Classification of Cells in Cervical Smears

  • Mathilde E. Boon
  • L. P. Kok


Presently, an increased effort to realize computer-assisted screening is generated in response to the American shortage of cytotechnologists after the Wall Street Journal in 1987 carried a major article questioning the accuracy of cervical screening in the USA (Bogdanich, 1987). Federal legislation was implemented limiting the number of smears screened (this number could formerly be as high as 300 per day for one cytotechnologist) and doubling in some states the salaries in six months.


Abnormal Cell Video Screen Invasive Squamous Cell Carcinoma Cervical Smear Conventional Screening 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Anderson TL, Nelson AC (1992) Automatic screening of conventional Papanicolaou smears. The AutoPap 300. Analyt Quant Cytol Histol 14:246–247.Google Scholar
  2. Bartoo GT (1992) Automated prescreening of conventionally prepared cervical smears. A feasibility study. Lab Invest 66; 116.Google Scholar
  3. Bogdanich W (1987) The Pap test misses much cervical cancer through lab’s errors. Wall Street Journal.Google Scholar
  4. Boon ME, Kok LP (1993) Neural network processing can provide means to catch errors that slip through human screening of Pap smears. Diagn Cytopath 9:416–416.CrossRefGoogle Scholar
  5. Boon ME, Suurmeijer (1992) The Pap Smear. Coulomb Press Leyden, Leiden.Google Scholar
  6. Bosch MMC, Rietveld-Scheffers PEM, Boon ME (1992) Characteristics of false-negative smears tested in the normal screening situation. Acta Cytol 36:711–716.Google Scholar
  7. Brindza LJ (1991) FDA regulation of computerized cytology devices. Anal Quant Cytol Histol 13:3–6.Google Scholar
  8. Elgert P, Re E, Schreiber K, Koss LG (1992) Rate of false-negative cervical smears in a laboratory with extensive Quality control. Analyt Quant Cytol Histol 14:256–257.Google Scholar
  9. IAC Committee on Quantitative Morphology (1991) Data on automated cytology systems as submitted by their developers. Analyt Quant Cytol Histol 13:300–306.Google Scholar
  10. Ishizuka Y, Mango LJ (1992) Evaluation of the PAPNET automated cytology screening system utilizing routine, conventionally prepared cervical Papanicolaou smears at the Japan Cytology and Pathology Laboratory. Analyt Quant Cytol Histol 14:264–265.Google Scholar
  11. Koss LG, Lin E, Schreiber K, Mango L, Elgert P (1992) Evaluation of cervical smears by the PAPNET apparatus. Analyt Quant Cytol Histol 14:269.Google Scholar
  12. Linder J (1992) Automation in Cytopathology. Am J Clin Pathol 98:S47–S51.Google Scholar
  13. Malberger E (1992) Determination of the suitability of the PAPNET automated cytology screening system to rapidly implement widescale screening for cervical cancer in a population that is currently largely unscreened. Analyt Quant Cytol Histol 14:272.Google Scholar
  14. Müller B, Reinhardt J (1990) Neural Networks. An Introduction. Springer, Berlin.zbMATHGoogle Scholar
  15. O’Leary TJ, Mikel UV, Becker RL (1992) Computer-assisted image interpretation. Use of a neural network to differentiate tubular carcinoma from sclerosing adenosis. Mod Pathol 5;402.Google Scholar
  16. Rosenthal DL (1992) Evaluation of PAPNET automated cytology screening system. Sensitivity and its relationship to the level of video training and experience of the reviewing cytologist. Anal Quant Cytol Histol 14:280.Google Scholar

Copyright information

© Springer Science+Business Media New York 1995

Authors and Affiliations

  • Mathilde E. Boon
    • 1
    • 2
  • L. P. Kok
    • 1
    • 2
  1. 1.Leiden Cytology and Pathology LaboratoryLeidenThe Netherlands
  2. 2.Institute for Theoretical PhysicsUniversity of GroningenGroningenThe Netherlands

Personalised recommendations