SpringerLink
Log in

MDUNet: deep-prior unrolling network with multi-parameter data integration for low-dose computed tomography reconstruction

  • RESEARCH
  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

The goal of this study is to reconstruct a high-quality computed tomography (CT) image from low-dose acquisition using an unrolling deep learning-based reconstruction network with less computational complexity and a more generalized model. We propose a MDUNet: Multi-parameters deep-prior unrolling network that employs the cascaded convolutional and deconvolutional blocks to unroll the model-based iterative reconstruction within a finite number of iterations by data-driven training. Furthermore, the embedded data consistency constraint in MDUNet ensures that the input low-dose images and the low-dose sinograms are consistent as well as incorporate the physics imaging geometry. Additionally, multi-parameter training was employed to enhance the model's generalization during the training process. Experimental results based on AAPM Low-dose CT datasets show that the proposed MDUNet significantly outperforms other state-of-the-art (SOTA) methods quantitatively and qualitatively. Also, the cascaded blocks reduce the computational complexity with reduced training parameters and generalize well on different datasets. In addition, the proposed MDUNet is validated on 8 different organs of interest, with more detailed structures recovered and high-quality images generated. The experimental results demonstrate that the proposed MDUNet generates favorable improvement over other competing methods in terms of visual quality, quantitative performance, and computational efficiency. The MDUNet has improved image quality with reduced computational cost and good generalization which effectively lowers radiation dose and reduces scanning time, making it favorable for future clinical deployment.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Canada)

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

Data availability

The dataset used for this study is publicly available online, please refer to this link https://www.aapm.org/GrandChallenge/LowDoseCT/.

References

  1. NIH: Computed tomography (CT), National institute of health. (2022), Accesed September 26, 2022, from https://www.nibib.nih.gov/science-education/science-topics/computed-tomography-ct/

  2. Journy, N., et al.: Are the studies on cancer risk from CT scans biased by indication? Elements of answer from a large-scale cohort study in France. Br. J. Cancer 112(1), 185–193 (2015)

    Article  Google Scholar 

  3. Brink, J.A., Miller, D.L.: U.S. National diagnostic reference levels: closing the gap. Radiology 277(1), 3–6 (2015)

    Article  Google Scholar 

  4. Zhang, Z., Liang, X., Dong, X., **e, Y., Cao, G.: A sparse-view CT reconstruction method based on combination of densenet and deconvolution. IEEE Trans. Med. Imaging 37(6), 1407–1417 (2018)

    Article  Google Scholar 

  5. Mileto, A., Guimaraes, L.S., McCollough, C.H., Fletcher, J.G., Yu, L.: State of the art in abdominal CT: the limits of iterative reconstruction algorithms. Radiology 293(3), 491–503 (2019)

    Article  Google Scholar 

  6. Tian, C., et al.: Deep learning on image denoising: an overview. Neural Netw. 131, 251–275 (2020)

    Article  Google Scholar 

  7. Zhang, Z., et al.: Self-supervised CT super-resolution with hybrid model. Compt. Biol. Med. 138, 104775 (2021)

    Article  Google Scholar 

  8. Wang, H., et al.: InDuDoNet: an interpretable dual domain network for CT metal artifact reduction. In: de Bruijne, M., et al. (eds.) MICCAI 2021 LNCS, vol. 12906, pp. 107–118. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87231-1_11

    Chapter  Google Scholar 

  9. Ghani, M. U., Karl, W. C.: Deep learning-based sinogram completion for low-dose CT. In: 2018 IEEE 13th Image, video, and multidimensional signal processing workshop (IVMSP), pp. 1–5, (2018) https://doi.org/10.1109/IVMSPW.2018.8448403.

