Advertisement

Slice-wise reconstruction for low-dose cone-beam CT using a deep residual convolutional neural network

  • Hong-Kai Yang
  • Kai-Chao Liang
  • Ke-Jun Kang
  • Yu-Xiang XingEmail author
Article
  • 16 Downloads

Abstract

Because of the growing concern over the radiation dose delivered to patients, X-ray cone-beam CT (CBCT) imaging of low dose is of great interest. It is difficult for traditional reconstruction methods such as Feldkamp to reduce noise and keep resolution at low doses. A typical method to solve this problem is using optimization-based methods with careful modeling of physics and additional constraints. However, it is computationally expensive and very time-consuming to reach an optimal solution. Recently, some pioneering work applying deep neural networks had some success in characterizing and removing artifacts from a low-dose data set. In this study, we incorporate imaging physics for a cone-beam CT into a residual convolutional neural network and propose a new end-to-end deep learning-based method for slice-wise reconstruction. By transferring 3D projection to a 2D problem with a noise reduction property, we can not only obtain reconstructions of high image quality, but also lower the computational complexity. The proposed network is composed of three serially connected sub-networks: a cone-to-fan transformation sub-network, a 2D analytical inversion sub-network, and an image refinement sub-network. This provides a comprehensive solution for end-to-end reconstruction for CBCT. The advantages of our method are that the network can simplify a 3D reconstruction problem to a 2D slice-wise reconstruction problem and can complete reconstruction in an end-to-end manner with the system matrix integrated into the network design. Furthermore, reconstruction can be less computationally expensive and easily parallelizable compared with iterative reconstruction methods.

