Automatic analysis of immunocytochemically stained tissue samples
- 78 Downloads
An automatic colour image segmentation and cell counting software system has been developed for immunocytochemical analysis of stained tissue samples. The system was designed to count the total number of positive and negative cells in tissue samples treated with cytokine DNA probes from pigs naturally parasitised with Taenia solium metacestodes, using in situ hybridisation. A reaction index was calculated as the ratio of the number of cells with a positive reaction to the total number of cells (positives plus negatives) for each of five different probes. The objectives of automatic counting were to improve the reproducibility of the analysis and reduce the processing time of large image batches. A fast KNN classifier was used for colour segmentation. Watershed segmentation combined with edge detection was used to isolate individual cells that were then automatically labelled, using the results of the corresponding colour segmented image. Validation was performed on 122 non-training digital images with a total of 1069 positive cells and 1459 negative cells, with the following results: a mean true positive rate of 90.2% for positive cells and a mean true positive rate of 85.4% for negative cells. The corresponding mean false positive rates were 9.6% and 6.6%. The mean reaction index error of the automatic analysis was 5.35%. The processing of each digital image took 10 s on a Pentium IV PC.
KeywordsAutomatic immunocytochemical analysis Automatic cell counting Colour classification Watershed segmentation
Unable to display preview. Download preview PDF.
- Baumgart, E., Schad, A., Vôlkl, A., andDariush Fahimi, H. (1997): ‘Detection of mRNAs encoding peroxisomal proteins by non-radiactive in situ hybridisation with digoxigenin-labelled cRNAs’,Histochem. Cell Biol.,108, pp. 371–379Google Scholar
- Bishop, C. M. (1997): ‘Neural networks for pattern recognition’ (Oxford University Press, 1997)Google Scholar
- Castleman, K. R., Riopka, T. P., andQuiang, W. (1996): ‘FISH Image analysis’IEEE Eng. Med. Biol., pp. 67–75Google Scholar
- Duda, R., andHart, P. (1973): ‘Pattern classification and scene analysis’, (Wiley, 1973)Google Scholar
- Marr, D. (1982).Vision (Freeman, San Francisco, 1982)Google Scholar
- Ranefall, P., Egevad, L., Nordin, B., andBengtsson, E. (1997): ‘A new method for segmentation of colour images applied to immunohistochemically stained cell nuclei’.Anal. Cell. Pathol. 15, pp. 145–156Google Scholar
- Ranefall, P., Wester, K., Andersson, A. C., Busch, C., andBengtsson, E. (1998): ‘Automatic quantification of immunohistochemically stained cell nuclei based on standard reference cells’,Anal. Cell. Pathol.,17, pp. 111–123.Google Scholar
- Russ, J. C. andRuss, J. C. (1988): ‘Improved implementation of a convex segmentation algorithm’,Acta Stereologica,7, pp. 33–40Google Scholar
- Russ, J. C. (2002): ‘The image processing handbook’. Fourth edn (CRC Press, 2002), pp. 425–434Google Scholar
- Willemse, F., Nap, M., Henzen-Logmans, S. C., andEggink, H. F. (1994): ‘Quantification of area percentage of immunohistochemical staining by true color image analysis with application of fixed thresholds’,Anal. Quant. Cytol. Histol.,16, pp. 357–364Google Scholar