Integrated decision support system/image archive for histological typing of breast cancer using a relation oriented inference system

P J Van Diest, J A Beliën, P E Zanstra, W W Wilhelm, J P Baak

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Histological typing of invasive breast cancer according to the World Health Organisation criteria is prognostically relevant, because some histological subtypes have a markedly better prognosis. However, reproducibility of histological typing is not high because of the absence of strict typing criteria, variations in the application of the typing criteria and the usually limited illustration of the relevant criteria. The aim of this study was to develop an expert system based on highly structured histological typing criteria, integrated with high-quality microscope images to illustrate the typing criteria. This system should be useful as a decision support system in the diagnosis of breast cancers and should increase the reproducibility of histological typing. Criteria for typing were extracted from textbooks and, based on experience, these criteria were structured and implemented in the Relation Oriented Inference System (ROIS), in which information can be structured by defining relations. Illustrative black and white images were digitized and integrated into the shell. The performance of the resulting decision support system was evaluated by a group of six pathologists using a set of slides covering the spectrum of the most frequently occurring histological types of invasive breast cancer. The pathologists first assessed histological type according to standard morphological procedures. The cases were then reassessed with the decision support system available for consultation. The use of the decision support system appeared to influence the previously assessed histological type in about half of the cases. Using the decision support system, histological typing was more uniform and more in accord with a 'gold standard' set by two experts.(ABSTRACT TRUNCATED AT 250 WORDS)

Original languageEnglish
Pages (from-to)253-9
Number of pages7
JournalHistopathology
Volume25
Issue number3
Publication statusPublished - Sep 1994

Cite this

@article{5e049fda27f24c56979222e3f2fe0aa1,
title = "Integrated decision support system/image archive for histological typing of breast cancer using a relation oriented inference system",
abstract = "Histological typing of invasive breast cancer according to the World Health Organisation criteria is prognostically relevant, because some histological subtypes have a markedly better prognosis. However, reproducibility of histological typing is not high because of the absence of strict typing criteria, variations in the application of the typing criteria and the usually limited illustration of the relevant criteria. The aim of this study was to develop an expert system based on highly structured histological typing criteria, integrated with high-quality microscope images to illustrate the typing criteria. This system should be useful as a decision support system in the diagnosis of breast cancers and should increase the reproducibility of histological typing. Criteria for typing were extracted from textbooks and, based on experience, these criteria were structured and implemented in the Relation Oriented Inference System (ROIS), in which information can be structured by defining relations. Illustrative black and white images were digitized and integrated into the shell. The performance of the resulting decision support system was evaluated by a group of six pathologists using a set of slides covering the spectrum of the most frequently occurring histological types of invasive breast cancer. The pathologists first assessed histological type according to standard morphological procedures. The cases were then reassessed with the decision support system available for consultation. The use of the decision support system appeared to influence the previously assessed histological type in about half of the cases. Using the decision support system, histological typing was more uniform and more in accord with a 'gold standard' set by two experts.(ABSTRACT TRUNCATED AT 250 WORDS)",
keywords = "Artificial Intelligence, Breast Neoplasms, Decision Support Techniques, Diagnosis, Computer-Assisted, Humans, Management Information Systems, Journal Article, Research Support, Non-U.S. Gov't",
author = "{Van Diest}, {P J} and Beli{\"e}n, {J A} and Zanstra, {P E} and Wilhelm, {W W} and Baak, {J P}",
year = "1994",
month = "9",
language = "English",
volume = "25",
pages = "253--9",
journal = "Histopathology",
issn = "0309-0167",
publisher = "Wiley-Blackwell",
number = "3",

}

Integrated decision support system/image archive for histological typing of breast cancer using a relation oriented inference system. / Van Diest, P J; Beliën, J A; Zanstra, P E; Wilhelm, W W; Baak, J P.

In: Histopathology, Vol. 25, No. 3, 09.1994, p. 253-9.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Integrated decision support system/image archive for histological typing of breast cancer using a relation oriented inference system

AU - Van Diest, P J

AU - Beliën, J A

AU - Zanstra, P E

AU - Wilhelm, W W

AU - Baak, J P

PY - 1994/9

Y1 - 1994/9

N2 - Histological typing of invasive breast cancer according to the World Health Organisation criteria is prognostically relevant, because some histological subtypes have a markedly better prognosis. However, reproducibility of histological typing is not high because of the absence of strict typing criteria, variations in the application of the typing criteria and the usually limited illustration of the relevant criteria. The aim of this study was to develop an expert system based on highly structured histological typing criteria, integrated with high-quality microscope images to illustrate the typing criteria. This system should be useful as a decision support system in the diagnosis of breast cancers and should increase the reproducibility of histological typing. Criteria for typing were extracted from textbooks and, based on experience, these criteria were structured and implemented in the Relation Oriented Inference System (ROIS), in which information can be structured by defining relations. Illustrative black and white images were digitized and integrated into the shell. The performance of the resulting decision support system was evaluated by a group of six pathologists using a set of slides covering the spectrum of the most frequently occurring histological types of invasive breast cancer. The pathologists first assessed histological type according to standard morphological procedures. The cases were then reassessed with the decision support system available for consultation. The use of the decision support system appeared to influence the previously assessed histological type in about half of the cases. Using the decision support system, histological typing was more uniform and more in accord with a 'gold standard' set by two experts.(ABSTRACT TRUNCATED AT 250 WORDS)

AB - Histological typing of invasive breast cancer according to the World Health Organisation criteria is prognostically relevant, because some histological subtypes have a markedly better prognosis. However, reproducibility of histological typing is not high because of the absence of strict typing criteria, variations in the application of the typing criteria and the usually limited illustration of the relevant criteria. The aim of this study was to develop an expert system based on highly structured histological typing criteria, integrated with high-quality microscope images to illustrate the typing criteria. This system should be useful as a decision support system in the diagnosis of breast cancers and should increase the reproducibility of histological typing. Criteria for typing were extracted from textbooks and, based on experience, these criteria were structured and implemented in the Relation Oriented Inference System (ROIS), in which information can be structured by defining relations. Illustrative black and white images were digitized and integrated into the shell. The performance of the resulting decision support system was evaluated by a group of six pathologists using a set of slides covering the spectrum of the most frequently occurring histological types of invasive breast cancer. The pathologists first assessed histological type according to standard morphological procedures. The cases were then reassessed with the decision support system available for consultation. The use of the decision support system appeared to influence the previously assessed histological type in about half of the cases. Using the decision support system, histological typing was more uniform and more in accord with a 'gold standard' set by two experts.(ABSTRACT TRUNCATED AT 250 WORDS)

KW - Artificial Intelligence

KW - Breast Neoplasms

KW - Decision Support Techniques

KW - Diagnosis, Computer-Assisted

KW - Humans

KW - Management Information Systems

KW - Journal Article

KW - Research Support, Non-U.S. Gov't

M3 - Article

VL - 25

SP - 253

EP - 259

JO - Histopathology

JF - Histopathology

SN - 0309-0167

IS - 3

ER -