Többváltozós matematikai eljárások alkalmazása az orvosdiagnosztikai rendszerekben--egy modell a citológiai kenetek kiértékelésére.

Translated title of the contribution: The use of multivariate mathematical methods in medical diagnostic systems--a model for the evaluation of cytological smears

B. Molnár, Z. Szentirmay, M. Bodó, J. Sugár, J. Fehér

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The methods of the multivariate mathematics have been applied in several studies to increase the diagnostic reliability of medical decision support system. In the recent years some new algorithms for decision support (fuzzy logic) and for pattern recognition (neural nets), both specified by nonlinearity, were developed. This paper provides results for the application of this methods in the area of quantitative cytology and the comparison with the traditional classifiers. 21 normal, 15 dysplastic, 23 malignant, Feulgen stained gastric imprint smears were analysed on a Leitz Miamed DNA equipment. The determination of mean DNA content, the 2c deviation index (2cDI), 5c Exceeding rate (RcER), G1,S,G2 phase fraction ratios, cell nucleus area, form factor was performed. The discriminant analysis classified correctly the 95.6% of malignant cases, 86.7% of dysplasias, and 80.7% normal cases. Our diagnostic system using fuzzy logic made the diagnostic borders fine tuneable, and reliable. The back propagation neural net could classify all three diagnostic groups above 95% correctly. The application of nonlinear computational methods made the diagnostic system more reliable. The application of these algorithms are encouraged.

Original languageHungarian
Pages (from-to)2697-2701
Number of pages5
JournalOrvosi Hetilap
Volume133
Issue number42
Publication statusPublished - Oct 18 1992

Fingerprint

Fuzzy Logic
Mathematics
G2 Phase
DNA
Discriminant Analysis
Cell Nucleus
S Phase
Cell Biology
Stomach
Equipment and Supplies

ASJC Scopus subject areas

  • Medicine(all)

Cite this

@article{0fc1bbf43cd84258a090b34595959e50,
title = "T{\"o}bbv{\'a}ltoz{\'o}s matematikai elj{\'a}r{\'a}sok alkalmaz{\'a}sa az orvosdiagnosztikai rendszerekben--egy modell a citol{\'o}giai kenetek ki{\'e}rt{\'e}kel{\'e}s{\'e}re.",
abstract = "The methods of the multivariate mathematics have been applied in several studies to increase the diagnostic reliability of medical decision support system. In the recent years some new algorithms for decision support (fuzzy logic) and for pattern recognition (neural nets), both specified by nonlinearity, were developed. This paper provides results for the application of this methods in the area of quantitative cytology and the comparison with the traditional classifiers. 21 normal, 15 dysplastic, 23 malignant, Feulgen stained gastric imprint smears were analysed on a Leitz Miamed DNA equipment. The determination of mean DNA content, the 2c deviation index (2cDI), 5c Exceeding rate (RcER), G1,S,G2 phase fraction ratios, cell nucleus area, form factor was performed. The discriminant analysis classified correctly the 95.6{\%} of malignant cases, 86.7{\%} of dysplasias, and 80.7{\%} normal cases. Our diagnostic system using fuzzy logic made the diagnostic borders fine tuneable, and reliable. The back propagation neural net could classify all three diagnostic groups above 95{\%} correctly. The application of nonlinear computational methods made the diagnostic system more reliable. The application of these algorithms are encouraged.",
author = "B. Moln{\'a}r and Z. Szentirmay and M. Bod{\'o} and J. Sug{\'a}r and J. Feh{\'e}r",
year = "1992",
month = "10",
day = "18",
language = "Hungarian",
volume = "133",
pages = "2697--2701",
journal = "Orvosi Hetilap",
issn = "0030-6002",
publisher = "Akademiai Kiado",
number = "42",

}

TY - JOUR

T1 - Többváltozós matematikai eljárások alkalmazása az orvosdiagnosztikai rendszerekben--egy modell a citológiai kenetek kiértékelésére.

AU - Molnár, B.

AU - Szentirmay, Z.

AU - Bodó, M.

AU - Sugár, J.

AU - Fehér, J.

PY - 1992/10/18

Y1 - 1992/10/18

N2 - The methods of the multivariate mathematics have been applied in several studies to increase the diagnostic reliability of medical decision support system. In the recent years some new algorithms for decision support (fuzzy logic) and for pattern recognition (neural nets), both specified by nonlinearity, were developed. This paper provides results for the application of this methods in the area of quantitative cytology and the comparison with the traditional classifiers. 21 normal, 15 dysplastic, 23 malignant, Feulgen stained gastric imprint smears were analysed on a Leitz Miamed DNA equipment. The determination of mean DNA content, the 2c deviation index (2cDI), 5c Exceeding rate (RcER), G1,S,G2 phase fraction ratios, cell nucleus area, form factor was performed. The discriminant analysis classified correctly the 95.6% of malignant cases, 86.7% of dysplasias, and 80.7% normal cases. Our diagnostic system using fuzzy logic made the diagnostic borders fine tuneable, and reliable. The back propagation neural net could classify all three diagnostic groups above 95% correctly. The application of nonlinear computational methods made the diagnostic system more reliable. The application of these algorithms are encouraged.

AB - The methods of the multivariate mathematics have been applied in several studies to increase the diagnostic reliability of medical decision support system. In the recent years some new algorithms for decision support (fuzzy logic) and for pattern recognition (neural nets), both specified by nonlinearity, were developed. This paper provides results for the application of this methods in the area of quantitative cytology and the comparison with the traditional classifiers. 21 normal, 15 dysplastic, 23 malignant, Feulgen stained gastric imprint smears were analysed on a Leitz Miamed DNA equipment. The determination of mean DNA content, the 2c deviation index (2cDI), 5c Exceeding rate (RcER), G1,S,G2 phase fraction ratios, cell nucleus area, form factor was performed. The discriminant analysis classified correctly the 95.6% of malignant cases, 86.7% of dysplasias, and 80.7% normal cases. Our diagnostic system using fuzzy logic made the diagnostic borders fine tuneable, and reliable. The back propagation neural net could classify all three diagnostic groups above 95% correctly. The application of nonlinear computational methods made the diagnostic system more reliable. The application of these algorithms are encouraged.

UR - http://www.scopus.com/inward/record.url?scp=17944393495&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17944393495&partnerID=8YFLogxK

M3 - Article

C2 - 1437099

AN - SCOPUS:17944393495

VL - 133

SP - 2697

EP - 2701

JO - Orvosi Hetilap

JF - Orvosi Hetilap

SN - 0030-6002

IS - 42

ER -