Parametric and Nonparametric Recognition by Computer: An Application to Leukocyte Image Processing

Publisher Summary Automation of the acquisition and interpretation of data in microscopy has been a focus in biomedical research for over a decade. In spite of many serious attempts, mechanical perception of microscopic fields with a reliability and cost-benefit ratio that would inspire routine clinical application is not yet a reality. Nevertheless, it is also no longer a speculation. Many facets of the problem of automating cell image analysis are within the grasp of present technology. Available histochemical techniques make it possible to prepare cytological material so that morphological integrity is preserved, key cell constituents are stained differentially, and, if desired, stoichiometrically, and specimens are favorably dispersed for viewing. Scanning microscopes have the requisite sensitivity, resolution, and stability to sample such objects, and make photometric measurements over a wide range of magnifications and wavelengths. Computer-managed microscanners with selective attention and controlled illumination, wavelength, magnification, focus, and stage motion are actively under development. Current generation information-processing facilities permit the rapid manipulation of the hitherto unmanageable quantities of optical information resident in all but the simplest microscopic images. However, the impact of very recent advances in high-speed digital circuitry, electro-optics, and hybrid digital-analog flow/scanning systems on our ability to implement algorithmic approaches to biomedical picture-processing efficiently is yet to be felt, and will likely turn feasibility into practicality. The automatic discrimination of human leukocytes or white blood cells has probably commanded more interdisciplinary effort and skill than any other biological picture-processing problem, perhaps with the exception of chromosome karyotyping. In the process, computer discrimination of leukocytes has become a classic example of the successful application of computer “pattern detection and recognition” to natural imagery and uncontrived scientific problems. The present chapter discusses the evolution and elaboration of these ideas, and subsequent advances in leukocyte discrimination by computer.

[1]  Herbert Freeman,et al.  On the Encoding of Arbitrary Geometric Configurations , 1961, IRE Trans. Electron. Comput..

[2]  R. Fisher THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[3]  M. R. Mickey,et al.  Estimation of Error Rates in Discriminant Analysis , 1968 .

[4]  J. G. Hoffman,et al.  FLYING SPOT METHODS FOR MEASURING DNA AND THE NUCLEOCYTOPLASMIC VOLUME RATIO IN TISSUE CELLS * , 1962, Annals of the New York Academy of Sciences.

[5]  Walter E. Tolles,et al.  SIZE AND SHAPE DETERMINATION IN SCANNING MISCROSCOPY , 1962 .

[6]  G. Box,et al.  A general distribution theory for a class of likelihood criteria. , 1949, Biometrika.

[7]  E. G. Diacumakos,et al.  EXFOLIATED CELL STUDIES AND THE CYTOANALYZER * , 1962, Annals of the New York Academy of Sciences.

[8]  L E Lipkin,et al.  THE ANALYSIS, SYNTHESIS, AND DESCRIPTION OF BIOLOGICAL IMAGES , 1966, Annals of the New York Academy of Sciences.

[9]  L EINARSON,et al.  On the theory of gallocyanin-chromalum staining and its application for quantitative estimation of basophilia; a selective staining of exquisite progressivity. , 2009, Acta pathologica et microbiologica Scandinavica.

[10]  Deitch Ad Microspectrophotometric study of the binding of the anionic dye, naphthol yellow S, by tissue sections and by purified proteins. , 1955 .

[11]  Kendall Preston,et al.  ADVANTAGES OF TOPOLOGY AS A BASIS FOR AUTOMATIC ANALYSIS OF BLOOD CELL IMAGES * , 1969 .

[12]  G. F. Hughes,et al.  On the mean accuracy of statistical pattern recognizers , 1968, IEEE Trans. Inf. Theory.

[13]  N. E. Day Linear and quadratic discrimination in pattern recognition (Corresp.) , 1969, IEEE Trans. Inf. Theory.

[14]  Gary Lotto,et al.  On the Generation of All Possible Stepwise Combinations , 1962 .

