Groupwise Simultaneous Manifold Alignment for High-Resolution Dynamic MR Imaging of Respiratory Motion

  • Christian F. Baumgartner
  • Christoph Kolbitsch
  • Jamie R. McClelland
  • Daniel Rueckert
  • Andrew P. King
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7917)


Respiratory motion is a complicating factor for many applications in medical imaging and there is significant interest in dynamic imaging that can be used to estimate such motion. Magnetic resonance imaging (MRI) is an attractive modality for motion estimation but current techniques cannot achieve good image contrast inside the lungs. Manifold learning is a powerful tool to discover the underlying structure of high-dimensional data. Aligning the manifolds of multiple datasets can be useful to establish relationships between different types of data. However, the current state-of-the-art in manifold alignment is not robust to the wide variations in manifold structure that may occur in clinical datasets. In this work we propose a novel, fully automatic technique for the simultaneous alignment of large numbers of manifolds with varying manifold structure. We apply the technique to reconstruct high-resolution and high-contrast dynamic 3D MRI images from multiple 2D datasets for the purpose of respiratory motion estimation. The proposed method is validated on synthetic data with known ground truth and real data. We demonstrate that our approach can be applied to reconstruct significantly more accurate and consistent dynamic images of the lungs compared to the current state-of-the-art in manifold alignment.


Manifold learning manifold alignment MRI of the lungs respiratory motion 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Belkin, M., Niyogi, P.: Laplacian eigenmaps and spectral techniques for embedding and clustering. Adv. Neur. In. 14, 585–591 (2001)Google Scholar
  2. 2.
    Bhatia, K.K., Rao, A., Price, A.N., Wolz, R., Hajnal, J., Rueckert, D.: Hierarchical manifold learning. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part I. LNCS, vol. 7510, pp. 512–519. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  3. 3.
    Buerger, C., Schaeffter, T., King, A.P.: Hierarchical adaptive local affine registration for fast and robust respiratory motion estimation. Med. Image Anal. 15(4), 551–564 (2011)CrossRefGoogle Scholar
  4. 4.
    Georg, M., Souvenir, R., Hope, A., Pless, R.: Manifold learning for 4D CT reconstruction of the lung. In: Proc. IEEE CVPRW, pp. 1–8 (2008)Google Scholar
  5. 5.
    Ham, J., Lee, D., Saul, L.: Semisupervised alignment of manifolds. In: AI and Statistics, vol. 10, pp. 120–127 (2005)Google Scholar
  6. 6.
    King, A.P., Buerger, C., Tsoumpas, C., Marsden, P.K., Schaeffter, T.: Thoracic respiratory motion estimation from MRI using a statistical model and a 2-D image navigator. Med. Im. Anal. 16(1), 252–264 (2012)CrossRefGoogle Scholar
  7. 7.
    Köhler, M.O., Denis de Senneville, B., Quesson, B., Moonen, C.T.W., Ries, M.: Spectrally selective pencil-beam navigator for motion compensation of MR-guided high-intensity focused ultrasound therapy of abdominal organs. Magn. Reson. Med. 66(1), 102–111 (2011)CrossRefGoogle Scholar
  8. 8.
    Kuhn, H.W.: The Hungarian method for the assignment problem. Nav. Res. Logist. Q 2(1-2), 83–97 (1955)CrossRefGoogle Scholar
  9. 9.
    Manke, D., Nehrke, K., Börnert, P.: Novel prospective respiratory motion correction approach for free-breathing coronary MR angiography using a patient-adapted affine motion model. Magn. Reson. Med. 50(1), 122–131 (2003)CrossRefGoogle Scholar
  10. 10.
    McClelland, J.R., Hawkes, D.J., Schaeffter, T., King, A.P.: Respiratory motion models: A review. Med. Image Anal. 17(1), 19–42 (2013)CrossRefGoogle Scholar
  11. 11.
    McClelland, J.R., Hughes, S., Modat, M., Qureshi, A., Ahmad, S., Landau, D.B., Ourselin, S., Hawkes, D.J.: Inter-fraction variations in respiratory motion models. Phys. Med. Biol. 56(1), 251–272 (2011)CrossRefGoogle Scholar
  12. 12.
    Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)CrossRefGoogle Scholar
  13. 13.
    Torki, M., Elgammal, A., Lee, C.S.: Learning a joint manifold representation from multiple data sets. In: Proc. IEEE ICPR, pp. 1068–1071 (2010)Google Scholar
  14. 14.
    Tsoumpas, C., Mackewn, J.E., Halsted, P., King, A.P., Buerger, C., Totman, J.J., Schaeffter, T., Marsden, P.K.: Simultaneous PET–MR acquisition and MR-derived motion fields for correction of non-rigid motion in PET. Ann. Nucl. Med. 24(10), 745–750 (2010)CrossRefGoogle Scholar
  15. 15.
    von Siebenthal, M., Székely, G., Gamper, U., Boesiger, P., Lomax, A., Cattin, P.: 4D MR imaging of respiratory organ motion and its variability. Phys. Med. Biol. 52(6), 1547–1564 (2007)CrossRefGoogle Scholar
  16. 16.
    Wachinger, C., Yigitsoy, M., Rijkhorst, E.J., Navab, N.: Manifold learning for image-based breathing gating in ultrasound and MRI. Med. Im. Anal. 16(4), 806–818 (2011)CrossRefGoogle Scholar
  17. 17.
    Wang, C., Mahadevan, S.: Manifold alignment using Procrustes analysis. In: Proc. ICML (2008)Google Scholar
  18. 18.
    Zhai, D., Li, B., Chang, H., Shan, S., Chen, X., Gao, W.: Manifold alignment via corresponding projections. In: Proc. BMVC, pp. 3–11 (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Christian F. Baumgartner
    • 1
  • Christoph Kolbitsch
    • 1
  • Jamie R. McClelland
    • 2
  • Daniel Rueckert
    • 3
  • Andrew P. King
    • 1
  1. 1.Division of Imaging Sciences & Biomedical EngineeringKing’s College LondonUK
  2. 2.Centre for Medical Image ComputingUniversity College LondonUK
  3. 3.Biomedical Image Analysis Group, Department of ComputingImperial College LondonUK

Personalised recommendations