Optimizing Computed Tomographic Angiography Image Segmentation Using Fitness Based Partitioning

  • Jeroen Eggermont
  • Rui Li
  • Ernst G. P. Bovenkamp
  • Henk Marquering
  • Michael T. M. Emmerich
  • Aad van der Lugt
  • Thomas Bäck
  • Jouke Dijkstra
  • Johan H. C. Reiber
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4974)

Abstract

Computed Tomographic Angiography (CTA) has become a popular image modality for the evaluation of arteries and the detection of narrowings. For an objective and reproducible assessment of objects in CTA images, automated segmentation is very important. However, because of the complexity of CTA images it is not possible to find a single parameter setting that results in an optimal segmentation for each possible image of each possible patient. Therefore, we want to find optimal parameter settings for different CTA images. In this paper we investigate the use of Fitness Based Partitioning to find groups of images that require a similar parameter setting for the segmentation algorithm while at the same time evolving optimal parameter settings for these groups. The results show that Fitness Based Partitioning results in better image segmentation than the original default parameter solutions or a single parameter solution evolved for all images.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bovenkamp, E., Eggermont, J., Li, R., Emmerich, M., Bäck, T., Dijkstra, J., Reiber, J.: Optimizing IVUS Lumen Segmentations using Evolutionary Algorithms. In: The 1st International Workshop on Computer Vision for IntraVascular and IntraCardiac Imaging, October 1–5, pp. 74–81 (2006)Google Scholar
  2. 2.
    Li, R., Emmerich, M., Eggermont, J., Bovenkamp, E., Bäck, T., Dijkstra, J., Reiber, J.: Mixed-Integer Optimization of Coronary Vessel Image Analysis using Evolution Strategies. In: Keijzer, M., et al. (eds.) Proceedings of the 8th annual conference on Genetic and Evolutionary Computation (GECCO), Seattle, WA, USA, pp. 1645–1652 (2006)Google Scholar
  3. 3.
    Jain, A.K., Murty, M.N., Flynn, P.J.: Data clustering: a review. ACM Comput. Surv. 31(3), 264–323 (1999)CrossRefGoogle Scholar
  4. 4.
    Vanneschi, L., Mauri, G., Valsecchi, A., Cagnoni, S.: Heterogeneous cooperative coevolution: strategies of integration between gp and ga. In: Proceedings of Genetic and Evolutionary Computation Conference, GECCO, Seattle, Washington, USA, July 8-12, pp. 361–368 (2006)Google Scholar
  5. 5.
    Roberts, M., Claridge, E.: Cooperative coevolution of image feature construction and object detection. In: Yao, X., Burke, E.K., Lozano, J.A., Smith, J., Merelo-Guervós, J.J., Bullinaria, J.A., Rowe, J.E., Tiňo, P., Kabán, A., Schwefel, H.-P. (eds.) PPSN 2004. LNCS, vol. 3242, pp. 902–911. Springer, Heidelberg (2004)Google Scholar
  6. 6.
    Li, R., Eggermont, J., Emmerich, M., Bovenkamp, E., Bäck, T., Dijkstra, J., Reiber, J.: Towards Dynamic Fitness Based Partitioning for IntraVascular UltraSound Image Analysis. In: Giacobini, M. (ed.) EvoWorkshops 2007. LNCS, vol. 4448, pp. 388–395. Springer, Heidelberg (2007)Google Scholar
  7. 7.
    Marquering, H., Dijkstra, J., de Koning, P., Stoel, B., Reiber, J.: Towards quantitative analysis of coronary cta. Int. J. Cardiovasc Imaging 21(1), 73–84 (2005)CrossRefGoogle Scholar
  8. 8.
    Emmerich, M., Grötzner, M., Groß, B., Schütz, M.: Mixed-integer evolution strategy for chemical plant optimization with simulators. In: Parmee, I. (ed.) Evolutionary Design and Manufacture - Selected papers from ACDM, pp. 55–67. Springer, London (2000)Google Scholar
  9. 9.
    Schwefel, H.P.: Evolution and Optimum Seeking. Sixth-Generation Computer Technology Series. Wiley, New York (1995)Google Scholar
  10. 10.
    Rudolph, G.: An evolutionary algorithm for integer programming. In: Davidor, Y., Männer, R., Schwefel, H.-P. (eds.) PPSN 1994. LNCS, vol. 866, pp. 139–148. Springer, Heidelberg (1994)Google Scholar
  11. 11.
    Bäck, T.: Evolutionary Algorithms in Theory and Practice. Oxford University Press, New York (1996)MATHGoogle Scholar
  12. 12.
    Keijzer, M., Merelo, J.J., Romero, G., Schoenauer, M.: Evolving objects: a general purpose evolutionary computation library. In: EA 2001, Evolution Artificielle, 5th International Conference in Evolutionary Algorithms, pp. 231–244 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Jeroen Eggermont
    • 1
  • Rui Li
    • 2
  • Ernst G. P. Bovenkamp
    • 1
  • Henk Marquering
    • 1
  • Michael T. M. Emmerich
    • 2
  • Aad van der Lugt
    • 3
  • Thomas Bäck
    • 2
  • Jouke Dijkstra
    • 1
  • Johan H. C. Reiber
    • 1
  1. 1.Div. of Image Processing, Dept. of Radiology C2SLeiden University Medical CenterLeidenThe Netherlands
  2. 2.Natural Computing GroupLeiden UniversityLeidenThe Netherlands
  3. 3.Department of RadiologyErasmus Medical CenterRotterdamThe Netherlands

Personalised recommendations