Application of multivariate, fuzzy set and neural network analysis in quantitative cytological examinations

B. Molnár, Z. Szentirmay, Miklos Bodo, Janos Sugar, J. Fehér

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

Multivariate statistical methods have been used in several studies to increase the diagnostic reliability of TV image analyser systems. In recent years some algorithms for decision support (fuzzy logic) and for pattern recognition (neural nets), both non-linear, were developed. This paper reports on preliminary results obtained with these methods in quantitative cytology and compares them to the traditional classifiers. A total of 21 normal, 15 dysplastic and 23 malignant, gastric imprint smears were Feulgen stained and analysed on a Leitz Miamed DNA cytophotometer system. Mean DNA content, the 2c deviation index (2cDI), 5c exceeding rate (5cER), G1, S, G2 phase fraction ratios, cell nucleus area and form factor were determined. Diagnostic accuracy of the discriminant analysis was 96% for the malignant cases, 87% for dysplasias and 81% for normal cases. Cluster analysis gave no significant result. Our diagnostic system utilizing fuzzy logic has made the diagnostic borders adjustable and reliable. The back-propagation neural net correctly classifed the normal and malignant cases (100%) and all but one of the dysplasias (98%). The non-linear mathematical methods improved the reliability of the diagnostic system. These new algorithms gave results comparable to traditional classifiers. The application of these methods to clinical samples is encouraging.

Original languageEnglish
Pages (from-to)161-175
Number of pages15
JournalAnalytical Cellular Pathology
Volume5
Issue number3
Publication statusPublished - May 1993

Fingerprint

Fuzzy Logic
G2 Phase
DNA
Discriminant Analysis
Cell Nucleus
S Phase
Cluster Analysis
Cell Biology
Stomach

Keywords

  • Back propagation
  • Cluster analysis
  • Discriminant analysis
  • Fuzzy logic
  • Gastric tumours
  • Neural net
  • TV cytometry

ASJC Scopus subject areas

  • Pathology and Forensic Medicine
  • Cell Biology

Cite this

Application of multivariate, fuzzy set and neural network analysis in quantitative cytological examinations. / Molnár, B.; Szentirmay, Z.; Bodo, Miklos; Sugar, Janos; Fehér, J.

In: Analytical Cellular Pathology, Vol. 5, No. 3, 05.1993, p. 161-175.

Research output: Contribution to journalArticle

@article{7e571470c67f4e178cba826f19dd9456,
title = "Application of multivariate, fuzzy set and neural network analysis in quantitative cytological examinations",
abstract = "Multivariate statistical methods have been used in several studies to increase the diagnostic reliability of TV image analyser systems. In recent years some algorithms for decision support (fuzzy logic) and for pattern recognition (neural nets), both non-linear, were developed. This paper reports on preliminary results obtained with these methods in quantitative cytology and compares them to the traditional classifiers. A total of 21 normal, 15 dysplastic and 23 malignant, gastric imprint smears were Feulgen stained and analysed on a Leitz Miamed DNA cytophotometer system. Mean DNA content, the 2c deviation index (2cDI), 5c exceeding rate (5cER), G1, S, G2 phase fraction ratios, cell nucleus area and form factor were determined. Diagnostic accuracy of the discriminant analysis was 96{\%} for the malignant cases, 87{\%} for dysplasias and 81{\%} for normal cases. Cluster analysis gave no significant result. Our diagnostic system utilizing fuzzy logic has made the diagnostic borders adjustable and reliable. The back-propagation neural net correctly classifed the normal and malignant cases (100{\%}) and all but one of the dysplasias (98{\%}). The non-linear mathematical methods improved the reliability of the diagnostic system. These new algorithms gave results comparable to traditional classifiers. The application of these methods to clinical samples is encouraging.",
keywords = "Back propagation, Cluster analysis, Discriminant analysis, Fuzzy logic, Gastric tumours, Neural net, TV cytometry",
author = "B. Moln{\'a}r and Z. Szentirmay and Miklos Bodo and Janos Sugar and J. Feh{\'e}r",
year = "1993",
month = "5",
language = "English",
volume = "5",
pages = "161--175",
journal = "Analytical Cellular Pathology",
issn = "0921-8912",
publisher = "Elsevier",
number = "3",

}

TY - JOUR

T1 - Application of multivariate, fuzzy set and neural network analysis in quantitative cytological examinations

AU - Molnár, B.

AU - Szentirmay, Z.

AU - Bodo, Miklos

AU - Sugar, Janos

AU - Fehér, J.

PY - 1993/5

Y1 - 1993/5

N2 - Multivariate statistical methods have been used in several studies to increase the diagnostic reliability of TV image analyser systems. In recent years some algorithms for decision support (fuzzy logic) and for pattern recognition (neural nets), both non-linear, were developed. This paper reports on preliminary results obtained with these methods in quantitative cytology and compares them to the traditional classifiers. A total of 21 normal, 15 dysplastic and 23 malignant, gastric imprint smears were Feulgen stained and analysed on a Leitz Miamed DNA cytophotometer system. Mean DNA content, the 2c deviation index (2cDI), 5c exceeding rate (5cER), G1, S, G2 phase fraction ratios, cell nucleus area and form factor were determined. Diagnostic accuracy of the discriminant analysis was 96% for the malignant cases, 87% for dysplasias and 81% for normal cases. Cluster analysis gave no significant result. Our diagnostic system utilizing fuzzy logic has made the diagnostic borders adjustable and reliable. The back-propagation neural net correctly classifed the normal and malignant cases (100%) and all but one of the dysplasias (98%). The non-linear mathematical methods improved the reliability of the diagnostic system. These new algorithms gave results comparable to traditional classifiers. The application of these methods to clinical samples is encouraging.

AB - Multivariate statistical methods have been used in several studies to increase the diagnostic reliability of TV image analyser systems. In recent years some algorithms for decision support (fuzzy logic) and for pattern recognition (neural nets), both non-linear, were developed. This paper reports on preliminary results obtained with these methods in quantitative cytology and compares them to the traditional classifiers. A total of 21 normal, 15 dysplastic and 23 malignant, gastric imprint smears were Feulgen stained and analysed on a Leitz Miamed DNA cytophotometer system. Mean DNA content, the 2c deviation index (2cDI), 5c exceeding rate (5cER), G1, S, G2 phase fraction ratios, cell nucleus area and form factor were determined. Diagnostic accuracy of the discriminant analysis was 96% for the malignant cases, 87% for dysplasias and 81% for normal cases. Cluster analysis gave no significant result. Our diagnostic system utilizing fuzzy logic has made the diagnostic borders adjustable and reliable. The back-propagation neural net correctly classifed the normal and malignant cases (100%) and all but one of the dysplasias (98%). The non-linear mathematical methods improved the reliability of the diagnostic system. These new algorithms gave results comparable to traditional classifiers. The application of these methods to clinical samples is encouraging.

KW - Back propagation

KW - Cluster analysis

KW - Discriminant analysis

KW - Fuzzy logic

KW - Gastric tumours

KW - Neural net

KW - TV cytometry

UR - http://www.scopus.com/inward/record.url?scp=0027273716&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027273716&partnerID=8YFLogxK

M3 - Article

VL - 5

SP - 161

EP - 175

JO - Analytical Cellular Pathology

JF - Analytical Cellular Pathology

SN - 0921-8912

IS - 3

ER -