Limits...
Region of interest based Hotelling observer for computed tomography with comparison to alternative methods.

Sanchez AA, Sidky EY, Pan X - J Med Imaging (Bellingham) (2014)

Bottom Line: This reduces the dimensionality of the image covariance matrix so that direct computation of HO metrics within the ROI is feasible.Here, we compare several of these methods, including the use of Laguerre-Gauss channels, discrete Fourier domain computation of the HO (which assumes noise stationarity), and two approaches to HO estimation through samples of noisy images.Since our method computes HO performance exactly within an ROI, this allows us to investigate the validity of the assumptions inherent in various common approaches to HO estimation, such as the stationarity assumption in the case of the discrete Fourier transform domain method.

View Article: PubMed Central - PubMed

Affiliation: The University of Chicago, Department of Radiology, 5841 South Maryland Avenue, Chicago, Illinois 60615, United States.

ABSTRACT

We compare several approaches to estimation of Hotelling observer (HO) performance in x-ray computed tomography (CT). We consider the case where the signal of interest is small so that the reconstructed image can be restricted to a small region of interest (ROI) surrounding the signal. This reduces the dimensionality of the image covariance matrix so that direct computation of HO metrics within the ROI is feasible. We propose that this approach is directly applicable to systems optimization in CT; however, many alternative approaches exist, which make computation of HO performance tractable through a range of approximations, assumptions, or estimation strategies. Here, we compare several of these methods, including the use of Laguerre-Gauss channels, discrete Fourier domain computation of the HO (which assumes noise stationarity), and two approaches to HO estimation through samples of noisy images. Since our method computes HO performance exactly within an ROI, this allows us to investigate the validity of the assumptions inherent in various common approaches to HO estimation, such as the stationarity assumption in the case of the discrete Fourier transform domain method.

No MeSH data available.


(a) HO  estimates from training and testing performed using the hold-out approach for 500, 1000, and 1500 training images, with an equal number of testing images. The prevalence of images from each class is also equal. (b) HO  estimates resulting from training and testing performed using resubstitution for 1000, 2000, and 3000 total images. The bias and variance of the estimates is worst for narrow filter widths, where the size of the ROI used is largest. Variance of the estimates is illustrated in Fig. 10 through 95% confidence intervals derived from bootstraping.
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC4326074&req=5

f9: (a) HO estimates from training and testing performed using the hold-out approach for 500, 1000, and 1500 training images, with an equal number of testing images. The prevalence of images from each class is also equal. (b) HO estimates resulting from training and testing performed using resubstitution for 1000, 2000, and 3000 total images. The bias and variance of the estimates is worst for narrow filter widths, where the size of the ROI used is largest. Variance of the estimates is illustrated in Fig. 10 through 95% confidence intervals derived from bootstraping.

Mentions: Figure 9 illustrates the use of linear classifier training and testing in order to estimate HO performance. In this case, prior knowledge of the mean images is not exploited, and sample estimates of the images are computed instead. The left-hand plot corresponds to the hold-out approach, where independent image sets are used for the training and testing phases, while the right-hand plot is generated using resubstitution. As seen in the figure, these two approaches introduce negative and positive biases in the estimates, respectively. Note that thousands of images are required in order to construct quantitatively meaningful estimates. However, the general trend of the results can be seen for comparatively few samples. This suggests that for certain tasks, such as rank-ordering of only a few options for algorithm implementation, the training and testing approach could be useful if one lacks an adequate model of the image covariance or class means.


Region of interest based Hotelling observer for computed tomography with comparison to alternative methods.

Sanchez AA, Sidky EY, Pan X - J Med Imaging (Bellingham) (2014)

(a) HO  estimates from training and testing performed using the hold-out approach for 500, 1000, and 1500 training images, with an equal number of testing images. The prevalence of images from each class is also equal. (b) HO  estimates resulting from training and testing performed using resubstitution for 1000, 2000, and 3000 total images. The bias and variance of the estimates is worst for narrow filter widths, where the size of the ROI used is largest. Variance of the estimates is illustrated in Fig. 10 through 95% confidence intervals derived from bootstraping.
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC4326074&req=5

f9: (a) HO estimates from training and testing performed using the hold-out approach for 500, 1000, and 1500 training images, with an equal number of testing images. The prevalence of images from each class is also equal. (b) HO estimates resulting from training and testing performed using resubstitution for 1000, 2000, and 3000 total images. The bias and variance of the estimates is worst for narrow filter widths, where the size of the ROI used is largest. Variance of the estimates is illustrated in Fig. 10 through 95% confidence intervals derived from bootstraping.
Mentions: Figure 9 illustrates the use of linear classifier training and testing in order to estimate HO performance. In this case, prior knowledge of the mean images is not exploited, and sample estimates of the images are computed instead. The left-hand plot corresponds to the hold-out approach, where independent image sets are used for the training and testing phases, while the right-hand plot is generated using resubstitution. As seen in the figure, these two approaches introduce negative and positive biases in the estimates, respectively. Note that thousands of images are required in order to construct quantitatively meaningful estimates. However, the general trend of the results can be seen for comparatively few samples. This suggests that for certain tasks, such as rank-ordering of only a few options for algorithm implementation, the training and testing approach could be useful if one lacks an adequate model of the image covariance or class means.

Bottom Line: This reduces the dimensionality of the image covariance matrix so that direct computation of HO metrics within the ROI is feasible.Here, we compare several of these methods, including the use of Laguerre-Gauss channels, discrete Fourier domain computation of the HO (which assumes noise stationarity), and two approaches to HO estimation through samples of noisy images.Since our method computes HO performance exactly within an ROI, this allows us to investigate the validity of the assumptions inherent in various common approaches to HO estimation, such as the stationarity assumption in the case of the discrete Fourier transform domain method.

View Article: PubMed Central - PubMed

Affiliation: The University of Chicago, Department of Radiology, 5841 South Maryland Avenue, Chicago, Illinois 60615, United States.

ABSTRACT

We compare several approaches to estimation of Hotelling observer (HO) performance in x-ray computed tomography (CT). We consider the case where the signal of interest is small so that the reconstructed image can be restricted to a small region of interest (ROI) surrounding the signal. This reduces the dimensionality of the image covariance matrix so that direct computation of HO metrics within the ROI is feasible. We propose that this approach is directly applicable to systems optimization in CT; however, many alternative approaches exist, which make computation of HO performance tractable through a range of approximations, assumptions, or estimation strategies. Here, we compare several of these methods, including the use of Laguerre-Gauss channels, discrete Fourier domain computation of the HO (which assumes noise stationarity), and two approaches to HO estimation through samples of noisy images. Since our method computes HO performance exactly within an ROI, this allows us to investigate the validity of the assumptions inherent in various common approaches to HO estimation, such as the stationarity assumption in the case of the discrete Fourier transform domain method.

No MeSH data available.