Fast approach to evaluate MAP reconstruction for lesion detection and localization

Jinyi Qi, Ronald H. Huesman

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

Lesion detection is an important task in emission tomography. Localization ROC (LROC) studies are often used to analyze the lesion detection and localization performance. Most researchers rely on Monte Carlo reconstruction samples to obtain LROC curves, which can be very time-consuming for iterative algorithms. In this paper we develop a fast approach to obtain LROC curves that does not require Monte Carlo reconstructions. We use a channelized Hotelling observer model to search for lesions, and the results can be easily extended to other numerical observers. We theoretically analyzed the mean and covariance of the observer output. Assuming the observer outputs are multivariate Gaussian random variables, an LROC curve can be directly generated by integrating the conditional probability density functions. The high-dimensional integrals are calculated using a Monte Carlo method. The proposed approach is very fast because no iterative reconstruction is involved. Computer simulations show that the results of the proposed method match well with those obtained using the tradition LROC analysis.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
EditorsD.P. Chakraborty, M.P. Eckstein
Pages273-282
Number of pages10
Volume5
Edition26
DOIs
StatePublished - 2004
Externally publishedYes
EventMedical Imaging 2004 - Image Perception, Observer Performance, and Technology Assessment - San Diego, CA, United States
Duration: Feb 17 2004Feb 19 2004

Other

OtherMedical Imaging 2004 - Image Perception, Observer Performance, and Technology Assessment
CountryUnited States
CitySan Diego, CA
Period2/17/042/19/04

Fingerprint

Random variables
Probability density function
Tomography
Monte Carlo methods
Computer simulation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Qi, J., & Huesman, R. H. (2004). Fast approach to evaluate MAP reconstruction for lesion detection and localization. In D. P. Chakraborty, & M. P. Eckstein (Eds.), Progress in Biomedical Optics and Imaging - Proceedings of SPIE (26 ed., Vol. 5, pp. 273-282). [33] https://doi.org/10.1117/12.535916

Fast approach to evaluate MAP reconstruction for lesion detection and localization. / Qi, Jinyi; Huesman, Ronald H.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. ed. / D.P. Chakraborty; M.P. Eckstein. Vol. 5 26. ed. 2004. p. 273-282 33.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Qi, J & Huesman, RH 2004, Fast approach to evaluate MAP reconstruction for lesion detection and localization. in DP Chakraborty & MP Eckstein (eds), Progress in Biomedical Optics and Imaging - Proceedings of SPIE. 26 edn, vol. 5, 33, pp. 273-282, Medical Imaging 2004 - Image Perception, Observer Performance, and Technology Assessment, San Diego, CA, United States, 2/17/04. https://doi.org/10.1117/12.535916
Qi J, Huesman RH. Fast approach to evaluate MAP reconstruction for lesion detection and localization. In Chakraborty DP, Eckstein MP, editors, Progress in Biomedical Optics and Imaging - Proceedings of SPIE. 26 ed. Vol. 5. 2004. p. 273-282. 33 https://doi.org/10.1117/12.535916
Qi, Jinyi ; Huesman, Ronald H. / Fast approach to evaluate MAP reconstruction for lesion detection and localization. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. editor / D.P. Chakraborty ; M.P. Eckstein. Vol. 5 26. ed. 2004. pp. 273-282
@inproceedings{e512e20c2ba74f71bbc5ad17f562cba4,
title = "Fast approach to evaluate MAP reconstruction for lesion detection and localization",
abstract = "Lesion detection is an important task in emission tomography. Localization ROC (LROC) studies are often used to analyze the lesion detection and localization performance. Most researchers rely on Monte Carlo reconstruction samples to obtain LROC curves, which can be very time-consuming for iterative algorithms. In this paper we develop a fast approach to obtain LROC curves that does not require Monte Carlo reconstructions. We use a channelized Hotelling observer model to search for lesions, and the results can be easily extended to other numerical observers. We theoretically analyzed the mean and covariance of the observer output. Assuming the observer outputs are multivariate Gaussian random variables, an LROC curve can be directly generated by integrating the conditional probability density functions. The high-dimensional integrals are calculated using a Monte Carlo method. The proposed approach is very fast because no iterative reconstruction is involved. Computer simulations show that the results of the proposed method match well with those obtained using the tradition LROC analysis.",
author = "Jinyi Qi and Huesman, {Ronald H.}",
year = "2004",
doi = "10.1117/12.535916",
language = "English (US)",
volume = "5",
pages = "273--282",
editor = "D.P. Chakraborty and M.P. Eckstein",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
edition = "26",

}

TY - GEN

T1 - Fast approach to evaluate MAP reconstruction for lesion detection and localization

AU - Qi, Jinyi

AU - Huesman, Ronald H.

PY - 2004

Y1 - 2004

N2 - Lesion detection is an important task in emission tomography. Localization ROC (LROC) studies are often used to analyze the lesion detection and localization performance. Most researchers rely on Monte Carlo reconstruction samples to obtain LROC curves, which can be very time-consuming for iterative algorithms. In this paper we develop a fast approach to obtain LROC curves that does not require Monte Carlo reconstructions. We use a channelized Hotelling observer model to search for lesions, and the results can be easily extended to other numerical observers. We theoretically analyzed the mean and covariance of the observer output. Assuming the observer outputs are multivariate Gaussian random variables, an LROC curve can be directly generated by integrating the conditional probability density functions. The high-dimensional integrals are calculated using a Monte Carlo method. The proposed approach is very fast because no iterative reconstruction is involved. Computer simulations show that the results of the proposed method match well with those obtained using the tradition LROC analysis.

AB - Lesion detection is an important task in emission tomography. Localization ROC (LROC) studies are often used to analyze the lesion detection and localization performance. Most researchers rely on Monte Carlo reconstruction samples to obtain LROC curves, which can be very time-consuming for iterative algorithms. In this paper we develop a fast approach to obtain LROC curves that does not require Monte Carlo reconstructions. We use a channelized Hotelling observer model to search for lesions, and the results can be easily extended to other numerical observers. We theoretically analyzed the mean and covariance of the observer output. Assuming the observer outputs are multivariate Gaussian random variables, an LROC curve can be directly generated by integrating the conditional probability density functions. The high-dimensional integrals are calculated using a Monte Carlo method. The proposed approach is very fast because no iterative reconstruction is involved. Computer simulations show that the results of the proposed method match well with those obtained using the tradition LROC analysis.

UR - http://www.scopus.com/inward/record.url?scp=12144251076&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=12144251076&partnerID=8YFLogxK

U2 - 10.1117/12.535916

DO - 10.1117/12.535916

M3 - Conference contribution

AN - SCOPUS:12144251076

VL - 5

SP - 273

EP - 282

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

A2 - Chakraborty, D.P.

A2 - Eckstein, M.P.

ER -