  10. Chen, H., et al.: Low-dose CT with a residual encoder-decoder convolutional neural network. IEEE Trans. Med. Imaging 36(12), 2524–2535 (2017)

    Article  Google Scholar 

  11. Yang, Q., 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)

    Article  Google Scholar 

  12. Jiao, F., et al.: A dual-domain CNN-based network for CT reconstruction. IEEE Access 9, 71091–71103 (2021)

    Article  Google Scholar 

  13. Wu, W., et al.: DRONE: Dual-domain residual-based optimization NEtwork for sparse-view CT reconstruction. IEEE Trans. Med. Imaging 40(11), 3002–3014 (2021)

    Article  Google Scholar 

  14. Monga, V., Li, Y., Eldar, Y.C.: Algorithm unrolling: interpretable, efficient deep learning for signal and image processing. IEEE Signal Process 38(2), 18–44 (2021)

    Article  Google Scholar 

  15. Adler, J., Öktem, O.: Learned primal-dual reconstruction. IEEE Trans. Med. Imaging 37(6), 1322–1332 (2018)

    Article  Google Scholar 

  16. Yang, Y., Sun, J., Li, H., Xu, Z.: ADMM-CSNet: a deep learning approach for image compressive sensing. IEEE Trans. Pattern Anal. 42(3), 521–538 (2020)

    Article  Google Scholar 

  17. Chen, H., et al.: LEARN: learned experts’ assessment-based reconstruction network for sparse-data CT. IEEE Trans. Med. Imaging 37(6), 1333–1347 (2018)

    Article  MathSciNet  Google Scholar 

  18. **a, W., et al.: MAGIC: manifold and graph integrative convolutional network for low-dose CT reconstruction. IEEE Trans. Med. Imaging 40(12), 2459–3472 (2021)

    Article  Google Scholar 

  19. Zeng, R., Lin, C.Y., Li, Q., Lu, J., Skopec, M., Fessler, J.A., Myers, K.: Performance of a deep learning-based CT image denoising method: generalizability over dose, reconstruction kernel and slice thickness. Med. Phys. 49(2), 836–853 (2021)

    Article  Google Scholar 

  20. Hadjiiski, L.M., Cha, K.H., Chan, H., Drukker, K., Morra, L., Näppi, J.J., Sahiner, B., Yoshida, H., Chen, Q., Deserno, T.M., Greenspan, H., Huisman, H.J., Huo, Z., Mazurchuk, R.V., Petrick, N.A., Regge, D., Samala, R.K., Summers, R.M., Suzuki, K., Tourassi, G.D., Vergara, D., Armato, S.G.: AAPM task group report 273: recommendations on best practices for AI and machine learning for computer-aided diagnosis in medical imaging. Med. Phys. 50(2), e1–e24 (2022)

    Google Scholar 

  21. Cormack, A.M.: Reconstruction of densities from their projections, with applications in radiological physics. Phys. Med. Biol. 18(2), 195–207 (1973). https://doi.org/10.1088/0031-9155/18/2/003

    Article  Google Scholar 

  22. Schofield, R., King, L., Tayal, U., Castellano, I., Stirrup, J., Pontana, F., Earls, J., Nicol, E.: Image reconstruction: Part 1—understanding filtered back projection, noise and image acquisition. J. Cardiovasc. Comput. Tomogr. 14(3), 219–225 (2020). https://doi.org/10.1016/j.jcct.2019.04.008

    Article  Google Scholar 

  23. Niu, et al.: Sparse-view x-ray CT reconstruction via total generalized variation regularization. Phys. Med. Biol. 59(12), 2997–3017 (2014)

    Article  Google Scholar 

  24. Roth, S. and Black, M. J.: Fields of experts: a framework for learning image priors, In: 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05), vol. 2, pp.860–867 (2005)

  25. Zhang, Y. et al.: LEARN++: Recurrent dual-domain reconstruction network for compressed sensing CT (2020). ar**v preprint ar**v:2012.06983

  26. Zhou, B., Zhou, S.K., Duncan, J.S., Liu, C.: Limited view tomographic reconstruction using a cascaded residual dense spatial-channel attention network with projection data fidelity layer. IEEE Trans. Med. Imaging 40(7), 1792–1804 (2021)

    Article  Google Scholar 

  27. Andersen, A.H., Kak, A.C.: Simultaneous algebraic reconstruction technique (SART): a superior implementation of the ART algorithm. Ultrason. Imaging 6(1), 81–94 (1984)

