Advertisement

Deep Learning for Low-Field to High-Field MR: Image Quality Transfer with Probabilistic Decimation Simulator

  • Hongxiang LinEmail author
  • Matteo Figini
  • Ryutaro Tanno
  • Stefano B. Blumberg
  • Enrico Kaden
  • Godwin Ogbole
  • Biobele J. Brown
  • Felice D’Arco
  • David W. Carmichael
  • Ikeoluwa Lagunju
  • Helen J. Cross
  • Delmiro Fernandez-Reyes
  • Daniel C. Alexander
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11905)

Abstract

MR images scanned at low magnetic field (\({<}1\)T) have lower resolution in the slice direction and lower contrast, due to a relatively small signal-to-noise ratio (SNR) than those from high field (typically 1.5T and 3T). We adapt the recent idea of Image Quality Transfer (IQT) to enhance very low-field structural images aiming to estimate the resolution, spatial coverage, and contrast of high-field images. Analogous to many learning-based image enhancement techniques, IQT generates training data from high-field scans alone by simulating low-field images through a pre-defined decimation model. However, the ground truth decimation model is not well-known in practice, and lack of its specification can bias the trained model, aggravating performance on the real low-field scans. In this paper we propose a probabilistic decimation simulator to improve robustness of model training. It is used to generate and augment various low-field images whose parameters are random variables and sampled from an empirical distribution related to tissue-specific SNR on a 0.36T scanner. The probabilistic decimation simulator is model-agnostic, that is, it can be used with any super-resolution networks. Furthermore we propose a variant of U-Net architecture to improve its learning performance. We show promising qualitative results from clinical low-field images confirming the strong efficacy of IQT in an important new application area: epilepsy diagnosis in sub-Saharan Africa where only low-field scanners are normally available.

Notes

Acknowledgements

This work was supported by EPSRC grants (EP/R014019/1, EP/R006032/1 and EP/M020533/1) and the NIHR UCLH Biomedical Research Centre. Data were provided in part by the Human Connectome Project, WU-Minn Consortium (Principal Investigators: David Van Essen and Kamil Ugurbil; 1U54MH091657) funded by NIH and Washington University. The 0.36T MRI data were acquired at the University College Hospital, Ibadan, Nigeria.

References

  1. 1.
    Wadghiri, Y.Z., Johnson, G., Turnbull, D.H.: Sensitivity and performance time in MRI dephasing artifact reduction methods. Magn. Reson. Med. 45(3), 470–476 (2001)CrossRefGoogle Scholar
  2. 2.
    Sotiropoulos, S.N., et al.: Advances in diffusion MRI acquisition and processing in the human connectome project. NeuroImage 80, 125–143 (2013)CrossRefGoogle Scholar
  3. 3.
    Marques, J.P., Simonis, F.F.J., Webb, A.G.: Low-field MRI: an MR physics perspective. J. Magn. Reson. Imaging 49(6), 1528–1542 (2019)CrossRefGoogle Scholar
  4. 4.
    Brown, R.W., Cheng, Y.-C.N., Haacke, E.M., Thompson, M.R., Venkatesan, R.: Magnetic Resonance Imaging: Physical Principles and Sequence Design, 2nd edn. Wiley, Hoboken (2014)CrossRefGoogle Scholar
  5. 5.
    Bahrami, K., Shi, F., Zong, X., Shin, H.W., An, H., Shen, D.: Reconstruction of 7T-Like Images from 3T MRI. IEEE Trans. Med. Imaging 35(9), 2085–2097 (2016)CrossRefGoogle Scholar
  6. 6.
    Wolterink, J.M., Dinkla, A.M., Savenije, M.H.F., Seevinck, P.R., van den Berg, C.A.T., Išgum, I.: Deep MR to CT synthesis using unpaired data. In: Tsaftaris, S.A., Gooya, A., Frangi, A.F., Prince, J.L. (eds.) SASHIMI 2017. LNCS, vol. 10557, pp. 14–23. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-68127-6_2CrossRefGoogle Scholar
  7. 7.
    Cohen, J.P., Luck, M., Honari, S.: Distribution matching losses can hallucinate features in medical image translation. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 529–536. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00928-1_60CrossRefGoogle Scholar
  8. 8.
    Alexander, D.C., et al.: Image quality transfer and applications in diffusion MRI. NeuroImage 152, 283–298 (2017)CrossRefGoogle Scholar
  9. 9.
    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. LNCS, vol. 9901, pp. 265–273. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46723-8_31CrossRefGoogle Scholar
  10. 10.
    Tanno, R., Worrall, D.E., Ghosh, A., Kaden, E., Sotiropoulos, S.N., Criminisi, A., Alexander, D.C.: Bayesian image quality transfer with CNNs: exploring uncertainty in dMRI super-resolution. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 611–619. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66182-7_70CrossRefGoogle Scholar
  11. 11.
    Blumberg, S.B., Tanno, R., Kokkinos, I., Alexander, D.C.: Deeper image quality transfer: training low-memory neural networks for 3D images. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 118–125. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00928-1_14CrossRefGoogle Scholar
  12. 12.
    Ashburner, J., Friston, K.J.: Unified segmentation. NeuroImage 26, 839–851 (2005)CrossRefGoogle Scholar
  13. 13.
    Heinrich, L., Bogovic, J.A., Saalfeld, S.: Deep learning for isotropic super-resolution from non-isotropic 3D electron microscopy. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10434, pp. 135–143. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66185-8_16CrossRefGoogle Scholar
  14. 14.
    Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 424–432. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46723-8_49CrossRefGoogle Scholar
  15. 15.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. CVPR 2016, 770–778 (2016)Google Scholar
  16. 16.
    Dong, C., Loy, C.C., Tang, X.: Accelerating the super-resolution convolutional neural network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 391–407. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46475-6_25CrossRefGoogle Scholar
  17. 17.
    Guerrero, R., et al.: White matter hyperintensity and stroke lesion segmentation and differentiation using convolutional neural networks. NeuroImage Clin. 17, 918–934 (2018)CrossRefGoogle Scholar
  18. 18.
    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
  19. 19.
    Chollet, F., et al.: Keras (2015). https://keras.io
  20. 20.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  21. 21.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: AISTATS 2010, PMLR, vol. 9, pp. 249–256 (2010)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Hongxiang Lin
    • 1
    Email author
  • Matteo Figini
    • 1
  • Ryutaro Tanno
    • 1
    • 2
  • Stefano B. Blumberg
    • 1
  • Enrico Kaden
    • 1
  • Godwin Ogbole
    • 3
  • Biobele J. Brown
    • 4
  • Felice D’Arco
    • 5
  • David W. Carmichael
    • 6
    • 7
  • Ikeoluwa Lagunju
    • 4
  • Helen J. Cross
    • 5
    • 6
  • Delmiro Fernandez-Reyes
    • 1
    • 4
  • Daniel C. Alexander
    • 1
  1. 1.Centre for Medical Image Computing and Department of Computer ScienceUniversity College LondonLondonUK
  2. 2.Machine Intelligence and Perception GroupMicrosoft Research CambridgeCambridgeUK
  3. 3.Department of Radiology, College of MedicineUniversity of IbadanIbadanNigeria
  4. 4.Department of Paediatrics, College of MedicineUniversity of IbadanIbadanNigeria
  5. 5.Great Ormond Street Hospital for ChildrenLondonUK
  6. 6.UCL Great Ormond Street Institute of Child HealthLondonUK
  7. 7.Department of Biomedical EngineeringKing’s College LondonLondonUK

Personalised recommendations