Learning-Based X-Ray Image Denoising Utilizing Model-Based Image Simulations

  • Sai Gokul HariharanEmail author
  • Christian Kaethner
  • Norbert Strobel
  • Markus Kowarschik
  • Shadi Albarqouni
  • Rebecca Fahrig
  • Nassir Navab
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11769)


X-ray guidance is an integral part of interventional procedures, but the exposure to ionizing radiation poses a non-negligible threat to patients and clinical staff. Unfortunately, a reduction in the X-ray dose results in a lower signal-to-noise ratio, which may impair the quality of X-ray images. To ensure an acceptable image quality while keeping the X-ray dose as low as possible, it is common practice to use denoising techniques. However, at very low dose levels, the application of conventional denoising techniques may lead to undesirable artifacts or oversmoothing. On the other hand, supervised learning techniques have outperformed conventional techniques in producing suitable results, provided aligned pairs of associated high- and low-dose X-ray images are available. Unfortunately, it is neither acceptable nor possible to acquire such image pairs during a clinical intervention. To enable the use of learning-based methods for the denoising of X-ray images, we propose a novel strategy that involves the use of model-based simulations of low-dose X-ray images during the training phase. We utilize a data-driven normalization step that increases the robustness of the proposed approach to varying amounts of signal-dependent noise associated with different X-ray image acquisition protocols. A quantitative and qualitative analysis based on clinical and phantom data shows that the proposed strategy outperforms well-established conventional X-ray image denoising methods. It also indicates that the proposed approach allows for a significant dose reduction without sacrificing important image information.


Low-dose X-ray image denoising Deep learning Noise simulation 


Acknowledgement and Disclaimer

This work was supported by Siemens Healthineers AG. The concepts and results presented in this paper are based on research and are not commercially available.


  1. 1.
    Borges, L.R., Guerrero, I., Bakic, P.R., Foi, A., Maidment, A.D., Vieira, M.A.: Method for simulating dose reduction in digital breast tomosynthesis. IEEE Trans. Med. Imaging 36(11), 2331–2342 (2017)CrossRefGoogle Scholar
  2. 2.
    Cerciello, T., Bifulco, P., Cesarelli, M., Fratini, A.: A comparison of denoising methods for x-ray fluoroscopic images. Biomed. Signal Process. Control 7(6), 550–559 (2012)CrossRefGoogle Scholar
  3. 3.
    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)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Gu, S., Zhang, L., Zuo, W., Feng, X.: Weighted nuclear norm minimization with application to image denoising. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2862–2869 (2014)Google Scholar
  5. 5.
    Hariharan, S.G., et al.: Preliminary results of DSA denoising based on a weighted low-rank approach using an advanced neurovascular replication system. Int. J. Comput. Assist. Radiol. Surg. 14(7), 1117–1126 (2019)CrossRefGoogle Scholar
  6. 6.
    Hariharan, S.G., et al.: A photon recycling approach to the denoising of ultra-low dose x-ray sequences. Int. J. Comput. Assist. Radiol. Surg. 13(6), 847–854 (2018)CrossRefGoogle Scholar
  7. 7.
    Hariharan, S.G., Strobel, N., Kaethner, C., Kowarschik, M., Fahrig, R., Navab, N.: An analytical approach for the simulation of realistic low-dose fluoroscopic images. Int. J. Comput. Assist. Radiol. Surg. 14, 601–610 (2019)CrossRefGoogle Scholar
  8. 8.
    Kang, E., Koo, H.J., Yang, D.H., Seo, J.B., Ye, J.C.: Cycle-consistent adversarial denoising network for multiphase coronary CT angiography. Med. Phys. 46(2), 550–562 (2019)CrossRefGoogle Scholar
  9. 9.
    Lehtinen, J., et al.: Noise2Noise: learning image restoration without clean data. In: Proceedings of International Conference on Machone Learning, pp. 2965–2974 (2018)Google Scholar
  10. 10.
    Matviychuk, Y., et al.: Learning a multiscale patch-based representation for image denoising in x-ray fluoroscopy. In: Proceedings of International Conference on Image Processing, pp. 2330–2334 (2016)Google Scholar
  11. 11.
    Siewerdsen, J., et al.: Empirical and theoretical investigation of the noise performance of indirect detection, active matrix flat-panel imagers (AMFPIs) for diagnostic radiology. Med. Phys. 24(1), 71–89 (1997)CrossRefGoogle Scholar
  12. 12.
    Yang, K., Huang, S.Y., Packard, N.J., Boone, J.M.: Noise variance analysis using a flat panel x-ray detector: a method for additive noise assessment with application to breast CT applications. Med. Phys. 37(7), 3527–3537 (2010)CrossRefGoogle Scholar
  13. 13.
    Zhang, K., Zuo, W., Chen, Y., Meng, D., Zhang, L.: Beyond a gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans. Image Process. 26(7), 3142–3155 (2017)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Computer Aided Medical ProceduresTechnische Universität MünchenMunichGermany
  2. 2.Siemens Healthineers AG, Advanced TherapiesForchheimGermany
  3. 3.Fakultät für ElektrotechnikHochschule für angewandte Wissenschaften Würzburg-SchweinfurtSchweinfurtGermany
  4. 4.Pattern Recognition LabFriedrich-Alexander-Universität Erlangen-NürnbergErlangenGermany
  5. 5.Whiting School of EngineeringJohns Hopkins UniversityBaltimoreUSA

Personalised recommendations