Self-learning Segmentation and Classification of Cell-Nuclei in 3D Volumetric Data Using Voxel-Wise Gray Scale Invariants

  • Janis Fehr
  • Olaf Ronneberger
  • Haymo Kurz
  • Hans Burkhardt
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3663)

Abstract

We introduce and discuss a new method for segmentation and classification of cells from 3D tissue probes. The anisotropic 3D volumetric data of fluorescent marked cell nuclei is recorded by a confocal laser scanning microscope (LSM). Voxel-wise gray scale features (see accompaning paper [1][2]) ), invariant towards 3D rotation of its neighborhood, are extracted from the original data by integrating over the 3D rotation group with non-linear kernels.

In an interactive process, support-vector machine models are trained for each cell type using user relevance feedback. With this reference database at hand, segmentation and classification can be achieved in one step, simply by classifying each voxel and performing a connected component labelling, automatically without further human interaction. This general approach easily allows adoption of other cell types or tissue structures just by adding new training samples and re-training the model. Experiments with datasets from chicken chorioallantoic membrane show encouraging results.

Keywords

Training Sample Nonlinear Kernel Connected Component Label Volumetric Dataset Kernel Point 
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.
    Ronneberger, O., Fehr, J., Burkhardt, H.: Voxel-wise gray scale invariants for simultaneous segmentation and classification. In: Kropatsch, W.G., Sablatnig, R., Hanbury, A. (eds.) DAGM 2005. LNCS, vol. 3663, pp. 85–92. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  2. 2.
    Ronneberger, O., Fehr, J., Burkhardt, H.: Voxel-wise gray scale invariants for simultaneous segmentation and classification – theory and application to cell-nuclei in 3d volumetric data. Internal report 2/05, IIF-LMB, University Freiburg (2005)Google Scholar
  3. 3.
    Schulz-Mirbach, H.: Invariant features for gray scale images. In: Sagerer, G., Posch, S., Kummert, F. (eds.) DAGM - Symposium “Mustererkennung”, Bielefeld, Reihe Informatik aktuell, vol. 17, pp. 1–14. Springer, Heidelberg (1995)Google Scholar
  4. 4.
    Burkhardt, H., Siggelkow, S.: Invariant features in pattern recognition – fundamentals and applications. In: Kotropoulos, C., Pitas, I. (eds.) Nonlinear Model-Based Image/Video Processing and Analysis, pp. 269–307. John Wiley & Sons, Chichester (2001)Google Scholar
  5. 5.
    Ronneberger, O., Burkhardt, H., Schultz, E.: General-purpose Object Recognition in 3D Volume Data Sets using Gray-Scale Invariants – Classification of Airborne Pollen-Grains Recorded with a Confocal Laser Scanning Microscope. In: Proceedings of the International Conference on Pattern Recognition, Quebec, Canada (2002)Google Scholar
  6. 6.
    Ronneberger, O., Schultz, E., Burkhardt, H.: Automated Pollen Recognition using 3D Volume Images from Fluorescence Microscopy. Aerobiologia 18, 107–115 (2002)CrossRefGoogle Scholar
  7. 7.
    Vapnik, V.N.: The nature of statistical learning theory. Springer, Heidelberg (1995)MATHGoogle Scholar
  8. 8.
    Ronneberger, O.: Libsvmtl - a support vector machine template library (2004), Download at http://lmb.informatik.uni-freiburg.de/lmbsoft/libsvmtl/
  9. 9.
    Kurz, H., et al.: Pericytes in experimental mda-mb231 tumor angiogenesis. Histochem. Cell. Biol. 117, 527–534 (2002)CrossRefGoogle Scholar
  10. 10.
    Kurz, H., et al.: Automatic classification of cell nuclei and cells during embryonic vascular development. Ann. Anat. 187(suppl.), 130 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Janis Fehr
    • 1
  • Olaf Ronneberger
    • 1
  • Haymo Kurz
    • 2
  • Hans Burkhardt
    • 1
  1. 1.Institut für Informatik, Lehrstuhl für Mustererkennung und BildverarbeitungAlbert-Ludwigs-Universität FreiburgFreiburg
  2. 2.Institut für Anatomie und Zell BiologieAlbert-Ludwigs-Universität Freiburg

Personalised recommendations