An Application for Dealing with Missing Data in Medical Images, with Application to Left Ventricle SPECT Data

  • Oscar Civit Flores
  • Isabel Navazo
  • Àlvar Vinacua
Conference paper
Part of the Mathematics and Visualization book series (MATHVISUAL)


When using data-capture methods designed to retrieve functional information, we may have incomplete morphological information in the presence of desease. This is specially so for SPECT data of an infarcted heart.

In this paper we present two techniques to deal with such missing data, appropriate for different scenarios. The first one reconstructs small infarcts that show as holes through the ventricle’s wall. This method uses two discrete elastic membranes that are deformed to wrap the myocardium without touching each other.

The second method handles cases where large portions of the heart are missing, by computing approximating ellipsoids to the walls of the myocardium, and filling the gaps.


Single Photon Emission Compute Tomography Medical Image Active Contour Deformable Model Elastic Membrane 
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.
    Fausto Bernardini and Chandrajit L. Bajaj. Sampling and reconstructing manifolds using alpha-shapes. In Proc. 9th Canadian Conf. Computational Geometry, pages 193–198, August 1997.Google Scholar
  2. 2.
    Andrew Blake and Michael Isard. Active Contours. Springer Verlag, 1998.Google Scholar
  3. 3.
    Candell-Riera, Castell-Conesa, and Aguadé-Bruix. Myocardium at risk and viable myocardium. Developments in Cardiovascular Medicine, 234, 2001.Google Scholar
  4. 4.
    J. Candell-Riera, J. Castell-Conesa, and S. Aguadé-Bruix, editors. Myocardium at risk and viable myocardium. Evaluation by SPET. Developments in cardiovascular medicine. Kluwer Academic Publishers, 2001.Google Scholar
  5. 5.
    Herbert Edelsbrunner and Ernst P. Mücke. Three-dimensional alpha shapes. ACM Transactions on Graphics, 13 (1): 43–72, January 1994.MATHCrossRefGoogle Scholar
  6. 6.
    J. Esteve, P. Brunet, and A. Vinacua. Aproximación de un conjunto de pun-tos disperso de densidad variable mediante una erosion gradual. In R. JoanArinyo, I. Navazo, and R. Quiros, editors, CEIG 2000, X Congreso Espanol de Informatica Grafica, pages 235–248. Universitat Jaume-I, 2000.Google Scholar
  7. 7.
    J. Esteve, P. Brunet, and A. Vinacua. Scattered data approximation through the erosion of discrete bands. In Research Report. Software Department, Universitat Politècnica de Catalunya, 2002.Google Scholar
  8. 8.
    N. Ezquerra, I. Navazo, T. Infantes, and E. Moncl•s. Graphics, vision and visualization in medical imaging. pages 21–80, 1999.Google Scholar
  9. 9.
    Walter Gander, Gene H. Golub, and Rolf Strebel. Least-squares fitting of circles and ellipses. BIT, 34 (4): 558–578, December 1994.MathSciNetMATHCrossRefGoogle Scholar
  10. 10.
    G. Germano, H. Kiat, P.B. Kavanagh, M. Moriel, M. Mazzanti, H. Su, and D.S. Van Train, K.and Berman. Automatic quantification of ejection fraction from gated myocardial perfusion spect. The Journal of Nuclear Medicine, 36 (11): 2138–2147, 2001.Google Scholar
  11. 11.
    Baining Guo, Jai Menon, and Brian Willette. Surface reconstruction using alpha shapes. In David Duke, Sabine Coquillart, and Toby Howard, editors, Computer Graphics Forum, volume 16(4), pages 177–190. Eurographics Association, 1997.Google Scholar
  12. 12.
    M. Leventon, W. Grimson, and O. Faugeras. Statistical shape influence in geodesic active contours. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR-00),pages 316–323, Los Alamitos, June 13–15 2000. IEEE.Google Scholar
  13. 13.
    P. Linares, L. Rodriguez, and G. Montilla. Genetic algorithm fitting of de-formable superquadric applied to left ventricle visualization. In Computers in Cardiology, volume 25, pages 657–660. IEEE, 1998.Google Scholar
  14. 14.
    W. Lorenson and H. Cline. Marching cubes: a high resolution 3d surface reconstrution algorithm. ACM Computer Graphics, 21: 163–169, 1987.CrossRefGoogle Scholar
  15. 15.
    T McInerney and D. Terzopoulos. Deformable models in medical image analisys: a survey. Medical Image Analysis, 1 (2): 91–108, 1996.CrossRefGoogle Scholar
  16. 16.
    T McInerney and D. Terzopoulos. Topology adaptative deformable surfaces for medical image volume segmentation. IEEE Transaction on Medical Imaging, 18 (10): 840–850, 1999.CrossRefGoogle Scholar
  17. 17.
    C. Montani, R. Scateni, and R. Scopigno. Discretized marching cubes. In IEEE Visualization’94, pages 281–287. IEEE, IEEE Computer Society, 1994.Google Scholar
  18. 18.
    M. K. O’Connor, R. J. Gibbons, J. E. Juni, J. O’Keefe, and A. Ali. Quantitative myocardial spect for infarct sizing: feasibility of a multicenter trial evaluated using a cardiac phantom. The Journal of Nuclear Medicine, 36 (6): 1130–1136, 1995.Google Scholar
  19. 19.
    Nikos Paragios. A variational approach for the segmentation of the left ventricle in mr cardiac images. In Proceedings of the IEEE Workshop on Variational and Level Set Methods in Computer Vision, 2001, pages 153–160, 2001.Google Scholar
  20. 20.
    William H. Press. Numerical recipes in C: the art of scientific computing. Cambridge University Press, 1992.Google Scholar
  21. 21.
    A. Susn, I. Navazo, A. Vinacua, and P. Brunet. Dymanic recognition and reconstruction of the human heart. In A. Sanfeliu, JJ. Villanueva, M. Vanrell, R. Alquézar, J. Crowley, and Y. Shirai, editors, Proceedings of 15th International Conference of Pattern Recognition, pages 88–93. IEEE Computer Society, 2001.Google Scholar
  22. 22.
    X. Zeng, L.H. Staib, R.T. Schultz, and J. S. Duncan. Volumetric layer segmentation using coupled surfaces propagation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR-98), pages 708–715, June 23–25 1998.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Oscar Civit Flores
    • 1
  • Isabel Navazo
    • 2
  • Àlvar Vinacua
    • 2
  1. 1.Departament de TecnologíaUniversitat Pompeu FabraBarcelonaSpain
  2. 2.Institut de Robòtica i Informàtica IndustrialUniversitat Politècnica de Catalunya Parc Tecnològic de Pedralbes, edifici UBarcelonaSpain

Personalised recommendations