Keywords

Cone-beam CT Slice-wise Residual U-net Low dose Image denoising 

References

  1. 1.
    Y. Xing, L. Zhang, A free-geometry cone beam CT and its FDK-type reconstruction. J. X-ray Sci. Technol. 15(3), 157–167 (2007)Google Scholar
  2. 2.
    K. Ozasa, Epidemiological research on radiation-induced cancer in atomic bomb survivors. J. Radiat. Res. 57(Suppl 1), i112–i117 (2016).  https://doi.org/10.1093/jrr/rrw005 CrossRefGoogle Scholar
  3. 3.
    D.L. Miglioretti, E. Johnson, A. Williams et al., The use of computed tomography in pediatrics and the associated radiation exposure and estimated cancer risk. Jama Pediatr. 167(8), 700–707 (2013).  https://doi.org/10.1001/jamapediatrics.2013.311 CrossRefGoogle Scholar
  4. 4.
    L.J.M. Kroft, J.J.H. Roelofs, J. Geleijns, Scan time and patient dose for thoracic imaging in neonates and small children using axial volumetric 320-detector row CT compared to helical 64-, 32-, and 16- detector row CT acquisitions. Pediatr. Radiol. 40(3), 294–300 (2010).  https://doi.org/10.1007/s00247-009-1436-x CrossRefGoogle Scholar
  5. 5.
    A.C. Silva, H.J. Lawder, A. Hara et al., Innovations in CT dose reduction strategy: application of the adaptive statistical iterative reconstruction algorithm. AJR Am. J. Roentgenol. 194(1), 191–199 (2010).  https://doi.org/10.2214/AJR.09.2953 CrossRefGoogle Scholar
  6. 6.
    A.K. Hara, R.G. Paden, A.C. Silva et al., Iterative reconstruction technique for reducing body radiation dose at CT: feasibility study. AJR Am. J. Roentgenol. 193(3), 764–771 (2009).  https://doi.org/10.2214/AJR.09.2397 CrossRefGoogle Scholar
  7. 7.
    I.A. Elbakri, J.A. Fessler, Statistical image reconstruction for polyenergetic X-ray computed tomography. IEEE Trans. Med. Imaging 21(2), 89–99 (2002).  https://doi.org/10.1109/42.993128 CrossRefGoogle Scholar
  8. 8.
    K. Li, J. Tang, G.H. Chen, Statistical model based iterative reconstruction (MBIR) in clinical CT systems: experimental assessment of noise performance. Med. Phys. (2014).  https://doi.org/10.1118/1.4867863 CrossRefGoogle Scholar
  9. 9.
    P.T. Lauzier, J. Tang, G. Chen, Prior image constrained compressed sensing: implementation and performance evaluation. Med. Phys. 39(1), 66–80 (2012).  https://doi.org/10.1118/1.3666946 CrossRefGoogle Scholar
  10. 10.
    G.H. Chen, J. Tang, S. Leng, Prior image constrained compressed sensing (PICCS): a method to accurately reconstruct dynamic CT images from highly undersampled projection data sets. Med. Phys. 35(2), 660–663 (2008).  https://doi.org/10.1118/1.2836423 CrossRefGoogle Scholar
  11. 11.
    J. Liu, Y. Hu, J. Yang et al., 3D feature constrained reconstruction for low dose CT imaging. IEEE Trans. Circuits Syst. Video Technol. 28(5), 1232–1247 (2016).  https://doi.org/10.1109/TCSVT.2016.2643009 CrossRefGoogle Scholar
  12. 12.
    Y. Chen, L. Shi, Q. Feng et al., Artifact suppressed dictionary learning for low-dose CT image processing. IEEE Trans. Med. Imaging 33(12), 2271–2292 (2014).  https://doi.org/10.1109/TMI.2014.2336860 CrossRefGoogle Scholar
  13. 13.
    J. Liu, J. Ma, Y. Zhang et al., Discriminative feature representation to improve projection data inconsistency for low dose CT imaging. IEEE Trans. Med. Imaging 36(12), 2499–2509 (2018).  https://doi.org/10.1109/TMI.2017.2739841 CrossRefGoogle Scholar
  14. 14.
    E.Y. Sidky, X. Pan, Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization. Phys. Med. Biol. 53(17), 4777–4807 (2008).  https://doi.org/10.1088/0031-9155/53/17/021 CrossRefGoogle Scholar
  15. 15.
    X. Jia, Y. Lou, J. Lewis et al., GPU-based fast low-dose cone beam CT reconstruction via total variation. J. X-ray Sci. Technol. 78(3), 139–154 (2010).  https://doi.org/10.3233/XST-2011-0283 CrossRefGoogle Scholar
  16. 16.
    Y. Lecun, Y. Bengio, G. Hinton, Deep learning. Nature 521(7553), 436 (2015).  https://doi.org/10.1038/nature14539 CrossRefGoogle Scholar
  17. 17.
    T.Y. Lin, A. Roychowdhury, S. Maji, Bilinear CNN models for fine-grained visual recognition. IEEE Int. Conf. Comput. Vis. (2015).  https://doi.org/10.1109/iccv.2015.170 CrossRefGoogle Scholar
  18. 18.
    A. Ramcharan, K. Baranowski, P. Mccloskey et al., Deep learning for image-based cassava disease detection. Front. Plant Sci. (2017).  https://doi.org/10.3389/fpls.2017.01852 CrossRefGoogle Scholar
  19. 19.
    E. Kang, J. Min, J.C. Ye, A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction. Med. Phys. 44(10), e360–e375 (2017).  https://doi.org/10.1002/mp.12344 CrossRefGoogle Scholar
  20. 20.
    H. Chen, Y. Zhang, M.K. Kalra et al., Low-dose CT with a residual encoder-decoder convolutional neural network (RED-CNN). IEEE Trans. Med. Imaging 99, 1 (2017).  https://doi.org/10.1109/TMI.2017.2715284 CrossRefGoogle Scholar
  21. 21.
    H. Chen, Y. Zhang, W. Zhang et al., Low-dose CT via convolutional neural network. Biomed. Opt. Express 8(2), 679–694 (2017).  https://doi.org/10.1364/BOE.8.000679 CrossRefGoogle Scholar
  22. 22.
    Q. Yang, P. Yan, Y. Zhang 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).  https://doi.org/10.1109/TMI.2018.2827462 CrossRefGoogle Scholar
  23. 23.
    Y. Zhang, H. Yu, Convolutional neural network based metal artifact reduction in X-ray computed tomography. IEEE Trans. Med. Imaging 37(6), 1370–1381 (2018).  https://doi.org/10.1109/TMI.2018.2823083 CrossRefGoogle Scholar
  24. 24.
    Y. Han, J.C. Ye, Framing U-net via deep convolutional framelets: application to sparse-view CT. IEEE Trans. Med. Imaging 37(6), 1418–1429 (2018).  https://doi.org/10.1109/TMI.2018.2823768 CrossRefGoogle Scholar
  25. 25.
    H. Chen, Y. Zhang, Y. Chen et al., LEARN: learned experts’ assessment-based reconstruction network for sparse-data CT. IEEE Trans. Med. Imaging 37(6), 1333–1347 (2018).  https://doi.org/10.1109/TMI.2018.2805692 MathSciNetCrossRefGoogle Scholar
  26. 26.
    O. Ronneberger, P. Fischer, T. Brox, U-net: convolutional networks for biomedical image segmentation. Int. Conf. Med. Image Comput. Comput. Assist. Interv. 9351, 234–241 (2015).  https://doi.org/10.1007/978-3-319-24574-4_28 CrossRefGoogle Scholar
  27. 27.
    J. Hao, L. Zhang, L. Li et al., A practical image reconstruction and processing method for symmetrically off-center detector CBCT system. Nucl. Sci. Technol. 24(4), 17–22 (2013)Google Scholar
  28. 28.
    D.L. Parker, Optimal short scan convolution reconstruction for fan beam CT. Med. Phys. 9(2), 254–257 (1982).  https://doi.org/10.1118/1.595078 CrossRefGoogle Scholar
  29. 29.
    H. Zhang, J. Ma, J. Wang et al., Statistical image reconstruction for low-dose CT using nonlocal means-based regularization. Comput. Med. Imaging Graph. 38(6), 423–435 (2014).  https://doi.org/10.1016/j.compmedimag.2014.05.002 CrossRefGoogle Scholar
  30. 30.
    K. Liang, L. Zhang, H. Yang, et al. Optimize interpolation-based MAR for practical dental CT with deep learning, in The 5th International Conference on Image Formation in X-ray Computed Tomography (CT meeting 2018) (2018), pp. 423–425Google Scholar

Copyright information

© China Science Publishing & Media Ltd. (Science Press), Shanghai Institute of Applied Physics, the Chinese Academy of Sciences, Chinese Nuclear Society and Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Hong-Kai Yang
    • 1
    • 2
  • Kai-Chao Liang
    • 1
  • Ke-Jun Kang
    • 1
    • 2
  • Yu-Xiang Xing
    • 1
    • 2
    Email author
  1. 1.Department of Engineering PhysicsTsinghua UniversityBeijingChina
  2. 2.Key Laboratory of Particle and Radiation Imaging, Ministry of EducationTsinghua UniversityBeijingChina

Personalised recommendations