Shannon information and ROC analysis in imaging

Eric W Clarkson, Johnathan B. Cushing

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Shannon information (SI) and the ideal-observer receiver operating characteristic (ROC) curve are two different methods for analyzing the performance of an imaging system for a binary classification task, such as the detection of a variable signal embedded within a random background. In this work we describe a new ROC curve, the Shannon information receiver operator curve (SIROC), that is derived from the SI expression for a binary classification task. We then show that the ideal-observer ROC curve and the SIROC have many properties in common, and are equivalent descriptions of the optimal performance of an observer on the task. This equivalence is described mathematically by an integral transform that maps the ideal-observer ROC curve onto the SIROC. This then leads to an integral transform relating the minimum probability of error, as a function of the odds against a signal, to the conditional entropy, as a function of the same variable. This last relation then gives us the complete mathematical equivalence between ideal-observer ROC analysis and SI analysis of the classification task for a given imaging system.We also find that there is a close relationship between the area under the ideal-observer ROC curve, which is often used as a figure of merit for imaging systems and the area under the SIROC. Finally, we show that the relationships between the two curves result in new inequalities relating SI to ROC quantities for the ideal observer.

Original languageEnglish (US)
Pages (from-to)1288-1301
Number of pages14
JournalJournal of the Optical Society of America A: Optics and Image Science, and Vision
Volume32
Issue number7
DOIs
StatePublished - 2015

Fingerprint

information analysis
ROC Curve
Imaging systems
receivers
Imaging techniques
curves
Information analysis
Entropy
operators
integral transformations
equivalence
figure of merit

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Computer Vision and Pattern Recognition

Cite this

Shannon information and ROC analysis in imaging. / Clarkson, Eric W; Cushing, Johnathan B.

In: Journal of the Optical Society of America A: Optics and Image Science, and Vision, Vol. 32, No. 7, 2015, p. 1288-1301.

Research output: Contribution to journalArticle

@article{dd023dafb20249319b080691f342eb3a,
title = "Shannon information and ROC analysis in imaging",
abstract = "Shannon information (SI) and the ideal-observer receiver operating characteristic (ROC) curve are two different methods for analyzing the performance of an imaging system for a binary classification task, such as the detection of a variable signal embedded within a random background. In this work we describe a new ROC curve, the Shannon information receiver operator curve (SIROC), that is derived from the SI expression for a binary classification task. We then show that the ideal-observer ROC curve and the SIROC have many properties in common, and are equivalent descriptions of the optimal performance of an observer on the task. This equivalence is described mathematically by an integral transform that maps the ideal-observer ROC curve onto the SIROC. This then leads to an integral transform relating the minimum probability of error, as a function of the odds against a signal, to the conditional entropy, as a function of the same variable. This last relation then gives us the complete mathematical equivalence between ideal-observer ROC analysis and SI analysis of the classification task for a given imaging system.We also find that there is a close relationship between the area under the ideal-observer ROC curve, which is often used as a figure of merit for imaging systems and the area under the SIROC. Finally, we show that the relationships between the two curves result in new inequalities relating SI to ROC quantities for the ideal observer.",
author = "Clarkson, {Eric W} and Cushing, {Johnathan B.}",
year = "2015",
doi = "10.1364/JOSAA.32.001288",
language = "English (US)",
volume = "32",
pages = "1288--1301",
journal = "Journal of the Optical Society of America A: Optics and Image Science, and Vision",
issn = "1084-7529",
publisher = "The Optical Society",
number = "7",

}

TY - JOUR

T1 - Shannon information and ROC analysis in imaging

AU - Clarkson, Eric W

AU - Cushing, Johnathan B.

PY - 2015

Y1 - 2015

N2 - Shannon information (SI) and the ideal-observer receiver operating characteristic (ROC) curve are two different methods for analyzing the performance of an imaging system for a binary classification task, such as the detection of a variable signal embedded within a random background. In this work we describe a new ROC curve, the Shannon information receiver operator curve (SIROC), that is derived from the SI expression for a binary classification task. We then show that the ideal-observer ROC curve and the SIROC have many properties in common, and are equivalent descriptions of the optimal performance of an observer on the task. This equivalence is described mathematically by an integral transform that maps the ideal-observer ROC curve onto the SIROC. This then leads to an integral transform relating the minimum probability of error, as a function of the odds against a signal, to the conditional entropy, as a function of the same variable. This last relation then gives us the complete mathematical equivalence between ideal-observer ROC analysis and SI analysis of the classification task for a given imaging system.We also find that there is a close relationship between the area under the ideal-observer ROC curve, which is often used as a figure of merit for imaging systems and the area under the SIROC. Finally, we show that the relationships between the two curves result in new inequalities relating SI to ROC quantities for the ideal observer.

AB - Shannon information (SI) and the ideal-observer receiver operating characteristic (ROC) curve are two different methods for analyzing the performance of an imaging system for a binary classification task, such as the detection of a variable signal embedded within a random background. In this work we describe a new ROC curve, the Shannon information receiver operator curve (SIROC), that is derived from the SI expression for a binary classification task. We then show that the ideal-observer ROC curve and the SIROC have many properties in common, and are equivalent descriptions of the optimal performance of an observer on the task. This equivalence is described mathematically by an integral transform that maps the ideal-observer ROC curve onto the SIROC. This then leads to an integral transform relating the minimum probability of error, as a function of the odds against a signal, to the conditional entropy, as a function of the same variable. This last relation then gives us the complete mathematical equivalence between ideal-observer ROC analysis and SI analysis of the classification task for a given imaging system.We also find that there is a close relationship between the area under the ideal-observer ROC curve, which is often used as a figure of merit for imaging systems and the area under the SIROC. Finally, we show that the relationships between the two curves result in new inequalities relating SI to ROC quantities for the ideal observer.

UR - http://www.scopus.com/inward/record.url?scp=84943250081&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943250081&partnerID=8YFLogxK

U2 - 10.1364/JOSAA.32.001288

DO - 10.1364/JOSAA.32.001288

M3 - Article

VL - 32

SP - 1288

EP - 1301

JO - Journal of the Optical Society of America A: Optics and Image Science, and Vision

JF - Journal of the Optical Society of America A: Optics and Image Science, and Vision

SN - 1084-7529

IS - 7

ER -