Probabilistic Brain Atlas Encoding Using Bayesian Inference
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.
KeywordsBayesian Inference Training Dataset Reference Position Mesh Node Message Block
- 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
- 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.Hoppe, H.: Progressive meshes. In: ACM SIGGRAPH 1996, pp. 99–108 (1996)Google Scholar