The problem of ROC analysis without truth: the EM algorithm and the information matrix

Sergey V. Beiden; Gregory Campbell; Kristen L. Meier; Robert F. Wagner

doi:10.1117/12.383099

14 April 2000 The problem of ROC analysis without truth: the EM algorithm and the information matrix

Sergey V. Beiden, Gregory Campbell, Kristen L. Meier, Robert F. Wagner

Proceedings Volume 3981, Medical Imaging 2000: Image Perception and Performance; (2000) https://doi.org/10.1117/12.383099
Event: Medical Imaging 2000, 2000, San Diego, CA, United States

Abstract

Henkelman, Kay, and Bronskill (HKB) showed that although the problem of ROC analysis without truth is underconstrained and thus not uniquely solvable in one dimension (one diagnostic test), it is in principle solvable in two or more dimensions. However, they gave no analysis of the resulting uncertainties. The present work provides a maximum-likelihood solution using the EM (expectation-maximization) algorithm for the two- dimensional case. We also provide an analysis of uncertainties in terms of Monte Carlo simulations as well as estimates based on Fisher Information Matrices for the complete- and the missing-data problem. We find that the number of patients required for a given precision of estimate for the truth- unknown problem is a very large multiple of that required for the corresponding truth-known case.

Citation Download Citation

Sergey V. Beiden, Gregory Campbell, Kristen L. Meier, and Robert F. Wagner "The problem of ROC analysis without truth: the EM algorithm and the information matrix", Proc. SPIE 3981, Medical Imaging 2000: Image Perception and Performance, (14 April 2000); https://doi.org/10.1117/12.383099

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available