    Article  Google Scholar 

  28. De Man, B. and Basu, S.: Distance-driven projection and backprojection, In: 2002 IEEE Nuclear science symposium conference record, vol. 3, pp. 1477–1480, (2002)

  29. Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. Ar**v, abs/1505.04597. (2015)

  30. Zheng, A., Gao, H., Zhang, L., **ng, Y.: A dual-domain deep learning-based reconstruction method for fully 3D sparse data helical CT. Phys. Med. Biol. 65, 245030 (2020)

    Article  Google Scholar 

  31. Zhou, B., Chen, X., Zhou, S.K., Duncan, J.S., Liu, C.: DuDoDR-Net: dual-domain data consistent recurrent network for simultaneous sparse view and metal artifact reduction in computed tomography. Med. Image Anal. 75, 102289 (2021)

    Article  Google Scholar 

  32. Tharsanee, R.M., Soundariya, R.S., Saran Kumar, A., Karthiga, M., Sountharrajan, S.: 7 - Deep convolutional neural network–based image classification for COVID-19 diagnosis. In: Kose, U., Gupta, D., de Albuquerque, V.H.C., Khanna, A. (eds.) Data Science for COVID-19, pp. 117–145. Elsevier, Amsterdam (2021)

    Chapter  Google Scholar 

  33. Gonzalez, R.C., Wood, R.E.: Digital image processing. IEEE Trans. Patt. Anal Mach Intll. 3, 242–243 (1981)

    Google Scholar 

  34. AAPM. Low dose CT grand challenge. [Online]. (2015) Available: https://www.aapm.org/GrandChallange/LowDoseCT/#

  35. Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. Adv. Neural. Inf. Process. Syst. 32, 8024–8035 (2019)

    Google Scholar 

  36. Kingma, D. P. and Ba, J.: Adam: A method for stochastic optimization. (2014) ar**v:1412.6980. [Online]. Available: http://arxiv.org/abs/1412.6980

  37. Komolafe, T.E., Sun, Y., Wang, N., Sun, K., Cao, G., Shen, D.: DPDudoNet: deep-prior based dual-domain network for low- dose computed tomography reconstruction. In: Haq, N., Johnson, P., Maier, A., Qin, C., Würfl, T., Yoo, J. (eds.) Machine Learning for Medical Image Reconstruction MLMIRLecture Notes in Computer Science, vol. 13587. Springer, Cham (2022)

    Google Scholar 

  38. Zhao, H., Gallo, O., Frosio, I., Kautz, J.: Loss functions for image restoration with neural networks. IEEE Trans Comput Imag 3(1), 47–57 (2017)

    Article  Google Scholar 

  39. Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K.: Image denoising by sparse 3-D transform domain collaborative filtering. IEEE Trans. Image Process. 16(8), 2080–2095 (2007)

    Article  MathSciNet  Google Scholar 

  40. Guan, S. and Loew, M.: Analysis of generalizability of deep neural networks based on the complexity of decision boundary, In: 19th IEEE International conference on machine learning and applications (ICMLA), pp.101–106, (2020)

  41. Kazerouni, A., Aghdam, E.K., Heidari, M., Azad, R., Fayyaz, M., Hacihaliloglu, I., Merhof, D.: Diffusion models in medical imaging: a comprehensive survey. Med. Image Anal. 88, 102846 (2023)

    Article  Google Scholar 

  42. Hu, D., Tao, Y. K., Oguz, I.: Unsupervised denoising of retinal OCT with diffusion probabilistic model. In: medical imaging 2022: image processing, Vol. 12032, pp. 25–34. SPIE, (2022)

  43. Liu, J., Anirudh, R., Thiagarajan, J. J., He, S., Mohan, K. A., Kamilov, U. S., & Kim, H.: DOLCE: A model-based probabilistic diffusion framework for limited-angle ct reconstruction. In: Proceedings of the IEEE/CVF International conference on computer vision. pp. 10498–10508, (2023)

