Two methods for analyzing pleural smears for the presence of abnormalities

@article{Pahlplatz1986TwoMF,
  title={Two methods for analyzing pleural smears for the presence of abnormalities},
  author={M. M. M. Pahlplatz and M. W. Katzko and G. H. F. M. Hesselmans and P. S. Oud and G. P. Vooys},
  journal={Pattern Recognition Letters},
  year={1986},
  volume={4},
  pages={405-411}
}
Two methods of designing a cell classifier as a first stage in a pleural sample classification procedure, where reliable a priori cell class labeling is not available, are presented. Cluster analysis is shown to be capable of taking into account structural information at the cell level, which may be lost in other methods.