Advertisement

Unsupervised Unstained Cell Detection by SIFT Keypoint Clustering and Self-labeling Algorithm

  • Firas Mualla
  • Simon Schöll
  • Björn Sommerfeldt
  • Andreas Maier
  • Stefan Steidl
  • Rainer Buchholz
  • Joachim Hornegger
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8675)

Abstract

We propose a novel unstained cell detection algorithm based on unsupervised learning. The algorithm utilizes the scale invariant feature transform (SIFT), a self-labeling algorithm, and two clustering steps in order to achieve high performance in terms of time and detection accuracy. Unstained cell imaging is dominated by phase contrast and bright field microscopy. Therefore, the algorithm was assessed on images acquired using these two modalities. Five cell lines having in total 37 images and 7250 cells were considered for the evaluation: CHO, L929, Sf21, HeLa, and Bovine cells. The obtained F-measures were between 85.1 and 89.5. Compared to the state-of-the-art, the algorithm achieves very close F-measure to the supervised approaches in much less time.

Keywords

Interest Point Scale Invariant Feature Transform Cell Detection Centeredness Error Supervise Approach 
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.

References

  1. 1.
    Sjöström, P.J., Frydel, B.R., Wahlberg, L.U.: Artificial neural network-aided image analysis system for cell counting. Cytometry 36(1), 18–26 (1999)CrossRefGoogle Scholar
  2. 2.
    Loukas, C.G., Wilson, G.D., Vojnovic, B., Linney, A.: An image analysis-based approach for automated counting of cancer cell nuclei in tissue sections. Cytometry Part A 55A(1), 30–42 (2003)CrossRefGoogle Scholar
  3. 3.
    Ali, R., Gooding, M., Szilágyi, T., Vojnovic, B., Christlieb, M., Brady, M.: Automatic segmentation of adherent biological cell boundaries and nuclei from brightfield microscopy images. Machine Vision and Applications 23(4), 607–621 (2012)CrossRefGoogle Scholar
  4. 4.
    Li, K., Chen, M., Kanade, T., Miller, E., Weiss, L., Campbell, P.: Cell population tracking and lineage construction with spatiotemporal context. Medical Image Analysis 12(5), 546–566 (2008)CrossRefGoogle Scholar
  5. 5.
    Long, X., Cleveland, W., Yao, Y.: Automatic detection of unstained viable cells in bright field images using a support vector machine with an improved training procedure. Computers in Biology and Medicine 36(4), 339–362 (2006)CrossRefGoogle Scholar
  6. 6.
    Lulevich, V., Shih, Y.P., Lo, S.H., Liu, G.Y.: Cell tracing dyes significantly change single cell mechanics. The Journal of Physical Chemistry B 113(18), 6511–6519 (2009)CrossRefGoogle Scholar
  7. 7.
    van Opstal, W., Ranger, C., Lejeune, O., Forgez, P., Boudin, H., Bisconte, J., Rostene, W.: Automated image analyzing system for the quantitative study of living cells in culture. Microscopy Research and Technique 28(5), 440–447 (1994)CrossRefGoogle Scholar
  8. 8.
    Long, X., Cleveland, W., Yao, Y.: A new preprocessing approach for cell recognition. IEEE Transactions on Information Technology in Biomedicine 9(3), 407–412 (2005)CrossRefGoogle Scholar
  9. 9.
    Mualla, F., Schöll, S., Sommerfeldt, B., Maier, A., Hornegger, J.: Automatic cell detection in bright-field microscope images using SIFT, random forests, and hierarchical clustering. IEEE Transactions on Medical Imaging 32(12), 2274–2286 (2013)CrossRefGoogle Scholar
  10. 10.
    Nattkemper, T., Ritter, H., Schubert, W.: Extracting patterns of lymphocyte fluorescence from digital microscope images. In: Intelligent Data Analysis in Medicine and Pharmacology, pp. 79–88 (1999)Google Scholar
  11. 11.
    Mualla, F., Schöll, S., Sommerfeldt, B., Maier, A., Steidl, S., Buchholz, R., Hornegger, J.: Using the low-pass monogenic signal framework for cell/background classification on multiple cell lines in bright-field microscope images. International Journal of Computer Assisted Radiology and Surgery, 1–8 (2013)Google Scholar
  12. 12.
    Pan, J., Kanade, T., Chen, M.: Learning to detect different types of cells under phase contrast microscopy. In: Microscopic Image Analysis with Applications in Biology (2009)Google Scholar
  13. 13.
    Arteta, C., Lempitsky, V., Noble, J.A., Zisserman, A.: Learning to detect cells using non-overlapping extremal regions. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012, Part I. LNCS, vol. 7510, pp. 348–356. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  14. 14.
    Pan, J., Kanade, T., Chen, M.: Heterogeneous conditional random field: Realizing joint detection and segmentation of cell regions in microscopic images. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2940–2947 (2010)Google Scholar
  15. 15.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Firas Mualla
    • 1
  • Simon Schöll
    • 1
    • 3
    • 4
  • Björn Sommerfeldt
    • 2
  • Andreas Maier
    • 1
    • 3
  • Stefan Steidl
    • 1
  • Rainer Buchholz
    • 2
  • Joachim Hornegger
    • 1
    • 3
  1. 1.Pattern Recognition LabFriedrich-Alexander-Universität Erlangen-NürnbergGermany
  2. 2.Institute of Bioprocess EngineeringFriedrich-Alexander-Universität Erlangen-NürnbergGermany
  3. 3.SAOT Graduate School in Advanced Optical TechnologiesGermany
  4. 4.ASTRUM IT GmbHGermany

Personalised recommendations