Advertisement

Spherical Harmonic Residual Network for Diffusion Signal Harmonization

  • Simon KoppersEmail author
  • Luke Bloy
  • Jeffrey I. Berman
  • Chantal M. W. Tax
  • J. Christopher Edgar
  • Dorit Merhof
Conference paper
Part of the Mathematics and Visualization book series (MATHVISUAL)

Abstract

Diffusion imaging is an important method in the field of neuroscience, as it is sensitive to changes within the tissue microstructure of the human brain. However, a major challenge when using MRI to derive quantitative measures is that the use of different scanners, as used in multi-site group studies, introduces measurement variability. This can lead to an increased variance in quantitative metrics, even if the same brain is scanned. Contrary to the assumption that these characteristics are comparable and similar, small changes in these values are observed in many clinical studies, hence harmonization of the signals is essential. In this paper, we present a method that does not require additional preprocessing, such as segmentation or registration, and harmonizes the signal based on a deep learningresidual network. For this purpose, a training database is required, which consist of the same subjects, scanned on different scanners. The results show that harmonized signals are significantly more similar to the ground truth signal compared to no harmonization, but also improve in comparison to another deep learning method. The same effect is also demonstrated in commonly used metrics derived from the diffusion MRI signal.

Keywords

Harmonization Diffusion imaging Magnetic resonance imaging Machine learning Deep learning SHResNet 

Notes

Acknowledgements

The authors would like to thank the 2017 computational dMRI challenge organizers (Francesco Grussu, Enrico Kaden, Lipeng Ning and Jelle Veraart) for help with data acquisition and processing, as well as Derek Jones, Umesh Rudrapatna, John Evans, Slawomir Kusmia, Cyril Charron, and David Linden at CUBRIC, Cardiff University, and Fabrizio Fasano at Siemens for their support with data acquisition.

This work was supported by a Rubicon grant from the NWO (680-50-1527), a Wellcome Trust Investigator Award (096646/Z/11/Z), and a Wellcome Trust Strategic Award (104943/Z/14/Z). The data were acquired at the UK National Facility for In Vivo MR Imaging of Human Tissue Microstructure funded by the EPSRC (grant EP/M029778/1), and The Wolfson Foundation. This work was supported by the International Research Training Group 2150 of the German Research Foundation (DFG).

References

  1. 1.
    Andersson, J.L., Skare, S., Ashburner, J.: How to correct susceptibility distortions in spin-echo echo-planar images: application to diffusion tensor imaging. Neuroimage 20(2), 870–888 (2003)CrossRefGoogle Scholar
  2. 2.
    Andersson, J.L., Sotiropoulos, S.N.: An integrated approach to correction for off-resonance effects and subject movement in diffusion MR imaging. Neuroimage 125, 1063–1078 (2016)CrossRefGoogle Scholar
  3. 3.
    Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157–166 (1994)CrossRefGoogle Scholar
  4. 4.
    Fortin, J.P., Parker, D., Tunç, B., Watanabe, T., Elliott, M.A., Ruparel, K., Roalf, D.R., Satterthwaite, T.D., Gur, R.C., Gur, R.E., Schultz, R.T., Verma, R., Shinohara, R.T.: Harmonization of multi-site diffusion tensor imaging data. NeuroImage 161, 149–170 (2017). http://www.sciencedirect.com/science/article/pii/S1053811917306948CrossRefGoogle Scholar
  5. 5.
    Golkov, V., Dosovitskiy, A., Sperl, J.I., Menzel, M.I., Czisch, M., Sämann, P., Brox, T., Cremers, D.: q-space deep learning for twelve-fold shorter and model-free diffusion MRI scans. IEEE Trans. Med. Imaging 35(5), 1344–1351 (2016)CrossRefGoogle Scholar
  6. 6.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)Google Scholar
  7. 7.
    Jenkinson, M., Beckmann, C.F., Behrens, T.E., Woolrich, M.W., Smith, S.M.: Fsl. NeuroImage 62(2), 782–790 (2012). http://www.sciencedirect.com/science/article/pii/S1053811911010603, 20 YEARS OF fMRICrossRefGoogle Scholar
  8. 8.
    Klein, S., Staring, M., Murphy, K., Viergever, M.A., Pluim, J.P.: elastix: a toolbox for intensity-based medical image registration. IEEE Trans. Med. Imaging 29(1), 196–205 (2010)CrossRefGoogle Scholar
  9. 9.
    Koppers, S., Haarburger, C., Merhof, D.: Diffusion MRI signal augmentation: from single shell to multi shell with deep learning. In: CDMRI, pp. 61–70. Springer (2016)Google Scholar
  10. 10.
    Mirzaalian, H., Ning, L., Savadjiev, P., Pasternak, O., Bouix, S., Michailovich, O., Karmacharya, S., Grant, G., Marx, C.E., Morey, R.A., Flashman, L.A., George, M.S., McAllister, T.W., Andaluz, N., Shutter, L., Coimbra, R., Zafonte, R.D., Coleman, M.J., Kubicki, M., Westin, C.F., Stein, M.B., Shenton, M.E., Rathi, Y.: Multi-site harmonization of diffusion MRI data in a registration framework. Brain Imaging Behav. 12(1), 284–295 (2018).  https://doi.org/10.1007/s11682-016-9670-yCrossRefGoogle Scholar
  11. 11.
    Mirzaalian, H., de Pierrefeu, A., Savadjiev, P., Pasternak, O., Bouix, S., Kubicki, M., Westin, C.F., Shenton, M.E., Rathi, Y.: Harmonizing diffusion MRI data across multiple sites and scanners. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A. (eds.) Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, pp. 12–19. Springer International Publishing, Cham (2015)CrossRefGoogle Scholar
  12. 12.
    Tax, M.W., C., Grussu, F., Kaden, E., Ning, L., Rudrapatna, U., Evans, J., St-Jean, S., Leemans, A., Puch, S., Rowe, M., Rodrigues, P., Prĉkovska, V., Koppers, S., Merhof, D., Ghosh, A., Tanno, R., C Alexander, D., Charron, C., Kusmia, S., EJ Linden, D., K Jones, D., Veraart, J.: Cross-vendor and cross-protocol harmonisation of diffusion tensor imaging data: a comparative study. ISMRM-ESMRMB (2018). https://projects.iq.harvard.edu/cdmri2017
  13. 13.
    Vollmar, C., Identical et al.: But not the same: Intra-site and inter-site reproducibility of fractional anisotropy measures on two 3.0 T scanners. Neuroimage 51(4), 1384–1394 (2010)CrossRefGoogle Scholar
  14. 14.
    Zhang, Y., et al.: Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm. IEEE Trans. Med. Imaging 20(1), 45–57 (2001)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Simon Koppers
    • 1
    • 2
    Email author
  • Luke Bloy
    • 2
  • Jeffrey I. Berman
    • 2
  • Chantal M. W. Tax
    • 3
  • J. Christopher Edgar
    • 2
  • Dorit Merhof
    • 1
  1. 1.Institute of Imaging & Computer VisionRWTH Aachen UniversityAachenGermany
  2. 2.Department of RadiologyChildren’s Hospital of PhiladelphiaPhiladelphiaUSA
  3. 3.CURBRIC, Cardiff UniversityCardiffUK

Personalised recommendations