Advertisement

Fast Predictive Simple Geodesic Regression

  • Zhipeng Ding
  • Greg Fleishman
  • Xiao Yang
  • Paul Thompson
  • Roland Kwitt
  • Marc Niethammer
  • The Alzheimer’s Disease Neuroimaging Initiative
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10553)

Abstract

Analyzing large-scale imaging studies with thousands of images is computationally expensive. To assess localized morphological differences, deformable image registration is a key tool. However, as registrations are costly to compute, large-scale studies frequently require large compute clusters. This paper explores a fast predictive approximation to image registration. In particular, it uses these fast registrations to approximate a simplified geodesic regression model to capture longitudinal brain changes. The resulting approach is orders of magnitude faster than the optimization-based regression approach and hence facilitates large-scale analysis on a single graphics processing unit. We show results on 2D and 3D brain magnetic resonance images from OASIS and ADNI.

References

  1. 1.
    Biobank website. www.ukbiobank.ac.uk
  2. 2.
    Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., van der Smagt, P., Cremers, D., Brox, T.: Flownet: learning optical flow with convolutional networks. In: ICCV, pp. 2758–2766 (2015)Google Scholar
  3. 3.
    Fleishman, G., Thompson, P.M.: Adaptive gradient descent optimization of initial momenta for geodesic shooting in diffeomorphisms. In: ISBI (2017)Google Scholar
  4. 4.
    Fleishman, G., Thompson, P.M.: The impact of matching functional on atrophy measurement from geodesic shooting in diffeomorphisms. In: ISBI (2017)Google Scholar
  5. 5.
    Fletcher, P.T.: Geodesic regression and the theory of least squares on Riemannian manifolds. IJCV 105(2), 171–185 (2013)MathSciNetCrossRefMATHGoogle Scholar
  6. 6.
    Hong, Y., Shi, Y., Styner, M., Sanchez, M., Niethammer, M.: Simple geodesic regression for image time-series. In: Dawant, B.M., Christensen, G.E., Fitzpatrick, J.M., Rueckert, D. (eds.) WBIR 2012. LNCS, vol. 7359, pp. 11–20. Springer, Heidelberg (2012). doi: 10.1007/978-3-642-31340-0_2 CrossRefGoogle Scholar
  7. 7.
    Hua, X., Ching, C.R.K., Mezher, A., Gutman, B., Hibar, D.P., Bhatt, P., Leow, A.D., Jack Jr., C.R., Bernstein, M.A., Weiner, M.W., Thompson, P.M., Alzheimer’s Disease Neuroimaging Initiative: MRI-based brain atrophy rates in ADNI phase 2: acceleration and enrichment considerations for clinical trials. Neurobiol. Aging 37, 26–37 (2016)Google Scholar
  8. 8.
    Hua, X., Hibar, D.P., Ching, C.R.K., Boyle, C.P., Rajagopalan, P., Gutman, B., Leow, A.D., Toga Jr., A.W., C.R.J., Harvey, D.J., Weiner, M.W., Thompson, P.M.: Unbiased tensor-based morphometry: improved robustness & sample size estimates for Alzheimer’s disease clinical trials. NeuroImage 66, 648–661 (2013)Google Scholar
  9. 9.
    Ikram, M.A., van der Lugt, A., Niessen, W.J., Koudstaal, P.J., Krestin, G.P., Hofman, A., Bos, D., Vernooij, M.W.: The Rotterdam scan study: design update 2016 and main findings. Eur. J. Epidemiol. 30(12), 1299–1315 (2015)CrossRefGoogle Scholar
  10. 10.
    Jack, C.R., Barnes, J., Bernstein, M.A., Borowski, B.J., Brewer, J., Clegg, S., Dale, A.M., Carmichael, O., Ching, C., DeCarli, C., et al.: Magnetic resonance imaging in ADNI 2. Alzheimer’s Dement. 11(7), 740–756 (2015)CrossRefGoogle Scholar
  11. 11.
    Liu, Z., Yeh, R., Tang, X., Liu, Y., Agarwala, A.: Video frame synthesis using deep voxel flow. arXiv preprint arXiv:1702.02463 (2017)
  12. 12.
    Niethammer, M., Huang, Y., Vialard, F.-X.: Geodesic regression for image time-series. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011. LNCS, vol. 6892, pp. 655–662. Springer, Heidelberg (2011). doi: 10.1007/978-3-642-23629-7_80 CrossRefGoogle Scholar
  13. 13.
    Schuster, T., Wolf, L., Gadot, D.: Optical flow requires multiple strategies (but only one network). arXiv preprint arXiv:1611.05607 (2016)
  14. 14.
    Singh, N., Hinkle, J., Joshi, S., Fletcher, P.T.: A vector momenta formulation of diffeomorphisms for improved geodesic regression and atlas construction. In: ISBI, pp. 1219–1222 (2013)Google Scholar
  15. 15.
    Yang, X., Kwitt, R., Niethammer, M.: Fast predictive image registration. In: Carneiro, G., et al. (eds.) LABELS/DLMIA -2016. LNCS, vol. 10008, pp. 48–57. Springer, Cham (2016). doi: 10.1007/978-3-319-46976-8_6 Google Scholar
  16. 16.
    Yang, X., Kwitt, R., Niethammer, M.: Quicksilver: fast predictive image registration-a deep learning approach. NeuroImage (2017, in press)Google Scholar
  17. 17.
    Yushkevich, P.A., Avants, B.B., Das, S.R., Pluta, J., Altinay, M., Craige, C.: Bias in estimation of hippocampal atrophy using deformation-based morphometry arises from asymmetric global normalization: an illustration in ADNI 3T MRI data. NeuroImage 50(2), 434–445 (2010)CrossRefGoogle Scholar
  18. 18.
    Zhang, M., Fletcher, P.T.: Finite-dimensional lie algebras for fast diffeomorphic image registration. In: Ourselin, S., Alexander, D.C., Westin, C.-F., Cardoso, M.J. (eds.) IPMI 2015. LNCS, vol. 9123, pp. 249–260. Springer, Cham (2015). doi: 10.1007/978-3-319-19992-4_19 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Zhipeng Ding
    • 1
  • Greg Fleishman
    • 3
    • 4
  • Xiao Yang
    • 1
  • Paul Thompson
    • 3
  • Roland Kwitt
    • 5
  • Marc Niethammer
    • 1
    • 2
  • The Alzheimer’s Disease Neuroimaging Initiative
  1. 1.Department of Computer ScienceUNC Chapel HillChapel HillUSA
  2. 2.Biomedical Research Imaging CenterUNC Chapel HillChapel HillUSA
  3. 3.Imaging Genetics CenterUSCLos AngelesUSA
  4. 4.Department of RadiologyUniversity of PennsylvaniaPhiladelphiaUSA
  5. 5.Department of Computer ScienceUniversity of SalzburgSalzburgAustria

Personalised recommendations