Academic Radiology
Volume 14, Issue 8 , Pages 985-991 , August 2007

Reliable Evaluation of Performance Level for Computer-Aided Diagnostic Scheme

  • Qiang Li, PhD

      Affiliations

    • Corresponding Author InformationAddress correspondence to: Q.L.

Received 9 December 2006 ,Accepted 29 April 2007.

References 

  1. Chan HP, Doi K, Vyborny CJ, et al. Improvement in radiologists’ detection of clustered microcalcifications on mammograms: the potential of computer-aided diagnosis. Invest Radiol. 1990;25:1102–1110
  2. Kobayashi T, Xu X, MacMahon H, et al. Effect of a computer-aided diagnosis scheme on radiologists’ performance in detection of lung nodules on radiographs. Radiology. 1996;199:843–848
  3. Fukunaga F, Hayes RR. Effects of sample size on classifier design. IEEE Trans Pattern Anal Mach Intell. 1989;11:873–885
  4. Fukunaga F, Hayes RR. Estimation of classifier performance. IEEE Trans Pattern Anal Mach Intell. 1989;11:1087–1101
  5. Wagner RF, Chan H-P, Mossoba JT, et al. Finite-sample effects and resampling plans: applications to linear classifiers in computer-aided diagnosis. Proc SPIE Conf Medical Imaging. 1997;3034:467–477
  6. Chan H-P, Sahiner B, Wagner RF, et al. Classifier design for computer-aided diagnosis: effects of finite sample size on the mean performance of classical and neural network classifiers. Med Phys. 1999;26:2654–2668
  7. Sahiner B, Chan H-P, Petrick N, et al. Feature selection and classifier performance in computer-aided diagnosis: the effect of finite sample size. Med Phys. 2000;27:1509–1522
  8. Gur D, Wagner RF, Chan H-P. On the repeated use of database for testing incremental improvement of computer-aided detection schemes. R. Acad Radiol. 2004;11:103–105
  9. Li Q, Doi K. The reduction of bias and variance for the evaluation of computer-aided diagnostic scheme. Med Phys. 2006;33:868–875
  10. Efron B, Tibshirani RF. An Antroduction to bootstrap. New York: Chapman and Hall; 1993;
  11. Aoyama M, Li Q, Katsuragawa S, et al. Automated computerized scheme for distinction between benign and malignant solitary pulmonary nodules on chest images. Med Phys. 2002;29:701–708
  12. Aoyama M, Li Q, Katsuragawa S, et al. Computerized scheme for determination of the likelihood measure of malignancy for pulmonary nodules on low-dose CT images. Med Phys. 2003;30:387–394
  13. MacKay DJC. Bayesian methods for adaptive models (PhD thesis from California Institute of Technology). 1992;Available online at: http://wol.ra.phy.cam.ac.uk/mackay/thesis.pdf
  14. Kupinski MA, Edwards DC, Giger ML, et al. Ideal observer approximation using Bayesian classification neural networks. IEEE Trans Med Imaging. 2001;20:886–899
  15. Kallergi M. Computer-aided diagnosis of mammographic microcalcification clusters. Med Phys. 2004;31:314–326
  16. Li H, Giger ML, Huo Z. Computerized analysis of mammographic parenchymal patterns for assessing breast cancer risk: effect of ROI size and location. Med Phys. 2004;31:549–555
  17. Sahiner B, Chan H-P, Roubidoux MA, et al. Computerized characterization of breast masses on three-dimensional ultrasound volumes. Med Phys. 2004;31:744–754
  18. Nakayama R, Uchiyama Y, Watanabe R, et al. Computer-aided diagnosis scheme for histological classification of clustered microcalcifications on magnification mammograms. Med Phys. 2004;31:789–799
  19. Nappi J, Frimmel H, Dachman AH, et al. Computerized detection of colorectal masses in CT colonography based on fuzzy merging and wall-thickening analysis. Med Phys. 2004;31:860–872
  20. Catarious D, Baydush AH, Floyd AE. Incorporation of an iterative, linear segmentation routine into a mammographic mass CAD system. Med Phys. 2004;31:1512–1520
  21. Iordanescu G, Summers RM. Reduction of false positives on the rectal tube in computer-aided detection for CT colonography. Med Phys. 2004;31:2855–2862
  22. Yin T-K, Chiu N-T. A computer-aided diagnosis for locating abnormalities in bone scintigraphy by a fuzzy system with a three step minimization approach. IEEE Trans Med Imag. 2004;23:639–654
  23. Paik DS, Beaulieu CF, Rubin GD, et al. Surface normal overlap: a computer-aided detection algorithm with application to colonic polyps and lung nodules in helical CT. IEEE Trans Med Imag. 2004;23:661–675
  24. Joo S, Yang YS, Moon WK, et al. Computer-aided diagnosis of solid breast nodules: use of an artificial neural network based on multiple sonographic features. IEEE Trans Med Imaging. 2004;23:1292–1300

1 This work was supported by USPHS grants CA62625, CA64370, and CA113820. Q. Li is a consultant to Riverain Medical Group, Miamisburg, OH. CAD technologies developed at the Kurt Rossmann Laboratories for Radiologic Image Research, the University of Chicago, have been licensed to companies including R2 Technologies, Riverain Medical Group, Deus Technologies, Median Technology, Mitsubishi Space Software Co., General Electric Corporation, and Toshiba Corporation. It is the policy of the University of Chicago that investigators disclose publicly actual or potential significant financial interests that may appear to be affected by research activities.

PII: S1076-6332(07)00241-3

doi: 10.1016/j.acra.2007.04.015

Academic Radiology
Volume 14, Issue 8 , Pages 985-991 , August 2007

Article Tools

* Image Usage & Resolution