A. Dulewicz, D. Piętka, and P. Jaszczak (Poland)
urinary bladder, carcinoma, computer image analysis.
The objective of this work is to introduce computer
based analysis of Feulgen-stained urinary bladder cell
nuclei to identify neoplastic urothelial nuclei. Nuclei
from 20 healthy people and 36 patients with urinary
bladder cancer of two grades of malignancy were
analysed. The cytological smears were obtained by
“bladder washing” technique. Image analysis was
carried out by means of digital image processing system
designed by the authors. As the first step of the
procedure, features describing nuclei were selected.
Then a multistage classifier was constructed to identify
positive and negative cases. The results of this study
yielded a 90% correct classification rate in the control
group, while an 80,6% rate was obtained among the
cancer patients. The sensitivity of the method was 91%
and the specificity was 84%.