Accelerated Dynamic MRI Reconstruction with Total Variation and Nuclear Norm Regularization

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9350)


In this paper, we propose a novel compressive sensing model for dynamic MR reconstruction. With total variation (TV) and nuclear norm (NN) regularization, our method can utilize both spatial and temporal redundancy in dynamic MR images. Due to the non-smoothness and non-separability of TV and NN terms, it is difficult to optimize the primal problem. To address this issue, we propose a fast algorithm by solving a primal-dual form of the original problem. The ergodic convergence rate of the proposed method is \(\mathcal{O}(1/N)\) for N iterations. In comparison with six state-of-the-art methods, extensive experiments on single-coil and multi-coil dynamic MR data demonstrate the superior performance of the proposed method in terms of both reconstruction accuracy and time complexity.


Compressive Sensing Nuclear Norm Coil Sensitivity Temporal Cross Section Anisotropic Total Variation 
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.


  1. 1.
    Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press, Cambridge (2004)CrossRefzbMATHGoogle Scholar
  2. 2.
    Caballero, J., Price, A.N., Rueckert, D., Hajnal, J.: Dictionary learning and time sparsity for dynamic MR data reconstruction. IEEE Transactions on Medical Imaging 33(4), 979–994 (2014)CrossRefGoogle Scholar
  3. 3.
    Chambolle, A.: An algorithm for total variation minimization and applications. Journal of Mathematical Imaging and Vision 20(1-2), 89–97 (2004)MathSciNetGoogle Scholar
  4. 4.
    Chambolle, A., Pock, T.: On the ergodic convergence rates of a first-order primal-dual algorithm. Technical report, Optimization online preprint No. 4532 (2014)Google Scholar
  5. 5.
    Chen, C., Li, Y., Axel, L., Huang, J.: Real time dynamic MRI with dynamic total variation. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014, Part I. LNCS, vol. 8673, pp. 138–145. Springer, Heidelberg (2014)Google Scholar
  6. 6.
    Gamper, U., Boesiger, P., Kozerke, S.: Compressed sensing in dynamic MRI. Magnetic Resonance in Medicine 59(2), 365–373 (2008)CrossRefGoogle Scholar
  7. 7.
    He, B., Yuan, X.: Convergence analysis of primal-dual algorithms for a saddle-point problem: From contraction perspective. SIAM Journal on Imaging Sciences 5(1), 119–149 (2012)MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Huang, J., Zhang, S., Li, H., Metaxas, D.: Composite splitting algorithms for convex optimization. Computer Vision and Image Understanding 115(12), 1610–1622 (2011)CrossRefGoogle Scholar
  9. 9.
    Huang, J., Zhang, S., Metaxas, D.: Efficient MR image reconstruction for compressed MR imaging. Medical Image Analysis 15(5), 670–679 (2011)CrossRefGoogle Scholar
  10. 10.
    Li, Y., Chen, C., Huang, X., Huang, J.: Instrument tracking via online learning in retinal microsurgery. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014, Part I. LNCS, vol. 8673, pp. 464–471. Springer, Heidelberg (2014)Google Scholar
  11. 11.
    Li, Y., Chen, C., Liu, W., Huang, J.: Sub-selective quantization for large-scale image search. In: Proc. AAAI Conference on Artificial Intelligence (AAAI), pp. 2803–2809 (2014)Google Scholar
  12. 12.
    Lingala, S.G., Hu, Y., DiBella, E., Jacob, M.: Accelerated dynamic MRI exploiting sparsity and low-rank structure: k-t SLR. IEEE Transactions on Medical Imaging 30(5), 1042–1054 (2011)CrossRefGoogle Scholar
  13. 13.
    Lustig, M., Donoho, D., Pauly, J.M.: Sparse MRI: The application of compressed sensing for rapid MR imaging. Magnetic Resonance in Medicine 58(6), 1182–1195 (2007)CrossRefGoogle Scholar
  14. 14.
    Lustig, M., Santos, J.M., Donoho, D.L., Pauly, J.M.: k-t SPARSE: High frame rate dynamic MRI exploiting spatio-temporal sparsity. In: Proceedings of the Annual Meeting of ISMRM, p. 2420 (2006)Google Scholar
  15. 15.
    Ma, S., Goldfarb, D., Chen, L.: Fixed point and bregman iterative methods for matrix rank minimization. Mathematical Programming 128(1-2), 321–353 (2011)MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Otazo, R., Cands, E., Sodickson, D.K.: Low-rank plus sparse matrix decomposition for accelerated dynamic MRI with separation of background and dynamic components. Magnetic Resonance in Medicine 73(3), 1125–1136 (2015)CrossRefGoogle Scholar
  17. 17.
    Otazo, R., Kim, D., Axel, L., Sodickson, D.K.: Combination of compressed sensing and parallel imaging for highly accelerated first-pass cardiac perfusion MRI. Magnetic Resonance in Medicine 64(3), 767–776 (2010)CrossRefGoogle Scholar
  18. 18.
    Trémoulhéac, B., Dikaios, N., Atkinson, D., Arridge, S.: Dynamic MR image reconstruction-separation from under-sampled (k,t)-space via low-rank plus sparse prior. IEEE Transactions on Medical Imaging 33(8), 1689–1701 (2014)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringUniversity of Texas at ArlingtonArlingtonUSA
  2. 2.Computer Science and Engineering DepartmentLehigh UniversityBethlehemUSA

Personalised recommendations