Cell Event Detection in Phase-Contrast Microscopy Sequences from Few Annotations

  • Melih Kandemir
  • Christian Wojek
  • Fred A. Hamprecht
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9351)


We study detecting cell events in phase-contrast microscopy sequences from few annotations. We first detect event candidates from the intensity difference of consecutive frames, and then train an unsupervised novelty detector on these candidates. The novelty detector assigns each candidate a degree of surprise. We annotate a tiny number of candidates chosen according to the novelty detector’s output, and finally train a sparse Gaussian process (GP) classifier. We show that the steepest learning curve is achieved when a collaborative multi-output Gaussian process is used as novelty detector, and its predictive mean and variance are used together to measure the degree of surprise. Following this scheme, we closely approximate the fully-supervised event detection accuracy by annotating only 3% of all candidates. The novelty detector based annotation used here clearly outperforms the studied active learning based approaches.


Gaussian Process Local Binary Pattern Scale Invariant Feature Transform Class Imbalance Steep Learning Curve 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Houlsby, N., Huszar, F., Ghahramani, Z., Hernández-Lobato, J.M.: Collaborative Gaussian processes for preference learning. In: NIPS (2012)Google Scholar
  2. 2.
    Huh, S., Chen, M.: Detection of mitosis within a stem cell population of high cell confluence in phase-contrast microscopy images. In: CVPR (2011)Google Scholar
  3. 3.
    Huh, S., Ker, D.-F.E., Bise, R., Chen, M., Kanade, T.: Automated mitosis detection of stem cell populations in phase-contrast microscopy images. Trans. Medical Imaging 30(3), 586–596 (2011)CrossRefGoogle Scholar
  4. 4.
    Huh, S., Ker, D.F.E., Su, H., Kanade, T.: Apoptosis detection for adherent cell populations in time-lapse phase-contrast microscopy images. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part I. LNCS, vol. 7510, pp. 331–339. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  5. 5.
    Kaakinen, M., Huttinen, S., Paavolainen, L., Marjomaki, V., Heikkila, J., Eklund, L.: Automatic detection and analysis of cell motility in phase-contrast time-lapse images using a combination of maximally stable extremal regions and kalman filter approaches. Journal of Microscopy 253(1), 65–78 (2014)CrossRefGoogle Scholar
  6. 6.
    Kandemir, M., Rubio, J.C., Schmidt, U., Wojek, C., Welbl, J., Ommer, B., Hamprecht, F.A.: Event Detection by Feature Unpredictability in Phase-Contrast Videos of Cell Cultures. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014, Part II. LNCS, vol. 8674, pp. 154–161. Springer, Heidelberg (2014)Google Scholar
  7. 7.
    Lu, C., Shi, J., Jia, J.: Abnormal event detection at 150 fps in MATLAB. In: ICCV, pp. 2720–2727 (2013)Google Scholar
  8. 8.
    Nguyen, V.T., Bonilla, E.: Collaborative multi-output Gaussian processes. In: UAI (2014)Google Scholar
  9. 9.
    Rasmussen, C.E., Williams, C.I.: Gaussian processes for machine learning (2006)Google Scholar
  10. 10.
    Schölkopf, B., Platt, J.C., Shawe-Taylor, J., Smola, A.J., Williamson, R.C.: Estimating the support of a high-dimensional distribution. Neural Computation 13(7), 1443–1471 (2001)CrossRefzbMATHGoogle Scholar
  11. 11.
    Seeger, M.: Bayesian Gaussian process models: PAC-Bayesian generalisation error bounds and sparse approximations. PhD Thesis (2003)Google Scholar
  12. 12.
    Shewry, M.C., Wynn, H.P.: Maximum entropy sampling. Journal of Applied Statistics 14(2), 165–170 (1987)CrossRefGoogle Scholar
  13. 13.
    Snelson, E., Ghahramani, Z.: Sparse Gaussian processes using pseudo-inputs. In: NIPS (2006)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Melih Kandemir
    • 1
  • Christian Wojek
    • 2
  • Fred A. Hamprecht
    • 1
  1. 1.Heidelberg University, HCI/IWRHeidelbergGermany
  2. 2.Carl Zeiss AGOberkochenGermany

Personalised recommendations