Back to search

University of British Columbia

Development, implementation and evaluation of segmentation algorithms for the automatic classification of cervical cells

Abstract

dc:description

Cancer of the uterine cervix is one of the most common cancers in women. An effective screening program for pre-cancerous and cancerous lesions can dramatically reduce the mortality rate for this disease. In British Columbia where such a screening program has been in place for some time, 2500 to 3000 slides of cervical smears need to be examined daily. More than 35 years ago, it was recognized that an automated pre-screening system could greatly assist people in this task. Such a system would need to find and recognize stained cells, segment the images of these cells into nucleus and cytoplasm, numerically describe the characteristics of the cells, and use these features to discriminate between normal and abnormal cells. The thrust of this work was 1) to research and develop new segmentation methods and compare their performance to those in the literature, 2) to determine dependence of the numerical cell descriptors on the segmentation method used, 3) to determine the dependence of cell classification accuracy on the segmentation used, and 4) to test the hypothesis that using numerical cell descriptors one can correctly classify the cells. The segmentation accuracies of 32 different segmentation procedures were examined. It was found that the best nuclear segmentation procedure was able to correctly segment 98% of the nuclei of a 1000 and a 3680 image database. Similarly the best cytoplasmic segmentation procedure was found to correctly segment 98.5% of the cytoplasm of the same 1000 image database. Sixty-seven different numerical cell descriptors (features) were calculated for every segmented cell. On a database of 800 classified cervical cells these features when used in a linear discriminant function analysis could correctly classify 98.7% of the normal cells and 97.0% of the abnormal cells. While some features were found to vary a great deal between segmentation procedures, the classification accuracy of groups of features was found to be independent of the segmentation procedure used. The cellular classification accuracy was found to be very dependent on the number and types of features used to form the discriminant functions. The thesis that a computerized system can classify cervical cells at least as well as an experienced cytologist has been demonstrated. This result requires that the system can segment cervical cells and reliably recognize incorrectly segmented cells.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy - PhD
Level thesis:degree_level
doctoral
Discipline thesis:degree_discipline
Physics
Grantor dc:publisher
University of British Columbia
Year dc:date
1989

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • MacAulay, Calum Eric

Rights

dc:rights
Statement dc:rights
  • For non-commercial purposes only, such as research, private study and education. Additional conditions apply, see Terms of Use https://open.library.ubc.ca/terms_of_use.
Language dc:language
eng

Identifiers

dc:identifier.*
Handle dc:identifier
http://hdl.handle.net/2429/29184

Chain of custody

source
Harvested from
University of British Columbia
Base URL
circle.library.ubc.ca/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

MacAulay, Calum Eric. Development, implementation and evaluation of segmentation algorithms for the automatic classification of cervical cells. doctoral thesis, University of British Columbia, 1989. http://hdl.handle.net/2429/29184