Patch-Based Generative Shape Model and MDL Model Selection for Statistical Analysis of Archipelagos

  • Melanie Ganz
  • Mads Nielsen
  • Sami Brandt
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6357)

Abstract

We propose a statistical generative shape model for archipelago-like structures. These kind of structures occur, for instance, in medical images, where our intention is to model the appearance and shapes of calcifications in x-ray radio graphs. The generative model is constructed by (1) learning a patch-based dictionary for possible shapes, (2) building up a time-homogeneous Markov model to model the neighbourhood correlations between the patches, and (3) automatic selection of the model complexity by the minimum description length principle. The generative shape model is proposed as a probability distribution of a binary image where the model is intended to facilitate sequential simulation. Our results show that a relatively simple model is able to generate structures visually similar to calcifications. Furthermore, we used the shape model as a shape prior in the statistical segmentation of calcifications, where the area overlap with the ground truth shapes improved significantly compared to the case where the prior was not used.

Keywords

Training Image Code Length Manual Annotation Minimum Description Length Code Book 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Zhang, T., Switzer, P., Journel, A.: Filter-based classification of training image patterns for spatial simulation. Mathematical Geology 38(1), 63–80 (2006)MATHCrossRefGoogle Scholar
  2. 2.
    Strebelle, S.: Conditional simulation of complex geological structures using multiple-point statistics. Mathematical Geology 34(1), 1–21 (2002)MATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Mairal, J., et al.: Discriminative learned dictionaries for local image analysis. In: IEEE Conference on Computer Vision and Pattern Recognition 2008 (2008)Google Scholar
  4. 4.
    Zhu, S., Wu, Y., Mumford, D.: Filters, random fields and maximum entropy (FRAME): Towards a unified theory for texture modeling. International Journal of Computer Vision 27(2), 107–126 (1998)CrossRefGoogle Scholar
  5. 5.
    Wilson, P., et al.: Abdominal aortic calcific deposits are an important predictor of vascular morbidity and mortality. Circulation 103(11), 1529 (2001)Google Scholar
  6. 6.
    Witteman, J., Kok, F., van Saase, J., Valkenburg, H.: Aortic calcification as a predictor of cardiovascular mortality. The Lancet 2(8516), 1120–1122 (1986)CrossRefGoogle Scholar
  7. 7.
    Bolland, M., et al.: Abdominal aortic calcification on vertebral morphometry images predicts incident myocardial infarction. Journal of Bone and Mineral Research 25, 1–28 (2009)Google Scholar
  8. 8.
    MacKay, D.: Information theory, inference, and learning algorithms. Cambridge Univ. Pr., Cambridge (2003)MATHGoogle Scholar
  9. 9.
    Rissanen, J.: MDL denoising. IEEE Transactions on Information Theory 46(7), 2537–2543 (2000)MATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Jaccard, P.: The distribution of the flora in the alpine zone. New Phytologist 11(2), 37–50 (1912)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Melanie Ganz
    • 1
    • 2
  • Mads Nielsen
    • 1
    • 2
  • Sami Brandt
    • 2
  1. 1.DIKU, University of CopenhagenDenmark
  2. 2.Nordic Bioscience ImagingHerlevDenmark

Personalised recommendations