Ideal-observer computation in medical imaging with use of Markov-chain Monte Carlo techniques

Research output: Contribution to journalArticle

82 Citations (Scopus)

Abstract

The ideal observer sets an upper limit on the performance of an observer on a detection or classification task. The performance of the ideal observer can be used to optimize hardware components of imaging systems and also to determine another observer's relative performance in comparison with the best possible observer. The ideal observer employs complete knowledge of the statistics of the imaging system, including the noise and object variability. Thus computing the ideal observer for images (large-dimensional vectors) is burdensome without severely restricting the randomness in the imaging system, e.g., assuming a flat object. We present a method for computing the ideal-observer test statistic and performance by using Markov-chain Monte Carlo techniques when we have a well-characterized imaging system, knowledge of the noise statistics, and a stochastic object model. We demonstrate the method by comparing three different parallel-hole collimator imaging systems in simulation.

Original languageEnglish (US)
Pages (from-to)430-438
Number of pages9
JournalJournal of the Optical Society of America A: Optics and Image Science, and Vision
Volume20
Issue number3
StatePublished - 2003

Fingerprint

Markov Chains
Medical imaging
Diagnostic Imaging
Imaging systems
Markov processes
Noise
Statistics
Hardware

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Computer Vision and Pattern Recognition

Cite this

@article{1398202d8a0e41d289742c4707d2aa89,
title = "Ideal-observer computation in medical imaging with use of Markov-chain Monte Carlo techniques",
abstract = "The ideal observer sets an upper limit on the performance of an observer on a detection or classification task. The performance of the ideal observer can be used to optimize hardware components of imaging systems and also to determine another observer's relative performance in comparison with the best possible observer. The ideal observer employs complete knowledge of the statistics of the imaging system, including the noise and object variability. Thus computing the ideal observer for images (large-dimensional vectors) is burdensome without severely restricting the randomness in the imaging system, e.g., assuming a flat object. We present a method for computing the ideal-observer test statistic and performance by using Markov-chain Monte Carlo techniques when we have a well-characterized imaging system, knowledge of the noise statistics, and a stochastic object model. We demonstrate the method by comparing three different parallel-hole collimator imaging systems in simulation.",
author = "Kupinski, {Matthew A} and Hoppin, {John W.} and Clarkson, {Eric W} and Barrett, {Harrison H}",
year = "2003",
language = "English (US)",
volume = "20",
pages = "430--438",
journal = "Journal of the Optical Society of America A: Optics and Image Science, and Vision",
issn = "1084-7529",
publisher = "The Optical Society",
number = "3",

}

TY - JOUR

T1 - Ideal-observer computation in medical imaging with use of Markov-chain Monte Carlo techniques

AU - Kupinski, Matthew A

AU - Hoppin, John W.

AU - Clarkson, Eric W

AU - Barrett, Harrison H

PY - 2003

Y1 - 2003

N2 - The ideal observer sets an upper limit on the performance of an observer on a detection or classification task. The performance of the ideal observer can be used to optimize hardware components of imaging systems and also to determine another observer's relative performance in comparison with the best possible observer. The ideal observer employs complete knowledge of the statistics of the imaging system, including the noise and object variability. Thus computing the ideal observer for images (large-dimensional vectors) is burdensome without severely restricting the randomness in the imaging system, e.g., assuming a flat object. We present a method for computing the ideal-observer test statistic and performance by using Markov-chain Monte Carlo techniques when we have a well-characterized imaging system, knowledge of the noise statistics, and a stochastic object model. We demonstrate the method by comparing three different parallel-hole collimator imaging systems in simulation.

AB - The ideal observer sets an upper limit on the performance of an observer on a detection or classification task. The performance of the ideal observer can be used to optimize hardware components of imaging systems and also to determine another observer's relative performance in comparison with the best possible observer. The ideal observer employs complete knowledge of the statistics of the imaging system, including the noise and object variability. Thus computing the ideal observer for images (large-dimensional vectors) is burdensome without severely restricting the randomness in the imaging system, e.g., assuming a flat object. We present a method for computing the ideal-observer test statistic and performance by using Markov-chain Monte Carlo techniques when we have a well-characterized imaging system, knowledge of the noise statistics, and a stochastic object model. We demonstrate the method by comparing three different parallel-hole collimator imaging systems in simulation.

UR - http://www.scopus.com/inward/record.url?scp=0037361771&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0037361771&partnerID=8YFLogxK

M3 - Article

C2 - 12630829

AN - SCOPUS:0037361771

VL - 20

SP - 430

EP - 438

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 - 3

ER -