Nonparametric ROC and LROC analysis

In this paper we review several results of the nonparametric receiver operating characteristic (ROC) analysis and present an extension to the nonparametric localization ROC (LROC) analysis. Equations for the estimation of the area under the characteristic curve and for the variance calculations are...

Full description

Saved in:
Bibliographic Details
Published in:Medical physics (Lancaster) 2007-05, Vol.34 (5), p.1556-1564
Main Author: Popescu, Lucretiu M.
Format: Article
Language:English
Subjects:
Algorithms
Biomedical modeling
COMPUTERIZED SIMULATION
Data analysis
Decision analysis
Image analysis
IMAGE PROCESSING
Image Processing, Computer-Assisted
Image sensors
LROC
Medical image noise
medical image processing
Medical imaging
Monte Carlo methods
nonparametric
nonparametric statistics
Probability theory, stochastic processes, and statistics
Radiography
RADIOLOGY AND NUCLEAR MEDICINE
REVIEWS
ROC
ROC Curve
SENSITIVITY ANALYSIS
SIGNALS
Statistical analysis
Statistical properties
Surveys and tutorial papers
resource letters
Technology, Radiologic - methods
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper we review several results of the nonparametric receiver operating characteristic (ROC) analysis and present an extension to the nonparametric localization ROC (LROC) analysis. Equations for the estimation of the area under the characteristic curve and for the variance calculations are derived. Expressions for the choice of the optimal ratio between the number of signal-absent and signal-present image samples are also presented. The results can be applied both with continuous or discrete scoring scales. The simulation studies carried out validate the theoretical derivations and show that the LROC analysis is considerably more sensitive than the ROC analysis.
ISSN:0094-2405
2473-4209
DOI:10.1118/1.2717407