, B., Gubser, M., et al.: Chest X-ray dose equivalent low-dose CT with tin filtration: potential role for the assessment of Pectus Excavatum. Acad. Radiol. 27(5), 644–650 (2020)

    Google Scholar 

  2. Brenner, D.J., Hall, E.J.: Computed tomography–an increasing source of radiation exposure. N. Engl. J. Med. 357(22), 2277–2284 (2007)

    Google Scholar 

  3. Jin, Y., Jiang, Z., Huang, M., et al.: Low-dose CT image restoration based on noise prior regression network. The Visual Computer. (2022).

  4. Naidich, D.P., Marshall, C.H., Gribbin, C., et al.: Low-dose CT of the lungs: preliminary observations. Radiology 175(3), 729–731 (1990)

    Google Scholar 

  5. Yang, Q., Yan, P., Zhang, Y., et al.: Low-dose CT image denoising using a generative adversarial network with wasserstein distance and perceptual loss. IEEE Trans. Med. Imaging 37(6), 1348–1357 (2018)

    Google Scholar 

  6. Wang, J., Li, T., Lu, H., et al.: Penalized weighted least-squares approach to sinogram noise reduction and image reconstruction for low-dose x-ray computed tomography. IEEE Trans. Med. Imaging 25(10), 1272–1283 (2006)

    Google Scholar 

  7. Ma, Y., Ren, Y., Feng, P., et al.: Sinogram denoising via attention residual dense convolutional neural network for low-dose computed tomography. Nucl. Sci. Tech. 32(4), 41 (2021)

    Google Scholar 

  8. Smith, P.R., Peters, T.M., Bates, R.H.T.: Image reconstruction from finite numbers of projections. J. Phys. A: Math. Nucl. Gen. 6(3), 361–382 (1973)

    MATH  Google Scholar 

  9. Jang, S., Kim, S., Kim, M., et al.: Head motion correction based on filtered backprojection in helical CT scanning. IEEE Trans. Med. Imaging 39(5), 1636–1645 (2020)

    Google Scholar 

  10. Zhang, T., Xing, Y., Zhang, L., et al.: Stationary computed tomography with source and detector in linear symmetric geometry: direct filtered backprojection reconstruction. Med. Phys. 47(5), 2222–2236 (2020)

    Google Scholar 

  11. Kachelrie, M., Watzke, O., Kalender, W.A.: Generalized multi-dimensional adptive filtering for conventionnal and spiral single-slice. Multi-slice and Cone-beam. Med. Phys. 28(4), 475–490 (2001)

    Google Scholar 

  12. Yu, L., Manduca, A., Trzasko, J.D., et al.: Sinogram smoothing with bilateral filtering for low-dose. Proc. SPIE Int. Soc. Opt. Eng. 6913, 691313–691325 (2008)

    Google Scholar 

  13. Wang, Y., Li, W., Fu, S., et al.: Adaptive filtering with self-similarity for low-dose CT imaging. Optik 126(24), 4949–4953 (2015)

    Google Scholar 

  14. Pathak, Y., Arya, K.V., Tiwari, S.: Fourth-order partial differential equations based anisotropic diffusion model for low-dose CT images. Mod. Phys. Lett. B 32(25), 1850300 (2018)

    MathSciNet  Google Scholar 

  15. Li, T., Li, X., Wang, J., et al.: Nonlinear sinogram smoothing for low-dose X-ray CT. IEEE Trans. Nucl. Sci. 51(5), 2505–2513 (2004)

    Google Scholar 

  16. Zhang, Y., Zhang, J., Lu, H.: Statistical sinogram smoothing for low-dose ct with segmentation-based adaptive filtering. IEEE Trans. Nucl. Sci. 57(5), 2587–2598 (2010)

    Google Scholar 

  17. Zhang, Q., Gui, Z., Chen, Y., et al.: Bayesian sinogram smoothing with an anisotropic diffusion weighted prior for low-dose X-ray computed tomography. Optik 124(17), 2811–2816 (2013)

