Advertisement

A Deep Ensemble Network for Compressed Sensing MRI

  • Huafeng Wu
  • Yawen Wu
  • Liyan Sun
  • Congbo Cai
  • Yue Huang
  • Xinghao Ding
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11301)

Abstract

Compressed sensing theory has been proven to accelerate magnetic resonance imaging by measuring less K-space data called CS-MRI. Conventional sparse-optimization based CS-MRI methods lack enough capacity to encode rich patterns within the MR images and the iterative optimization for sparse recovery is often time-consuming. Although the deep convolutional neural network (CNN) models have achieved the state-of-the-art performance on CS-MRI reconstruction recently, the fine structure details can be degraded due to the information loss when the network goes deep. In order to better transfer the information in lossless way, we design deep ensemble network (DEN) architecture inspired by the novel interpretation of deep neural network in ensemble respect. The DEN model is formed by cascaded basic blocks for CS-MRI. Within the blocks, information flows forward through different depth. The intermediate outputs reconstructed by each block are merged via \(3\times 3\) convolution to generate the final reconstruction result. The experimental results show the proposed DEN model outperforms other state-of-the-art nondeep and deep CS-MRI models.

Keywords

Compressed sensing magnetic resonance imaging Convolutional neural network Ensemble learning 

References

  1. 1.
    Lustig, M., Donoho, D.L., Santos, J.M., Pauly, J.M.: Compressed sensing MRI. IEEE Sig. Process. Mag. 25(2), 72–82 (2008)CrossRefGoogle Scholar
  2. 2.
    Lustig, M., Donoho, D., Pauly, J.M.: Sparse MRI: the application of compressed sensing for rapid MR imaging. Magn. Reson. Med.: Official J. Int. Soc. Magn. Reson. Med. 58(6), 1182–1195 (2007)CrossRefGoogle Scholar
  3. 3.
    Qu, X., et al.: Undersampled MRI reconstruction with patch-based directional wavelets. Magn. Reson. Imaging 30(7), 964–977 (2012)CrossRefGoogle Scholar
  4. 4.
    Lai, Z., et al.: Image reconstruction of compressed sensing MRI using graph-based redundant wavelet transform. Med. Image Anal. 27, 93–104 (2016)CrossRefGoogle Scholar
  5. 5.
    Ravishankar, S.: Magnetic resonance image reconstruction from highly undersampled K-space data using dictionary learning (2011)Google Scholar
  6. 6.
    Huang, Y., Paisley, J., Lin, Q., Ding, X., Fu, X., Zhang, X.P.: Bayesian nonparametric dictionary learning for compressed sensing MRI. IEEE Trans. Image Process. 23(12), 5007–5019 (2014)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Ravishankar, S., Bresler, Y.: Sparsifying transform learning for compressed sensing MRI. In: 2013 IEEE 10th International Symposium on Biomedical Imaging (ISBI), pp. 17–20. IEEE (2013)Google Scholar
  8. 8.
    Qu, X., Hou, Y., Lam, F., Guo, D., Zhong, J., Chen, Z.: Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator. Med. Image Anal. 18(6), 843–856 (2014)CrossRefGoogle Scholar
  9. 9.
    Wang, S., et al.: Accelerating magnetic resonance imaging via deep learning. In: 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), pp. 514–517. IEEE (2016)Google Scholar
  10. 10.
    Lee, D., Yoo, J., Ye, J.C.: Deep residual learning for compressed sensing MRI. In: 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), pp. 15–18. IEEE (2017)Google Scholar
  11. 11.
    Hammernik, K., et al.: Learning a variational network for reconstruction of accelerated MRI data. Magn. Reson. Med. 79(6), 3055–3071 (2018)CrossRefGoogle Scholar
  12. 12.
    Schlemper, J., Caballero, J., Hajnal, J.V., Price, A., Rueckert, D.: A deep cascade of convolutional neural networks for MR image reconstruction. arXiv preprint arXiv:1703.00555 (2017)
  13. 13.
    Breiman, L.: Stacked regressions. Mach. Learn. 24(1), 49–64 (1996)MathSciNetzbMATHGoogle Scholar
  14. 14.
    Breiman, L.: Bagging predictors. Mach. Learn. 24(2), 123–140 (1996)MathSciNetzbMATHGoogle Scholar
  15. 15.
    Freund, Y., Schapire, R.E., et al.: Experiments with a new boosting algorithm. In: ICML, vol. 96, pp. 148–156. Citeseer (1996)Google Scholar
  16. 16.
    Drucker, H., Cortes, C., Jackel, L.D., LeCun, Y., Vapnik, V.: Boosting and other ensemble methods. Neural Comput. 6(6), 1289–1301 (1994)CrossRefGoogle Scholar
  17. 17.
    Veit, A., Wilber, M.J., Belongie, S.: Residual networks behave like ensembles of relatively shallow networks. In: Advances in Neural Information Processing Systems, pp. 550–558 (2016)Google Scholar
  18. 18.
    Larsson, G., Maire, M., Shakhnarovich, G.: FractalNet: ultra-deep neural networks without residuals. arXiv preprint arXiv:1605.07648 (2016)
  19. 19.
    Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, vol. 1, p. 3 (2017)Google Scholar
  20. 20.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  21. 21.
    Kim, J., Kwon Lee, J., Mu Lee, K.: Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1646–1654 (2016)Google Scholar
  22. 22.
    Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: OSDI, vol. 16, pp. 265–283 (2016)Google Scholar
  23. 23.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249–256 (2010)Google Scholar
  24. 24.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  25. 25.
    Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Huafeng Wu
    • 1
  • Yawen Wu
    • 1
  • Liyan Sun
    • 1
  • Congbo Cai
    • 1
  • Yue Huang
    • 1
  • Xinghao Ding
    • 1
  1. 1.Fujian Key Laboratory of Sensing and Computing for Smart City, School of Information Science and EngineeringXiamen UniversityXiamenChina

Personalised recommendations