Skip to content
naulon
Get started

No retraction, correction or concern found when last checked on Oct 27, 2026.

Scanner invariant representations for diffusion MRI harmonization

Daniel Moyer, Greg Ver Steeg, Chantal M. W. Tax and 1 more

Magnetic Resonance in Medicine · 2020 · CC BY

doi:10.1002/mrm.28243

Abstract

Purpose. In the present work, we describe the correction of diffusion‐weighted MRI for site and scanner biases using a novel method based on invariant representation.

Theory and Methods. Pooled imaging data from multiple sources are subject to variation between the sources. Correcting for these biases has become very important as imaging studies increase in size and multi‐site cases become more common. We propose learning an intermediate representation invariant to site/protocol variables, a technique adapted from information theory‐based algorithmic fairness; by leveraging the data processing inequality, such a representation can then be used to create an image reconstruction that is uninformative of its original source, yet still faithful to underlying structures. To implement this, we use a deep learning method based on variational auto‐encoders (VAE) to construct scanner invariant encodings of the imaging data.

Results. To evaluate our method, we use training data from the 2018 MICCAI Computational Diffusion MRI (CDMRI) Challenge Harmonization dataset. Our proposed method shows improvements on independent test data relative to a recently published baseline method on each subtask, mapping data from three different scanning contexts to and from one separate target scanning context.

Conclusions. As imaging studies continue to grow, the use of pooled multi‐site imaging will similarly increase. Invariant representation presents a strong candidate for the harmonization of these data.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

Read at PubMed Central

References 53

  1. 1.

    Chen J, Liu J, Calhoun VD, et al. Exploration of scanning effects in multi‐site structural MRI studies. J Neurosci Methods. 2014;230:37–50.

    Not in our library10.1016/j.jneumeth.2014.04.023

  2. 2.

    Fortin JP, Parker D, Tunc B, et al. Harmonization of multi‐site diffusion tensor imaging data. Neuroimage. 2017;161:149–170.

    Not in our library10.1016/j.neuroimage.2017.08.047

  3. 3.

    Jovicich J, Czanner S, Greve D, et al. Reliability in multi‐site structural MRI studies: effects of gradient non‐linearity correction on phantom and human data. Neuroimage. 2006;30:436–443.

    Not in our library10.1016/j.neuroimage.2005.09.046

  4. 4.

    Hawco C, Viviano JD, Chavez S, et al. A longitudinal human phantom reliability study of multi‐center T1‐weighted, DTI, and resting state fMRI data. Psychiatry Res‐Neuroim. 2018;282:134–142.

    Not in our library10.1016/j.pscychresns.2018.06.004

  5. 5.
    Widespread white matter microstructural differences in schizophrenia across 4322 individuals: results from the ENIGMA Schizophrenia DTI Working Group · 2017
    No notice
  6. 6.

    Magnotta VA, Matsui JT, Liu D, et al. Multicenter reliability of diffusion tensor imaging. Brain Connectivity. 2012;2:345–355.

    Not in our library10.1089/brain.2012.0112

  7. 7.

    Zavaliangos‐Petropulu A, Nir TM, Thomopoulos SI, et al. Diffusion MRI indices and their relation to cognitive impairment in brain aging: the updated multi‐protocol approach in ADNI3. Front Neuroinform. 2019;13:2.

    Not in our library10.3389/fninf.2019.00002

  8. 8.

    Correia MM, Carpenter TA, Williams GB. Looking for the optimal DTI acquisition scheme given a maximum scan time: are more b‐values a waste of time? Magn Reson Imaging. 2009;27:163–175.

    Not in our library10.1016/j.mri.2008.06.011

  9. 9.

    Giannelli M, Cosottini M, Michelassi MC, et al. Dependence of brain DTI maps of fractional anisotropy and mean diffusivity on the number of diffusion weighting directions. J Appl Clin Med Phys. 2010;11:176–190.

