CLASSIFICATION OF ATYPICAL CELLS IN THE AUTOMATIC CYTOSCREENING FOR CERVICAL CANCER.

L. H. Oliver, R. S. Poulsen, Godfried Toussaint

Research output: Contribution to conferencePaper

Abstract

The recognition of pre-cancer abnormalities in Pap smear images by computer is discussed. Classification systems discussed treat these images as the source of feature vectors that are multi-modal and can be classified using the Bayes decision model with knowledge of the various subclasses that comprise the sample. A cell classification system must be capable of using information about the various subclasses of normal and abnormal cells. Two parametric decision rules are shown which are applicable to this multi-modal problem, and are suitable for the classification required for automated detection of atypical cells in a cervical smear. Test results from a series of experiments indicate that correct recognition rates of about 85% can be achieved on the atypical cells, while maintaining an error rate of about 1% on the normal cells.

Original languageEnglish (US)
Pages476-448
Number of pages29
Publication statusPublished - Jan 1 2017
EventProc IEEE Comput Soc Conf Pattern Recognition Image Process - Chicago, IL, USA
Duration: May 31 1978Jun 2 1978

Other

OtherProc IEEE Comput Soc Conf Pattern Recognition Image Process
CityChicago, IL, USA
Period5/31/786/2/78

    Fingerprint

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Oliver, L. H., Poulsen, R. S., & Toussaint, G. (2017). CLASSIFICATION OF ATYPICAL CELLS IN THE AUTOMATIC CYTOSCREENING FOR CERVICAL CANCER.. 476-448. Paper presented at Proc IEEE Comput Soc Conf Pattern Recognition Image Process, Chicago, IL, USA, .