350 rub
Journal Technologies of Living Systems №6 for 2012 г.
Article in number:
Automated detection and classification of buccal epithelium cell nuclei using a combination of classifiers
Keywords: cell segmentation automated nuclei recognition buccal epithelium threshold classifier nucleus detection
Authors:
A.S. Bobe, I.B. Alchinova, N.P. Antonova, E.N. Arkhipova, Yu.S. Medvedeva, M.Yu. Karganov
Abstract:
The article describes an algorithm which performs detection and classification of buccal epithelium cell nuclei basing on the microscopic images, with cytological samples colored with Feulgen-s stain. Automated segmentation of denoted samples is considered to be useful for rapid and qualitative analysis of the microcell tests results. Considering the basic features of the explored samples, the decision was made to build a two-step classifier to find the boundaries of nuclei on the images. On the first step a threshold is established for an image in two different color spaces: RGB and CIE Lab. The images obtained are then combined into one, on which the morphological operations are conducted. For the latter the information about the supposed size and shape of a nuclei is used. Localization of each nuclei within the cytoplasm area is checked. As a result of the first step the areas which probably refer to the cell nuclei are determined. The exact boundaries are established during the second step using the Canny edge filter. The proposed algorithm allows to detect 94.3% of cell nuclei with the wrong detection error level of 1.1% (estimated by testing on the available image base). Classification of different types of nuclei in order to detect anomalies can be conducted by analyzing the nuclei width function in several directions. The classifier is based on approximation of these curves by polynomials and forming the sets corresponding to specific anomalies. The algorithm has been developed. The image base for testing the algorithm and adjustment of its parameters is currently being collected.
Pages: 34-42
References
  1. Мурашов Д.М. Метод автоматизированной сегментации изображений цитологических препаратов на основе модели активного контура // Труды МФТИ. 2009. Т. 1. № 1. С. 80-89.
  2. Юрченко В.В. Цитогенетические нарушения в эпителии человека при экспозиции генотоксикантами // Токсикологический вестник. 2005. № 6. C. 14-21.
  3. Chul Ko B., Gim J.-W., Nam J.-Y. Automatic white blood cell segmentation using stepwise merging rules and gradient vector flow snake // Micron. 2011. V. 42. P. 695-705.
  4. Canny J. A Computational approach to edge detection // IEEE Transactions on pattern analysis and machine intelligence. 1986. V. PAMI-8. № 6. P. 679-698.
  5. Chieco P., Derenzini M. The Feulgen reaction 75 years on // Histochemistry and Cell Biology. 1999. V. 111 (5). P. 345-358.
  6. Cloppet F., Boucher A. Segmentation of complex nucleus configurations in biological images // Pattern Recognition Letters. 2010. № 31. P. 755-761.
  7. Gebäck T., Koumoutsakos P. Edge detection in microscopy images using curvelets // BMC Bioinformatics. 2009. № 10. P. 75.
  8. Hoffman G. CIELab Color Space. 2009. http://issuu.com/estebanjacobo/docs/cielab_color_space
  9. Cheng J., Rajapakse J.C. Segmentation of clus-
    tered nuclei with shape markers and marking function // IEEE Transactions on biomedical engineering. 2009. V. 56. № 3. P. 741-748.
  10. Karacali B., Vamvakidou A.P., Tözeren A. Automated recognition of cell phenotypes in histology images based on membrane- and nuclei-targeting biomarkers // BMC Medical Imaging. - 2007. № 7. P. 7.
  11. Krukc M., Osowskia S., Koktyszd R. Recognition and classification of colon cells applying the ensemble of classifiers // Computers in Biology and Medicine. 2009. V. 39. P. 156-165.
  12. He L., Peng Z., Everding B., Xun Wang, Chia Y. Han, Weiss K.L., Wee W.G. A comparative study of deformable contour methods on medical image segmentation // Image and Vision Computing. 2008. V. 26. P.141-163.
  13. Guo N., Zeng L., Wu Q. A method based on multispectral imaging technique for White Blood Cell segmentation // Computers in Biology and Medicine. 2006. V. 37. P.70 - 76.
  14. Plissiti M.E., Charchanti A., Krikoni O., Fotiadis D.I. Automated segmentation of cell nuclei in PAP smear images // Proceedings of IEEE International Special Topic Conference on Information Technology in Biomedicine, Greece. 2006.
  15. Sadeghian F., Seman Z., Ramli A.R., Abdul Kahar B.H., Saripan M.I. A framework for white blood cell segmentation in microscopic blood images using digital image processing // Biological Procedures Online. 2009. V. 11(1). P.196-206.