Temporally downsampled cerebral CT perfusion image restoration using deep residual learning | International Journal of Computer Assisted Radiology and Surgery Skip to main content
Springer Nature Link
Log in

Temporally downsampled cerebral CT perfusion image restoration using deep residual learning

  • Original Article
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Purpose

Acute ischemic stroke is one of the most causes of death all over the world. Onset to treatment time is critical in stroke diagnosis and treatment. Considering the time consumption and high price of MR imaging, CT perfusion (CTP) imaging is strongly recommended for acute stroke. However, too much CT radiation during CTP imaging may increase the risk of health problems. How to reduce CT radiation dose in CT perfusion imaging has drawn our great attention.

Methods

In this study, the original 30-pass CTP images are downsampled to 15 passes in time sequence, which equals to 50% radiation dose reduction. Then, a residual deep convolutional neural network (DCNN) model is proposed to restore the downsampled 15-pass CTP images to 30 passes to calculate the parameters such as cerebral blood flow, cerebral blood volume, mean transit time, time to peak for stroke diagnosis and treatment. The deep restoration CNN is implemented simply and effectively with 16 successive convolutional layers which form a wide enough receptive field for input image data. 18 patients’ CTP images are employed as training set and the other six patients’ CTP images are treated as test dataset in this study.

Results

Experiments demonstrate that our CNN can restore high-quality CTP images in terms of structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). The average SSIM and PSNR for test images are 0.981 and 56.25, and the SSIM and PSNR of regions of interest are 0.915 and 42.44, respectively, showing promising quantitative level. In addition, we compare the perfusion maps calculated from the restored images and from the original images, and the average perfusion results of them are extremely close. Areas of hypoperfusion of six test cases could be detected with comparable accuracy by radiologists.

Conclusion

The trained model can restore the temporally downsampled 15-pass CTP to 30 passes very well. According to the contrast test, sufficient information cannot be restored with, e.g., simple interpolation method and deep convolutional generative adversarial network, but can be restored with the proposed CNN model. This method can be an optional way to reduce radiation dose during CTP imaging.

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
¥17,985 /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 (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Wang L, Wang J, Peng B (2016) China stroke prevention report 2016 summary. Chin J Cerebrovasc Dis 14:217–224

    Google Scholar 

  2. Chinese Medical Association Cerebrovascular Disease Group (2018) Guidelines for the diagnosis and treatment of acute ischemic stroke in China. Chin J Neurol 51:666–682

    Google Scholar 

  3. Krishnamoorthi R, Ramarajan N, Wang NE, Newman B, Rubesova E, Mueller CM, Barth RA (2011) Effectiveness of a staged US and CT protocol for the diagnosis of pediatric appendicitis: reducing radiation exposure in the age of ALARA. Radiology 259:231–239

    Article  Google Scholar 

  4. Liu J, Hu Y, Yang J, Chen Y, Shu H, Luo L, Feng Q, Gui Z, Coatrieux G (2018) 3D feature constrained reconstruction for low dose CT imaging. IEEE Trans Circuits Syst Video Technol 28:1232–1247

    Article  Google Scholar 

  5. Bian J, Wang J, Han X, Sidky EY, Shao L, Pan X (2013) Optimization-based image reconstruction from sparse-view data in offset-detector CBCT. Phys Med Biol 58:205

    Article  Google Scholar 

  6. Cho S, Pearson E, Pelizzari CA, Pan X (2009) Region-of-interest image reconstruction with intensity weighting in circular cone-beam CT for image-guided radiation therapy. Med Phys 36:1184–1192

    Article  Google Scholar 

  7. Kalke M, Siltanen S (2014) Sinogram interpolation method for sparse-angle tomography. Appl Math 5:423

    Article  Google Scholar 

  8. Zhang H, Sonke JJ (2013) Directional sinogram interpolation for sparse angular acquisition in cone-beam computed tomography. J X-ray Sci Technol 21:481–496

    Article  Google Scholar 

  9. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  10. Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans Pattern Anal Mach Intell 40:834–848

    Article  Google Scholar 

  11. Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention, pp 234–241

    Google Scholar 

  12. Dong C, Loy CC, He K, Tang X (2016) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38:295–307

    Article  Google Scholar 

  13. Chen H, Zhang Y, Chen Y, Zhang J, Zhang W, Sun H, Lv Y, Liao P, Zhou J, Wang G (2018) LEARN: learned experts’ assessment-based reconstruction network for sparse-data CT. IEEE Trans Med Imaging 37:1333–1347

    Article  Google Scholar 

  14. Lee D, Choi S, Kim HJ (2018) High quality imaging from sparsely sampled computed tomography data with deep learning and wavelet transform in various domains. Med Phys 46:104–115

    Article  Google Scholar 

  15. Lee H, Lee J, Cho S (2017) View-interpolation of sparsely sampled sinogram using convolutional neural network. Medical imaging 2017: image processing. Int Soc Opt Photon. https://doi.org/10.1117/12.2254244

    Article  Google Scholar 

  16. Wolterink JM, Leiner T, Viergever MA, Ivana I (2017) Generative adversarial networks for noise reduction in low-dose CT. IEEE Trans Med Imaging 36:2536–2545

