Advertisement

Automatic Segmentation of the Left Ventricle in 3D SPECT Data by Registration with a Dynamic Anatomic Model

  • Lars Dornheim
  • Klaus D. Tönnies
  • Kat Dixon
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3749)

Abstract

We present a fully automatic 3D segmentation method for the left ventricle (LV) in human myocardial perfusion SPECT data. This model-based approach consists of 3 phases: 1. finding the LV in the dataset, 2. extracting its approximate shape and 3. segmenting its exact contour.

Finding of the LV is done by flexible pattern matching, whereas segmentation is achieved by registering an anatomical model to the functional data. This model is a new kind of stable 3D mass spring model using direction-weighted 3D contour sensors.

Our approach is much faster than manual segmention, which is standard in this application up to now. By testing it on 41 LV SPECT datasets of mostly pathological data, we could show, that it is very robust and its results are comparable with those made by human experts.

Keywords

Mass Point Pattern Match Automatic Segmentation Manual Segmentation Initial Placement 
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.

References

  1. 1.
    Fernandez-Maloigne, C., Rakotobe, R.H., Langevin, F., Fauchet, M.: 3D segmentation and visualization of cardiac SPECT studies. In: 28th AIPR Workshop. Proceedings of SPIE, vol. 3905, pp. 222–231 (2000)Google Scholar
  2. 2.
    Pohle, R., Wegner, M., Rink, K., Tönnies, K., Celler, A., Blinder, S.: Segmentation of the left ventricle in 4D-dSPECT data using free form deformation of super quadrics. In: Medical Imaging: Image Processing. Proceedings of SPIE, vol. 5370, pp. 1388–1394 (2004)Google Scholar
  3. 3.
    Bardinet, E., Cohen, L.D., Ayache, N.: Tracking and motion analysis of the left ventricle with deformable superquadrics. Medical Image Analysis 1, 129–149 (1996)CrossRefGoogle Scholar
  4. 4.
    Gould, P.L.: Introduction to Linear Elasticity. Springer, Heidelberg (1994)Google Scholar
  5. 5.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. IJCV 1, 321–331 (1988)CrossRefGoogle Scholar
  6. 6.
    Cootes, T.F., Taylor, C.J., Cooper, D.H., Graham, J.: Active shape models - their training and application. CVIU 61, 38–59 (1995)Google Scholar
  7. 7.
    Dornheim, L., Tönnies, K.D., Dornheim, J.: Stable dynamic 3D shape models. In: ICIP (2005)Google Scholar
  8. 8.
    Dornheim, L., Tönnies, K.D.: Automatische Generierung dynamischer 3D-Modelle zur Segmentierung des linken Ventrikels in 3D-SPECT-Daten. In: Bildverarbeitung für die Medizin (2005)Google Scholar
  9. 9.
    Kohonen, T.: Self-Organization and Associative Memory. Springer, Heidelberg (1987)Google Scholar
  10. 10.
    Dornheim, L.: Generierung und Dynamik physikalisch basierter 3D-Modelle zur Segmentierung des linken Ventrikels in SPECT-Daten. Diplomarbeit, Fakultät für Informatik, Otto-von-Guericke-Universität Magdeburg (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Lars Dornheim
    • 1
  • Klaus D. Tönnies
    • 1
  • Kat Dixon
    • 2
  1. 1.Institut für Simulation und Graphik, Fakultät für InformatikOtto-von-Guericke-Universität MagdeburgGermany
  2. 2.Medical Imaging Research GroupUniversity of British ColumbiaCanada

Personalised recommendations