Ultrasound Medical Image Deblurring and Denoising Method Using Variational Model on CUDA

  • Biswajit Biswas
  • Biplab Kanti Sen
  • Kashi Nath Dey
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 666)


This paper introduces a new variational model on CUDA platform for the restoration (deblurring and denoising) of ultrasound image degraded by additive Gaussian noise and blur effect. In the deblurring step, we apply an inverse algorithm with the fast transform approach. In the denoising step, a total variational model (TVM) using second-order partial anisotropic diffusion equations is used. A unique and stable solution for the proposed model is presented in terms of the Euler–Lagrange equation. Later, an accurate numerical approximation is constituted by the finite-difference-based discretization technique and the parameter dependence of the proposed model is also described. To achieve better acceleration with satisfactory performance, the proposed algorithm is properly devised on the CUDA GPU and compared with a sequential execution of the multicore CPU system. Experimental results and quantitative analysis show that our algorithm is efficient to restore the ultrasound image compared to the state-of-the-art restoration methods.


Ultrasound image denoising Partial differential equation Total variation Euler–Lagrange equation Computation Unified Device Architecture (CUDA) Graphics Processing Units (GPU) Signal-to-noise ratio 


  1. 1.
    Chan, T., Esedoglu, S. et al., Recent developments in total variation image restoration. Mathematical Models of Computer Vision. Springer, New York (2005)Google Scholar
  2. 2.
    Aubert, G., Kornprobst, P.: Mathematical Problems in Image Processing. Springer Science, New York (2006). ISBN 978-0387-32200-1zbMATHGoogle Scholar
  3. 3.
    Barbu, T., Barbu, V.: PDE approach to image restoration problem with an observation on a meager domain. Nonlinear Anal. Real World Appl.,vol.13, no. 3, pp. 1206–15, 2012Google Scholar
  4. 4.
    Barbu, T., et al.: A novel variational PDE technique for image denoising, pp. 501–508. Springer, Heidelberg (2013)Google Scholar
  5. 5.
    Barbu, T., Favini, A.: Rigorous mathematical investigation of a nonlinear anisotropic diffusion-based image restoration model. Electron. J. Differ. Eqs. 129, 1–9 (2014)zbMATHGoogle Scholar
  6. 6.
    Vega, M., Mateos, J., et al.: Astronomical image restoration using variational methods and model combination. Statistical Methodology 9, 19–31 (2012)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Xu, J., Feng, A., et al.: Image deblurring and denoising by an improved variational model. Int. J. Electron. Commun. (AUE) 70(9), 1128–1133 (2016)CrossRefGoogle Scholar
  8. 8.
    Wen, Y., Ng, M., Ching, W.: Iterative algorithm based on decoupling of deblurring and denoising for image restoration. SIAM J. Sci. Comput. 30(5), 265574 (2008)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Liu, G., Huang, T., Liu, J.: High-order TVL1-based images restoration and spatially adapted regularization parameter selection. Comput. Math Appl. 67, 201526 (2014)MathSciNetzbMATHGoogle Scholar
  10. 10.
    Takeda, H., Farsiu, S., Milanfar, P.: Deblurring using regularized locally adaptive kernel regression. IEEE Trans. Image Process. 17(4), 550–563 (2008)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Huang, J., Huang, T., et al.: Two soft-thresholding based iterative algorithms for image deblurring. Inf. Sci. 271, 179–195 (2014)CrossRefGoogle Scholar
  12. 12.
    Beck, A., Teboulle, M.: Fast gradient-based algorithms for constrained total variation image denoising and deblurring problems. IEEE Trans. Image Process. 18(11), 2419–2434 (2009)MathSciNetCrossRefGoogle Scholar
  13. 13.
    NVIDIA, CUDA: Compute Unified Device Architecture.
  14. 14.
    Kandrot, E., Sanders, J.: CUDA by Example. Addison Wesley, Boston (2011)Google Scholar
  15. 15.

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringUniversity of CalcuttaKolkataIndia

Personalised recommendations