Advertisement

A Sparse Bayesian Learning Algorithm for White Matter Parameter Estimation from Compressed Multi-shell Diffusion MRI

  • Pramod Kumar Pisharady
  • Stamatios N. Sotiropoulos
  • Guillermo Sapiro
  • Christophe Lenglet
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10433)

Abstract

We propose a sparse Bayesian learning algorithm for improved estimation of white matter fiber parameters from compressed (under-sampled q-space) multi-shell diffusion MRI data. The multi-shell data is represented in a dictionary form using a non-monoexponential decay model of diffusion, based on continuous gamma distribution of diffusivities. The fiber volume fractions with predefined orientations, which are the unknown parameters, form the dictionary weights. These unknown parameters are estimated with a linear un-mixing framework, using a sparse Bayesian learning algorithm. A localized learning of hyperparameters at each voxel and for each possible fiber orientations improves the parameter estimation. Our experiments using synthetic data from the ISBI 2012 HARDI reconstruction challenge and in-vivo data from the Human Connectome Project demonstrate the improvements.

Keywords

Sparse Bayesian Learning Linear un-mixing Multi-shell Diffusion MRI Sparse signal recovery 

Notes

Acknowledgemens

This work was partly supported by NIH grants P41 EB015894, P30 NS076408, and the Human Connectome Project (U54 MH091657).

References

  1. 1.
    Behrens, T.E., Woolrich, M.W., et al.: Characterization and propagation of uncertainty in diffusion-weighted MR imaging. MRM 50, 1077–1088 (2003)CrossRefGoogle Scholar
  2. 2.
    Behrens, T.E., Berg, H.J., Jbabdi, S., et al.: Probabilistic diffusion tractography with multiple fibre orientations: what can we gain? Neuroimage 34, 144–155 (2007)CrossRefGoogle Scholar
  3. 3.
    Vu, A.T., Auerbach, E., Lenglet, C., et al.: High resolution whole brain diffusion imaging at 7T for the human connectome project. Neuroimage 122, 318–331 (2015)CrossRefGoogle Scholar
  4. 4.
    Tipping, M.E.: Sparse bayesian learning and the relevance vector machine. J. Mach. Learn. Res. 1, 211–244 (2001)MathSciNetMATHGoogle Scholar
  5. 5.
    MacKay, D.J.C.: Bayesian methods for backpropagation networks. In: Domany, E., van Hemmen, J.L., Schulten, K. (eds.) Models of Neural Networks III. Physics of Neural Networks, pp. 211–254. Springer, New York (1994). doi: 10.1007/978-1-4612-0723-8. Chap. 6Google Scholar
  6. 6.
    Duarte-Carvajalino, J.M., Lenglet, C., et al.: Estimation of the CSA-ODF using bayesian compressed sensing of multi-shell HARDI. MRM 72, 1471–1485 (2014)CrossRefGoogle Scholar
  7. 7.
    Manzanares, A.R., et al.: Diffusion basis functions decomposition for estimating white matter intravoxel fiber geometry. IEEE TMI 26, 1091–1102 (2007)Google Scholar
  8. 8.
    Rathi, Y., Michailovich, O., Setsompop, K., Bouix, S., Shenton, M.E., Westin, C.-F.: Sparse multi-shell diffusion imaging. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011. LNCS, vol. 6892, pp. 58–65. Springer, Heidelberg (2011). doi: 10.1007/978-3-642-23629-7_8 CrossRefGoogle Scholar
  9. 9.
    Tristán-Vega, A., Westin, C.-F.: Probabilistic ODF estimation from reduced HARDI data with sparse regularization. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011. LNCS, vol. 6892, pp. 182–190. Springer, Heidelberg (2011). doi: 10.1007/978-3-642-23629-7_23 CrossRefGoogle Scholar
  10. 10.
    Aranda, R., Manzanares, A.R., Rivera, M.: Sparse and adaptive diffusion dictionary for recovering intra-voxel white matter structure. MedIA 26, 243–255 (2015)Google Scholar
  11. 11.
    Dobigeon, N., et al.: Semi-supervised linear spectral unmixing using a hierarchical bayesian model for hyperspectral imagery. IEEE TSP 56, 2684–2695 (2008)MathSciNetGoogle Scholar
  12. 12.
    Daducci, A., et al.: Sparse regularization for fiber ODF reconstruction: from the suboptimality of l2 and l1 priors to l0. Med. Image Anal. 18, 820–833 (2014)CrossRefGoogle Scholar
  13. 13.
    Pisharady, P.K., Duarte-Carvajalino, J.M., Sotiropoulos, S.N., Sapiro, G., Lenglet, C.: Sparse bayesian inference of white matter fiber orientations from compressed multi-resolution diffusion MRI. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9349, pp. 117–124. Springer, Cham (2015). doi: 10.1007/978-3-319-24553-9_15 CrossRefGoogle Scholar
  14. 14.
    Jbabdi, S., et al.: Model-based analysis of multishell diffusion MR data for tractography: how to get over fitting problems. MRM 68, 1846–1855 (2012)CrossRefGoogle Scholar
  15. 15.
    Daducci, A., et al.: Quantitative comparison of reconstruction methods for intra-voxel fiber recovery from diffusion MRI. IEEE TMI 33, 384–399 (2014)Google Scholar
  16. 16.
    Essen, D.C.V., Smith, S.M., Barch, D.M., et al.: The WU-Minn human connectome project: an overview. Neuroimage 80, 62–79 (2013)CrossRefGoogle Scholar
  17. 17.
    Rodriguez, E.J.C., Medina, Y.I., Alemán-Gómez, Y., Melie-García, L.: Deconvolution in diffusion spectrum imaging. Neuroimage 50, 136–149 (2010)CrossRefGoogle Scholar
  18. 18.
    Ozarslan, E., Shepherd, T.M., et al.: Resolution of complex tissue microarchitecture using the diffusion orientation transform. Neuroimage 31, 1086–1103 (2006)CrossRefGoogle Scholar
  19. 19.
    Rodriguez, E.J.C., Lin, C.P., Medina, Y.I., Yeh, C.H., Cho, K.H., Melie-Garcia, L.: Diffusion orientation transform revisited. Neuroimage 49, 1326–1339 (2009)CrossRefGoogle Scholar
  20. 20.
    Tournier, J.D., Calamante, F., Connelly, A.: Robust determination of the fibre orientation distribution in diffusion MRI. Neuroimage 35, 1459–1472 (2007)CrossRefGoogle Scholar
  21. 21.
    Jeurissen, B., et al.: Multi-tissue constrained spherical deconvolution for improved analysis of multi-shell diffusion MRI data. Neuroimage 103, 411–426 (2014)CrossRefGoogle Scholar
  22. 22.
    Marcus, D.S., Harwell, J., et al.: Informatics and data mining: tools and strategies for the human connectome project. Front. Neuroinform. 5, 1–12 (2011)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Pramod Kumar Pisharady
    • 1
  • Stamatios N. Sotiropoulos
    • 2
    • 3
  • Guillermo Sapiro
    • 4
    • 5
  • Christophe Lenglet
    • 1
  1. 1.CMRR, RadiologyUniversity of MinnesotaMinneapolisUSA
  2. 2.Centre for Functional MRI of the Brain (FMRIB)University of OxfordOxfordUK
  3. 3.School of Medicine, Sir Peter Mansfield Imaging CentreUniversity of NottinghamNottinghamUK
  4. 4.Electrical and Computer EngineeringDuke UniversityDurhamUSA
  5. 5.Biomedical Engineering and Computer ScienceDuke UniversityDurhamUSA

Personalised recommendations