FULLY-AUTOMATED SEGMENTATION OF TUMOR AREAS IN TISSUE CONFOCAL IMAGES - Comparison between a Custom Unsupervised and a Supervised SVM Approach

Santa Di Cataldo, Elisa Ficarra, Enrico Macii

Abstract

In this paper we present a fully-automated method for the detection of tumor areas in immunohistochemical confocal images. The image segmentation provided by the proposed technique allows quantitative protein activity evaluation on the target tumoral tissue disregarding tissue areas that are not affected by the pathology, such as connective tissue. The automated method, that is based on an innovative unsupervised clustering approach, enables more accurate tissue segmentation compared to traditional supervised methods that can be found in literature, such as Support Vector Machine (SVM). Experimental results conducted on a large set of heterogeneous immunohistochemical lung cancer tissue images demonstrate that the proposed approach overcomes the performance of SVM by 8%, achieving on average an accuracy of 90%.

References

  1. Angelini, E, Campanini, R., Iampieri, E., Lanconelli, N. Masotti, M., Roffilli, M., 2006. Testing the performances of different image representation for mass classification in digital mammograms. Int. J. Mod. Phys. 17(1):113-131.
  2. Anguita, D., Boni, A., Ridella, S., Rivieccio F., Sterpi, D., 2005. Theoretical and Practical Model Selection Methods for Support Vector Classifiers. Springer, Studies in Fuzziness and Soft Computing, Support Vector Machines: Theory and Application.
  3. Brey, E.M., Lalani, Z., Hohnston, C., Wong, M., McIntire, L.V., Duke, P.J., Patrick, C.W., 2003. Automated selection of DAB-labeled tissue for immunohistochemical quantification. In J. Histochem. Cytochem., 51(5), pp.575-584.
  4. Cai, C.Z., W.L.Wang, Y.Z: Chen, 2003. Int.J.Mod.Phys. 14:575.
  5. Demandolx D, Davoust J. , 1997. Multiparameter image cytometry: from confocal micrographs to subcellular fluorograms. Bioimaging. 4:159-169.
  6. Dybowski R., 2000. Neural computation in medicine: perspectives and prospects. Proc. ANNIMAB-1. pp. 27-36.
  7. E. Osuna, R. Freund, F. Girrosi, 1997. Training Support Vector Machines: an Application to Face Detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'97). pp. 130.
  8. Ficarra, E., Macii, E., De Micheli, G., 2006. Computeraided evaluation of protein expression in pathological tissue images. In Proc. of IEEE CBMS'06., pp.413- 418.
  9. Jain, A.K., Dubes, R.C., 1988. Algorithms for clustering data, Prentice Hall.
  10. Landini, G., 2007. Software, http://www.dentistry.bham.ac .uk/landinig/software/software.html
  11. Malpica N, de Solorzano CO, Vaquero JJ, Santos A, Vallcorba I, Garcia-Sagredo JM, del Pozo F, 1997. Applying watershed algorithms to the segmentation of clustered nuclei. Cytometry. 28(4): 289-297.
  12. Muller K.R:, S. Mika,G. Ratsch, K. Tsuda, 2001. IEEE Trans. Neural Networks, 12:181.
  13. Nattkemper, T.W., 2004. Automatic segmentation of digital micrographs: A survey. Medinfo, 11(Pt 2):847-51.
  14. Nedzved A, Ablameyko S, Pitas I., 2000. Morphological segmentation of histology cell images. ICPR. 1:500-3.
  15. Platt, J., 1999. Fast training of support vector machines using sequential minimal optimization. In Scholkopf, B., Advances in kernel methods-support vector learning. MIT Press, Cambridge, MA, USA.
  16. Ruifrok, A.C., Johnston, D.A., 2001. Quantification of histochemical staining by color deconvolution. In Anal.Quant.Cytol.Histol., 23(4), pp.291-299.
  17. Ruifrok, A.C., Katz, R., Johnston, D., 2004. Comparison of quantification of histochemical staining by HueSaturation-Intensity (HSI) transformation and color deconvolution. In Appl. Immunohisto. M. M., 11(1), pp.85-91.
  18. Statnikov, A., Aliferis, C.F., Tsamardinos, I., Hardin, D., Levy, S., 2005. A comprehensive evaluation of multicategory classification methods for microarray gene expression cancer diagnosis. In Bioinformatics, 21(5), pp.631-643.
  19. Taneja, T.K., SK.Sharma Markers of small cell lung cancer. World Journal of Surgical Oncology, Vol(2):10.
  20. Vapnik, V., 1998. Statistical learning theory, WileyInterscience, New York, NY, USA.
  21. Wang, L., 2004. Support vector machines: theory and applications, Springer.
Download


Paper Citation


in Harvard Style

Di Cataldo S., Ficarra E. and Macii E. (2008). FULLY-AUTOMATED SEGMENTATION OF TUMOR AREAS IN TISSUE CONFOCAL IMAGES - Comparison between a Custom Unsupervised and a Supervised SVM Approach . In Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2008) ISBN 978-989-8111-18-0, pages 116-123. DOI: 10.5220/0001068501160123


in Bibtex Style

@conference{biosignals08,
author={Santa Di Cataldo and Elisa Ficarra and Enrico Macii},
title={FULLY-AUTOMATED SEGMENTATION OF TUMOR AREAS IN TISSUE CONFOCAL IMAGES - Comparison between a Custom Unsupervised and a Supervised SVM Approach},
booktitle={Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2008)},
year={2008},
pages={116-123},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001068501160123},
isbn={978-989-8111-18-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2008)
TI - FULLY-AUTOMATED SEGMENTATION OF TUMOR AREAS IN TISSUE CONFOCAL IMAGES - Comparison between a Custom Unsupervised and a Supervised SVM Approach
SN - 978-989-8111-18-0
AU - Di Cataldo S.
AU - Ficarra E.
AU - Macii E.
PY - 2008
SP - 116
EP - 123
DO - 10.5220/0001068501160123