Literature DB >> 23747155

Validation of Monte Carlo estimates of three-class ideal observer operating points for normal data.

Darrin C Edwards1.   

Abstract

RATIONALE AND
OBJECTIVES: Traditional two-class receiver operating characteristic (ROC) analysis is inadequate for the complete evaluation of observer performance in tasks with more than two classes.
MATERIALS AND METHODS: Here, a Monte Carlo estimation method for operating point coordinates on a three-class ROC surface is developed and compared with analytically calculated coordinates in two special cases: (1) univariate and (2) restricted bivariate trinormal underlying data.
RESULTS: In both cases, the statistical estimates were found to be good in the sense that the analytical values lay within the 95% confidence interval of the estimated values about 95% of the time.
CONCLUSIONS: The statistical estimation method should be key in the development of a pragmatic performance metric for evaluation of observers in classification tasks with three or more classes.
Copyright © 2013 AUR. Published by Elsevier Inc. All rights reserved.

Entities:  

Mesh:

Year:  2013        PMID: 23747155      PMCID: PMC3697838          DOI: 10.1016/j.acra.2013.04.002

Source DB:  PubMed          Journal:  Acad Radiol        ISSN: 1076-6332            Impact factor:   3.173


  23 in total

1.  "Proper" Binormal ROC Curves: Theory and Maximum-Likelihood Estimation.

Authors: 
Journal:  J Math Psychol       Date:  1999-03       Impact factor: 2.223

2.  Comparing three-class diagnostic tests by three-way ROC analysis.

Authors:  S Dreiseitl; L Ohno-Machado; M Binder
Journal:  Med Decis Making       Date:  2000 Jul-Sep       Impact factor: 2.583

3.  Nonparametric Bayesian estimation of the three-way receiver operating characteristic surface.

Authors:  Vanda Inácio; Antónia A Turkman; Christos T Nakas; Todd A Alonzo
Journal:  Biom J       Date:  2011-11       Impact factor: 2.207

4.  The hypervolume under the ROC hypersurface of "near-guessing" and "near-perfect" observers in N-class classification tasks.

Authors:  Darrin C Edwards; Charles E Metz; Robert M Nishikawa
Journal:  IEEE Trans Med Imaging       Date:  2005-03       Impact factor: 10.048

5.  Three-class ROC analysis--a decision theoretic approach under the ideal observer framework.

Authors:  Xin He; Charles E Metz; Benjamin M W Tsui; Jonathan M Links; Eric C Frey
Journal:  IEEE Trans Med Imaging       Date:  2006-05       Impact factor: 10.048

6.  ROC analysis with multiple classes and multiple tests: methodology and its application in microarray studies.

Authors:  Jialiang Li; Jason P Fine
Journal:  Biostatistics       Date:  2008-02-27       Impact factor: 5.899

7.  Three-way ROCs.

Authors:  D Mossman
Journal:  Med Decis Making       Date:  1999 Jan-Mar       Impact factor: 2.583

8.  Three-class ROC analysis--toward a general decision theoretic solution.

Authors:  Xin He; Brandon D Gallas; Eric C Frey
Journal:  IEEE Trans Med Imaging       Date:  2009-10-30       Impact factor: 10.048

9.  Three-class ROC analysis--the equal error utility assumption and the optimality of three-class ROC surface using the ideal observer.

Authors:  Xin He; Eric C Frey
Journal:  IEEE Trans Med Imaging       Date:  2006-08       Impact factor: 10.048

10.  Application of three-class ROC analysis to task-based image quality assessment of simultaneous dual-isotope myocardial perfusion SPECT (MPS).

Authors:  Xin He; Xiyun Song; Eric C Frey
Journal:  IEEE Trans Med Imaging       Date:  2008-11       Impact factor: 10.048

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.