Better Fiber ODFs from Suboptimal Data with Autoencoder Based Regularization

  • Kanil Patel
  • Samuel Groeschel
  • Thomas SchultzEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11072)


We propose a novel way of estimating fiber orientation distribution functions (fODFs) from diffusion MRI. Our method combines convex optimization with unsupervised learning in a way that preserves the relative benefits of both. In particular, we regularize constrained spherical deconvolution (CSD) with a prior that is derived from an fODF autoencoder, effectively encouraging solutions that are similar to fODFs observed in high-quality training data. Our method improves results on independent test data, especially when only few measurements or relatively weak diffusion weighting (low b values) are available.


  1. 1.
    Ankele, M., Lim, L.H., Gröschel, S., Schultz, T.: Versatile, robust, and efficient tractography with constrained higher-order tensor fODFs. Int. J. Comput. Assist. Radiol. Surg. 12(8), 1257–1270 (2017)CrossRefGoogle Scholar
  2. 2.
    Bigdeli, S.A., Zwicker, M., Favaro, P., Jin, M.: Deep mean-shift priors for image restoration. In: Advances in Neural Information Processing Systems (NIPS), pp. 763–772 (2017)Google Scholar
  3. 3.
    Golkov, V., et al.: q-space deep learning: twelve-fold shorter and model-free diffusion MRI scans. IEEE Trans. Med. Imaging 35(5), 1344–1351 (2016)CrossRefGoogle Scholar
  4. 4.
    Jenkinson, M., Beckmann, C.F., Behrens, T.E., Woolrich, M.W., Smith, S.M.: FSL. NeuroImage 62(2), 782–790 (2012)CrossRefGoogle Scholar
  5. 5.
    Meinardt, T., Moeller, M., Hazirbas, C., Cremers, D.: Learning proximal operators: using denoising networks for regularizing inverse imaging problems. In: IEEE International Conference on Computer Vision, pp. 1799–1808 (2017)Google Scholar
  6. 6.
    Nedjati-Gilani, G.L., et al.: Machine learning based compartment models with permeability for white matter microstructure imaging. NeuroImage 150, 119–135 (2017)CrossRefGoogle Scholar
  7. 7.
    Neher, P.F., Côté, M.A., Houde, J.C., Descoteaux, M., Maier-Hein, K.H.: Fiber tractography using machine learning. NeuroImage 158, 417–429 (2017)CrossRefGoogle Scholar
  8. 8.
    Tax, C.M., Jeurissen, B., Vos, S.B., Viergever, M.A., Leemans, A.: Recursive calibration of the fiber response function for spherical deconvolution of diffusion MRI data. NeuroImage 86, 67–80 (2014)CrossRefGoogle Scholar
  9. 9.
    Tournier, J.D., Calamante, F., Connelly, A.: Robust determination of the fibre orientation distribution in diffusion MRI: non-negativity constrained super-resolved spherical deconvolution. NuroImage 35, 1459–1472 (2007)CrossRefGoogle Scholar
  10. 10.
    Tournier, J.D., Calamante, F., Connelly, A.: Determination of the appropriate b value and number of gradient directions for high-angular-resolution diffusion-weighted imaging. NMR Biomed. 26(12), 1775–1786 (2013)CrossRefGoogle Scholar
  11. 11.
    Vandenberghe, L.: The CVXOPT linear and quadratic cone program solvers. Technical report, UCLA Electrical Engineering Department (2010).
  12. 12.
    Zeiler, M.D.: ADADELTA: an adaptive learning rate method. CoRR abs/1212.5701 (2012).
  13. 13.
    Zhang, K., Zuo, W., Gu, S., Zhang, L.: Learning deep CNN denoiser prior for image restoration. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2808–2817 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of BonnBonnGermany
  2. 2.Department of Pediatric Neurology and Developmental Medicine and Experimental Pediatric NeuroimagingUniversity Children’s Hospital TübingenTübingenGermany
  3. 3.Bonn-Aachen International Center for Information TechnologyBonnGermany

Personalised recommendations