Improved chromosome classification using monotonic functions of mahalanobis distance and the transportation method

It is shown that the accuracy of chromosome classification constrained by class size can be improved over previously reported results by a combination of straightforward modifications to previously used methods. These are (i) the use of the logarithm of the Mahalanobis distance of an unknown chromosome's feature vector to estimated class mean vectors as the basis of the transportation method objective function, rather than the estimated likelihood; (ii) the use of all available features and full estimated covariance to compute the Mahalanobis distance, rather than a subset of features and the diagonal (variance) terms only; (iii) a modification to the way the transportation model deals with the constraint on the number of sex chromosomes in a metaphase cell; and (iv) the use of a newly discovered heuristic to weight off-diagonal elements of the covariance; this proved to be particularly valuable in cases where relatively few training examples were available to estimate covariance. The methods have been verified using 5 different sets of chromosome data.

[1]  R. E. Slot.  On the profit of taking into account the known number of objects per class in classification methods (Corresp.) , 1979, IEEE Trans. Inf. Theory.

[2]  M. Goodman.  Distance Analysis in Biology , 1972 .

[3]  E Granum,et al.  Automatically inferred Markov network models for classification of chromosomal band pattern structures. , 1990, Cytometry.

[4]  F. Rohlf.  PERSPECTIVES ON THE APPLICATION OF MULTIVARIATE STATISTICS TO TAXONOMY , 1971 .

[5]  Jim Graham,et al.  The transportation algorithm as an aid to chromosome classification , 1983, Pattern Recognit. Lett..

[6]  W. P. Sweeney,et al.  Classification of chromosomes using a probabilistic neural network. , 1994, Cytometry.

[7]  J D Habbema,et al.  Statistical methods for classification of human chromosomes. , 1979, Biometrics.

[8]  C. Theobald,et al.  Discrimination Using Covariance Selection Models in the Automated Allocation of Human Chromosomes , 1995 .

[9]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[10]  Jim Graham,et al.  An efficient transportation algorithm for automatic chromosome karyotyping , 1991, Pattern Recognit. Lett..

[11]  Erik Granum.  Application of Statistical and Syntactical Methods of Analysis and Classification to Chromosome Data , 1982 .

[12]  J. Piper,et al.  On fully automatic feature measurement for banded chromosome classification. , 1989, Cytometry.

[13]  J Piper,et al.  An automated system for karyotyping mouse chromosomes. , 1989, Cytogenetics and cell genetics.

[14]  Jim Piper.  The effect of zero feature correlation assumption on maximum likelihood based classification of chromosomes , 1987 .

[15]  A D Carothers,et al.  Some methods of combining class information in multivariate normal discrimination for the classification of human chromosomes. , 1991, Statistics in medicine.

[16]  F. Arrighi,et al.  Automated homologue matching of human G-banded chromosomes. , 1986, Computers in biology and medicine.

[17]  C Lundsteen,et al.  Automatic classification of chromosomes as part of a routine system for clinical analysis. , 1986, Cytometry.

[18]  L. Fahrmeir,et al.  Multivariate statistische Verfahren , 1984 .

[19]  R. Tibshirani,et al.  An introduction to the bootstrap , 1993 .

[20]  T. W. Anderson.  An Introduction to Multivariate Statistical Analysis, 2nd Edition. , 1985 .

[21]  J. Piper,et al.  The effect of digital image filtering on the performance of an automatic chromosome classifier , 1982 .

[22]  Iscn.  International System for Human Cytogenetic Nomenclature , 1978 .

[23]  Arnold W. M. Smeulders,et al.  Human chromosome classification based on local band descriptors , 1989, Pattern Recognit. Lett..

[24]  P A Errington,et al.  Application of artificial neural networks to chromosome classification. , 1993, Cytometry.

[25]  K. Paton.  Automatic chromosome identification by the maximum‐likelihood method , 1969, Annals of human genetics.

[26]  Jim Piper,et al.  Variability and bias in experimentally measured classifier error rates , 1992, Pattern Recognit. Lett..

[27]  Peter Kleinschmidt,et al.  A hybrid method for automatic chromosome karyotyping , 1994, Pattern Recognit. Lett..

[28]  E Granum,et al.  Visual classification of banded human chromosomes I. Karyotyping compared with classification of isolated chromosomes , 1976, Annals of human genetics.