Advertisement

Randomized Tree Ensembles for Object Detection in Computational Pathology

  • Thomas J. Fuchs
  • Johannes Haybaeck
  • Peter J. Wild
  • Mathias Heikenwalder
  • Holger Moch
  • Adriano Aguzzi
  • Joachim M. Buhmann
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5875)

Abstract

Modern pathology broadly searches for biomarkers which are predictive for the survival of patients or the progression of cancer. Due to the lack of robust analysis algorithms this work is still performed manually by estimating staining on whole slides or tissue microarrays (TMA). Therefore, the design of decision support systems which can automate cancer diagnosis as well as objectify it pose a highly challenging problem for the medical imaging community.

In this paper we propose Relational Detection Forests (RDF) as a novel object detection algorithm, which can be applied in an off-the-shelf manner to a large variety of tasks. The contributions of this work are twofold: (i) we describe a feature set which is able to capture shape information as well as local context. Furthermore, the feature set is guaranteed to be generally applicable due to its high flexibility. (ii) we present an ensemble learning algorithm based on randomized trees, which can cope with exceptionally high dimensional feature spaces in an efficient manner. Contrary to classical approaches, subspaces are not split based on thresholds but by learning relations between features.

The algorithm is validated on tissue from 133 human clear cell renal cell carcinoma patients (ccRCC) and on murine liver samples of eight mice. On both species RDFs compared favorably to state of the art methods and approaches the detection accuracy of trained pathologists.

Keywords

Renal Cell Carcinoma Object Detection Clear Cell Renal Cell Carcinoma Voronoi Tessellation Trained Pathologist 
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.
    Yang, L., Meer, P., Foran, D.J.: Unsupervised segmentation based on robust estimation and color active contour models. IEEE Transactions on Information Technology in Biomedicine 9, 475–486 (2005)CrossRefGoogle Scholar
  2. 2.
    Mertz, K.D., Demichelis, F., Kim, R.,, Schraml, P., Storz, M., Diener, P.-A., Moch, H., Rubin, M.A.: Automated immunofluorescence analysis defines microvessel area as a prognostic parameter in clear cell renal cell cancer. Human Pathology 38, 1454–1462 (2007)CrossRefGoogle Scholar
  3. 3.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features (2001)Google Scholar
  4. 4.
    Grabner, H., Leistner, C., Bischof, H.: Semi-supervised on-line boosting for robust tracking. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 234–247. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  5. 5.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR 2005: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), Washington, DC, USA, vol. 1, pp. 886–893. IEEE Computer Society, Los Alamitos (2005)Google Scholar
  6. 6.
    Freund, Y., Schapire, R.: Experiments with a new boosting algorithm. In: Machine Learning: Proceedings of the Thirteenth International Conference, pp. 148–156 (1996)Google Scholar
  7. 7.
    Breiman, L.: Random forests. Machine Learning 45, 5–32 (2001)zbMATHCrossRefGoogle Scholar
  8. 8.
    Geurts, P., Ernst, D., Wehenkel, L.: Extremely randomized trees. Machine Learning 63, 3–42 (2006)zbMATHCrossRefGoogle Scholar
  9. 9.
    Strobl, C., Thomas Augustin, A.L.B.: Unbiased split selection for classification trees based on the gini index. Computational Statistics & Data Analysis 52, 483–501 (2007)zbMATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Kuhn, H.W.: The hungarian method for the assignment problem. Naval Research Logistic Quarterly 2, 83–97 (1955)CrossRefGoogle Scholar
  11. 11.
    R Development Core Team: R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria (2009) ISBN 3-900051-07-0Google Scholar
  12. 12.
    Hall, B., Chen, W., Reiss, M., Foran, D.J.: A clinically motivated 2-fold framework for quantifying and classifying immunohistochemically stained specimens. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part II. LNCS, vol. 4792, pp. 287–294. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  13. 13.
    Yang, L., Chen, W., Meer, P., Salaru, G., Feldman, M.D., Foran, D.J.: High throughput analysis of breast cancer specimens on the grid. Med. Image Comput. Comput. Assist. Interv. Int. Conf. Med. Image Comput. Comput. Assist Interv. 10, 617–625 (2007)Google Scholar
  14. 14.
    Nikiforidis, G.: An image-analysis system based on support vector machines for automatic grade diagnosis of brain-tumour astrocytomas in clinical routine. Medical Informatics and the Internet in Medicine 30, 179–193 (2005)CrossRefGoogle Scholar
  15. 15.
    Fuchs, T.J., Lange, T., Wild, P.J., Moch, H., Buhmann, J.M.: Weakly supervised cell nuclei detection and segmentation on tissue microarrays of renal cell carcinoma. In: Rigoll, G. (ed.) DAGM 2008. LNCS, vol. 5096, pp. 173–182. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  16. 16.
    Soille, P.: Morphological Image Analysis: Principles and Applications. Springer, Secaucus (2003)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Thomas J. Fuchs
    • 1
    • 4
  • Johannes Haybaeck
    • 2
  • Peter J. Wild
    • 3
  • Mathias Heikenwalder
    • 2
  • Holger Moch
    • 3
    • 4
  • Adriano Aguzzi
    • 2
  • Joachim M. Buhmann
    • 1
    • 4
  1. 1.Department of Computer ScienceETH ZürichZürichSwitzerland
  2. 2.Department of Pathology, Institute for NeuropathologyUniversity HospitalZürich
  3. 3.Department of Pathology, Institute of Surgical PathologyUniversity Hospital Zürich 
  4. 4.Competence Center for Systems Physiology and Metabolic DiseasesETH Zürich 

Personalised recommendations