Fusing Correspondenceless 3D Point Distribution Models

  • Marco Pereañez
  • Karim Lekadir
  • Constantine Butakoff
  • Corné Hoogendoorn
  • Alejandro Frangi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8149)


This paper presents a framework for the fusion of multiple point distribution models (PDMs) with unknown point correspondences. With this work, models built from distinct patient groups and imaging modalities can be merged, with the aim to obtain a PDM that encodes a wider range of anatomical variability. To achieve this, two technical challenges are addressed in this work. Firstly, the model fusion must be carried out directly on the corresponding means and eigenvectors as the original data is not always available and cannot be freely exchanged across centers for various legal and practical reasons. Secondly, the PDMs need to be normalized before fusion as the point correspondence is unknown. The proposed framework is validated by integrating statistical models of the left and right ventricles of the heart constructed from different imaging modalities (MRI and CT) and with different landmark representations of the data. The results show that the integration is statistically and anatomically meaningful and that the quality of the resulting model is significantly improved.


Point Correspondence Statistical Shape Model Target Mesh Point Distribution Model Surface Correspondence 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Butakoff, C., Frangi, A.F.: A framework for weighted fusion of multiple statistical models of shape and appearance. IEEE Trans. Pattern Anal. Machine Intell. 28(11), 1847–1857 (2006)CrossRefGoogle Scholar
  2. 2.
    Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models—their training and application. Comput. Vis. Image Understand. 61(1), 38–59 (1995)CrossRefGoogle Scholar
  3. 3.
    Durrleman, S., Pennec, X., Trouvé, A., Ayache, N.: Statistical models of sets of curves and surfaces based on currents. Med. Image Anal. 13(5), 793–808 (2009)CrossRefGoogle Scholar
  4. 4.
    Franco, A., Lumini, A., Maio, D.: Eigenspace merging for model updating. In: Proc. Int. Conf. Pattern Recognition (ICPR), vol. 2, pp. 156–159 (2002)Google Scholar
  5. 5.
    Hall, P., Marshall, D., Martin, R.: Merging and splitting eigenspace models. IEEE Trans. Pattern Anal. Machine Intell. 22(9), 1042–1049 (2000)CrossRefGoogle Scholar
  6. 6.
    Heimann, T., Meinzer, H.P.: Statistical shape models for 3D medical image segmentation: A review. Med. Image Anal. 13(4), 543–563 (2009)CrossRefGoogle Scholar
  7. 7.
    Hoogendoorn, C., Duchateau, N., Sánchez-Quintana, D., Whitmarsh, T., De Craene, M., Sukno, F.M., Lekadir, K., Frangi, A.F.: A high-resolution atlas and statistical model of the human heart from multislice CT. IEEE Trans. Med. Imaging 32(1), 28–44 (2013)CrossRefGoogle Scholar
  8. 8.
    Horn, B.K.P.: Closed-form solution of absolute orientation using unit quaternions. J. Opt. Soc. Am. A Optic. Image Sci. Vis. 4(4), 629–642 (1987)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Loop, C.: Smooth subdivision surfaces based on triangles. Master’s thesis, Department of mathematics, University of Utah, Utah, USA (1987)Google Scholar
  10. 10.
    Valette, S., Chassery, J.M.: Approximated centroidal Voronoi diagrams for uniform polygonal mesh coarsening. Comput. Graph. Forum 24(3), 381–389 (2004)CrossRefGoogle Scholar
  11. 11.
    Zhou, X.S., Gupta, A., Comaniciu, D.: An information fusion framework for robust shape tracking. IEEE Trans. Pattern Anal. Machine Intell. 27(1), 115–129 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Marco Pereañez
    • 1
  • Karim Lekadir
    • 1
  • Constantine Butakoff
    • 2
  • Corné Hoogendoorn
    • 1
  • Alejandro Frangi
    • 3
  1. 1.CISTIBUniversitat Pompeu Fabra and CIBER-BBNBarcelonaSpain
  2. 2.PhySenseUniversitat Pompeu FabraBarcelonaSpain
  3. 3.CISTIBUniversity of SheffieldSheffieldUK

Personalised recommendations