Weakly Supervised Group-Wise Model Learning Based on Discrete Optimization

  • René Donner
  • Horst Wildenauer
  • Horst Bischof
  • Georg Langs
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5762)


In this paper we propose a method for the weakly supervised learning of sparse appearance models from medical image data based on Markov random fields (MRF). The models are learnt from a single annotated example and additional training samples without annotations. The approach formulates the model learning as solving a set of MRFs. Both the model training and the resulting model are able to cope with complex and repetitive structures. The weakly supervised model learning yields sparse MRF appearance models that perform equally well as those trained with manual annotations, thereby eliminating the need for tedious manual training supervision. Evaluation results are reported for hand radiographs and cardiac MRI slices.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Cootes, T.F., Edwards, G.J., Taylor, C.J.: Active appearance models. IEEE Trans. PAMI 23(6), 681–685 (2001)Google Scholar
  2. 2.
    Langs, G., Peloschek, P., Donner, R., Reiter, M., Bischof, H.: Active Feature Models. In: Proc. ICPR, pp. 417–420 (2006)Google Scholar
  3. 3.
    Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images. In: Proc. ICCV, pp. 105–112 (2001)Google Scholar
  4. 4.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. International Journal on Computer Vision 1, 321–331 (1988)CrossRefGoogle Scholar
  5. 5.
    Paragios, N., Deriche, R.: Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects. IEEE PAMI 22(3) (2000)Google Scholar
  6. 6.
    Davies, R.H., Twining, C.J., Cootes, T.F., Waterton, J.C., Taylor, C.J.: 3D statistical shape models using direct optimisation of description length. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 3–20. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  7. 7.
    Cootes, T., Twining, C., Petrović, V., Taylor, C.: Groupwise construction of appearance models using piece-wise affine deformations. In: BMVC 2005 (2005)Google Scholar
  8. 8.
    Zöllei, L., Learned-Miller, E.G., Grimson, W.E.L., Wells, W.M.: Efficient population registration of 3D data. In: Liu, Y., Jiang, T.-Z., Zhang, C. (eds.) CVBIA 2005. LNCS, vol. 3765, pp. 291–301. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  9. 9.
    Langs, G., Donner, R., Peloschek, P., Bischof, H.: Robust autonomous model learning from 2D and 3D data sets. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part I. LNCS, vol. 4791, pp. 968–976. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  10. 10.
    Glocker, B., Komodakis, N., Tziritas, G., Navab, N., Paragios, N.: Dense image registration through MRFs and efficient linear programming. Medical Image Analysis 12(6), 731–741 (2008)CrossRefGoogle Scholar
  11. 11.
    Donner, R., Mičušík, B., Langs, G., Bischof, H.: Sparse MRF Appearance Models for Fast Anatomical Structure Localisation. In: Proc. BMVC (2007)Google Scholar
  12. 12.
    Wildenauer, H., Micusik, B., Vincze, M.: Efficient texture representation using multi-scale regions. In: ACCV, pp. 65–74 (2007)Google Scholar
  13. 13.
    Stegmann, M.B.: An annotated dataset of 14 cardiac MR images. Technical report, Technical University of Denmark, DTU (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • René Donner
    • 1
    • 2
  • Horst Wildenauer
    • 3
  • Horst Bischof
    • 2
  • Georg Langs
    • 1
  1. 1.Computational Image Analysis and Radiology Lab, Department of RadiologyMedical University of ViennaAustria
  2. 2.Institute for Computer Graphics and VisionGraz University of TechnologyAustria
  3. 3.Pattern Recognition and Image Processing GroupVienna University of TechnologyAustria

Personalised recommendations