Alpha 2.0
Login Register
» Articles » PMID: 12630828

Experimental Determination of Object Statistics from Noisy Images

Overview
Journal J Opt Soc Am A Opt Image Sci Vis
Specialty Ophthalmology
Date 2003 Mar 13
PMID 12630828
Citations 19
Authors
Matthew A Kupinski
Eric Clarkson
John W Hoppin
Liying Chen
Harrison H Barrett
Affiliations
Soon will be listed here.
Abstract

Modern imaging systems rely on complicated hardware and sophisticated image-processing methods to produce images. Owing to this complexity in the imaging chain, there are numerous variables in both the hardware and the software that need to be determined. We advocate a task-based approach to measuring and optimizing image quality in which one analyzes the ability of an observer to perform a task. Ideally, a task-based measure of image quality would account for all sources of variation in the imaging system, including object variability. Often, researchers ignore object variability even though it is known to have a large effect on task performance. The more accurate the statistical description of the objects, the more believable the task-based results will be. We have developed methods to fit statistical models of objects, using only noisy image data and a well-characterized imaging system. The results of these techniques could eventually be used to optimize both the hardware and the software components of imaging systems.

Citing Articles

Approximating the Hotelling observer with autoencoder-learned efficient channels for binary signal detection tasks.

Granstedt J, Zhou W, Anastasio M J Med Imaging (Bellingham). 2023; 10(5):055501.

PMID: 37767114 PMC: 10520791. DOI: 10.1117/1.JMI.10.5.055501.

Ideal Observer Computation by Use of Markov-Chain Monte Carlo With Generative Adversarial Networks.

Zhou W, Villa U, Anastasio M IEEE Trans Med Imaging. 2023; 42(12):3715-3724.

PMID: 37578916 PMC: 10769588. DOI: 10.1109/TMI.2023.3304907.

Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networks.

Zhou W, Bhadra S, Brooks F, Li H, Anastasio M J Med Imaging (Bellingham). 2022; 9(1):015503.

PMID: 35229009 PMC: 8866417. DOI: 10.1117/1.JMI.9.1.015503.

Generating patient-specific virtual tumor populations with reaction-diffusion models and molecular imaging data.

Henscheid N Math Biosci Eng. 2020; 17(6):6531-6556.

PMID: 33378865 PMC: 7780222. DOI: 10.3934/mbe.2020341.

Approximating the Ideal Observer for Joint Signal Detection and Localization Tasks by use of Supervised Learning Methods.

Zhou W, Li H, Anastasio M IEEE Trans Med Imaging. 2020; 39(12):3992-4000.

PMID: 32746143 PMC: 7768793. DOI: 10.1109/TMI.2020.3009022.

References
1.
Myers K, Barrett H . Addition of a channel mechanism to the ideal-observer model. J Opt Soc Am A. 1987; 4(12):2447-57. DOI: 10.1364/josaa.4.002447. View
2.
Schwartz O, Simoncelli E . Natural signal statistics and sensory gain control. Nat Neurosci. 2001; 4(8):819-25. DOI: 10.1038/90526. View
3.
Clarkson E, Kupinski M, Barrett H . Transformation of characteristic functionals through imaging systems. Opt Express. 2009; 10(13):536-9. PMC: 3143023. DOI: 10.1364/oe.10.000536. View
4.
Abbey C, Barrett H . Human- and model-observer performance in ramp-spectrum noise: effects of regularization and object variability. J Opt Soc Am A Opt Image Sci Vis. 2001; 18(3):473-88. PMC: 2943344. DOI: 10.1364/josaa.18.000473. View
5.
Rolland J, Barrett H . Effect of random background inhomogeneity on observer detection performance. J Opt Soc Am A. 1992; 9(5):649-58. DOI: 10.1364/josaa.9.000649. View