    Not in our library10.1120/jacmp.v11i1.2927

  10. 10.

    Pagani E, Hirsch JG, Pouwels PJ, et al. Intercenter differences in diffusion tensor MRI acquisition. J Magn Reson Imaging. 2010;31:1458–1468.

    Not in our library10.1002/jmri.22186

  11. 11.

    Papinutto ND, Maule F, Jovicich J. Reproducibility and biases in high field brain diffusion MRI: an evaluation of acquisition and analysis variables. Magn Reson Imaging. 2013;31:827–839.

    Not in our library10.1016/j.mri.2013.03.004

  12. 12.
    Identical, but not the same: Intra-site and inter-site reproducibility of fractional anisotropy measures on two 3.0T scanners · 2010
    No notice
  13. 13.

    White T, Magnotta VA, Bockholt HJ, et al. Global white matter abnormalities in schizophrenia: a multisite diffusion tensor imaging study. Schizophrenia Bull. 2009;37:222–232.

    Not in our library10.1093/schbul/sbp088

  14. 14.

    Zhan L, Leow AD, Jahanshad N, et al. How does angular resolution affect diffusion imaging measures? Neuroimage. 2010;49:1357–1371.

    Not in our library10.1016/j.neuroimage.2009.09.057

  15. 15.

    Zhan L, Mueller BA, Jahanshad N, et al. Magnetic resonance field strength effects on diffusion measures and brain connectivity networks. Brain Connectivity. 2013;3:72–86.

    Not in our library10.1089/brain.2012.0114

  16. 16.

    Zhan L, Franc D, Patel V, et al. How do spatial and angular resolution affect brain connectivity maps from diffusion MRI? In: 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI). Barcelona, Spain: IEEE; 2012:1–4.

    Not in our library10.1109/isbi.2012.6235469

  17. 17.

    Blumberg SB, Tanno R, Kokkinos I, Alexander DC. Deeper image quality transfer: training low‐memory neural networks for 3D images In: MICCAI. Granada, Spain: Springer; 2018 118–125.

    Not in our library

  18. 18.

    Tanno R, Worrall DE, Ghosh A, et al. Bayesian image quality transfer with CNNs: exploring uncertainty in dMRI super‐resolution In: MICCAI. Quebec City, Canada: Springer; 2017;611–619.

    Not in our library

  19. 19.

    Mirzaalian H, Ning L, Savadjiev P. Multi‐site harmonization of diffusion MRI data in a registration framework. Brain Imaging Behavior. 2018;12:284–295.

    Not in our library10.1007/s11682-016-9670-y

  20. 20.

    Ning L, Bonet‐Carne E, Grussu F, et al. Multi‐shell diffusion MRI harmonisation and enhancement challenge (MUSHAC): progress and results In: International Conference on Medical Image Computing and Computer‐Assisted Intervention. Granada, Spain: Springer; 2018;217–224.

    Not in our library

  21. 21.

    Tax CM, Grussu F, Kaden E, et al. Cross‐vendor and cross‐protocol harmonisation of diffusion MRI data: a comparative study In: Proceedings of the International Society for Magnetic Resonance in Medicine. Paris. 2018;471.

    Not in our library

  22. 22.

    Zhu AH, Moyer DC, Nir TM, Thompson PM, Jahanshad N. Challenges and opportunities in dMRI data harmonization In: International Conference on Medical Image Computing and Computer‐Assisted Intervention. Granada, Spain: Springer; 2018:157–172.

    Not in our library

  23. 23.

    Johnson WE, Li C, Rabinovic A. Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostatistics. 2007;8:118–127.

    Not in our library10.1093/biostatistics/kxj037

  24. 24.

    Mirzaalian H, de Pierrefeu A, Savadjiev P, et al. Harmonizing diffusion MRI data across multiple sites and scanners In: MICCAI. Munich, Germany: Springer; 2015;12–19.

    Not in our library10.1007/978-3-319-24553-9_2

  25. 25.

