Advertisement

Leveraging Random Forests for Interactive Exploration of Large Histological Images

  • Loïc Peter
  • Diana Mateus
  • Pierre Chatelain
  • Noemi Schworm
  • Stefan Stangl
  • Gabriele Multhoff
  • Nassir Navab
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8673)

Abstract

The large size of histological images combined with their very challenging appearance are two main difficulties which considerably complicate their analysis. In this paper, we introduce an interactive strategy leveraging the output of a supervised random forest classifier to guide a user through such large visual data. Starting from a forest-based pixelwise estimate, subregions of the images at hand are automatically ranked and sequentially displayed according to their expected interest. After each region suggestion, the user selects among several options a rough estimate of the true amount of foreground pixels in this region. From these one-click inputs, the region scoring function is updated in real time using an online gradient descent procedure, which corrects on-the-fly the shortcomings of the initial model and adapts future suggestions accordingly. Experimental validation is conducted for extramedullary hematopoesis localization and demonstrates the practical feasibility of the procedure as well as the benefit of the online adaptation strategy.

References

  1. 1.
    Veta, M., Pluim, J., van Diest, P., Viergever, M.: Breast cancer histopathology image analysis: A review. IEEE Transactions on Biomedical Engineering (2014)Google Scholar
  2. 2.
  3. 3.
    Crowley, R.S., Naus, G.J., Stewart, J., Friedman, C.P.: Development of visual diagnostic expertise in pathology - an information-processing study. Journal of the American Medical Informatics Association 10(1), 39–51 (2003)CrossRefGoogle Scholar
  4. 4.
    Zhao, P., Hoi, S.C.: OTL: A framework of online transfer learning. In: Proceedings of the 27th International Conference on Machine Learning, pp. 1231–1238 (2010)Google Scholar
  5. 5.
    Tommasi, T., Orabona, F., Kaboli, M., Caputo, B.: Leveraging over prior knowledge for online learning of visual categories. In: BMVC (2012)Google Scholar
  6. 6.
    Jain, V., Learned-Miller, E.: Online domain adaptation of a pre-trained cascade of classifiers. In: CVPR, pp. 577–584 (2011)Google Scholar
  7. 7.
    Breiman, L.: Random forests. Machine Learning (2001)Google Scholar
  8. 8.
    Criminisi, A., Shotton, J.: Decision Forests for Computer Vision and Medical Image Analysis. Springer (2013)Google Scholar
  9. 9.
    Saffari, A., Leistner, C., Santner, J., Godec, M., Bischof, H.: On-line random forests. In: ICCV Workshops, pp. 1393–1400 (September 2009)Google Scholar
  10. 10.
    Hastie, T., Tibshirani, R., Friedman, J.: The elements of statistical learning: data mining, inference and prediction, 2nd edn. Springer (2009)Google Scholar
  11. 11.
    Shalev-Shwartz, S.: Online learning and online convex optimization. Found. Trends Mach. Learn. 4(2), 107–194 (2012)CrossRefGoogle Scholar
  12. 12.
    Tao, K., Fang, M., Alroy, J., Sahagian, G.: Imagable 4t1 model for the study of late stage breast cancer. BMC Cancer 8(1) (2008)Google Scholar
  13. 13.
    Winn, J., Criminisi, A., Minka, T.: Object categorization by learned universal visual dictionary. In: ICCV (2005)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Loïc Peter
    • 1
  • Diana Mateus
    • 1
    • 2
  • Pierre Chatelain
    • 1
    • 3
  • Noemi Schworm
    • 4
  • Stefan Stangl
    • 4
  • Gabriele Multhoff
    • 4
    • 5
  • Nassir Navab
    • 1
    • 6
  1. 1.Computer Aided Medical ProceduresTechnische Universität MünchenGermany
  2. 2.Institute of Computational BiologyHelmholtz Zentrum MünchenGermany
  3. 3.Université de Rennes 1, IRISAFrance
  4. 4.Department of Radiation OncologyTechnische Universität MünchenGermany
  5. 5.CCG - Innate Immunity in Tumor BiologyHelmholtz Zentrum MünchenGermany
  6. 6.Computer Aided Medical ProceduresJohns Hopkins UniversityUSA

Personalised recommendations