Advertisement

Rapidly Adaptive Cell Detection Using Transfer Learning with a Global Parameter

  • Nhat H. Nguyen
  • Eric Norris
  • Mark G. Clemens
  • Min C. Shin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7009)

Abstract

Recent advances in biomedical imaging have enabled the analysis of many different cell types. Learning-based cell detectors tend to be specific to a particular imaging protocol and cell type. For a new dataset, a tedious re-training process is required. In this paper, we present a novel method of training a cell detector on new datasets with minimal effort. First, we combine the classification rules extracted from existing data with the training samples of new data using transfer learning. Second, a global parameter is incorporated to refine the ranking of the classification rules. We demonstrate that our method achieves the same performance as previous approaches with only 10% of the training effort.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Balagopalan, L., Sherman, E., Barr, V., Samelson, L.: Imaging techniques for assaying lymphocyte activation in action. Nat. Rev. Immunol. 11(1), 21–33 (2011)CrossRefGoogle Scholar
  2. 2.
    Carpenter, A., Jones, T., Lamprecht, M., Clarke, C., Kang, I., Friman, O., Guertin, D., Moffat, J., et al.: Cellprofiler: image analysis software for identifying and quantifying cell phenotypes. Genome Biology 7(10), R100 (2006)CrossRefGoogle Scholar
  3. 3.
    Freund, Y., Schapire, R.: A short introduction to boosting. Japonese Society for Artificial Intelligence 14(5), 771–780 (1999)Google Scholar
  4. 4.
    Hodneland, E., Bukoreshtliev, N., Eichler, T., Tai, X.C., Gurke, S., Lundervold, A., Gerdes, H.H.: A unified framework for automated 3-d segmentation of surface-stained living cells and a comprehensive segmentation evaluation. IEEE Transactions on Medical Imaging 28(5), 720–738 (2009)CrossRefGoogle Scholar
  5. 5.
    Kullback, S.: The kullback-leibler distance. The American Statistician 41(4), 340–341 (1987)Google Scholar
  6. 6.
    Mukherjee, D., Ray, N., Acton, S.: Level set analysis for leukocyte detection and tracking. IEEE Transactions on Image Processing 13(4), 562–572 (2004)CrossRefGoogle Scholar
  7. 7.
    Nguyen, N., Keller, S., Huynh, T., Shin, M.: Tracking colliding cells. In: IEEE Workshop in Applications of Computer Vision (2009)Google Scholar
  8. 8.
    Pan, J., Kanade, T., Chen, M.: Heterogeneous conditional random field: Realizing joint detection and segmentation of cell regions in microscopic images. In: 2010 on Computer Vision and Pattern Recognition (CVPR), pp. 2940–2947 (2010)Google Scholar
  9. 9.
    Toomre, D., Bewersdorf, J.: A new wave of cellular imaging. Annual Review of Cell and Developmental Biology (January 2010)Google Scholar
  10. 10.
    Yao, Y., Doretto, G.: Boosting for transfer learning with multiple sources. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1855–1862 (June 2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Nhat H. Nguyen
    • 1
  • Eric Norris
    • 2
  • Mark G. Clemens
    • 2
  • Min C. Shin
    • 1
  1. 1.Department of Computer ScienceUniversity of North CarolinaCharlotte
  2. 2.Department of BiologyUniversity of North CarolinaCharlotte

Personalised recommendations