Advertisement

Relevance Vector Machines for Harmonization of MRI Brain Volumes Using Image Descriptors

  • Maria Ines MeyerEmail author
  • Ezequiel de la Rosa
  • Koen Van Leemput
  • Diana M. Sima
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11796)

Abstract

With the increased need for multi-center magnetic resonance imaging studies, problems arise related to differences in hardware and software between centers. Namely, current algorithms for brain volume quantification are unreliable for the longitudinal assessment of volume changes in this type of setting. Currently most methods attempt to decrease this issue by regressing the scanner- and/or center-effects from the original data. In this work, we explore a novel approach to harmonize brain volume measurements by using only image descriptors. First, we explore the relationships between volumes and image descriptors. Then, we train a Relevance Vector Machine (RVM) model over a large multi-site dataset of healthy subjects to perform volume harmonization. Finally, we validate the method over two different datasets: (i) a subset of unseen healthy controls; and (ii) a test-retest dataset of multiple sclerosis (MS) patients. The method decreases scanner and center variability while preserving measurements that did not require correction in MS patient data. We show that image descriptors can be used as input to a machine learning algorithm to improve the reliability of longitudinal volumetric studies.

Keywords

RVM Harmonization MRI Brain volumes 

References

  1. 1.
    Bermel, R.A., Bakshi, R.: The measurement and clinical relevance of brain atrophy in multiple sclerosis. Lancet Neurol. 5(2), 158–170 (2006)CrossRefGoogle Scholar
  2. 2.
    Biberacher, V., et al.: Intra- and interscanner variability of magnetic resonance imaging based volumetry in multiple sclerosis. NeuroImage 142, 188–197 (2016).  https://doi.org/10.1016/j.neuroimage.2016.07.035CrossRefGoogle Scholar
  3. 3.
    Biomedical Image Analysis Group, Imperial College London: Ixi dataset. https://brain-development.org/ixi-dataset/. Accessed on 18 Mar 2019
  4. 4.
    Chen, J., et al.: Exploration of scanning effects in multi-site structural MRI studies. J. Neurosci. Methods 230, 37–50 (2014).  https://doi.org/10.1016/j.jneumeth.2014.04.023CrossRefGoogle Scholar
  5. 5.
    Chua, A.S., et al.: Handling changes in MRI acquisition parameters in modeling whole brain lesion volume and atrophy data in multiple sclerosis subjects: comparison of linear mixed-effect models. NeuroImage: Clin. 8, 606–610 (2015)CrossRefGoogle Scholar
  6. 6.
    Fortin, J.P., et al.: Harmonization of cortical thickness measurements across scanners and sites. NeuroImage 167, 104–120 (2018).  https://doi.org/10.1016/j.neuroimage.2017.11.024CrossRefGoogle Scholar
  7. 7.
    Jain, S., et al.: Automatic segmentation and volumetry of multiple sclerosis brain lesions from MR images. NeuroImage: Clin. 8, 367–375 (2015).  https://doi.org/10.1016/j.nicl.2015.05.003CrossRefGoogle Scholar
  8. 8.
    Jones, B.C., et al.: Quantification of multiple-sclerosis-related brain atrophy in two heterogeneous MRI datasets using mixed-effects modeling. NeuroImage: Clin. 3, 171–179 (2013).  https://doi.org/10.1016/j.nicl.2013.08.001CrossRefGoogle Scholar
  9. 9.
    MacKay, D.J.C.: Bayesian interpolation. Neural Comput. 4(3), 415–447 (1992).  https://doi.org/10.1162/neco.1992.4.3.415CrossRefzbMATHGoogle Scholar
  10. 10.
    Marcus, D.S., et al.: Open access series of imaging studies (oasis): cross-sectional mri data in young, middle aged, nondemented, and demented older adults. J. Cogn. Neurosci. 19(9), 1498–1507 (2007)CrossRefGoogle Scholar
  11. 11.
    Nyúl, L.G., Udupa, J.K.: On standardizing the MR image intensity scale. Magn. Reson. Med. 42(6), 1072–1081 (1999)CrossRefGoogle Scholar
  12. 12.
    Robitaille, N., Mouiha, A., Crépeault, B., Valdivia, F., Duchesne, S.: Tissue-based MRI intensity standardization: application to multicentric datasets. Int. J. Biomed. Imaging 2012, 1–11 (2012)Google Scholar
  13. 13.
    Salat, D., et al.: Age-associated alterations in cortical gray and white matter signal intensity and gray to white matter contrast. NeuroImage 48(1), 21–28 (2009)CrossRefGoogle Scholar
  14. 14.
    Takao, H., Hayashi, N., Ohtomo, K.: Effect of scanner in longitudinal studies of brain volume changes. J. Magn. Reson. Imaging 34(2), 438–444 (2011).  https://doi.org/10.1002/jmri.22636CrossRefGoogle Scholar
  15. 15.
    Tipping, M.E.: Sparse Bayesian learning and the relevance vector machine. J. Mach. Learn. Res. 1(3), 211–244 (2001).  https://doi.org/10.1162/15324430152748236MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Zhuge, Y., Udupa, J.K.: Intensity standardization simplifies brain MR image segmentation. Comput. Vis. Image Understand. 113(10), 1095–1103 (2009).  https://doi.org/10.1016/J.CVIU.2009.06.003CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Maria Ines Meyer
    • 1
    • 2
    Email author
  • Ezequiel de la Rosa
    • 1
  • Koen Van Leemput
    • 2
    • 3
  • Diana M. Sima
    • 1
  1. 1.icometrixLeuvenBelgium
  2. 2.Department of Health TechnologyTechnical University of DenmarkLyngbyDenmark
  3. 3.Martinos Center for Biomedical ImagingMassachusetts General Hospital and Harvard Medical SchoolBostonUSA

Personalised recommendations