Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration

  • Adrian V. DalcaEmail author
  • Guha Balakrishnan
  • John Guttag
  • Mert R. Sabuncu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11070)


Traditional deformable registration techniques achieve impressive results and offer a rigorous theoretical treatment, but are computationally intensive since they solve an optimization problem for each image pair. Recently, learning-based methods have facilitated fast registration by learning spatial deformation functions. However, these approaches use restricted deformation models, require supervised labels, or do not guarantee a diffeomorphic (topology-preserving) registration. Furthermore, learning-based registration tools have not been derived from a probabilistic framework that can offer uncertainty estimates. In this paper, we present a probabilistic generative model and derive an unsupervised learning-based inference algorithm that makes use of recent developments in convolutional neural networks (CNNs). We demonstrate our method on a 3D brain registration task, and provide an empirical analysis of the algorithm. Our approach results in state of the art accuracy and very fast runtimes, while providing diffeomorphic guarantees and uncertainty estimates. Our implementation is available online at



This research was funded by NIH grants R01LM012719, R01AG053949, and 1R21AG050122, and NSF NeuroNex Grant grant 1707312.


  1. 1.
    Arsigny, V., Commowick, O., Pennec, X., Ayache, N.: A log-euclidean framework for statistics on diffeomorphisms. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4190, pp. 924–931. Springer, Heidelberg (2006). Scholar
  2. 2.
    Ashburner, J., et al.: A fast diffeomorphic image registration algorithm. Neuroimage 38(1), 95–113 (2007)CrossRefGoogle Scholar
  3. 3.
    Avants, B.B., et al.: Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain. Med. Image Anal. 12(1), 26–41 (2008)CrossRefGoogle Scholar
  4. 4.
    Bajcsy, R., Kovacic, S.: Multiresolution elastic matching. Comput. Vis. Graph. Image Process. 46, 1–21 (1989)CrossRefGoogle Scholar
  5. 5.
    Balakrishnan, G., et al.: An unsupervised learning model for deformable medical image registration. arXiv:1802.02604 (2018)
  6. 6.
    Beg, M.F., et al.: Computing large deformation metric mappings via geodesic flows of diffeomorphisms. Int. J. Comput. Vis. 61, 139–157 (2005)CrossRefGoogle Scholar
  7. 7.
    Dagley, A., et al.: Harvard aging brain study: dataset and accessibility. NeuroImage 144, 255–258 (2015)CrossRefGoogle Scholar
  8. 8.
    Dalca, A.V., Bobu, A., Rost, N.S., Golland, P.: Patch-based discrete registration of clinical brain images. In: Wu, G., et al. (eds.) Patch-MI 2016. LNCS, vol. 9993, pp. 60–67. Springer, Cham (2016). Scholar
  9. 9.
    de Vos, B.D., et al.: End-to-end unsupervised deformable image registration with a convolutional neural network. In: DLMIA, pp. 204–212 (2017)Google Scholar
  10. 10.
    Di Martino, A., et al.: The autism brain imaging data exchange: towards a large-scale evaluation of the intrinsic brain architecture in autism. Mol. Psychiatry 19(6), 659–667 (2014)CrossRefGoogle Scholar
  11. 11.
    Fischl, B.: Freesurfer. Neuroimage 62(2), 774–781 (2012)CrossRefGoogle Scholar
  12. 12.
    Glocker, B., et al.: Dense image registration through MRFs and efficient linear programming. Med. Image Anal. 12(6), 731–741 (2008)CrossRefGoogle Scholar
  13. 13.
    Gollub, R.L., et al.: The mcic collection: a shared repository of multi-modal, multi-site brain image data from a clinical investigation of schizophrenia. Neuroinformatics 11(3), 367–388 (2013)CrossRefGoogle Scholar
  14. 14.
    Holmes, A.J., et al.: Brain genomics superstruct project initial data release with structural, functional, and behavioral measures. Sci. Data 2 (2015)CrossRefGoogle Scholar
  15. 15.
    Jaderberg, M., et al.: Spatial transformer networks. In: NIPS, pp. 2017–2025 (2015)Google Scholar
  16. 16.
    Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR (2014)Google Scholar
  17. 17.
    Klein, A., et al.: Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration. Neuroimage 46(3), 786–802 (2009)CrossRefGoogle Scholar
  18. 18.
    Li, H., Fan, H.: Non-rigid image registration using fully convolutional networks with deep self-supervision. arXiv preprint arXiv:1709.00799 (2017)
  19. 19.
    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
  20. 20.
    Marek, K., et al.: The parkinson progression marker initiative (PPMI). Prog. Neurobiol. 95(4), 629–635 (2011)CrossRefGoogle Scholar
  21. 21.
    Milham, M.P., et al.: The adhd-200 consortium: a model to advance the translational potential of neuroimaging in clinical neuroscience. Front. Sys. Neurosci. 6, 62 (2012)Google Scholar
  22. 22.
    Mueller, S.G., et al.: Ways toward an early diagnosis in Alzheimer’s disease: the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Alzheimer’s Dement. 1(1), 55–66 (2005)CrossRefGoogle Scholar
  23. 23.
    Rohé, M.-M., Datar, M., Heimann, T., Sermesant, M., Pennec, X.: SVF-Net: learning deformable image registration using shape matching. In: Descoteaux, M., et al. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 266–274. Springer, Cham (2017). Scholar
  24. 24.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). Scholar
  25. 25.
    Rueckert, D., et al.: Nonrigid registration using free-form deformation: application to breast MR images. IEEE Trans. Med. Imaging 18(8), 712–721 (1999)CrossRefGoogle Scholar
  26. 26.
    Sokooti, H., et al.: Nonrigid image registration using multi-scale 3D convolutional neural networks. In: Descoteaux, M., et al. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 232–239. Springer, Cham (2017). Scholar
  27. 27.
    Thirion, J.P.: Image matching as a diffusion process: an analogy with maxwell’s demons. Med. Image Anal. 2(3), 243–260 (1998)CrossRefGoogle Scholar
  28. 28.
    Yang, X., et al.: Quicksilver: Fast predictive image registration-a deep learning approach. NeuroImage 158, 378–396 (2017)CrossRefGoogle Scholar
  29. 29.
    Zhang, M., et al.: Frequency diffeomorphisms for efficient image registration. In: Niethammer, M., et al. (eds.) IPMI 2017. LNCS, vol. 10265, pp. 559–570. Springer, Cham (2017). Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Adrian V. Dalca
    • 1
    • 2
    • 3
    Email author
  • Guha Balakrishnan
    • 1
  • John Guttag
    • 1
  • Mert R. Sabuncu
    • 3
  1. 1.Computer Science and Artificial Intelligence Lab, MITCambridgeUSA
  2. 2.Martinos Center for Biomedical Imaging, Massachusetts General Hospital, HMSCharlestownUSA
  3. 3.School of Electrical and Computer EngineeringCornell UniversityIthacaUSA

Personalised recommendations