[15]  King-Sun Fu,et al.  On the generalized Karhunen-Loeve expansion (Corresp.) , 1967, IEEE Trans. Inf. Theory.

[16]  C. K. Chow,et al.  An optimum character recognition system using decision functions , 1957, IRE Trans. Electron. Comput..

[17]  O. J. Dunn,et al.  Probabilities of Correct Classification in Discriminant Analysis , 1966 .

[18]  Katsuji Kato,et al.  Leucocytes in infancy and childhood , 1935 .

[19]  S. S. Wilks CERTAIN GENERALIZATIONS IN THE ANALYSIS OF VARIANCE , 1932 .

[20]  King-Sun Fu,et al.  Selection and Ordering of Feature Observations in a Pattern Recognition System , 1968, Inf. Control..

[21]  R. Fisher THE STATISTICAL UTILIZATION OF MULTIPLE MEASUREMENTS , 1938 .

[22]  R. C. Bostrom,et al.  Performance of the cytoanalyzer in recent clinical trials. , 1962, Journal of the National Cancer Institute.

[23]  A. Wald On a Statistical Problem Arising in the Classification of an Individual into One of Two Groups , 1944 .

[24]  Philip M. Lewis,et al.  The characteristic selection problem in recognition systems , 1962, IRE Trans. Inf. Theory.

[25]  W. Tolles SECTION OF BIOLOGY: THE CYTOANALYZER—AN EXAMPLE OF PHYSICS IN MEDICAL RESEARCH* , 1955 .

[26]  J. T. Chu,et al.  Error Probability in Decision Functions for Character Recognition , 1967, JACM.

[27]  Azriel Rosenfeld,et al.  Sequential Operations in Digital Picture Processing , 1966, JACM.

[28]  H. P. Mansberg,et al.  COUNTING OF NEURONS BY FLYING SPOT MICROSCOPE * , 1962, Annals of the New York Academy of Sciences.

[29]  K PRESTON,et al.  IMPORTANCE OF AUTOMATIC PATTERN RECOGNITION TECHNIQUES IN THE EARLY DETECTION OF ALTERED BLOOD‐CELL PRODUCTION * , 1964, Annals of the New York Academy of Sciences.

[30]  A. Bøyum SEPARATION OF WHITE BLOOD CELLS. , 1964 .

[31]  G. Hughes,et al.  Number of pattern classifier design samples per class (Corresp.) , 1969, IEEE Trans. Inf. Theory.

[32]  J. Prewitt,et al.  A versatile clustering algorithm with objective function and objective measure. , 1972, Computer programs in biomedicine.

[33]  O. J. Dunn,et al.  Elimination of variates in linear discrimination problems. , 1966, Biometrics.

[34]  M. S. Bartlett,et al.  The vector representation of a sample , 1934, Mathematical Proceedings of the Cambridge Philosophical Society.

[35]  R. Bechhofer Multiple Comparisons with a Control for Multiply-Classified Variances of Normal Populations* , 1968 .

[36]  J M PREWITT,et al.  THE SELECTION OF SAMPLING RATE FOR DIGITAL SCANNING. , 1965, IEEE transactions on bio-medical engineering.

[37]  H M Shapiro,et al.  Spectre II: general-purpose microscope input for a computer. , 1969, Science.

[38]  Richard Y. Kain The mean accuracy of pattern recognizers with many pattern classes (Corresp.) , 1969, IEEE Trans. Inf. Theory.

[39]  P. Hsu,et al.  Notes on Hotelling's Generalized $T$ , 1938 .

[40]  T. W. Anderson Classification by multivariate analysis , 1951 .

[41]  J. M.S Prewitt,et al.  Pictorial Data Processing Methods In Microscopy , 1966, Other Conferences.

[42]  T. Caspersson,et al.  SCANNING MICROSCOPY TECHNIQUES FOR HIGH RESOLUTION QUANTITATIVE CYTOCHEMISTRY , 1962, Annals of the New York Academy of Sciences.

