Artificially Enlarged Training Set in Image Segmentation

  • Tuomas Tölli
  • Juha Koikkalainen
  • Kirsi Lauerma
  • Jyrki Lötjönen
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4190)


Due to small training sets, statistical shape models constrain often too much the deformation in medical image segmentation. Hence, an artificial enlargement of the training set has been proposed as a solution for the problem. In this paper, the error sources in the statistical shape model based segmentation were analyzed and the optimization processes were improved. The method was evaluated with 3D cardiac MR volume data. The enlargement method based on non-rigid movement produced good results – with 250 artificial modes, the average error for four-chamber model was 2.11 mm when evaluated using 25 subjects.


Simulated Annealing Shape Model Normalize Mutual Information Segmentation Accuracy Segmentation Error 
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.


  1. 1.
    Cootes, T., Taylor, C., Cooper, D., Graham, J.: Active shape models - their training and application. Computer Vision and Image Understanding 61, 38–59 (1995)CrossRefGoogle Scholar
  2. 2.
    Mitchell, S.C., Bosch, J.G., Lelieveldt, B.P.F., van der Geest, R.J., Reiber, J.H.C., Sonka, M.: 3-D active active appearance models: segmentation of cardiac MR and ultrasound images. IEEE Trans. Med. Imaging 21, 1167–1178 (2002)CrossRefGoogle Scholar
  3. 3.
    Lötjönen, J., Kivistö, S., Koikkalainen, J., Smutek, D., Lauerma, K.: Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images. Medical Image Analysis 8, 371–386 (2004)CrossRefGoogle Scholar
  4. 4.
    Assen, H., Danilouchkine, M.G., Frangi, A.F., Ordás, S., Westenberg, J.J.M., Reiber, J.H.C., Lelieveldt, B.P.F.: SPASM: A 3D-ASM for segmentation of sparse and arbitrarily oriented cardiac MRI data. Medical Image Analysis 10, 286–303 (2006)CrossRefGoogle Scholar
  5. 5.
    van Ginneken, B., Frangi, A., Staal, J., ter Haar Romeny, B., Viergever, M.: Active shape model segmentation with optimal features. IEEE Trans. Med. Imaging 21, 924–933 (2002)CrossRefGoogle Scholar
  6. 6.
    Lorenzo-Valdéz, M., Sanchez-Ortiz, G.I., Elkington, A.G., Mohiaddin, R.H., Rueckert, D.: Segmentation of 4D cardiac MR images using a probabilistic atlas and the EM algorithm. Medical Image Analysis 8, 255–265 (2004)CrossRefGoogle Scholar
  7. 7.
    Davatzikos, C., Tao, C., Shen, D.: Hierarchical active shape models using the wavelet transform. IEEE Trans. Med. Imaging 22, 414–423 (2003)CrossRefGoogle Scholar
  8. 8.
    Zhao, Z., Aylward, S.R., Teoh, E.K.: A novel 3D partitioned active shape model for segmentation of brain MRI images. In: Duncan, J.S., Gerig, G. (eds.) MICCAI 2005. LNCS, vol. 3749, pp. 221–228. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  9. 9.
    de Bruijne, M., van Ginneken, B., Viergever, M., Niessen, W.: Adapting active shape models for 3D segmentation of tubular structures in medical images. In: Taylor, C.J., Noble, J.A. (eds.) IPMI 2003. LNCS, vol. 2732, pp. 136–147. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  10. 10.
    Lötjönen, J., Antila, K., Lamminmäki, E., Koikkalainen, J., Lilja, M.: Artificial enlargement of a training set for statistical shape models: Application to cardiac images. In: Frangi, A.F., Radeva, P.I., Santos, A., Hernandez, M. (eds.) FIMH 2005. LNCS, vol. 3504, pp. 92–101. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  11. 11.
    Cootes, T.: Statistical modes of appearance for computer vision. Tech. report, Univ. of Manchester (2004)Google Scholar
  12. 12.
    Studholme, C., Hill, D., Hawkes, D.J.: An overlap invariant entropy measure of 3D medical image alignment. Pattern Recognition 32, 71–86 (1999)CrossRefGoogle Scholar
  13. 13.
    Press, W., Teukolsky, S., Vetterling, W., Flannery, B.: Numerical recipes in C: the art of scientific computing, 2nd edn. Cambridge University Press, Cambridge (1992)Google Scholar
  14. 14.
    Kauss, M., von Berg, J., Weese, J., Niessen, W., Pekar, V.: Automated segmentation of the left ventricle in cardiac MRI. Medical Image Analysis 8, 245–254 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Tuomas Tölli
    • 1
  • Juha Koikkalainen
    • 2
  • Kirsi Lauerma
    • 3
  • Jyrki Lötjönen
    • 2
  1. 1.Laboratory of Biomedical EngineeringHelsinki University of TechnologyHUTFinland
  2. 2.VTT Information TechnologyTampereFinland
  3. 3.Helsinki Medical Imaging CenterUniversity of HelsinkiHUSFinland

Personalised recommendations