    Google Scholar 

  18. Gao, Y., Liang, Z., Xing, Y., et al.: Characterization of tissue-specific pre-log bayesian CT reconstruction by texture–dose relationship. Med. Phys. 47(10), 5032–5047 (2020)

    Google Scholar 

  19. Wang, W., Xia, X., He, C., et al.: An end-to-end deep network for reconstructing CT images directly from sparse sinograms. IEEE Trans. Comput. Imag. 6, 1548–1560 (2020)

    MathSciNet  Google Scholar 

  20. Shi, Z., Li, H., Cheng, M., et al.: A projection data denoising method based on SDN-GMM network for low-dose dual-energy computed tomography. J Tianjin Univ (Sci Technol). 54(9), 899–906 (2021)

    Google Scholar 

  21. Huang, Y., Zhu, H., Duan, X., et al.: GapFill-recon net: a cascade network for simultaneously PET gap filling and image reconstruction. Comput. Meth. Progr. Biomed. 208, 106271 (2021)

    Google Scholar 

  22. Shangguan, H., Zhang, Q., Liu, Y., et al.: Low-dose CT Statistical Iterative Reconstruction via Modified MRF Regularization. Comput. Meth. Progr. Biomed. 123, 129–141 (2016)

    Google Scholar 

  23. Sidky, E.Y., Pan, X.: Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization. Phys. Med. Biol. 53(17), 4777–4807 (2008)

    Google Scholar 

  24. Chen, M., Pu, Y., Bai, Y.: Low-dose ct image denoising using residual convolutional network with fractional TV loss. Neurocomputing 452, 510–520 (2021)

    Google Scholar 

  25. Góes, D.A., Mascarenhas, N.D.A.: Poisson denoising under a bayesian nonlocal approach using geodesic distances with low-dose CT applications. Digital Signal Process. 106, 102835 (2020)

    Google Scholar 

  26. Chen, Y., Yin, X., Shi, L., et al.: Improving abdomen tumor low-dose CT images using a fast dictionary learning based processing. Phys. Med. Biol. 58(16), 5803–5820 (2013)

    Google Scholar 

  27. Cui, X., Gui, Z., Zhang, Q., et al.: Learning-based artifact removal via image decomposition for low-dose CT image processing. IEEE Trans. Nucl. Sci. 63(3), 1860–1873 (2016)

    Google Scholar 

  28. Gu, S., Zhang, L., Zuo, W., et al.: Weighted Nuclear Norm Minimization with Application to Image Denoising. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Columbus, OH, USA (2014)

  29. Yuan, H., Zheng, C.: Adaptive rendering based on robust principal component analysis. Vis. Comput. 34, 551–562 (2018)

    Google Scholar 

  30. Wang, S., Xia, K., Wang, L., et al.: Improved RPCA method via non-convex regularisation for image denoising. IET Signal Proc. 14(5), 269–277 (2020)

    Google Scholar 

  31. Yahya, A.A., Tan, J., Su, B., et al.: BM3D image denoising algorithm based on an adaptive filtering. Multimedia Tools Appl. 79(27), 20391–20427 (2020)

    Google Scholar 

  32. Lyu, Q., Yang, C., Gao, H., et al.: Technical note: iterative megavoltage CT (MVCT) reconstruction using block-matching 3D-transform (BM3D) regularization. Med. Phys. 45(6), 2603–2610 (2018)

    Google Scholar 

  33. Zhao, T., Hoffman, J., McNitt-Gray, M., et al.: Ultra-low-dose CT image denoising using modified BM3D scheme tailored to data statistics. Med. Phys. 46(1), 190–198 (2019)

    Google Scholar 

  34. He, Y., Zeng, L., Yu, W., et al.: Noise suppression-guided image filtering for Low-SNR CT reconstruction. Med. Biol. Eng. Compu. 58(11), 2621–2629 (2020)

    Google Scholar 

  35. Lecun, Y., Bengio, Y., Hinton, G.: Deep learwning. Nature 521(7553), 436–444 (2015)

    Google Scholar 

  36. Zhuang, H., Zhang, J., Liao, F.: A systematic review on application of deep learning in digestive system image processing. The Visual Computer. (2021).

