Abstract
Low-dose CT (LDCT) is a feasible method to reduce the radiation dose to the patient. However, both artifacts and noise appear in the reconstructed images, reducing the clarity of the images. To remove artifacts and noise and improve image quality, a deep learning method based on edge prior and high-frequency sensitive fusion network (EHSFN) is proposed. The EHSFN first decomposes the LDCT image into high-frequency (HF) and low-frequency (LF) parts for decoupling the artifact noise from the LF part. And then a trainable edge prior is introduced to enrich tissue edge information and guide the extraction of tissue structure feature in HF part. To fully extract and fuse edge and HF information, a multi-stage feature extraction module and a multi-level fusion module are designed. Besides, edge loss, HF loss and reconstruction loss are applied to guide the training of the network. Experimental results show that the proposed network can not only effectively remove noise and artifacts but also retain more texture and tissue details, compared with the existing network.
Similar content being viewed by others
Availability of data and materials
We used a clinical dataset, which has been authorized by Mayo Clinic for “The 2016 NIH-AAPM-Mayo Clinic Low Dose CT Grand Challenge”. [Online], http://www.aapm.org/GrandChallenge/LowDoseCT.
References
Jiang, H.: Adaptive streak artifact reduction in computed tomography resulting from excessive x-ray photon noise. Med. Phys. 25(11), 2139–2147 (1998)
Cui, X.Y., Zhang, Q., Shangguan, H., et al.: The adaptive sinogram restoration algorithm based on anisotropic diffusion by energy minimization for low-dose X-ray CT. Optik 125(5), 1694–1697 (2014)
Beister, M., Kolditz, D., Kalender, W.A.: Iterative reconstruction methods in X-ray CT. Phys. Med. 28(2), 94–108 (2012)
Chen, Y., Yang, Z., Hu, Y.N., et al.: Thoracic low-dose CT image processing using an artifact suppressed large-scale nonlocal means. Phys. Med. Biol. 57(9), 2667–2688 (2012)
Chen, H., Zhang, Y., Kalra, M.K., et al.: Low-dose CT with a residual encoder-decoder convolutional neural network. IEEE Trans. Med. Imaging 36(12), 2524–2535 (2017)
Shan, H., et al.: 3-D convolutional encoder-decoder network for low-dose CT via transfer learning from a 2-D trained network. IEEE Trans. Med. Imaging 37(6), 1522–1534 (2018)
Yang, L.L., Shangguan, H., Zhang, X., et al.: High-frequency sensitive generative adversarial network for low-dose CT image denoising. IEEE access 8, 930–943 (2019)
Jiao, F.Y., Gui, Z.G., Liu, Y., et al.: Low-dose CT image denoising via frequency division and encoder-dual decoder GAN. Signal Image Video Process. 15(8), 1907–1915 (2021)
Bai, Y., Zhao, H., Zhang, S., et al.: Multi-scale hierarchy feature fusion generative adversarial network for low-dose CT denoising. In: 2020 9th International Conference on Bioinformatics and Biomedical Science (2020) https://doi.org/10.1145/3431943.343228610.