    Mirzaalian H, Ning L, Savadjiev P. Inter‐site and inter‐scanner diffusion MRI data harmonization. Neuroimage. 2016;135:311–323.

    Not in our library10.1016/j.neuroimage.2016.04.041

  26. 26.

    Karayumak SC, Bouix S, Ning L, et al. Retrospective harmonization of multi‐site diffusion MRI data acquired with different acquisition parameters. Neuroimage. 2019;184:180–200.

    Not in our library10.1016/j.neuroimage.2018.08.073

  27. 27.

    Karayumak SC, Kubicki M, Rathi Y. Harmonizing diffusion MRI data across magnetic field strengths In: International Conference on Medical Image Computing and Computer‐Assisted Intervention. Granada, Spain: Springer; 2018;116–124.

    Not in our library

  28. 28.

    Koppers S, Bloy L, Berman JI, Tax CM, Edgar JC, Merhof D. Spherical harmonic residual network for diffusion signal harmonization. 2018; arXiv preprint arXiv:1808.01595

    Not in our library

  29. 29.

    Cover TM, Thomas JA. Elements of Information Theory. Hoboken, NJ: John Wiley & Sons; 2012.

    Not in our library

  30. 30.

    Moyer D, Gao S, Brekelmans R, Galstyan A, Ver Steeg G. Invariant representations without adversarial training In: Advances in Neural Information Processing Systems. Montreal, Canada: Curran Associates, Inc.; 2018;31:9102–9111.

    Not in our library

  31. 31.

    Kingma DP, Welling M. Auto‐encoding variational Bayes. 2013; arXiv preprint arXiv:1312.6114.

    Not in our library

  32. 32.

    Higgins I, Matthey L, Pal A, et al. beta‐VAE: learning basic visual concepts with a constrained variational framework. ICLR. 2017;2:6.

    Not in our library

  33. 33.

    Goodfellow I, Bengio Y, Courville A. Deep Learning. Cambridge, MA: MIT Press; 2016.

    Not in our library

  34. 34.

    Rumelhart DE, Hinton GE, Williams RJ. Learning internal representations by error propagation. Technical Report, California Univ San Diego La Jolla Inst for Cognitive Science; 1985.

    Not in our library

  35. 35.

    Kingma, DP, Ba J. Adam: a method for stochastic optimization. 2014; arXiv preprint arXiv:1412.6980.

    Not in our library

  36. 36.

    Tax CM, Grussu F, Kaden E, et al. Cross‐scanner and cross‐protocol diffusion mri data harmonisation: a benchmark database and evaluation of algorithms. Neuroimage. 2019;195:285–299.

    Not in our library10.1016/j.neuroimage.2019.01.077

  37. 37.

    Andersson JL, Skare S, Ashburner J. How to correct susceptibility distortions in spin‐echo echo‐planar images: application to diffusion tensor imaging. Neuroimage. 2003;20:870–888.

    Not in our library10.1016/s1053-8119(03)00336-7

  38. 38.
    An integrated approach to correction for off-resonance effects and subject movement in diffusion MR imaging · 2016
    No notice
  39. 39.

    Glasser MF, Sotiropoulos SN, Wilson JA, et al. The minimal preprocessing pipelines for the Human Connectome Project. Neuroimage. 2013;80:105–124.

    Not in our library10.1016/j.neuroimage.2013.04.127

  40. 40.

    Rudrapatna S, Parker G, Roberts J, Jones D. Can we correct for interactions between subject motion and gradient‐nonlinearity in diffusion MRI. In: Proceedings of the International Society for Magnetic Resonance in Medicine, Paris, France; 2018;1206.

    Not in our library

All 53 references

Cited by papers we hold 3

Reads

Read by people on this page

None yet.

Checked or read by AI through naulon

None yet.

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.

Are you an author?

Is this your paper?

Claim it to add your note and be paid when agents cite it. Free.