This paper discusses the application of statistical pattern recognition techniques to problems in diagnostic ultrasound. Using our own system as an example, we describe the concepts and specific methods that we have applied to a problem involving the computer-aided classification of breast tissue in vivo. Topics include feature generation, feature selection and classification, as well as a method which estimates the probability of error on classifying future data. An accompanying paper applies these methods to the classification of backscattered RF signals from normal and diseased breast tissue.
FinetteS.BleierA.R.SwindellW.Breast tissue classification using diagnostic ultrasound and pattern recognition techniques: II. experimental results, Ultrasonic Imaging5, 71–86 (1983).
2.
GoodM.S.RoseJ.L.GoldbergB.B.Application of pattern recognition techniques to breast cancer detection: ultrasonic analysis of 100 pathologically confirmed tissue areas, Ultrasonic Imaging4, 378–396 (1982).
LerskiR.A.BarnettE.MorleyP.MillsP.R.WatkinsonG.MacSweenR.N.M.Computer analysis of ultrasonic signals in diffuse liver disease, Ultrasound Med. & Biol.5, 341–350 (1979).
5.
LerskiR.A.SmithM.J.MorleyP.BarnettE.MillsP.R.WatkinsonG.MacSweenR.N.M.Discriminant analysis of ultrasonic texture data in diffuse alcoholic liver disease. I. fatty liver and cirrhosis, Ultrasonic Imaging3, 164–172 (1981).
6.
PrestonK.Jr.CzerwinskiM.J.SkolnikM.L.LebD.E.Recent Developments in Obtaining Histopathological Information from Ultrasound Tissue Signatures, in Ultrasonic Tissue Characterization II, LinzerM., ed., NBS Spec. Publ. 525, pp. 303–313 (U.S. Government Printing Office, Washington, DC, 1979).
7.
ReinhardD.K.GiftD.A.HarrisG.I.De SostaC.J.Limitations of tissue differentiation by spectral measures of backscattered ultrasound, Ultrasonic Imaging3, 108–112 (1981).
8.
von SeelenW.GacaA.LockE.ScheidingW.WesselsG.Recognition of Patterns in Ultrasonic Sectional Pictures of the Prostate for Tumor Diagnosis, in Ultrasonic Tissue Characterization II, LinzerM., ed., NBS Spec. Publ. 525, pp. 297–302 (U.S. Government Printing Office, Washington, DC, 1979).
9.
JuleszB.Experiments in the visual perception of texture, Sci. Am.232, 39–43 (1975).
FoleyD.Considerations of sample and feature size, IEEE Trans. Inform. TheoryIT-18, 618–626 (1972).
13.
YoungT.Y.CalvertT.W.Classification, Estimation and Pattern Recognition (American Elsevier Publishing Co., New York, 1974).
14.
MeiselW.S.Computer-Oriented Approaches to Pattern Recognition (Academic Press, New York, 1972).
15.
ToussaintG.T.Bibliography on estimation of misclassification, IEEE Trans. Inform. Theory 1T-20, 472–479 (1974).
16.
HighleymanW.H.The design and analysis of pattern recognition experiments, Bell Syst. Tech. J.41, 723–744 (1962).
17.
ToussaintG.T.SharpeP.M.An efficient method for estimating the probability of misclassification applied to a problem in medical diagnosis, Comput. Biol. Med.4, 269–278 (1975).
18.
BartelsP.H.OlsonG.B.The Design and Analysis of Lymphocyte Images, in Methods of Cell Separation, Vol. 3, CatsimpoolasN., ed., pp. 1–99 (Plenum Press, New York, 1980).
19.
WalpoleR.E.MyersR.H.Probability and Statistics for Engineers and Scientists, 2nd ed. (MacMillan Publishing Co., New York, 1978).
20.
BartelsP.H.Numerical evaluation of cytologic data: III. selection of features for discrimination, Anal. Quant. Cytol.1, 153–159 (1979).
21.
GenchiH.MoriK.Evaluation and feature extraction on automated pattern recognition system, Denki Tsushin Gakkai Part1 (in Japanese), quoted in TanakaN.IkedaH.UenoT.WatanabeS.ImasatoY.KashidaR.Fundamental Study of an Automated Cytoscreening System Utilizing the Pattern Recognition System. I. Feature Evaluation in the Pattern Recognition System, in The Automation of Uterine Cancer Cytology, WiedG.L.BahrG.F.BartelsP.H., eds., pp. 223–227 (Tutorials of Cytology, Chicago, 1976).
22.
MetzC.E.Basic principles of ROC analysis, Seminars in Nucl. Med. VIII, 283–298 (1978).
23.
MucciardiA.N.GoseE.E.A comparison of seven techniques for choosing subsets of pattern recognition properties, IEEE Trans. Comput.C-20, 1023–1031 (1971).
24.
KleckaW.R.Discriminant Analysis, Series Quantitative Applications in the Social Sciences, SullivanJ.L., ed. (Sage Publications, Beverly Hills, CA, 1980).
25.
CooleyW.W.LohnesP.R.Multivariate Data Analysis (John Wiley and Sons, New York, 1971).
26.
LachenbruchP.A.Discriminant Analysis (Hafner Press, New York, 1975).
27.
SternsS.D.On Selecting Features for Pattern Classifiers, in Proc. Third Int. Joint Conf. Pattern Recognition, pp. 71–75 (IEEE Cat. No. 76CH 1140-3C, 1976).
