Computer analysis of cervical cells. Automatic feature extraction and classification.

A prescreening instrument for cervical smears using computerized image processing and pattern recognition techniques requires that single cells in the specimen can be automatically isolated and analyzed. This paper describes a dual wavelength method for automatic isolation of the cytoplasm and nuclei of cells. Density-oriented, shape-oriented and texture-oriented parameters were calculated and evaluated for more than 600 cells. It is shown that the computer can be taught to distinguish between normal and atypical cells with an accuracy of ca. 97%, while human classification reproducibility is ca. 95%. In addition, an attempt to assign a measure of atypia to individual cells is described.

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

[2]  Gösta H. Granlund,et al.  Fourier Preprocessing for Hand Print Character Recognition , 1972, IEEE Transactions on Computers.

[3]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[4]  The occurrence of isolated dysplastic and carcinoma in situ type cells in cervical smears from patients with dysplasia and carcinoma in situ: significance to prescreening using image processing techniques. , 1973, Acta cytologica.

[5]  P. Bartels,et al.  PERFORMANCE TESTING FOR AUTOMATED PRESCREENING DEVICES IN CERVICAL CYTOLOGY , 1974, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[6]  P H Bartels,et al.  Implementation of a hierarchical cell classification procedure. , 1974, Acta cytologica.

[7]  J. Taylor,et al.  Development and evaluation of automatic nucleus finding routines: thresholding of cervical cytology images. , 1975, Acta cytologica.

[8]  B. Stenkvist,et al.  Classification of cells in vaginal smears with television microscopy , 1976, Virchows Archiv. B, