Applying the J-optimal channelized quadratic observer to SPECT myocardial perfusion defect detection

Meridith Kathryn Kupinski, Eric W Clarkson, Michael Ghaly, Eric C. Frey

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

Abstract

To evaluate performance on a perfusion defect detection task from 540 image pairs of myocardial perfusion SPECT image data we apply the J-optimal channelized quadratic observer (J-CQO). We compare AUC values of the linear Hotelling observer and J-CQO when the defect location is fixed and when it occurs in one of two locations. As expected, when the location is fixed a single channels maximizes AUC; location variability requires multiple channels to maximize the AUC. The AUC is estimated from both the projection data and reconstructed images. J-CQO is quadratic since it uses the first- and second- order statistics of the image data from both classes. The linear data reduction by the channels is described by an L x M channel matrix and in prior work we introduced an iterative gradient-based method for calculating the channel matrix. The dimensionality reduction from M measurements to L channels yields better estimates of these sample statistics from smaller sample sizes, and since the channelized covariance matrix is L x L instead of M x M, the matrix inverse is easier to compute. The novelty of our approach is the use of Jeffrey's divergence (J) as the figure of merit (FOM) for optimizing the channel matrix. We previously showed that the J-optimal channels are also the optimum channels for the AUC and the Bhattacharyya distance when the channel outputs are Gaussian distributed with equal means. This work evaluates the use of J as a surrogate FOM (SFOM) for AUC when these statistical conditions are not satisfied.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment
PublisherSPIE
Volume9787
ISBN (Electronic)9781510600225
DOIs
StatePublished - 2016
EventMedical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment - San Diego, United States
Duration: Mar 2 2016Mar 3 2016

Other

OtherMedical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment
CountryUnited States
CitySan Diego
Period3/2/163/3/16

Fingerprint

Single-Photon Emission-Computed Tomography
Area Under Curve
Perfusion
defects
Statistics
Covariance matrix
Data reduction
matrices
figure of merit
Sample Size
Defects
Defect detection
statistics
data reduction
divergence
projection
gradients
output
estimates

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Kupinski, M. K., Clarkson, E. W., Ghaly, M., & Frey, E. C. (2016). Applying the J-optimal channelized quadratic observer to SPECT myocardial perfusion defect detection. In Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment (Vol. 9787). [978708] SPIE. https://doi.org/10.1117/12.2217846

Applying the J-optimal channelized quadratic observer to SPECT myocardial perfusion defect detection. / Kupinski, Meridith Kathryn; Clarkson, Eric W; Ghaly, Michael; Frey, Eric C.

Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment. Vol. 9787 SPIE, 2016. 978708.

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

Kupinski, MK, Clarkson, EW, Ghaly, M & Frey, EC 2016, Applying the J-optimal channelized quadratic observer to SPECT myocardial perfusion defect detection. in Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment. vol. 9787, 978708, SPIE, Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment, San Diego, United States, 3/2/16. https://doi.org/10.1117/12.2217846
Kupinski MK, Clarkson EW, Ghaly M, Frey EC. Applying the J-optimal channelized quadratic observer to SPECT myocardial perfusion defect detection. In Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment. Vol. 9787. SPIE. 2016. 978708 https://doi.org/10.1117/12.2217846
Kupinski, Meridith Kathryn ; Clarkson, Eric W ; Ghaly, Michael ; Frey, Eric C. / Applying the J-optimal channelized quadratic observer to SPECT myocardial perfusion defect detection. Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment. Vol. 9787 SPIE, 2016.
@inproceedings{8909123d7cac46bc9bb7d0a4b3503a36,
title = "Applying the J-optimal channelized quadratic observer to SPECT myocardial perfusion defect detection",
abstract = "To evaluate performance on a perfusion defect detection task from 540 image pairs of myocardial perfusion SPECT image data we apply the J-optimal channelized quadratic observer (J-CQO). We compare AUC values of the linear Hotelling observer and J-CQO when the defect location is fixed and when it occurs in one of two locations. As expected, when the location is fixed a single channels maximizes AUC; location variability requires multiple channels to maximize the AUC. The AUC is estimated from both the projection data and reconstructed images. J-CQO is quadratic since it uses the first- and second- order statistics of the image data from both classes. The linear data reduction by the channels is described by an L x M channel matrix and in prior work we introduced an iterative gradient-based method for calculating the channel matrix. The dimensionality reduction from M measurements to L channels yields better estimates of these sample statistics from smaller sample sizes, and since the channelized covariance matrix is L x L instead of M x M, the matrix inverse is easier to compute. The novelty of our approach is the use of Jeffrey's divergence (J) as the figure of merit (FOM) for optimizing the channel matrix. We previously showed that the J-optimal channels are also the optimum channels for the AUC and the Bhattacharyya distance when the channel outputs are Gaussian distributed with equal means. This work evaluates the use of J as a surrogate FOM (SFOM) for AUC when these statistical conditions are not satisfied.",
author = "Kupinski, {Meridith Kathryn} and Clarkson, {Eric W} and Michael Ghaly and Frey, {Eric C.}",
year = "2016",
doi = "10.1117/12.2217846",
language = "English (US)",
volume = "9787",
booktitle = "Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment",
publisher = "SPIE",
address = "United States",