[43]  Kari Karhunen,et al.  Über lineare Methoden in der Wahrscheinlichkeitsrechnung , 1947 .

[44]  W J HORVATH,et al.  A study of the quantitative characteristics of exfoliated cells from the female genital tract. I. Measurement methods and results , 1961, Cancer.

[45]  R. V. Mises,et al.  On the Classification of Observation Data into Distinct Groups , 1945 .

[46]  W. G. Cochran,et al.  Some Classification Problems with Multivariate Qualitative Data , 1961 .

[47]  William J. Schull,et al.  On the robustness of the T02 test in multivariate analysis of variance when variance-covariance matrices are not equal , 1964 .

[48]  J. H. Ward Hierarchical Grouping to Optimize an Objective Function , 1963 .

[49]  K PRESTON,et al.  MACHINE TECHNIQUES FOR AUTOMATIC LEUKOCYTE PATTERN ANALYSIS * , 1962, Annals of the New York Academy of Sciences.

[50]  B. Chandrasekaran,et al.  Comments on "On the mean accuracy of statistical pattern recognizers" by Hughes, G. F , 1969, IEEE Trans. Inf. Theory.

[51]  P. Mahalanobis On the generalized distance in statistics , 1936 .

[52]  J. Lukomski On Some Properties of Multidimensional Distributions , 1939 .

[53]  W. Tolles,et al.  Instrumentation for Automatically Prescreening Cytological Smears , 1959, Proceedings of the IRE.

[54]  B. Chandrasekaran,et al.  On dimensionality and sample size in statistical pattern classification , 1971, Pattern Recognit..

[55]  W. G. Cochran On the Performance of the Linear Discriminant Function , 1964 .

[56]  B. L. Welch ii) Note on Discriminant Functions , 1939 .

[57]  M L Mendelsohn,et al.  THE ANALYSIS OF CELL IMAGES * , 1966, Annals of the New York Academy of Sciences.

[58]  Thomas Marill,et al.  On the effectiveness of receptors in recognition systems , 1963, IEEE Trans. Inf. Theory.

[59]  M. Ingram,et al.  Automatic analysis of blood cells. , 1970, Scientific American.

[60]  H Elias,et al.  Three-Dimensional Structure Identified from Single Sections , 1971, Science.

[61]  L. A. Kamentsky,et al.  RAPID MULTIPLE MASS CONSTITUENT ANALYSIS OF BIOLOGICAL CELLS , 1969 .

[62]  W. Tolles,et al.  Applications and methods of counting and sizing in medicine and biology , 1962 .

[63]  W. Gaffey Discriminatory Analysis - Perfect Discrimination as the Number of Variables Increases , 1951 .

[64]  R. Albrecht,et al.  Error analysis of a statistical decision method , 1964, IEEE Trans. Inf. Theory.

[65]  W. H. Highleyman,et al.  The design and analysis of pattern recognition experiments , 1962 .

[66]  Norman M. Abramson,et al.  Learning to recognize patterns in a random environment , 1962, IRE Trans. Inf. Theory.

[67]  C. R. Rao,et al.  The Utilization of Multiple Measurements in Problems of Biological Classification , 1948 .

[68]  J. T. Chu Optimal Decision Functions for Computer Character Recognition , 1965, JACM.

[69]  Kendall Preston,et al.  Feature Extraction by Golay Hexagonal Pattern Transforms , 1971, IEEE Transactions on Computers.

[70]  L. Kamentsky,et al.  Spectrophotometer: New Instrument for Ultrarapid Cell Analysis , 1965, Science.

[71]  M. Bartlett Further aspects of the theory of multiple regression , 1938, Mathematical Proceedings of the Cambridge Philosophical Society.

[72]  W. W. Bledsoe,et al.  Some Results on Multicategory Pattern Recognition , 1966, J. ACM.

[73]  S. John Errors in Discrimination , 1961 .

[74]  J. Elashoff,et al.  On the choice of variables in classification problems with dichotomous variables. , 1967, Biometrika.