An impulse noise removal model algorithm based on logarithmic image prior for medical image

Abstract

With the rapid development of computer science and technology in modern society, image science is widely used in various fields, especially in medicine field. Image processing plays an important role in medical images. Medical images are often corrupted by noise due to various sources of interference and other phenomena during their acquisition and transmission that affects the measurement processes in imaging reduced image detail due to the introduction of noise. Keeping useful diagnostic information to suppress noise is a challenging task. Salt and pepper noise as a kind of ordinary noise is one of the impulse noises. In this work, we will use a logarithmic image prior constraint the objective function for the removal of the impulse noise. Also, we used the split Bregman iterative method to solve the objective function. Theoretically, under reasonable assumptions, we give partial convergence analysis of the algorithm. Computationally, we use the split Bregman iterative method under the guarantee of convergence analysis and the weight of SVD decomposition; a complex problem is transformed into several simple subproblems to solving, wherein u-subproblem can be solved by fast Fourier transform; hd-subproblems can be solved use shrinkage operator, respectively. In the experimental aspects, we have done a lot of experiments and compared with other state-of-the-art methods. The experimental results show that the method is superior to other methods in terms of effectiveness impulse noise (salt and pepper noise) for medical images (CT or MRI).

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2

References

  1. 1.

    Dong, W., Shi, G., Li, X., Ma, Y., Huang, F.: Compressive sensing via nonlocal low-rank regularization. IEEE Trans. Image Process. 23(8), 3618–3632 (2014)

    MathSciNet  Article  Google Scholar 

  2. 2.

    Chen, Y., Yu, W., Pock, T.: On learning optimized reaction diffusion processes for effective image restoration. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5261–5269 (2015)

  3. 3.

    Chen, Y., Pock, T.: Trainable nonlinear reaction diffusion: a flexible framework for fast and effective image restoration. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1256–1272 (2016)

    Article  Google Scholar 

  4. 4.

    Li, C., Li, Y., Zhao, Z., Yu, L., Luo, Z.: A mixed noise removal algorithm based on multi-fidelity modeling with nonsmooth and nonconvex regularization. Multimed Tools Appl 78, 1–24 (2019)

    Article  Google Scholar 

  5. 5.

    Yuan, G., Ghanem, B.: lotv: A new method for image restoration in the presence of impulse noise. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5369–5377 (2015)

  6. 6.

    Ryu, E.K., Liu, J., Wang, S., Chen, X., Wang, Z., Yin, W.: Plug-and-play methods provably converge with properly trained denoisers. arXiv preprint arXiv:1905.05406 (2019)

  7. 7.

    Cai, J., Zeng, H., Yong, H., Cao, Z., Zhang, L.: Toward real-world single image super-resolution: a new benchmark and a new model. arXiv preprint arXiv:1904.00523 (2019)

  8. 8.

    Zhang, K., Zuo, W., Zhang, L.: Deep plug-and-play super-resolution for arbitrary blur kernels. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1671–1681 (2019)

  9. 9.

    Guo, S., Yan, Z., Zhang, K., Zuo, W., Zhang, L.: Toward convolutional blind denoising of real photographs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1712–1722 (2019)

  10. 10.

    Qin, C., Schlemper, J., Caballero, J., Price, A.N., Hajnal, J.V., Rueckert, D.: Convolutional recurrent neural networks for dynamic mr image reconstruction. IEEE Trans. Med. Imaging 38(1), 280–290 (2018)

    Article  Google Scholar 

  11. 11.

    Lyu, J., Nakarmi, U., Liang, D., Sheng, J., Ying, L.: Kernl: Kernel-based nonlinear approach to parallel mri reconstruction. IEEE Trans. Med. Imaging 38(1), 312–321 (2018)

    Article  Google Scholar 

  12. 12.

    Li, S., Zeng, D., Peng, J., Bian, Z., Zhang, H., Xie, Q., Wang, Y., Liao, Y., Zhang, S., Huang, J., et al.: An efficient iterative cerebral perfusion ct reconstruction via low-rank tensor decomposition with spatial-temporal total variation regularization. IEEE Trans. Med. Imaging 38(2), 360–370 (2018)

    Article  Google Scholar 

  13. 13.

    van Tulder, G., de Bruijne, M.: Learning cross-modality representations from multi-modal images. IEEE Trans. Med. Imaging 38(2), 638–648 (2018)

    Article  Google Scholar 

  14. 14.

    Jifara, W., Jiang, F., Rho, S., Cheng, M., Liu, S.: Medical image denoising using convolutional neural network: a residual learning approach. J. Supercomput. 75(2), 704–718 (2019)

    Article  Google Scholar 

  15. 15.

    Liu, P., El Basha, M.D., Li, Y., Xiao, Y., Sanelli, P.C., Fang, R.: Deep evolutionary networks with expedited genetic algorithms for medical image denoising. Med. Image Anal. 54, 306–315 (2019)

    Article  Google Scholar 

  16. 16.

    Rani, M.L.P., Rao, G.S., Rao, B.P.: Ann application for medical image denoising. In: Soft Computing for Problem Solving, pp. 675–684. Springer (2019)

  17. 17.

