Kinetic Modeling Based Probabilistic Segmentation for Molecular Images

  • Ahmed Saad
  • Ghassan Hamarneh
  • Torsten Möller
  • Ben Smith
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5241)

Abstract

We propose a semi-supervised, kinetic modeling based segmentation technique for molecular imaging applications. It is an iterative, self-learning algorithm based on uncertainty principles, designed to alleviate low signal-to-noise ratio (SNR) and partial volume effect (PVE) problems. Synthetic fluorodeoxyglucose (FDG) and simulated Raclopride dynamic positron emission tomography (dPET) brain images with excessive noise levels are used to validate our algorithm. We show, qualitatively and quantitatively, that our algorithm outperforms state-of-the-art techniques in identifying different functional regions and recovering the kinetic parameters.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Rudin, M.: Molecular Imaging: Basic Principles and Applications in Biomedical Research. Imperial College Press (2005)Google Scholar
  2. 2.
    Morris, E.D., Endres, C.J., Schmidt, K.C., Christian, B.T.: Kinetic modeling in Positron Emission Tomography. In: Wernick, M., Aarsvold, J.N. (eds.) Emission Tomography: The Fundamentals of PET and SPECT. Academic, San Diego (2004)Google Scholar
  3. 3.
    Barber, D.C.: The use of principal components in the quantitative analysis of Gamma camera dynamic studies. Phys. Med. Biol. 25, 283–292 (1980)CrossRefGoogle Scholar
  4. 4.
    Guo, H., Renaut, R., Chen, K., Reiman, E.: Clustering huge data sets for parametric PET imaging. Journal of Biosystems 71, 81–92 (2001)CrossRefGoogle Scholar
  5. 5.
    Kamasak, M.E., Bayraktarb, B.: Unsupervised clustering of dynamic PET images on the projection domain. In: Proceedings of the SPIE Medical Imaging, pp. 1539–1548 (2006)Google Scholar
  6. 6.
    Maroy, R., Boisgard, R., Comtat, C., Frouin, V., Cathier, P., Duchesnay, E., Dolle, F., Nielsen, P.E., Trebossen, R., Tavitian, B.: Segmentation of Rodent whole-body dynamic PET images: An unsupervised method based on voxel dynamics. IEEE TMI 27, 342–354 (2008)Google Scholar
  7. 7.
    Saad, A., Smith, B., Hamarneh, G., Möller, T.: Simultaneous segmentation, kinetic parameter estimation, and uncertainty visualization of dynamic PET images. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part II. LNCS, vol. 4792, pp. 726–733. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  8. 8.
    Grady, L.: Multilabel random walker image segmentation using prior models. In: Proceedings of CVPR, pp. 763–770 (2005)Google Scholar
  9. 9.
    Scott, D.: Multivariate Density Estimation. Wiley, New York (1992)MATHCrossRefGoogle Scholar
  10. 10.
    Zhu, X.: Semi-supervised learning literature survey. Technical report, Department of Computer Sciences, University of Wisconsin, Madison (2005)Google Scholar
  11. 11.
    Reilhac, A., Batan, G., Michel, C., Grova, C., Tohka, J., Costes, N., Evans, A.C.: Validation of PET SORTEO: a platform for simulating realistic PET studies and development of a database of simulated PET volumes. IEEE Trans. Nucl. Sci. 52, 1321–1328 (2004)CrossRefGoogle Scholar
  12. 12.
    Muzic, R., Cornelius, S.: COMKAT: compartment model kinetic analysis tool. JNM 42(4), 636–645 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Ahmed Saad
    • 1
    • 2
  • Ghassan Hamarneh
    • 1
  • Torsten Möller
    • 2
  • Ben Smith
    • 1
    • 2
  1. 1.Medical Image Analysis Lab 
  2. 2.Graphics, Usability, and Visualization Lab, School of Computing ScienceSimon Fraser UniversityCanada

Personalised recommendations