  37. Chen, H., Zhang, Y., Zhang, W., et al.: Low-dose CT Denoising with Convolutional Neural Network. In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), Melbourne, VIC, Australia (2017)

  38. Chen, H., Zhang, Y., Kalra, M.K., et al.: Low dose CT with a residual encoder decoder convolutional neural network. IEEE Trans. Med. Imag. 36(12), 2524–2535 (2017)

    Google Scholar 

  39. Yu, H., Liu, D., Shi, H., et al.: Computed Tomography Super-resolution Using Convolutional Neural Networks. In: IEEE International Conference on Image Processing (ICIP), Beijing, China (2017)

  40. Jiang, X., Jin, Y., Yao, Y.: Low-dose CT lung images denoising based on multiscale parallel convolution neural network. Vis. Comput. 37, 2419–2431 (2021)

    Google Scholar 

  41. Li, S., Li, Q., Li, R., et al.: An adaptive self-guided wavelet convolutional neural network with compound loss for low-dose CT denoising. Biomed. Signal Process. Control 75, 103543 (2022)

    Google Scholar 

  42. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial networks. Adv. Neural. Inf. Process. Syst. 3(11), 2672–2680 (2014)

    Google Scholar 

  43. Wolterink, J.M., Leiner, T., Viergever, M.A., et al.: Generative adversarial networks for noise reduction in low-dose CT. IEEE Trans. Med. Imag. 36(12), 2536–2545 (2017)

    Google Scholar 

  44. Li, Z., Shi, W., Xing, Q., et al.: Low-dose CT image denoising with improving WGAN and hybrid loss function. Comput. Math. Methods Med. 2021, 2973108 (2021)

    Google Scholar 

  45. Huang, Z., Liu, X., Wang, R., et al.: Considering anatomical prior information for low-dose CT image enhancement using attribute-agumented wasserstein generative adversarial networks. Neurocomputing 428, 104–115 (2021)

    Google Scholar 

  46. Bayoudh, K., Knani, R., Hamdaoui, F. et al.: A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets. The Visual Computer. (2021).

  47. Huang, Z., Chen, Z., Zhang, Q., et al.: CaGAN: a cycle-consistent generative adversarial network with attention for low-dose CT imaging. IEEE Trans. Comput. Imag. 6, 1203–1218 (2020)

    MathSciNet  Google Scholar 

  48. Li, M., Hsu, W., Xie, X., et al.: SACNN: self-attention convolutional neural network for low-dose CT denoising with self-supervised perceptual loss network. IEEE Trans. Med. Imag 39(7), 2289–2301 (2020)

    Google Scholar 

  49. Qiu, D., Cheng, Y., Wang, X., et al.: Multi-window back-projection residual networks for reconstructing COVID-19 CT super-resolution images. Comput. Methods Progr Biomed. 200, 105934 (2021)

    Google Scholar 

  50. Zhu, J., Park, T., Isola, P., et al.: Unpaired Image-to-Image Translation Using Cycle-consistent Adversarial Networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy (2017).

  51. Yi, Z., Zhang, H., Tan, P., et al.: DualGAN: Unsupervised Dual Learning for Image-to-Image Translation. In: 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy (2017).

  52. Kang, E., Koo, H.J., Yang, D.H., et al.: Cycle-consistent adversarial denoising network for multiphase coronary CT angiography. Med. Phys. 46(2), 550–562 (2018)

    Google Scholar 

  53. Tang, C., Li, J., Wang, L., et al.: Unpaired low-dose CT denoising network based on cycle-consistent generative adversarial network with prior image information. Comput. Math. Methods Med. 2019(12), 1–11 (2019)

    MATH  Google Scholar 

  54. You, C., Li, G., Zhang, Y., et al.: CT super-resolution GAN constrained by the identical, residual, and cycle learning ensemble (GAN-CIRCLE). IEEE Trans. Med. Imag 39(1), 188–203 (2019)

    Google Scholar 

  55. Gu, J., Yang, T., Ye, J., et al.: CycleGAN denoising of extreme low-dose cardiac CT using wavelet-assisted noise disentanglement. Med. Image Anal. 74, 102209 (2021)

    Google Scholar 

  56. Yang, Z., Yan, C., Chen, H.: Unpaired Low-Dose CT Denoising using Conditional GAN with Structural Loss. 2021 International Conference on Wireless Communications and Smart Grid (ICWCSG), Hangzhou, China (2021).

