Advertisement

Linear discriminants and image quality

  • H H Barrett
  • T Gooley
  • K Girodias
  • J Rolland
  • T White
  • J Yao
9. Image Quality, Display And Interaction
Part of the Lecture Notes in Computer Science book series (LNCS, volume 511)

Abstract

The use of linear discriminant functions, and particularly a discriminant function derived from the work of Harold Hotelling, as a means of assessing image quality is reviewed. The relevant theory of ideal or Bayesian observers is briefly reviewed, and the circumstances under which this observer reduces to a linear discriminant are discussed. The Hotelling oberver is suggested as a linear discriminant in more general circumstances where the ideal observer is nonlinear and usually very difficult to calculate. Methods of calculation of the Hotelling discriminant and the associated figure of merit, the Hotelling trace, are discussed. Psychophysical studies carried out at the University of Arizona to test the predictive value of the Hotelling observer are reviewed, and it is concluded that the Hotelling model is quite useful as a predictive tool unless there are high-pass noise correlations introduced by post-processing of the images. In that case, we suggest that the Hotelling observer be modified to include spatial-frequency-selective channels analogous to those in the visual system.

Keywords

Image quality medical imaging linear discriminant functions ideal observer Hotelling trace 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Barrett HH, Rolland JP, Wagner RF, and Myers KJ (1989). Detection of known signals in inhomogeneous, random backgrounds. Proc. SPIE, 1090:176–182.Google Scholar
  2. Barrett HH (1990). Objective assessment of image quality: effect of object variability and quantum noise, J. Opt. Soc. Am. A. 7:1266–1278.Google Scholar
  3. Cargill EB (1989). A mathematical liver model and its application to system optimization and texture analysis. Ph.D. Dissertation, University of Arizona.Google Scholar
  4. Fiete RD, Barrett HH, Smith WE, and Myers KJ (1987). The Hotelling trace criterion and its correlation with human observer performance. J. Opt. Soc. Am. A. 4:945–953.Google Scholar
  5. Fisher RA (1936). The use of multiple measurements in taxonomic problems. Ann. Eugenics 7 (part2):179–188.Google Scholar
  6. Gooley TA (1990). Quantitative comparisons of statistical methods in image reconstruction. Ph. D. dissertation, University of Arizona.Google Scholar
  7. Hotelling H (1931). The generalization of Student's ratio. Ann. Math. Stat. 2:360–378.Google Scholar
  8. Myers KJ, Barrett HH, Borgstrom MC, Patton DD, and Seeley GW (1985). Effect of noise correlation on detectability of disk signals in medical imaging. J. Opt. Soc. Am. A, 2:1752–1759.Google Scholar
  9. Myers KJ and Barrett HH (1987). Addition of a channel mechanism to the ideal-observer model. J. Opt. Soc. Am. A, 46:2447–2457.Google Scholar
  10. Rolland JPY, (1990). Factors influencing lesion detection in medical imaging. Ph. D. dissertation, University of Arizona.Google Scholar
  11. Smith WE and Barrett HH (1986). Hotelling trace criterion as a figure of merit for the optimization of imaging systems. J. Opt. Soc. Am. A, 3:717–725.Google Scholar
  12. Smith WE and Barrett HH (1988). Linear estimation theory applied to the evaluation of a priori information and system optimization in coded-aperture imaging. J. Opt. Soc. Am. A,5:315–330.Google Scholar
  13. White TA, Barrett HH, Cargill EB, Fiete RD, and Ker M (1989). The use of the Hotelling trace to optimize collimator performance. The Society of Nuclear Medicine 36th Annual Meeting, St. Louis, MO, (abstract).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • H H Barrett
    • 1
    • 2
    • 3
  • T Gooley
    • 3
  • K Girodias
    • 2
  • J Rolland
    • 1
    • 2
    • 4
  • T White
    • 1
    • 2
  • J Yao
    • 1
    • 2
  1. 1.Optical Sciences CenterUniversity of ArizonaTucson
  2. 2.Department of RadiologyUniversity of ArizonaTucson
  3. 3.Program in Applied MathematicsUniversity of ArizonaTucson
  4. 4.Dept. of Computer ScienceUniversity of North CarolinaChapel Hill

Personalised recommendations