This paper addresses the problem of creating probabilistic brain atlases from manually labeled training data. We propose a general mesh-based atlas representation, and compare different atlas models by evaluating their posterior probabilities and the posterior probabilities of their parameters. Using such a Baysian framework, we show that the widely used ”average” brain atlases constitute relatively poor priors, partly because they tend to overfit the training data, and partly because they do not allow to align corresponding anatomical features across datasets. We also demonstrate that much more powerful representations can be built using content-adaptive meshes that incorporate non-rigid deformation field models. We believe extracting optimal prior probability distributions from training data is crucial in light of the central role priors play in many automated brain MRI analysis techniques.


Bayesian Inference Training Dataset Reference Position Mesh Node Message Block 
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.
    Van Leemput, K., Maes, F., Vandermeulen, D., Suetens, P.: Automated model-based tissue classification of MR images of the brain. IEEE Transactions on Medical Imaging 18(10), 897–908 (1999)CrossRefGoogle Scholar
  2. 2.
    Pohl, K.M., Wells III, W.M., Guimond, A., Kasai, K., Shenton, M.E., Kikinis, R., Grimson, W.E.L., Warfield, S.K.: Incorporating Non-rigid Registration into Expectation Maximization Algorithm to Segment MR Images. In: Dohi, T., Kikinis, R. (eds.) MICCAI 2002. LNCS, vol. 2488, pp. 564–571. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  3. 3.
    Zijdenbos, A.P., Forghani, R., Evans, A.C.: Automatic ”pipeline” analysis of 3-D MRI data for clinical trials: Application to multiple sclerosis. IEEE Transactions on Medical Imaging 21(10), 1280–1291 (2002)CrossRefGoogle Scholar
  4. 4.
    Fischl, B., Salat, D.H., van der Kouwe, A.J.W., Makris, N., Segonne, F., Quinn, B.T., Dalea, A.M.: Sequence-independent segmentation of magnetic resonance images. NeuroImage 23, S69–S84 (2004)CrossRefGoogle Scholar
  5. 5.
    Ashburner, J., Friston, K.J.: Unified segmentation. NeuroImage 26, 839–851 (2005)CrossRefGoogle Scholar
  6. 6.
    Prastawa, M., Gilmore, J.H., Lin, W., Gerig, G.: Automatic segmentation of MR images of the developing newborn brain. Medical Image Analysis 9, 457–466 (2005)CrossRefGoogle Scholar
  7. 7.
    D’Agostino, E., Maes, F., Vandermeulen, D., Suetens, P.: Non-rigid Atlas-to-Image Registration by Minimization of Class-Conditional Image Entropy. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004. LNCS, vol. 3216, pp. 745–753. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  8. 8.
    De Craene, M., du Bois d’Aische, A., Macq, B., Warfield, S.K.: Multi-subject registration for unbiased statistical atlas construction. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004. LNCS, vol. 3216, pp. 655–662. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  9. 9.
    Lorenzen, P., Prastawa, M., Davis, B., Gerig, G., Bullitt, E., Joshi, S.: Multi-modal image set registration and atlas formation. Medical Image Analysis (in press, 2006)Google Scholar
  10. 10.
    Hoppe, H.: Progressive meshes. In: ACM SIGGRAPH 1996, pp. 99–108 (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Koen Van Leemput
    • 1
  1. 1.Helsinki Medical Imaging CenterHelsinki University Central HospitalFinland

Personalised recommendations