  57. Yin, Z., Xia, K., He, Z., et al.: Unpaired image denoising via wasserstein GAN in low-dose CT image with multi-perceptual loss and fidelity loss. Symmetry. 13(1), 126 (2021)

    Google Scholar 

  58. Oktay, O., Schlemper, J., Folgoc, L. L., et al.: Attention U-Net: Learning Where to Look for the Pancreas. arXiv preprint arXiv:1804.03999 (2018).

  59. Isola, P., Zhu, J., Zhou, T., et al.: Image-to-Image Translation with Conditional Adversarial Networks. In: Conference on Computer Vision & Pattern Recognition (CVPR), Los Alamitos, CA, USA (2017).

  60. Gulrajani, I., Ahmed, F., Arjovsky, M., et al.: Improved Training of Wasserstein GANs. arXiv preprint arXiv: 1704.00028 (2017).

  61. Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance Normalization: the Missing Ingredient for Fast Stylization. arXiv preprint arXiv:1607.08022 (2016).

  62. Mao, X., Li, Q., Xie, H., et al.: Least Squares Generative Adversarial Networks. In: 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy (2017).

  63. Zhu, S., Wang, J., Cai, Y.: Low-dose CT denoising algorithm based on improved CycleGAN. Acta Optica Sinica. 40(22), 22100021–22100029 (2020)

    Google Scholar 

  64. Li, P., Wang, S., Li, T., et al.: A large-scale CT and PET/CT dataset for lung cancer diagnosis. Cancer Imag. Arch. (2020). https://doi.org/10.7937/TCIA.2020.NNC2-0461

    Article  Google Scholar 

  65. Zeng, D., Huang, J., Bian, Z., et al.: A simple low-dose X-ray CT simulation from high-dose scan. IEEE Trans. Nucl. Sci. 62(5), 2226–2233 (2015)

    Google Scholar 

  66. Zhang, Y., Yi, B., Wu, C., et al.: Low-dose CT image denoising method based on convolutional neural network. Acta Optica Sinica. 38(4), 1–7 (2018)

    Google Scholar 

Download references

Funding

This study was funded by the National Natural Science Foundation of China (grant number NO. U1813222, NO. 42075129); Hebei Province Natural Science Foundation (grant number NO. E2021202179); Key Research and Development Project from Hebei Province (grant number NO. 19210404D, NO. 20351802D, NO. 21351803D); Beijing Natural Science Foundation (grant number NO. 4214062); and the Other Commissions Project of Beijing (grant number NO. Q6025001202001).

Author information

Authors and Affiliations

  1. School of Electronics and Information Engineering, Hebei University of Technology, Tianjin, 300401, China

    Zhixian Yin, Kewen Xia, Sijie Wang, Ziping He & Jiangnan Zhang

  2. Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China

    Baokai Zu

Authors
  1. Zhixian Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kewen Xia
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sijie Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ziping He
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jiangnan Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Baokai Zu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kewen Xia.

Ethics declarations

Conflict of interest

All the authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendices

Appendix

A denoising methods for medical images

See Table 10.

Table 10 Summary of denoising methods for medical images
Full size table

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yin, Z., Xia, K., Wang, S. et al. Unpaired low-dose CT denoising via an improved cycle-consistent adversarial network with attention ensemble. Vis Comput 39, 4423–4444 (2023). https://doi.org/10.1007/s00371-022-02599-8

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00371-022-02599-8

Keywords

Search

Navigation