Classification of atypical cells in the automatic cytoscreening for cervical cancer

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

Research output: Contribution to journalArticle

Abstract

One of the pattern recognition problems that is of importance in automated cytology is the detection of abnormal cells that may be present in a sample taken from a person. This work describes the problem and some possible solutions within the context of the detection of pre-cancer abnormalities in samples that have been prepared as Pap smears for observation under light microscopy. A cell classification system must be capable of using information concerning the existence of various subclasses of normal and abnormal cells. The classification of multi-modal data can be modeled using the Bayesian decision model with knowledge of the various subclasses composing each of the classes being decided. Two decision rules are shown which are applicable to this problem, and are suitable for the classification required for automated detection of atypical cells in a cervical smear. Test results from a series of holdout experiments indicate that average 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)
Pages (from-to)205-212
Number of pages8
JournalPattern Recognition
Volume11
Issue number3
DOIs
StatePublished - Jan 1 1979

Fingerprint

Cytology
Pattern recognition
Optical microscopy
Experiments

Keywords

  • Automated cytology
  • Biomedical images
  • Multivariate density functions
  • Pattern recognition

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Classification of atypical cells in the automatic cytoscreening for cervical cancer. / Oliver, L. H.; Poulsen, R. S.; Toussaint, Godfried; Louis, C.

In: Pattern Recognition, Vol. 11, No. 3, 01.01.1979, p. 205-212.

Research output: Contribution to journalArticle

Oliver, L. H. ; Poulsen, R. S. ; Toussaint, Godfried ; Louis, C. / Classification of atypical cells in the automatic cytoscreening for cervical cancer. In: Pattern Recognition. 1979 ; Vol. 11, No. 3. pp. 205-212.
@article{9f597bd48a89477180e3007505142111,
title = "Classification of atypical cells in the automatic cytoscreening for cervical cancer",
abstract = "One of the pattern recognition problems that is of importance in automated cytology is the detection of abnormal cells that may be present in a sample taken from a person. This work describes the problem and some possible solutions within the context of the detection of pre-cancer abnormalities in samples that have been prepared as Pap smears for observation under light microscopy. A cell classification system must be capable of using information concerning the existence of various subclasses of normal and abnormal cells. The classification of multi-modal data can be modeled using the Bayesian decision model with knowledge of the various subclasses composing each of the classes being decided. Two decision rules are shown which are applicable to this problem, and are suitable for the classification required for automated detection of atypical cells in a cervical smear. Test results from a series of holdout experiments indicate that average 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.",
keywords = "Automated cytology, Biomedical images, Multivariate density functions, Pattern recognition",
author = "Oliver, {L. H.} and Poulsen, {R. S.} and Godfried Toussaint and C. Louis",
year = "1979",
month = "1",
day = "1",
doi = "10.1016/0031-3203(79)90007-4",
language = "English (US)",
volume = "11",
pages = "205--212",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "3",

}

TY - JOUR

T1 - Classification of atypical cells in the automatic cytoscreening for cervical cancer

AU - Oliver, L. H.

AU - Poulsen, R. S.

AU - Toussaint, Godfried

AU - Louis, C.

PY - 1979/1/1

Y1 - 1979/1/1

N2 - One of the pattern recognition problems that is of importance in automated cytology is the detection of abnormal cells that may be present in a sample taken from a person. This work describes the problem and some possible solutions within the context of the detection of pre-cancer abnormalities in samples that have been prepared as Pap smears for observation under light microscopy. A cell classification system must be capable of using information concerning the existence of various subclasses of normal and abnormal cells. The classification of multi-modal data can be modeled using the Bayesian decision model with knowledge of the various subclasses composing each of the classes being decided. Two decision rules are shown which are applicable to this problem, and are suitable for the classification required for automated detection of atypical cells in a cervical smear. Test results from a series of holdout experiments indicate that average 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.

AB - One of the pattern recognition problems that is of importance in automated cytology is the detection of abnormal cells that may be present in a sample taken from a person. This work describes the problem and some possible solutions within the context of the detection of pre-cancer abnormalities in samples that have been prepared as Pap smears for observation under light microscopy. A cell classification system must be capable of using information concerning the existence of various subclasses of normal and abnormal cells. The classification of multi-modal data can be modeled using the Bayesian decision model with knowledge of the various subclasses composing each of the classes being decided. Two decision rules are shown which are applicable to this problem, and are suitable for the classification required for automated detection of atypical cells in a cervical smear. Test results from a series of holdout experiments indicate that average 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.

KW - Automated cytology

KW - Biomedical images

KW - Multivariate density functions

KW - Pattern recognition

UR - http://www.scopus.com/inward/record.url?scp=0018653928&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0018653928&partnerID=8YFLogxK

U2 - 10.1016/0031-3203(79)90007-4

DO - 10.1016/0031-3203(79)90007-4

M3 - Article

AN - SCOPUS:0018653928

VL - 11

SP - 205

EP - 212

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 3

ER -