Components of variance in ROC analysis of CADx classifier performance

Proceedings of SPIE - The International Society for Optical Engineering

Volumn 3338, Issue , 1998, Pages 859-875

  Wagner, Robert F ^a   Chan, Heang Ping ^b   Mossoba, Joseph T ^a   Sahiner, Berkman ^b   Petrick, Nicholas ^b  

^a CENTER FOR DRUG EVALUATION AND RESEARCH   (United States)

^b UNIVERSITY OF MICHIGAN   (United States)

Author keywords

Analysis of variance; Classifier performance; Computer aided diagnosis; ROC analysis; Wilcoxon statistic

Indexed keywords

CLASSIFIERS; COMPUTER AIDED ANALYSIS; COMPUTER AIDED DIAGNOSIS; IMAGE PROCESSING; IMAGING SYSTEMS; LEARNING SYSTEMS; MEDICAL IMAGING; POPULATION STATISTICS; REGRESSION ANALYSIS; STATISTICAL TESTS;

AREA UNDER THE ROC CURVES; CLASSIFIER PERFORMANCE; DATA SETS; NON-PARAMETRIC ESTIMATES; POPULATION VARIANCES; RE SAMPLINGS; ROC ANALYSIS; TEST SAMPLES; TRAINING SAMPLES; WILCOXON STATISTIC;

UNCERTAINTY ANALYSIS;

EID: 0005188869     PISSN: 0277786X     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1117/12.310896     Document Type: Conference Paper

References (16)

1. K. Fukunaga, "Introduction to Statistical Pattern Recognition" (Second Edition, Chapter 5), Academic (Boston), 1990.
2. R.F. Wagner, D.G. Brown, J.-P. Guedon, K.J. Myers, K.A. Wear, "On combining a few diagnostic tests or features," Proc. of the SPIE 2167, 503-512 (1994).
3. D.G. Brown, A.C. Schneider, M.P. Anderson, R.F. Wagner, "Effect of finite sample size and correlated/noisy input features on neural network pattern classification," Proc. of the SPIE 2167, 180-190 (1994).
4. R.F. Wagner, H-P Chan, B. Sahiner, N. Petrick, J.T. Mossoba, "Finite-sample effects and resampling plans: Applications to linear classifiers in computer-aided diagnosis," Proc. of the SPIE 3034-45 (1997).
5. H-P Chan, B. Sahiner, R.F. Wagner, N. Petrick, J.T. Mossoba, "Effects of sample size on classifier design: quadratic and neural network classifiers," Proc. of the SPIE 3034-114 (1997).
6. H-P Chan, B. Sahiner, R.F. Wagner, N. Petrick, "Effects of sample size on classifier design for computer-aided diagnosis," Proc. of the SPIE 3338-201 (this workshop, 1998).
7. B. Efron, "The Jackknife, the Bootstrap and other Resampling Plans," Soc. for Ind. & Appl. Math. (Phila.), 1982.
8. C. E. Metz, B. A. Herman, J-H Shen, "Maximum-likelihood estimation of receiver operating characteristic (ROC) curves from continuously-distributed data," Statistics in Medicine (in press, 1997).
9. E.R. DeLong, D.M. DeLong, and D.L. Clarke-Pearson, "Computing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach," Biometrics 44, 837-845 (1988).
10. G. Campbell, M.A. Douglas, J.J. Bailey, "Nonparametric comparison of two tests of cardiac function on the same patient population using the entire ROC curve," Proc. of Computers in Cardiology, Computer Society of the IEEE, 267-270 (1988).
11. H.E. Rockette, N.A. Obuchowski, and D. Gur, "Nonparametric estimation of degenerate ROC data sets used for comparison of imaging systems," Invest. Rad. 25, 835-837 (1990).
12. C.E. Metz, Personal communication and discussions at University of Michigan, Feb. 1998.
13. C.E. Metz, Personal communications, Spring 1997.
14. D.D. Dorfman, K.E. Berbaum, C.E. Metz, "Receiver operating characteristic rating analysis: Generalization to the population of readers and patients with the jackknife method," Invest. Radiol. 27, 723-731 (1992).
15. C.A.Gatsonis, C.B. Begg, S. Wieand, "Advances in Statistical Methods for Diagnostic Radiology: A Symposium," Acad. Radiol. 2 (Supplement 1), March 1995.
16. C. A. Roe and C.E. Metz, "Variance-component modeling in the analysis of receiver operating characteristic index estimates," Acad. Radiol. 4, 587-600 (1997).