We study the widespread, but rarely discussed, tendency of atlas-based segmentation to under-segment the organs of interest. Commonly used error measures do not distinguish between under- and over-segmentation, contributing to the problem. We explicitly quantify over- and under-segmentation in several typical examples and present a new hypothesis for the cause. We provide evidence that segmenting only one organ of interest and merging all surrounding structures into one label creates bias towards background in the label estimates suggested by the atlas. We propose a generative model that corrects for this effect by learning the background structures from the data. Inference in the model separates the background into distinct structures and consequently improves the segmentation accuracy. Our experiments demonstrate a clear improvement in several applications.


Left Atrium Parotid Gland Local Approach Dirichlet Process Segmentation Accuracy 
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.
    Arthur, D., Vassilvitskii, S.: k-means++: the advantages of careful seeding. In: ACM-SIAM Symposium on Discrete Algorithms (SODA), pp. 1027–1035 (2007)Google Scholar
  2. 2.
    Chang, J., Fisher III, J.W.: Parallel sampling of dp mixture models using sub-clusters splits. In: Neural Information Processing Systems, pp. 620–628 (2013)Google Scholar
  3. 3.
    Dice, L.: Measures of the amount of ecologic association between species. Ecology 26(3), 297–302 (1945)CrossRefGoogle Scholar
  4. 4.
    Dubuisson, M., Jain, A.: A modified hausdorff distance for object matching. In: International Conference on Pattern Recognition, vol. 1, pp. 566–568 (1994)Google Scholar
  5. 5.
    Görür, D., Rasmussen, C.E.: Dirichlet process gaussian mixture models: Choice of the base distribution. Computer Science and Technology 25(4), 653–664 (2010)CrossRefMathSciNetGoogle Scholar
  6. 6.
    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
  7. 7.
    Kulis, B., Jordan, M.I.: Revisiting k-means: New algorithms via bayesian nonparametrics. In: International Conference on Machine Learning, pp. 513–520 (2012)Google Scholar
  8. 8.
    Rohlfing, T., Brandt, R., Menzel, R., Maurer, C., et al.: Evaluation of atlas selection strategies for atlas-based image segmentation with application to confocal microscopy images of bee brains. NeuroImage 21(4), 1428–1442 (2004)CrossRefGoogle Scholar
  9. 9.
    Sabuncu, M., Yeo, B., Van Leemput, K., Fischl, B., Golland, P.: A Generative Model for Image Segmentation Based on Label Fusion. IEEE Transactions on Medical Imaging 29 (2010)Google Scholar
  10. 10.
    Sudderth, E.B.: Graphical Models for Visual Object Recognition and Tracking. Ph.D. thesis, Massachusetts Institute of Technology (2006)Google Scholar
  11. 11.
    Wachinger, C., Sharp, G.C., Golland, P.: Contour-driven regression for label inference in atlas-based segmentation. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part III. LNCS, vol. 8151, pp. 211–218. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  12. 12.
    Wang, H., Yushkevich, P.A.: Spatial bias in multi-atlas based segmentation. In: Computer Vision and Pattern Recognition (CVPR), pp. 909–916 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Christian Wachinger
    • 1
    • 2
  • Polina Golland
    • 1
  1. 1.Computer Science and Artificial Intelligence LabMITUSA
  2. 2.Massachusetts General Hospital, Harvard Medical SchoolUSA

Personalised recommendations