Chen, L. L., Gou, S. P., Yao, Y., et al.: Denoising of low dose CT image with context-based BM3D. In: 2016 IEEE Region 10 Conference (TENCON). pp. 682–685 (2016)
Chen, Y., Yin, X.D., Shi, L.Y., et al.: Improving abdomen tumor low-dose CT images using a fast dictionary learning based processing. Phys. Med. Biol. 58(16), 5803–5820 (2013)
Chen, Y., Shi, L., Feng, Q., et al.: Artifact suppressed dictionary learning for low-dose CT image processing. IEEE Trans. Med. Imaging 33(12), 2271–2292 (2014)
Cui, X.Y., GuiZhang, Z.G.Q., et al.: Learning-based artifact removal via image decomposition for low-dose CT image procession. IEEE Trans. Nucl. Sci. 63, 1860–1873 (2016)
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 (2017)
Liu, P., Fang, R.: SDCNet: Smoothed dense-convolution network for restoring low-dose cerebral CT perfusion. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (2018)
Kang, E., Yoo, J., Ye, J. C.: Wavelet residual network for low-dose CT via deep convolutional framelets. (2017). https://doi.org/10.48550/arXiv.1707.09938
Xia, W., Lu, Z., Huang, Y., et al.: CT reconstruction with PDF: parameter-dependent framework for data from multiple geometries and dose levels. IEEE Trans. Med. Imaging 40(11), 3065–3076 (2021)
Bai, T., Wang, B., Nguyen, D., et al.: Probabilistic self-learning framework for low-dose CT denoising. Med. Phys. 48(5), 2258–2270 (2021)
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)
You, C., Yang, Q., Shan, H., et al.: Structurally-sensitive multi-scale deep neural network for low-dose CT denoising. IEEE Access 20, 41839–41855 (2018)
Yi, X., Babyn, P.: Sharpness-aware low-dose CT denoising using conditional generative adversarial network. J. Digit. Imaging 31(5), 655–669 (2018)
Huang, Z., Zhang, J., Zhang, Y., et al.: DU-GAN: Generative adversarial networks with dual-domain U-Net-based discriminators for low-dose CT denoising. IEEE Trans. Instrum. Meas. 71, 1–12 (2021)
Han, Z.F., Shangguan, H., Zhang, X., et al.: A dual-encoder-single-decoder based low-dose CT denoising Network. IEEE J. Biomed. Health Inform. 26(7), 3251–3260 (2022)
Gu, J., Ye, J.C.: AdaIN-based tunable CycleGAN for efficient unsupervised low-dose CT denoising. IEEE Trans. Comput. Imaging 7, 73–85 (2021)
Zhang, Z., Yu, L., Liang, X., et al.: TransCT: dual-path transformer for low dose computed tomography. In: International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), Cham, 55–64 (2021)
Gholizadeh-Ansari, M., Alirezaie, J., Babyn, P.: Deep learning for low-dose CT denoising using perceptual loss and edge detection layer. J. Digit. Imaging 33(2), 504–515 (2020)
Liang, T., Jin, Y., Li, Y., et al.: Edcnn: Edge enhancement-based densely connected network with compound loss for low-dose ct denoising. In: 2020 15th IEEE International Conference on Signal Processing 1, 193–198 (2020)
Luthra, A., Sulakhe, H., Mittal, T., et al.: Eformer: Edge enhancement based transformer for medical image denoising. (2021). https://doi.org/10.48550/arXiv.2109. p. 08044.
Zhang, X., Han, Z.F., Shangguan, H., et al.: Artifact and detail attention generative adversarial networks for low-dose CT denoising. IEEE Trans. Med. Imaging 40(12), 3901–3918 (2021)
Fang, F., Li, J., Yuan, Y., et al.: Multilevel edge features guided network for image denoising. IEEE Trans. Neural Netw. Learn. Syst. 32(9), 3956–3970 (2020)
Jiang, K., Wang, Z.Y., Yi, P., et al.: Multi-scale progressive fusion network for single image deraining. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (2020)
Jiang, K., Wang, Z.Y., Yi, P., et al.: Multi-scale hybrid fusion network for single image deraining. IEEE Trans. Neural Netw. Learn. Syst. (2021). https://doi.org/10.1109/TNNLS.2021.3112235
Zamir, S. W., Arora, A., Khan S., et al.: Learning Enriched Features for Real Image Restoration and Enhancement. https://arxiv:2003.06792v2 (2020)
AAPM, Low dose CT grand challenge. [Online]. http://ww w.aapm.org/GrandChallenge/LowDoseCT (2017)
Acknowledgements
This work was supported in part by the national natural science foundation of China (No. 62001321), in part by the natural science foundation of Shanxi province (No. 201901D111261, No. 20210302 1224274, No.202103021224265), in part by research project supported by Shanxi scholarship council of China (2022-163) and the Taiyuan University of Science and Technology doctoral promoter (20212033).
Author information
Authors and Affiliations
Contributions
XC conceived the study design and wrote the manuscript, YG performed the experiments and the data analysis, WH debugged the code, all authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Ethical Approval
Not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Cui, X., Guo, Y., Hao, W. et al. Low-dose CT image denoising based on edge prior and high-frequency sensitive feature fusion network. SIViP 17, 3387–3396 (2023). https://doi.org/10.1007/s11760-023-02560-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-023-02560-9