Skip to main content

Clinical Neonatal Brain MRI Segmentation Using Adaptive Nonparametric Data Models and Intensity-Based Markov Priors

  • Conference paper

Part of the Lecture Notes in Computer Science book series (LNIP,volume 4791)

Abstract

This paper presents a Bayesian framework for neonatal brain-tissue segmentation in clinical magnetic resonance (MR) images. This is a challenging task because of the low contrast-to-noise ratio and large variance in both tissue intensities and brain structures, as well as imaging artifacts and partial-volume effects in clinical neonatal scanning. We propose to incorporate a spatially adaptive likelihood model using a data-driven nonparametric statistical technique. The method initially learns an intensity-based prior, relying on the empirical Markov statistics from training data, using fuzzy nonlinear support vector machines (SVM). In an iterative scheme, the models adapt to spatial variations of image intensities via nonparametric density estimation. The method is effective even in the absence of anatomical atlas priors. The implementation, however, can naturally incorporate probabilistic atlas priors and Markov-smoothness priors to impose additional regularity on segmentation. The maximum-a-posteriori (MAP) segmentation is obtained within a graph-cut framework. Cross validation on clinical neonatal brain-MR images demonstrates the efficacy of the proposed method, both qualitatively and quantitatively.

Keywords

  • Support Vector Machine
  • Manual Segmentation
  • Neonatal Brain
  • Support Vector Machine Training
  • Fuzzy Support Vector Machine

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. van der Knaap, M., Valik, J.: MR imaging of the various stages of normal myelination during the first year of life. Neuroradiology 31(6), 459–470 (1990)

    CrossRef  Google Scholar 

  2. Dietrich, R.: Maturation, Myelination, and Dysmyelination. In: Magnetic Resonance Imaging. Mosby. pp. 1425–1447 (1999)

    Google Scholar 

  3. Barkovich, A.: Magnetic resonance techniques in the assessment of myelin and myelination. J Inherit Metab Dis. 28(3), 311–343 (2005)

    CrossRef  Google Scholar 

  4. Prastawa, M., Gilmore, J., Lin, W., Gerig, G.: Automatic segmentation of MR images of the developing newborn brain. Med Image Anal. 9(5), 457–466 (2005)

    CrossRef  Google Scholar 

  5. Song, Z., Tustison, N., Avants, B., Gee, J.: Integrated graph cuts for brain mri segmentation. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4191, pp. 831–838. Springer, Heidelberg (2006)

    CrossRef  Google Scholar 

  6. Leemput, K.V., Maes, F., Vandermeulen, D., Seutens, P.: Automated model-based tissue classification of MR images of the brain. IEEE Tr. Med. Imaging 18, 897–908 (1999)

    CrossRef  Google Scholar 

  7. Greenspan, H., Ruf, A., Goldberger, J.: Constrained gaussian mixture model framework for automatic segmentation of MR brain images. IEEE Trans. Medical Imaging 25(9), 1233–1245 (2006)

    CrossRef  Google Scholar 

  8. Awate, S., Tasdizen, T., Foster, N., Whitaker, R.: Adaptive, nonparametric markov modeling for unsupervised, MRI brain-tissue classification. Medical Image Analysis 10(5), 726–739 (2006)

    CrossRef  Google Scholar 

  9. Awate, S.P., Gee, J.C.: A fuzzy, nonparametric segmentation framework for DTI and MRI analysis. In: Proc. Info. Proc. in Med. Imag (IPMI) (to appear, 2007)

    Google Scholar 

  10. Burges, C.: A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery 2, 121–167 (1998)

    CrossRef  Google Scholar 

  11. Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Machine Intell. 23(11), 1222–1239 (2001)

    CrossRef  Google Scholar 

  12. Chow, Y., Geman, S., Wu, L.: Consistent cross-validated density estimation. Annals of Statistics 11(1), 25–38 (1983)

    MATH  MathSciNet  Google Scholar 

  13. Collobert, R., Bengio, S.: Svmtorch: Support vector machines for large-scale regression problems. Journal of machine learning research 1, 143–160 (2001)

    CrossRef  MathSciNet  Google Scholar 

  14. Platt, J.: Probabilistic outputs for support vector machines and comparison to regularized likelihood methods. In: Advances in Large Margin Classifiers, MIT Press, Cambridge (1999)

    Google Scholar 

  15. Weisenfeld, N., Mewes, A., Warfield, S.: Highly accurate segmentation of brain tissue and subcortical gray matter from newborn mri. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4190, pp. 199–206. Springer, Heidelberg (2006)

    CrossRef  Google Scholar 

  16. Avants, B., Gee, J.: Geodesic estimation for large deformation anatomical shape and intensity averaging. Neuroimage Suppl. 1, S139–150 (2004)

    Google Scholar 

  17. Likar, B., Viergever, M.A., Pernus, F.: Retrospective correction of MR intensity inhomogeneity by information minimization. IEEE Trans. Med. Imaging 20(12), 1398–1410 (2001)

    CrossRef  Google Scholar 

  18. Stark, J.: Adaptive image contrast enhancement using generalizations of histogram equalization. IEEE Trans. Image Processing 9(5), 889–896 (2000)

    CrossRef  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2007 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Song, Z., Awate, S.P., Licht, D.J., Gee, J.C. (2007). Clinical Neonatal Brain MRI Segmentation Using Adaptive Nonparametric Data Models and Intensity-Based Markov Priors. In: Ayache, N., Ourselin, S., Maeder, A. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2007. MICCAI 2007. Lecture Notes in Computer Science, vol 4791. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75757-3_107

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-75757-3_107

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-75756-6

  • Online ISBN: 978-3-540-75757-3

  • eBook Packages: Computer ScienceComputer Science (R0)