}

TY - GEN

T1 - Applying the J-optimal channelized quadratic observer to SPECT myocardial perfusion defect detection

AU - Kupinski, Meridith Kathryn

AU - Clarkson, Eric W

AU - Ghaly, Michael

AU - Frey, Eric C.

PY - 2016

Y1 - 2016

N2 - To evaluate performance on a perfusion defect detection task from 540 image pairs of myocardial perfusion SPECT image data we apply the J-optimal channelized quadratic observer (J-CQO). We compare AUC values of the linear Hotelling observer and J-CQO when the defect location is fixed and when it occurs in one of two locations. As expected, when the location is fixed a single channels maximizes AUC; location variability requires multiple channels to maximize the AUC. The AUC is estimated from both the projection data and reconstructed images. J-CQO is quadratic since it uses the first- and second- order statistics of the image data from both classes. The linear data reduction by the channels is described by an L x M channel matrix and in prior work we introduced an iterative gradient-based method for calculating the channel matrix. The dimensionality reduction from M measurements to L channels yields better estimates of these sample statistics from smaller sample sizes, and since the channelized covariance matrix is L x L instead of M x M, the matrix inverse is easier to compute. The novelty of our approach is the use of Jeffrey's divergence (J) as the figure of merit (FOM) for optimizing the channel matrix. We previously showed that the J-optimal channels are also the optimum channels for the AUC and the Bhattacharyya distance when the channel outputs are Gaussian distributed with equal means. This work evaluates the use of J as a surrogate FOM (SFOM) for AUC when these statistical conditions are not satisfied.

AB - To evaluate performance on a perfusion defect detection task from 540 image pairs of myocardial perfusion SPECT image data we apply the J-optimal channelized quadratic observer (J-CQO). We compare AUC values of the linear Hotelling observer and J-CQO when the defect location is fixed and when it occurs in one of two locations. As expected, when the location is fixed a single channels maximizes AUC; location variability requires multiple channels to maximize the AUC. The AUC is estimated from both the projection data and reconstructed images. J-CQO is quadratic since it uses the first- and second- order statistics of the image data from both classes. The linear data reduction by the channels is described by an L x M channel matrix and in prior work we introduced an iterative gradient-based method for calculating the channel matrix. The dimensionality reduction from M measurements to L channels yields better estimates of these sample statistics from smaller sample sizes, and since the channelized covariance matrix is L x L instead of M x M, the matrix inverse is easier to compute. The novelty of our approach is the use of Jeffrey's divergence (J) as the figure of merit (FOM) for optimizing the channel matrix. We previously showed that the J-optimal channels are also the optimum channels for the AUC and the Bhattacharyya distance when the channel outputs are Gaussian distributed with equal means. This work evaluates the use of J as a surrogate FOM (SFOM) for AUC when these statistical conditions are not satisfied.

UR - http://www.scopus.com/inward/record.url?scp=84976329662&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84976329662&partnerID=8YFLogxK

U2 - 10.1117/12.2217846

DO - 10.1117/12.2217846

M3 - Conference contribution

AN - SCOPUS:84976329662

VL - 9787

BT - Medical Imaging 2016: Image Perception, Observer Performance, and Technology Assessment

PB - SPIE

ER -