Learning Splines for Sparse Tomographic Reconstruction

  • Elham Sakhaee
  • Alireza Entezari
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8887)


In a few-view or limited-angle computed tomography (CT), where the number of measurements is far fewer than image unknowns, the reconstruction task is an ill-posed problem. We present a spline-based sparse tomographic reconstruction algorithm where content-adaptive patch sparsity is integrated into the reconstruction process. The proposed method leverages closed-form Radon transforms of tensor-product B-splines and non-separable box splines to improve the accuracy of reconstruction afforded by higher order methods. The experiments show that enforcing patch-based sparsity, in terms of a learned dictionary, on higher order spline representations, outperforms existing methods that utilize pixel-basis for image representation as well as those employing wavelets as sparsifying transform.


Sparse Representation Tomographic Reconstruction Dictionary Learning Orthogonal Match Pursuit Projection Angle 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Lustig, M., Donoho, D., Pauly, J.M.: Sparse mri: The application of compressed sensing for rapid mr imaging. Magnetic resonance in medicine 58, 1182–1195 (2007)CrossRefGoogle Scholar
  2. 2.
    Pan, X., Sidky, E.Y., Vannier, M.: Why do commercial CT scanners still employ traditional, filtered back-projection for image reconstruction? Inverse Problems 25, 123009 (2009)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Shtok, J., Elad, M., Zibulevsky, M.: Sparsity-based sinogram denoising for low-dose computed tomography. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 569–572 (2011)Google Scholar
  4. 4.
    Natterer, F.: The mathematics of computerized tomography. In: Society for Industrial and Applied Mathematics, Philadelphia, PA, USA (2001)Google Scholar
  5. 5.
    Sidky, E.Y., Kao, C.M., Pan, X.: Accurate image reconstruction from few-views and limited-angle data in divergent-beam ct. Journal of X-ray Science and Technology 14, 119–139 (2006)Google Scholar
  6. 6.
    Rantala, M., Vanska, S., Jarvenpaa, S., Kalke, M., Lassas, M., Moberg, J., Siltanen, S.: Wavelet-based reconstruction for limited-angle x-ray tomography. IEEE Transactions on Medical Imaging 25, 210–217 (2006)CrossRefGoogle Scholar
  7. 7.
    Mirzargar, M., Sakhaee, E., Entezari, A.: A spline framework for sparse tomographic reconstruction. In: 2013 IEEE 10th International Symposium on Biomedical Imaging (ISBI), pp. 1272–1275 (2013)Google Scholar
  8. 8.
    Liao, H., Sapiro, G.: Sparse representations for limited data tomography. In: 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2008, pp. 1375–1378 (2008)Google Scholar
  9. 9.
    Xu, Q., Yu, H., Mou, X., Zhang, L., Hsieh, J., Wang, G.: Low-dose x-ray ct reconstruction via dictionary learning. IEEE Trans. Med. Img. 31, 1682–1697 (2012)CrossRefGoogle Scholar
  10. 10.
    Meijering, E.: Quantitative evaluation of convolution-based methods for medical image interpolation. Med. Img. Ana. 5, 111–126 (2001)CrossRefGoogle Scholar
  11. 11.
    Thévenaz, P., Blu, T., Unser, M.: Interpolation revisited. IEEE Transactions on Medical Imaging 19, 739–758 (2000)CrossRefGoogle Scholar
  12. 12.
    Entezari, A., Nilchian, M., Unser, M.: A box spline calculus for the discretization of computed tomography reconstruction problems. IEEE Transactions on Medical Imaging 31, 1532–1541 (2012)CrossRefGoogle Scholar
  13. 13.
    De Boor, C., Höllig, K., Riemenschneider, S.: Box Splines. Applied Mathematical Sciences, vol. 98. Springer, New York (1993)CrossRefzbMATHGoogle Scholar
  14. 14.
    Entezari, A., Unser, M.: A box spline calculus for computed tomography. In: IEEE International Symposium on Biomedical Imaging, pp. 600–603 (2010)Google Scholar
  15. 15.
    Smith, L.N., Elad, M.: Improving dictionary learning: Multiple dictionary updates and coefficient reuse. IEEE Signal Processing Letters 20, 79–82 (2013)CrossRefGoogle Scholar
  16. 16.
    Kolehmainen, V., Lassas, M., Niinimäki, K., Siltanen, S.: Sparsity-promoting bayesian inversion. Inverse Problems 28, 025005 (2012)Google Scholar
  17. 17.
    Ravishankar, S., Bresler, Y.: Mr image reconstruction from highly undersampled k-space data by dictionary learning. IEEE Trans. on Med. Img. 30, 1028–1041 (2011)CrossRefGoogle Scholar
  18. 18.
    Aharon, M., Elad, M.A.B.: K-svd: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE T. on Sig. Proc. 54, 4311–4322 (2006)CrossRefGoogle Scholar
  19. 19.
    Elbakri, I.A., Fessler, J.: Statistical image reconstruction for polyenergetic x-ray computed tomography. IEEE Trans. on Med. Img. 21, 89–99 (2002)CrossRefGoogle Scholar
  20. 20.
    Guerquin-Kern, M., Lejeune, L., Pruessmann, K.P., Unser, M.: Realistic analytical phantoms for parallel magnetic resonance imaging. IEEE Transactions on Medical Imaging 31, 626–636 (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Elham Sakhaee
    • 1
  • Alireza Entezari
    • 1
  1. 1.CISE DepartmentUniversity of FloridaGainesvilleUSA

Personalised recommendations