skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Analysis and minimization of overtraining effect in rule-based classifiers for computer-aided diagnosis

Abstract

Computer-aided diagnostic (CAD) schemes have been developed to assist radiologists detect various lesions in medical images. In CAD schemes, classifiers play a key role in achieving a high lesion detection rate and a low false-positive rate. Although many popular classifiers such as linear discriminant analysis and artificial neural networks have been employed in CAD schemes for reduction of false positives, a rule-based classifier has probably been the simplest and most frequently used one since the early days of development of various CAD schemes. However, with existing rule-based classifiers, there are major disadvantages that significantly reduce their practicality and credibility. The disadvantages include manual design, poor reproducibility, poor evaluation methods such as resubstitution, and a large overtraining effect. An automated rule-based classifier with a minimized overtraining effect can overcome or significantly reduce the extent of the above-mentioned disadvantages. In this study, we developed an 'optimal' method for the selection of cutoff thresholds and a fully automated rule-based classifier. Experimental results performed with Monte Carlo simulation and a real lung nodule CT data set demonstrated that the automated threshold selection method can completely eliminate overtraining effect in the procedure of cutoff threshold selection, and thus can minimize overall overtraining effect in themore » constructed rule-based classifier. We believe that this threshold selection method is very useful in the construction of automated rule-based classifiers with minimized overtraining effect.« less

Authors:
;  [1]
  1. Department of Radiology, University of Chicago, 5841 S. Maryland Avenue, Chicago, Illinois 60637 (United States)
Publication Date:
OSTI Identifier:
20775055
Resource Type:
Journal Article
Resource Relation:
Journal Name: Medical Physics; Journal Volume: 33; Journal Issue: 2; Other Information: DOI: 10.1118/1.1999126; (c) 2006 American Association of Physicists in Medicine; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States
Language:
English
Subject:
62 RADIOLOGY AND NUCLEAR MEDICINE; COMPUTERIZED SIMULATION; COMPUTERIZED TOMOGRAPHY; DIAGNOSIS; IMAGE PROCESSING; IMAGES; LUNGS; MONTE CARLO METHOD; NEOPLASMS; NEURAL NETWORKS

Citation Formats

Li Qiang, and Doi Kunio. Analysis and minimization of overtraining effect in rule-based classifiers for computer-aided diagnosis. United States: N. p., 2006. Web. doi:10.1118/1.1999126.
Li Qiang, & Doi Kunio. Analysis and minimization of overtraining effect in rule-based classifiers for computer-aided diagnosis. United States. doi:10.1118/1.1999126.
Li Qiang, and Doi Kunio. Wed . "Analysis and minimization of overtraining effect in rule-based classifiers for computer-aided diagnosis". United States. doi:10.1118/1.1999126.
@article{osti_20775055,
title = {Analysis and minimization of overtraining effect in rule-based classifiers for computer-aided diagnosis},
author = {Li Qiang and Doi Kunio},
abstractNote = {Computer-aided diagnostic (CAD) schemes have been developed to assist radiologists detect various lesions in medical images. In CAD schemes, classifiers play a key role in achieving a high lesion detection rate and a low false-positive rate. Although many popular classifiers such as linear discriminant analysis and artificial neural networks have been employed in CAD schemes for reduction of false positives, a rule-based classifier has probably been the simplest and most frequently used one since the early days of development of various CAD schemes. However, with existing rule-based classifiers, there are major disadvantages that significantly reduce their practicality and credibility. The disadvantages include manual design, poor reproducibility, poor evaluation methods such as resubstitution, and a large overtraining effect. An automated rule-based classifier with a minimized overtraining effect can overcome or significantly reduce the extent of the above-mentioned disadvantages. In this study, we developed an 'optimal' method for the selection of cutoff thresholds and a fully automated rule-based classifier. Experimental results performed with Monte Carlo simulation and a real lung nodule CT data set demonstrated that the automated threshold selection method can completely eliminate overtraining effect in the procedure of cutoff threshold selection, and thus can minimize overall overtraining effect in the constructed rule-based classifier. We believe that this threshold selection method is very useful in the construction of automated rule-based classifiers with minimized overtraining effect.},
doi = {10.1118/1.1999126},
journal = {Medical Physics},
number = 2,
volume = 33,
place = {United States},
year = {Wed Feb 15 00:00:00 EST 2006},
month = {Wed Feb 15 00:00:00 EST 2006}
}