Advertisement

Bayesian Deep Learning for Accelerated MR Image Reconstruction

  • Jo SchlemperEmail author
  • Daniel C. Castro
  • Wenjia Bai
  • Chen Qin
  • Ozan Oktay
  • Jinming Duan
  • Anthony N. Price
  • Jo Hajnal
  • Daniel Rueckert
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11074)

Abstract

Recently, many deep learning (DL) based MR image reconstruction methods have been proposed with promising results. However, only a handful of work has been focussing on characterising the behaviour of deep networks, such as investigating when the networks may fail to reconstruct. In this work, we explore the applicability of Bayesian DL techniques to model the uncertainty associated with DL-based reconstructions. In particular, we apply MC-dropout and heteroscedastic loss to the reconstruction networks to model epistemic and aleatoric uncertainty. We show that the proposed Bayesian methods achieve competitive performance when the test images are relatively far from the training data distribution and outperforms when the baseline method is over-parametrised. In addition, we qualitatively show that there seems to be a correlation between the magnitude of the produced uncertainty maps and the error maps, demonstrating the potential utility of the Bayesian DL methods for assessing the reliability of the reconstructed images.

Notes

Acknowledgements

Jo Schlemper is partially funded by EPSRC Grant (EP/P001009/1).

References

  1. 1.
    Cohen, J.P., Luck, M., Honari, S.: Distribution matching losses can hallucinate features in medical image translation. arXiv preprint arXiv:1805.08841 (2018)
  2. 2.
    Gal, Y.: Uncertainty in deep learning. University of Cambridge (2016)Google Scholar
  3. 3.
    Hammernik, K., et al.: Learning a variational network for reconstruction of accelerated MRI data. Magn. Reson. Med. 79, 3055–3071 (2017)CrossRefGoogle Scholar
  4. 4.
    Han, Y., Yoo, J., Kim, H.H., Shin, H.J., Sung, K., Ye, J.C.: Deep learning with domain adaptation for accelerated projection-reconstruction MR. Magn. Reson. Med. 80(3), 1189–1205 (2018)CrossRefGoogle Scholar
  5. 5.
    Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: Advances in Neural Information Processing Systems, pp. 5580–5590 (2017)Google Scholar
  6. 6.
    Knoll, F., Hammernik, K., Kobler, E., Pock, T., Recht, M.P., Sodickson, D.K.: Assessment of the generalization of learned image reconstruction and the potential for transfer learning. Magn. Reson. Med. (2018)Google Scholar
  7. 7.
    Mardani, M., et al.: Deep generative adversarial networks for compressed sensing automates MRI. arXiv preprint arXiv:1706.00051 (2017)
  8. 8.
    Petersen, S.E., et al.: UK Biobank’s cardiovascular magnetic resonance protocol. J. Cardiovasc. Magn. Reson. 18(1), 8 (2016). FebCrossRefGoogle Scholar
  9. 9.
    Schlemper, J., Caballero, J., Hajnal, J.V., Price, A., Rueckert, D.: A deep cascade of convolutional neural networks for dynamic MR image reconstruction. IEEE Trans. Med. Imaging 37 (2017)Google Scholar
  10. 10.
    Tanno, R., Ghosh, A., Grussu, F., Kaden, E., Criminisi, A., Alexander, D.C.: Bayesian image quality transfer. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016 Part II. LNCS, vol. 9901, pp. 265–273. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46723-8_31CrossRefGoogle Scholar
  11. 11.
    Tezcan, K.C., Baumgartner, C.F., Konukoglu, E.: MR image reconstruction using the learned data distribution as prior. CoRR abs/1711.11386 (2017). http://arxiv.org/abs/1711.11386
  12. 12.
    Yang, G., et al.: DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing MRI reconstruction. IEEE Trans. Med. Imaging 37(6), 1310–1321 (2018)CrossRefGoogle Scholar
  13. 13.
    Ye, J.C., Han, Y., Cha, E.: Deep convolutional framelets: a general deep learning framework for inverse problems. SIAM J. Imaging Sci. 11(2), 991–1048 (2018)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Jo Schlemper
    • 1
    Email author
  • Daniel C. Castro
    • 1
  • Wenjia Bai
    • 1
  • Chen Qin
    • 1
  • Ozan Oktay
    • 1
  • Jinming Duan
    • 1
  • Anthony N. Price
    • 2
  • Jo Hajnal
    • 2
  • Daniel Rueckert
    • 1
  1. 1.Biomedical Image Analysis GroupImperial College LondonLondonUK
  2. 2.Imaging and Biomedical Engineering Clinical Academic GroupKing’s College LondonLondonUK

Personalised recommendations