Supervised Nonparametric Image Parcellation

  • Mert R. Sabuncu
  • B. T. Thomas Yeo
  • Koen Van Leemput
  • Bruce Fischl
  • Polina Golland
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5762)

Abstract

Segmentation of medical images is commonly formulated as a supervised learning problem, where manually labeled training data are summarized using a parametric atlas. Summarizing the data alleviates the computational burden at the expense of possibly losing valuable information on inter-subject variability. This paper presents a novel framework for Supervised Nonparametric Image Parcellation (SNIP). SNIP models the intensity and label images as samples of a joint distribution estimated from the training data in a non-parametric fashion. By capitalizing on recently developed fast and robust pairwise image alignment tools, SNIP employs the entire training data to segment a new image via Expectation Maximization. The use of multiple registrations increases robustness to occasional registration failures. We report experiments on 39 volumetric brain MRI scans with manual labels for the white matter, cortex and subcortical structures. SNIP yields better segmentation than state-of-the-art algorithms in multiple regions of interest.

Keywords

Training Image Expectation Maximization Algorithm Normalize Mutual Information Training Subject Manual Label 
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.
    Fischl, B., Salat, D., van der Kouwe, A., Makris, N., Segonne, F., Quinn, B., Dale, A.: Sequence-independent segmentation of magnetic resonance images. Neuroimage 23, 69–84 (2004)CrossRefGoogle Scholar
  2. 2.
    Han, X., Fischl, B.: Atlas renormalization for improved brain MR image segmentation across scanner platforms. IEEE TMI 26(4), 479–486 (2007)Google Scholar
  3. 3.
    Mazziotta, J., Toga, A., Evans, A., Fox, P., Lancaster, J.: A probabilistic atlas of the human brain: Theory and rationale for its development: The international consortium for brain mapping (ICBM). Neuroimage 2(2), 89–101 (1995)CrossRefGoogle Scholar
  4. 4.
    Pohl, K., Fisher, J., Grimson, W., Kikinis, R., Wells, W.: A bayesian model for joint segmentation and registration. Neuroimage 31, 228–239 (2006)CrossRefGoogle Scholar
  5. 5.
    Yeo, B., Sabuncu, M., Desikan, R., Fischl, B., Golland, P.: Effects of registration regularization and atlas sharpness on segmentation accuracy. Medical Image Analysis 12(5), 603–615 (2008)CrossRefGoogle Scholar
  6. 6.
    Guimond, A., Meunier, F., Thirion, J.: Average brain models: A convergence study. Computer Vision and Image Understanding 77(2), 192–210 (2000)CrossRefGoogle Scholar
  7. 7.
    Joshi, S., Davis, B., Jomier, M., Gerig, G.: Unbiased diffeomorphism atlas construction for computational anatomy. Neuroimage 23, 151–160 (2004)CrossRefGoogle Scholar
  8. 8.
    Ashburner, J., Friston, K.: Unified segmentation. Neuroimage 26, 839–851 (2005)CrossRefGoogle Scholar
  9. 9.
    Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Symmetric log-domain diffeomorphic registration: A demons-based approach. In: Metaxas, D., Axel, L., Fichtinger, G., Székely, G. (eds.) MICCAI 2008, Part I. LNCS, vol. 5241, pp. 754–761. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  10. 10.
    Sabuncu, M., Yeo, B., Vercauteren, T., Leemput, K.V., Golland, P.: Asymmetric image template registration. In: Yang, G.-Z., et al. (eds.) MICCAI 2009, Part I. LNCS, vol. 5761, pp. 565–573. Springer, Heidelberg (2009)Google Scholar
  11. 11.
    Aljabar, P., Heckemann, R.A., Hammers, A., Hajnal, J.V., Rueckert, D.: Classifier selection strategies for label fusion using large atlas databases. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part I. LNCS, vol. 4791, pp. 523–531. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  12. 12.
    Heckemann, R., Hajnal, J., Aljabar, P., Rueckert, D., Hammers, A.: Automatic anatomical brain MRI segmentation combining label propagation and decision fusion. Neuroimage 33(1), 115–126 (2006)CrossRefGoogle Scholar
  13. 13.
    Isgum, I., Staring, M., Rutten, A., Prokop, M., Viergever, M., van Ginneken, B.: Multi-atlas-based segmentation with local decision fusion-application to cardiac and aortic segmentation in CT scans. TM (in press, 2009)Google Scholar
  14. 14.
    Allassonniere, S., Kuhn, E., Trouve, A.: Construction of Bayesian deformable models via stochastic approximation algorithm: a convergence study. arXiv.org (2009)Google Scholar
  15. 15.
    Van Leemput, K.: Probabilistic brain atlas encoding using bayesian inference. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4190, pp. 704–711. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  16. 16.
    Davis, B., Fletcher, P., Bullitt, E., Joshi, S.: Population shape regression from random design data. In: Proc. of ICCV, pp. 1–7 (2007)Google Scholar
  17. 17.
    Warfield, S., Zou, K., Wells, W.: Simultaneous truth and performance level estimation (STAPLE): an algorithm for validation of image segmentation. TMI 23(7), 903–921 (2004)Google Scholar
  18. 18.
    Arsigny, V., Commowick, O., Pennec, X., Ayache, N.: A log-euclidean framework for statistics on diffeomorphisms. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4190, pp. 924–931. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  19. 19.
    MacKay, D.: Information Theory, Pattern Recognition and Neural Networks (2003)Google Scholar
  20. 20.
    Dice, L.: Measures of the amount of ecologic association between species. Ecology 26(3), 297–302 (1945)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Mert R. Sabuncu
    • 1
  • B. T. Thomas Yeo
    • 1
  • Koen Van Leemput
    • 1
    • 2
    • 3
  • Bruce Fischl
    • 1
    • 2
  • Polina Golland
    • 1
  1. 1.Computer Science and Artificial Intelligence LabMIT 
  2. 2.Department of RadiologyHarvard Medical School 
  3. 3.Dept. of Information and Computer ScienceHelsinki University of Technology 

Personalised recommendations