Skip to main content
SpringerLink
Log in
Book cover

Biennial International Conference on Information Processing in Medical Imaging

IPMI 1993: Information Processing in Medical Imaging pp 507–524Cite as

Multivariate gaussian pattern classification: Effects of finite sample size and the addition of correlated or noisy features on summary measures of goodness

  • Conference paper
  • First Online:

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 687))

Abstract

The addition of correlated or noisy features to a given feature set can degrade estimates of certain figures of merit used to characterize the class separability offered by the set. We review three such figures of merit and consider the effects of correlation and noise on their estimation from a finite training set. These effects cause some measures to be biased optimistically, others pessimistically. Previous studies of these biases have tended to overlook the large variances involved, particularly in low-dimensional space. Several methods of bias reduction are compared. A method due to Fukunaga and Hayes is compared with the “jackknife”; only the former reduces the bias without increasing the variance of the estimate for problems considered here.

This is a preview of subscription content, log in via an institution.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. M.F.Insana,R.F.Wagner,B-S.Garra,R.Momenan,T.H.Shawker: Pattern Recognition Methods for Optimizing Multivariate Tissue Signatures in Diagnostic Ultrasound. Ultrason. Imaging 8, 165–180 (1986).

    Article  PubMed  Google Scholar 

  2. R.F.Wagner,M.F.Insana,D.G.Brown (1987): Statistical Properties of Radio-Frequency and Envelope-Detected Signals with Applications to Medical Ultrasound. J. Opt. Soc Am. A4, 910–922 (1987).

    Google Scholar 

  3. B.S.Garra, M.F.Insana, T.H.Shawker, R.F.Wagner, M.Bradford, M.Russell: Quantitative Ultrasonic Detection and Classification of Diffuse Liver Disease: Comparison with Human Observer Performance. Invest.Radiol. 24, 196–203 (1989).

    PubMed  Google Scholar 

  4. K.J.Myers,K.A.Wear,L.W.Grossman,R.F.Wagner,S.S.Rajan,B.S.Garra: Multimodality quantitative tissue characterization using ultrasound and magnetic resonance spectroscopy: Initial results. Twelfth International Conference on Information Processing in Medical Imaging. Wye, UK, July 7–12, 1991.

    Google Scholar 

  5. K.R.Castleman: Digital Image Processing. Prentice-Hall, Englewood Cliffs (1979).

    Google Scholar 

  6. K.Fukunaga,R.R.Hayes: Effects of Sample Size in Classifier Design. IEEE Trans. Pattern Anal. Machine Intell. PAMI-11, 873–885 (1989).

    Article  Google Scholar 

  7. S J.Raudys,A.K.Jain: Small Sample Size Effects in Statistical Pattern Recognition: Recommendations for Practitioners. IEEE Trans. Pattern Anal. Machine Intell. PAMI-13: 252–264 (1991).

    Article  Google Scholar 

  8. D.F.Morrison: Multivariate Statistical Methods. McGraw-Hill, New York (1967).

    Google Scholar 

  9. R.A.Johnson,D.W.Wichern: Applied Multivariate Statistical Analysis. Prentice-Hall, Englewood Cliffs (1982).

    Google Scholar 

  10. H.Hotelling. The generalization of Student's ratio. Annals of Mathematical Statistics 2, 360–378 (1931).

    Google Scholar 

  11. S.Das Gupta,M.D.Perlman: Power of the Noncentral F-Test: Effect of Additional Variates on Hotelling's T2-Test. J. Amer. Stat. Assoc. 69, 174–180 (1974).

    Google Scholar 

  12. K.Fukunaga: Introduction to Statistical Pattern Recognition. Academic, Orlando (1972).

    Google Scholar 

  13. R.D.Fiete,H.H.Barrett,W.E.Smith,K.J.Myers: Hotelling Trace Criterion and its Correlation with Human-observer Performance. J.Opt.Soc.Am. A4, 945–953 (1987).

    Google Scholar 

  14. R.A.Fisher: The use of Multiple Measurements in Taxonomic Problems. Annals of Eugenics 7, 179–188 (1936).

    Google Scholar 

  15. D.M.Green,J.A.Swets: Signal Detection Theory and Psychophysics. Robert E.Krieger, Huntington NY (1974).

    Google Scholar 

  16. J.A.Swets,R.M.Pickett. Evaluation of Diagnostic Systems: Methods from Signal Detection Theory. Academic Press, New York (1982).

    Google Scholar 

  17. C.E.Metz: ROC Methodology in Radiologic Imaging. Invest.Radiol. 21, 720–733 (1986).

    PubMed  Google Scholar 

  18. A.Gmitro,A.Alexander: Private Communication via H.H.Barrett (1991).

    Google Scholar 

  19. H.H.Barrett: Private Communication (1991) (if in S, N is used instead of N-1).

    Google Scholar 

  20. B.Efron: The Jackknife, the Bootstrap and Other Resampling Plans. Soc. for Ind. & Appl. Math., Philadelphia (1982).

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Center for Devices & Radiological Health, FDA, 20857, Rockville, MD

    R. F. Wagner, D. G. Brown, J. -P. Guedon, K. J. Myers & K. A. Wear

Authors
  1. R. F. Wagner
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. D. G. Brown
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. J. -P. Guedon
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. K. J. Myers
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. K. A. Wear
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Harrison H. Barrett A. F. Gmitro

Rights and permissions

Reprints and permissions

Copyright information

© 1993 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Wagner, R.F., Brown, D.G., Guedon, J.P., Myers, K.J., Wear, K.A. (1993). Multivariate gaussian pattern classification: Effects of finite sample size and the addition of correlated or noisy features on summary measures of goodness. In: Barrett, H.H., Gmitro, A.F. (eds) Information Processing in Medical Imaging. IPMI 1993. Lecture Notes in Computer Science, vol 687. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0013808

Download citation

  • DOI: https://doi.org/10.1007/BFb0013808

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-56800-1

  • Online ISBN: 978-3-540-47742-6

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation