Abstract
It is well known that image assessment is task dependent. This is demonstrated in the context of images reconstructed from sparse data using MEM- SYS3. We demonstrate that the problem of determining the regularization- or hy- perparameter α has a task-dependent character independent of whether the images are viewed by human observers or by classical or neural-net classifiers. This issue is not addressed by Bayesian image analysts. We suggest, however, that knowledge of the task, or the use to which the images are to be put, is a form of prior knowledge that should be incorporated into a Bayesian analysis. We sketch a frequent ist approach that may serve as a guide to a Bayesian solution.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
K. Rossmann, “Image quality and patient exposure,” Current Problems in Radiology, 2(2), pp. 1–34, Year Book Medical Publishers, Chicago, 1972.
D.G. Brown, M.F. Insana, and M. Tapiovaara, “Detection performance of the ideal decision function and its McLaurin expansion: Signal position unknown,” J. Acoust. Soc. Am. 97, pp. 379–398, 1995.
R.F. Wagner, K.J. Myers, A.E. Burgess, D.G. Brown, and M.J. Tapiovaara, “Maximum a posteriori detection: Figures of merit for detection under uncertainty,” Proc. SPIE 1232, pp. 195–204, (Bellingham WA) 1990.
A.D. Whalen, Detection of Signals in Noise, (Electrical Science Series) Academic Press, New York, 1971.
K.M. Hanson, “Making binary decisions based on the posterior probability distribution associated with tomographic reconstructions,” in Maximum Entropy and Bayesian Methods, C.R. Smith, G.J. Erickson, and P.O. Neudorfer, eds., pp 313–326, Kluwer Academic, Dordrecht, 1992.
K.J. Myers, R.F. Wagner, and K.M. Hanson, “Binary task performance on images reconstructed using MEMSYS3: Comparison of machine and human observers,” in Maximum Entropy and Bayesian Methods, A. Mohammad-Djafari and G. Demoment, eds., pp. 415–421, Kluwer Academic, Dordrecht, 1993.
K.M. Hanson and K.J. Myers, “Rayleigh task performance as a method to evaluate image reconstruction algorithms,” in Maximum Entropy and Bayesian Methods, W.T. Grandy Jr., and L.H. Schick, eds., pp. 303–312, Kluwer Academic, The Netherlands, 1991.
S.F. Gull and J. Skilling, Quantified Maximum Entropy “MEMSYS 3” Users’ Manual, Maximum Entropy Data Consultants Ltd., Royston England, 1989.
J. Skilling and S.F. Gull, “Bayesian maximum entropy image reconstruction,” in Spatial Statistics and Imaging, A. Possolo, ed., pp. 341–367, Institute of Mathematical Statistics Lecture Notes-Monograph Series 20, IMS, Hay ward CA, 1991.
J.O. Berger, Statistical Decision Theory and Bayesian Analysis, Springer-Verlag, New York, 1985.
C.K. Abbey and H.H. Barrett, “Linear iterative reconstruction algorithms: Study of observer performance,” in Information Processing in Medical Imaging, Y. Bizais et al. eds., pp. 65–76, Kluwer Academic, The Netherlands, 1995.
K.M. Hanson, “Variations in task and the ideal observer,” Proc. SPIE 419, pp. 60–67, 1983.
K.J. Myers, J.P. Rolland, H.H. Barrett, and R.F. Wagner, “Aperture optimization for emission imaging: Effect of a spatially varying background,” J. Opt. Soc. Am. A7, pp. 1279–1293, 1990.
H.H. Barrett, “Objective assessment of image quality: Effects of quantum noise and object variability,” J. Opt. Soc. Am. A7, pp. 1266–1278, 1990.
H.H. Barrett, J.L. Denny, R.F. Wagner, and K.J. Myers, “Objective assessment of image quality. II. Fisher information, Fourier crosstalk and figures of merit for task performance,” J. Opt. Soc. Am. A12, pp. 834–852, 1995.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Springer Science+Business Media Dordrecht
About this paper
Cite this paper
Wagner, R.F., Myers, K.J., Brown, D.G., Anderson, M.P., Hanson, K.M. (1996). Toward Optimal Observer Performance of Detection and Discrimination Tasks on Reconstructions from Sparse Data. In: Hanson, K.M., Silver, R.N. (eds) Maximum Entropy and Bayesian Methods. Fundamental Theories of Physics, vol 79. Springer, Dordrecht. https://doi.org/10.1007/978-94-011-5430-7_25
Download citation
DOI: https://doi.org/10.1007/978-94-011-5430-7_25
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-010-6284-8
Online ISBN: 978-94-011-5430-7
eBook Packages: Springer Book Archive