Advertisement

Adaptive Deep Dictionary Learning for MRI Reconstruction

  • D. John Lewis
  • Vanika SinghalEmail author
  • Angshul Majumdar
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11301)

Abstract

This work addresses the well known problem of reconstructing magnetic resonance images from their partially samples K-space. Compressed sensing (CS) based techniques have been used rampantly for the said problem. Later studies, instead of employing a fixed basis (like DCT, wavelet etc. as used in CS), learnt the basis adaptively from the image itself. Such studies, loosely dubbed as dictionary learning (DL) showed marked improvement over CS. This work proposes deep dictionary learning based inversion. Instead of learning a single level of basis, we learn multiple levels adaptively from the image, while reconstructing it. The results show marked improvement over all previously known techniques.

Keywords

Dictionary learning Deep learning Reconstruction 

Notes

Acknowledgements

We are thankful in part to the Infosys Center for Artificial Intelligence @ IIITD for partial support and in part to 5IOA036 FA23861610004 grant by Air Force Office of Scientific Research (AFOSR), AOARD.

References

  1. 1.
    Lustig, M., Donoho, D., Pauly, J.M.: Sparse MRI: The application of compressed sensing for rapid MR imaging. Magn. Reson. Med. 58(6), 1182–1195 (2007)CrossRefGoogle Scholar
  2. 2.
    Ravishankar, S., Bresler, Y.: MR image reconstruction from highly under sampled k-space data by dictionary learning. IEEE Trans. Med. Imaging 30(5), 1028–1041 (2011)CrossRefGoogle Scholar
  3. 3.
    Ravishankar, S., Bresler, Y.: Sparsifying transform learning for compressed sensing MRI. In: IEEE ISBI, pp. 17–20 (2013)Google Scholar
  4. 4.
    Majumdar, A.: Compressed Sensing for Magnetic Resonance Image Reconstruction. Cambridge University Press, Cambridge (2015)CrossRefGoogle Scholar
  5. 5.
    Mehta, J., Majumdar, A.: RODEO: robust DE-aliasing auto encoder for real-time medical image reconstruction. Pattern Recogn. 63, 499–510 (2017)CrossRefGoogle Scholar
  6. 6.
    Kulkarni, K., Lohit, S., Turaga, P., Kerviche, R., Ashok, A.: ReconNet: non-iterative reconstruction of images from compressively sensed measurements. In: IEEE CVPR, pp. 449–458 (2016)Google Scholar
  7. 7.
    Tariyal, S., Majumdar, A., Singh, R., Vatsa, M.: Deep dictionary learning. IEEE Access 4, 10096–10109 (2016)CrossRefGoogle Scholar
  8. 8.
    Combettes, P.L., Pesquet, J.C.: Proximal splitting methods in signal processing. In: Fixed-point Algorithms for Inverse Problems in Science and Engineering, pp. 185–212 (2011)Google Scholar
  9. 9.
    Afonso, M.V., Bioucas-Dias, J.M., Figueiredo, M.A.: An augmented Lagrangian approach to the constrained optimization formulation of imaging inverse problems. IEEE Trans. Image Process. 20(3), 681–695 (2011)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends® Mach. Learn. 3(1), 1–122 (2011)CrossRefGoogle Scholar
  11. 11.
    Daubechies, I., Defrise, M., De Mol, C.: An iterative thresholding algorithm for linear inverse problems with a sparsity constraint. Commun. Pure Appl. Math. 57(11), 1413–1457 (2004)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Maggu, J., Singh, P., Majumdar, A.: Multi-echo reconstruction from partial K-space scans via adaptively learnt basis. Magn. Reson. Imaging 45, 105–112 (2018)CrossRefGoogle Scholar
  13. 13.
    Majumdar, A., Ward, R.K.: Joint reconstruction of multiecho MR images using correlated sparsity. Magn. Reson. Imaging 29(7), 899–906 (2011)CrossRefGoogle Scholar
  14. 14.
    Majumdar, A., Ward, R.K.: Accelerating multi-echo T2 weighted MR imaging: analysis prior group-sparse optimization. J. Magn. Reson. 210(1), 90–97 (2011)CrossRefGoogle Scholar
  15. 15.
    Majumdar, A., Ward, R.K.: Calibration-less multi-coil MR image reconstruction. Magn. Reson. Imaging 30(7), 1032–1045 (2012)CrossRefGoogle Scholar
  16. 16.
    Majumdar, A., Ward, R.K.: Nuclear norm-regularized SENSE reconstruction. Magn. Reson. Imaging 30(2), 213–221 (2012)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • D. John Lewis
    • 1
  • Vanika Singhal
    • 1
    Email author
  • Angshul Majumdar
    • 1
  1. 1.Indraprastha Institute of Information TechnologyDelhiIndia

Personalised recommendations