    Article  Google Scholar 

  17. Kudo K, Sasaki M, Yamada K, Momoshima S, Utsunomiya H, Shirato H, Ogasawara K (2009) Differences in CT perfusion maps generated by different commercial software: quantitative analysis by using identical source data of acute stroke patients. Radiology 254:200–209

    Article  Google Scholar 

  18. Wang G (2016) A perspective on deep imaging. IEEE Access 4:8914–8924

    Article  Google Scholar 

  19. Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. Proc IEEE Conf Comput Vis Pattern Recognit 2015:3431–3440

    Google Scholar 

  20. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 2012:1097–1105

    Google Scholar 

  21. Petneházi G (2019) Recurrent neural networks for time series forecasting. arXiv preprint arXiv:1901.00069

  22. Chen H, Zhang Y, Kalra MK, Feng L, Yang C, Peixi L, Jiliu Z, Ge W (2017) Low-dose CT with a residual encoder-decoder convolutional neural network. IEEE Trans Med Imaging 36:2524–2535

    Article  Google Scholar 

  23. Yang W, Zhang H, Yang J, Wu J, Yin X, Chen Y, Shu H, Luo L, Coatrieux G, Gui Z, Feng Q (2017) Improving low-dose ct image using residual convolutional network. IEEE Access 5:24698–24705

    Article  Google Scholar 

  24. Yin X, Zhao Q, Liu J, Yang W, Yang J, Quan G, Chen Y, Shu HZ, Luo LL, Coatrieux JL (2019) Domain progressive 3D residual convolution network to improve low dose CT imaging. IEEE Trans Med Imaging. https://doi.org/10.1109/TMI.2019.2917258

    Article  PubMed  Google Scholar 

  25. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980

  26. Radford A, Metz L, Chintala S (2016) Unsupervised representation learning with deep convolutional generative adversarial networks. In: International conference on learning representations (ICLR)

  27. Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courvile A (2017) Improved training of wasserstein gans. In: Advances in neural information processing systems (NIPS), pp 5767–5777

  28. Karen S, Andrew Z (2015) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations (ICLR)

  29. Austein F, Riedel C, Kerby T, Meyne J, Binder A, Lindner T, Huhndorf M, Wodarg F, Jansen O (2016) Comparison of perfusion CT software to predict the final infarct volume after thrombectomy. Stroke 47:2311–2317

    Article  Google Scholar 

  30. Kudo K, Christensen S, Sasaki M, Ostergaard L, Shirato H, Wintermark M, Warach S (2013) Accuracy and reliability assessment of CT and MR perfusion analysis software using a digital phantom. Radiology 267:201–211

    Article  Google Scholar 

  31. Liu J, Ma J, Zhang Y, Chen Y, Yang J, Shu H, Luo L, Coatrieux G (2017) Discriminative feature representation to improve projection data inconsistency for low dose CT imaging. IEEE Trans Med Imaging 36:2499–2509

    Article  Google Scholar 

Download references

Funding

This work was supported in part by the State’s Key Project of Research and Development Plan under Grant 2017YFA0104302, Grant 2017YFC0109202 and 2017YFC0107900, National Natural Science Foundation under Grant 81530060, 31571001 and 81471752 and the R&D Projects in Key Technology Areas of Guangdong Province under Grant 2018B030333001.

Author information

Author notes

  1. Haichen Zhu and Dan Tong have contributed equally to this study.

Authors and Affiliations

  1. Lab of Image Science and Technology, Key Laboratory of Computer Network and Information Integration (Ministry of Education), Southeast University, Nanjing, 210096, China

    Haichen Zhu, Shijie Wang, Hui Tang, Yang Chen & Limin Luo

  2. Department of Radiology, The First Hospital of Jilin University, Changchun, 130021, China

    Dan Tong

  3. IETR, CNRS, UMR 6164, INSA Rennes, 35708, Rennes, France

    Lu Zhang

  4. Key Lab of Optoelectronic Technology and Systems, Ministry of Education, Chongqing University, Chongqing, 400044, China

    Weiwen Wu

  5. Centre de Recherche en Information Biomedicale, Sino-Francais (LIA CRIBs), 35000, Rennes, France

    Yang Chen

  6. Department of Radiation Oncology, Shandong Cancer Hospital, Shandong University, Jinan, 250117, China

    Jian Zhu & Baosheng Li

  7. School of Cyber Science and Engineering, Southeast University, Nanjing, 210096, China

    Yang Chen

Authors
  1. Haichen Zhu
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Dan Tong
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Lu Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Shijie Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Weiwen Wu
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Hui Tang
    View author publications

    You can also search for this author inPubMed Google Scholar

  7. Yang Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  8. Limin Luo
    View author publications

    You can also search for this author inPubMed Google Scholar

  9. Jian Zhu
    View author publications

    You can also search for this author inPubMed Google Scholar

  10. Baosheng Li
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding authors

Correspondence to Yang Chen or Jian Zhu.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed consent

Informed consent was obtained from all individual participants included in the study.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhu, H., Tong, D., Zhang, L. et al. Temporally downsampled cerebral CT perfusion image restoration using deep residual learning. Int J CARS 15, 193–201 (2020). https://doi.org/10.1007/s11548-019-02082-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-019-02082-1

Keywords