High resolution analysis of cervical cells: a progress report

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

Research output: Contribution to journalArticle

Abstract

This paper presents preliminary results of research toward the development of a high resolution analysis stage for a dual resolution image processing based prescreening device for cervical cytology. Experiments using both manual and automatic methods for cell segmentation are described. In both cases, 1500 cervical cells were analyzed and classified as normal or abnormal (dysplastic or malignant) using a minimum Mahalanobis distance classifier with 8 subclasses of normal cells, and 5 subclasses of abnormal cells. With manual segmentation, false positive and false negative error rates of 2.98 and 7.73% were obtained. Similar experiments using automatic cell segmentation methods yielded false positive and false negative error rates of 3.90 and 11.56%, respectively. In both cases, independant training and testing data were used.

Original languageEnglish (US)
Pages (from-to)689-695
Number of pages7
JournalUnknown Journal
Volume25
Issue number7
DOIs
StatePublished - Jan 1 1977

Fingerprint

High Resolution
Cytology
Cell
Segmentation
Image processing
Classifiers
False Positive
Experiments
Error Rate
Testing
Mahalanobis Distance
Minimum Distance
Experiment
Cell Biology
Image Processing
Classifier
Equipment and Supplies
Research
False

ASJC Scopus subject areas

  • Anatomy
  • Histology

Cite this

High resolution analysis of cervical cells : a progress report. / Poulsen, R. S.; Oliver, L. H.; Cahn, R. L.; Louis, C.; Toussaint, Godfried.

In: Unknown Journal, Vol. 25, No. 7, 01.01.1977, p. 689-695.

Research output: Contribution to journalArticle

Poulsen, RS, Oliver, LH, Cahn, RL, Louis, C & Toussaint, G 1977, 'High resolution analysis of cervical cells: a progress report', Unknown Journal, vol. 25, no. 7, pp. 689-695. https://doi.org/10.1177/25.7.330722
Poulsen, R. S. ; Oliver, L. H. ; Cahn, R. L. ; Louis, C. ; Toussaint, Godfried. / High resolution analysis of cervical cells : a progress report. In: Unknown Journal. 1977 ; Vol. 25, No. 7. pp. 689-695.
@article{4430ca8e580f452784893808b8025831,
title = "High resolution analysis of cervical cells: a progress report",
abstract = "This paper presents preliminary results of research toward the development of a high resolution analysis stage for a dual resolution image processing based prescreening device for cervical cytology. Experiments using both manual and automatic methods for cell segmentation are described. In both cases, 1500 cervical cells were analyzed and classified as normal or abnormal (dysplastic or malignant) using a minimum Mahalanobis distance classifier with 8 subclasses of normal cells, and 5 subclasses of abnormal cells. With manual segmentation, false positive and false negative error rates of 2.98 and 7.73{\%} were obtained. Similar experiments using automatic cell segmentation methods yielded false positive and false negative error rates of 3.90 and 11.56{\%}, respectively. In both cases, independant training and testing data were used.",
author = "Poulsen, {R. S.} and Oliver, {L. H.} and Cahn, {R. L.} and C. Louis and Godfried Toussaint",
year = "1977",
month = "1",
day = "1",
doi = "10.1177/25.7.330722",
language = "English (US)",
volume = "25",
pages = "689--695",
journal = "Theoretical Computer Science",
issn = "0304-3975",
publisher = "Elsevier",
number = "7",

}

TY - JOUR

T1 - High resolution analysis of cervical cells

T2 - a progress report

AU - Poulsen, R. S.

AU - Oliver, L. H.

AU - Cahn, R. L.

AU - Louis, C.

AU - Toussaint, Godfried

PY - 1977/1/1

Y1 - 1977/1/1

N2 - This paper presents preliminary results of research toward the development of a high resolution analysis stage for a dual resolution image processing based prescreening device for cervical cytology. Experiments using both manual and automatic methods for cell segmentation are described. In both cases, 1500 cervical cells were analyzed and classified as normal or abnormal (dysplastic or malignant) using a minimum Mahalanobis distance classifier with 8 subclasses of normal cells, and 5 subclasses of abnormal cells. With manual segmentation, false positive and false negative error rates of 2.98 and 7.73% were obtained. Similar experiments using automatic cell segmentation methods yielded false positive and false negative error rates of 3.90 and 11.56%, respectively. In both cases, independant training and testing data were used.

AB - This paper presents preliminary results of research toward the development of a high resolution analysis stage for a dual resolution image processing based prescreening device for cervical cytology. Experiments using both manual and automatic methods for cell segmentation are described. In both cases, 1500 cervical cells were analyzed and classified as normal or abnormal (dysplastic or malignant) using a minimum Mahalanobis distance classifier with 8 subclasses of normal cells, and 5 subclasses of abnormal cells. With manual segmentation, false positive and false negative error rates of 2.98 and 7.73% were obtained. Similar experiments using automatic cell segmentation methods yielded false positive and false negative error rates of 3.90 and 11.56%, respectively. In both cases, independant training and testing data were used.

UR - http://www.scopus.com/inward/record.url?scp=0017662063&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0017662063&partnerID=8YFLogxK

U2 - 10.1177/25.7.330722

DO - 10.1177/25.7.330722

M3 - Article

VL - 25

SP - 689

EP - 695

JO - Theoretical Computer Science

JF - Theoretical Computer Science

SN - 0304-3975

IS - 7

ER -