  44. Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International conference on machine learning, pp. 2256–2265. PMLR, (2015)

  45. Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840–6851 (2020)

    Google Scholar 

  46. LeCun, Y., Bottou, L., Orr, G.B., Müller, K.R.: Efficient backprop. In: Neural Networks: Tricks of the trade, pp. 9–50. Springer, Berlin (2002)

    Google Scholar 

  47. Chung, H., Ye, J.C.: Score-based diffusion models for accelerated MRI. Med. Image Anal. 80, 102479 (2022)

    Article  Google Scholar 

Download references

Acknowledgements

The authors acknowledge the funding received from the National Natural Science Foundation of China [Grant Numbers: 82072228 and 62376152], and the Three-Year Action Plan for Strengthening the Construction of the Public Health System in Shanghai (2023-2025) [Grant Number: GWVI-6]. The authors thank Professor Dinggang Shen for his guidance during the preliminary work conducted at the IDEA lab, School of Biomedical Engineering, ShanghaiTech University, Shanghai. Additionally, the authors extend their appreciation to the anonymous reviewers for their valuable and insightful feedback.

Funding

The authors did not receive any funding for this project.

Author information

Authors and Affiliations

  1. Collaborative Research Center, Shanghai University of Medicine & Health Sciences, Shanghai, 201318, China

    Temitope Emmanuel Komolafe

  2. Department of Chinese and Bilingual Studies, The Hong Kong Polytechnic University, Kowloon, Hong Kong SAR, China

    Nizhuan Wang

  3. School of Biomedical Engineering, ShanghaiTech University, Shanghai, 201210, China

    Nizhuan Wang

  4. Academy of Engineering, Fudan University, Shanghai, 200433, China

    Yuchi Tian

  5. Department of Ear, Nose, and Throat Head and Neck Surgery, Federal Medical Centre, Owo, 341101, Nigeria

    Adegbola Oyedotun Adeniji

  6. Department of Radiology, Jiading District Central Hospital Affiliated Shanghai University of Medicine & Health Sciences, Shanghai, 201318, China

    Liang Zhou

  7. Biomedical Engineering Fusion Laboratory, Jiangning Hospital, affiliated with Nan**g Medical University, Nan**g, 211166, China

    Liang Zhou

Authors
  1. Temitope Emmanuel Komolafe
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nizhuan Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yuchi Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Adegbola Oyedotun Adeniji
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Liang Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

T.E.K: Methodology, validation, formal analysis, investigation, data curation, conceptualization, writing (original draft), writing (reviewing and editing), project administration, and supervision. N.Y.: Methodology, validation, formal analysis, investigation, data curation, conceptualization, writing (original draft), writing (reviewing and editing). Y.T.: Methodology, validation, formal analysis, investigation, data curation, conceptualization, writing (original draft), writing (reviewing and editing). A.O.A.: Methodology, validation, formal analysis, investigation, writing (original draft), writing (reviewing and editing), L.Z. Methodology, validation, writing (reviewing and editing), project administration and supervision. All authors have thoroughly reviewed and approved the final manuscript.

Corresponding author

Correspondence to Temitope Emmanuel Komolafe.

Ethics declarations

Conflicts of interest

We confirm that there are no known conflicts of interest associated with this publication and there has been no significant financial support for this work that could have influenced its outcome.

Ethical approval

This study utilized publicly available data obtained from https://www.aapm.org/GrandChallenge/LowDoseCT/. As the data used in this study were anonymized and publicly accessible, no ethical approval was required for the present analysis. We ensured that the use of the dataset complied with all relevant terms of use and licensing agreements. All analyses were conducted in accordance with the principles outlined in the Declaration of Helsinki.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Komolafe, T.E., Wang, N., Tian, Y. et al. MDUNet: deep-prior unrolling network with multi-parameter data integration for low-dose computed tomography reconstruction. Machine Vision and Applications 35, 95 (2024). https://doi.org/10.1007/s00138-024-01568-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00138-024-01568-6

Keywords

Search

Navigation