    Oh, S., Woo, H., Yun, S., Kang, M.: Non-convex hybrid total variation for image denoising. J. Vis. Commun. Image Represent. 24(3), 332–344 (2013)

    Article  Google Scholar 

  18. 18.

    Adam, T., Paramesran, R.: Image denoising using combined higher order non-convex total variation with overlapping group sparsity. Multidimens. Syst. Signal Process. 30(1), 503–527 (2019)

    MathSciNet  Article  Google Scholar 

  19. 19.

    Hammernik, K., Klatzer, T., Kobler, E., Recht, M.P., Sodickson, D.K., Pock, T., Knoll, F.: Learning a variational network for reconstruction of accelerated MRI data. Magn. Reson. Med. 79(6), 3055–3071 (2018)

    Article  Google Scholar 

  20. 20.

    Hammernik, K., Kobler, E., Pock, T., Recht, M.P., Sodickson, D.K., Knoll, F.: Variational adversarial networks for accelerated MR image reconstruction. In: Joint Annual Meeting ISMRM-ESMRMB 2018 (2018)

  21. 21.

    Li, C., Li, J., Luo, Z.: An impulse noise removal model algorithm based on logarithmic image prior. In: Proceedings of the 2019 8th International Conference on Computing and Pattern Recognition, pp. 246–253 (2019)

  22. 22.

    Fazel, M., Hindi, H., Boyd, S.: Log-det heuristic for matrix rank minimization with applications to Hankel and Euclidean distance matrices vol .3, pp. 2156–2162 (2003)

  23. 23.

    Huang, T., Dong, W., Xie, X., Shi, G., Bai, X.: Mixed noise removal via laplacian scale mixture modeling and nonlocal low-rank approximation. IEEE Trans. Image Process. 26(7), 3171–3186 (2017)

    MathSciNet  Article  Google Scholar 

  24. 24.

    Rudin, L.I., Osher, S., Fatemi, E.: Nonlinear total variation based noise removal algorithms. Phys. D 60(1–4), 259–268 (1992)

    MathSciNet  Article  Google Scholar 

  25. 25.

    Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imaging Vis. 40(1), 120–145 (2011)

    MathSciNet  Article  Google Scholar 

  26. 26.

    Goldstein, T., Osher, S.: The split bregman method for L1-regularized problems. SIAM J. Imaging Sci. 2(2), 323–343 (2009)

    MathSciNet  Article  Google Scholar 

  27. 27.

    Jung, M., Kang, M., Kang, M.: Variational image segmentation models involving non-smooth data-fidelity terms. J. Sci. Comput. 59(2), 277–308 (2014)

    MathSciNet  Article  Google Scholar 

  28. 28.

    Wang, Y., Yang, J., Yin, W., Zhang, Y.: A new alternating minimization algorithm for total variation image reconstruction. SIAM J. Imaging Sci. 1(3), 248–272 (2008)

    MathSciNet  Article  Google Scholar 

  29. 29.

    Yang, J., Zhang, Y., Yin, W.: An efficient TVL1 algorithm for deblurring multichannel images corrupted by impulsive noise. SIAM J. Sci. Comput. 31(4), 2842–2865 (2009)

    MathSciNet  Article  Google Scholar 

  30. 30.

    Zhang, M., Liu, Y., Li, G., Qin, B., Liu, Q.: Iterative scheme-inspired network for impulse noise removal. Pattern Anal. Appl. 23(1), 135–145 (2020)

    MathSciNet  Article  Google Scholar 

  31. 31.

    Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001, vol. 2, pp. 416–423. IEEE (2001)

  32. 32.

    http://overcode.yak.net/15?size=m.,

Download references

Acknowledgements

This research is supported by the Science and Technology Service Network Initiative, CAS, the IT integrated service platform of Sichuan Wolong Natural Reserve (Y82E01); The National R and D Infrastructure and Facility Development Program of China, “Fundamental Science Data Sharing Platform” (DKA2018-12-02-XX); supported by the Strategic Priority Research Program of the Chinese Academy of Sciences (XDA19060205); The Special Project of Informatization of Chinese Academy of Sciences) (XXH13505-03-205); The Special Project of Informatization of Chinese Academy of Sciences) (XXH13506-305); The Special Project of Informatization of Chinese Academy of Sciences (XXH13506-303); supported by Around Five Top Priorities of “One-Three-Five” Strategic Planning, CNIC (CNIC-PY-1408); supported by Around Five Top Priorities of “One-Three-Five” Strategic Planning, CNIC (CNIC-PY-1409); Science and Technology Service Network Initiative, CAS, the IT integrated service platform of Sichuan Wolong Natural Reserve (KFJ-STS-QYZD-058); Giant Panda International Cooperation Fund Project, Application and Research of Image Recognition Technology Based on Deep Learning in Wild Animal Identification.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Chun Li.

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

Verify currency and authenticity via CrossMark

Cite this article

Li, C., Li, J. & Luo, Z. An impulse noise removal model algorithm based on logarithmic image prior for medical image. SIViP (2021). https://doi.org/10.1007/s11760-020-01842-w

Download citation

Keywords

  • Impulse noise removal
  • Image processing
  • Image reconstruction
  • Split Bregman iterative
  • Low-rank learning