Advertisement

Highly Accurate Segmentation of Brain Tissue and Subcortical Gray Matter from Newborn MRI

  • Neil I. Weisenfeld
  • Andrea U. J. Mewes
  • Simon K. Warfield
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4190)

Abstract

The segmentation of newborn brain MRI is important for assessing and directing treatment options for premature infants at risk for developmental disorders, abnormalities, or even death. Segmentation of infant brain MRI is particularly challenging when compared with the segmentation of images acquired from older children and adults. We sought to develop a fully automated segmentation strategy and present here a Bayesian approach utilizing an atlas of priors derived from previous segmentations and a new scheme for automatically selecting and iteratively refining classifier training data using the STAPLE algorithm. Results have been validated by comparison to hand-drawn segmentations.

Keywords

Training Point Cortical Gray Matter Accurate Segmentation Tissue Class Subcortical Gray Matter 
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.
    Martin, J.A., Hamilton, B.E., Sutton, P.D., Ventura, S.J., Menakcker, F., Munson, M.L.: Births: Final data for 2003. National Vital Statistics Reports 54(2) (2005)Google Scholar
  2. 2.
    Warfield, S.K., Zou, K.H., Wells, W.M.: Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Trans. Med. Imag. 23, 903–921 (2004)CrossRefGoogle Scholar
  3. 3.
    Viola, P.A.: Alignment by maximization of mutual information. PhD thesis, MIT, Cambridge, MA, USA (1995)Google Scholar
  4. 4.
    Mangin, J.F.: Entropy minimization for automatic correction of intensity non-uniformity. In: Math. Methods in Biomed. Imag. Anal., pp. 162–169. IEEE Computer Society, Los Alamitos (2000)Google Scholar
  5. 5.
    Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Pat. Anal. Mach. Intel. 12, 629–639 (1990)CrossRefGoogle Scholar
  6. 6.
    Gerig, G., Kubler, O., Kikinis, R., Jolesz, F.: Nonlinear anistropic filtering of MRI data. IEEE Trans. Med. Imag. 2, 221–232 (1992)CrossRefGoogle Scholar
  7. 7.
    Yoo, T.S.: Insight into Images. A.K. Peters (2004)Google Scholar
  8. 8.
    Warfield, S.K., Kaus, M., Jolesz, F.A., Kikinis, R.: Adaptive, template moderated, spatially varying statistical classification. Medical Image Analysis 4(1), 43–55 (2000)CrossRefGoogle Scholar
  9. 9.
    Warfield, S.K.: Segmentation of Magnetic Resonance Images of the Brain. PhD thesis, The University of New South Wales, Australia (1997)Google Scholar
  10. 10.
    Weisenfeld, N.I., Mewes, A.U.J., Warfield, S.K.: Segmentation of newborn brain MRI. In: Proceedings of the 2006 IEEE International Symposium on Biomedical Imaging, Piscataway, Crystal City, Virginia, USA. IEEE, Los Alamitos (2006)Google Scholar
  11. 11.
    Duda, R.O., Hart, P.E.: Pattern Classification and Scence Analysis. John Wiley and Sons, New York (1973)Google Scholar
  12. 12.
    Leemput, K.V., Maes, F., Vandermeulen, D., Suetens, P.: Automated model-based tissue classification of MR images of the brain. IEEE Trans. Med. Imag. 18, 897–908 (1999)CrossRefGoogle Scholar
  13. 13.
    Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26, 207–302 (1945)CrossRefGoogle Scholar
  14. 14.
    Zijdenbos, A.P., Dawant, B.M., Margolin, R.A., Palmer, A.C.: Morphometric analysis of white matter lesions in MR images: Method and validation. IEEE Trans. Med. Imag. 13(4), 716–724 (1994)CrossRefGoogle Scholar
  15. 15.
    Wells, W.M., Kikinis, R., Grimson, W.E.L., Jolesz, F.: Adaptive segmentation of MRI data. IEEE Trans. Med. Imag. 15(4), 429–442 (1996)CrossRefGoogle Scholar
  16. 16.
    Zhang, Y., Brady, M., Smith, S.M.: Segmentation of brain MR images thorough a hidden markov random field model and the expectation maximization algorithm. IEEE Trans. Med. Imag. 20(1), 45–57 (2002)CrossRefGoogle Scholar
  17. 17.
    Fischl, B., Salat, D.H., Busa, E., Albert, M., Dieterich, M., Haselgrove, C., van der Kouwe, A., Killiany, R., Kennedy, D., Klaveness, S., Montillo, A., Makris, N., Rosen, B., Dale, A.M.: Whole brain segmentation: Automated labeling of neuroanatomical structures in the human brain. Neuron 33(3), 341–355 (2002)CrossRefGoogle Scholar
  18. 18.
    Peterson, B.S., Anderson, A.W., Ehrenkranz, R., Staib, L.H., Tageldin, M., Colson, E., Gore, J.C., Duncan, C.C., Makuch, R., Ment, L.R.: Regional brain volumes and their later neurodevelopmental correlates in term and preterm infants. Pediatrics 111, 939–948 (2006)CrossRefGoogle Scholar
  19. 19.
    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
  20. 20.
    Cocosco, C.A., Zijdenbos, A.P., Evans, A.C.: A fully automatic and robust brain MRI tissue classification method. Medical Image Analysis 7, 513–527 (2003)CrossRefGoogle Scholar
  21. 21.
    Grau, V., Mewes, A.U.J., Raya, M.A., Kikinis, R., Warfield, S.K.: Improved watershed transform for medical image segmentation using prior information. IEEE Trans. Med. Imag. 23(4), 447–458 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Neil I. Weisenfeld
    • 1
    • 2
  • Andrea U. J. Mewes
    • 1
  • Simon K. Warfield
    • 1
  1. 1.Computational Radiology LaboratoryBrigham and Women’s and Children’s Hospitals, Harvard Medical SchoolBoston
  2. 2.Department of Cognitive and Neural SystemsBoston UniversityBoston

Personalised recommendations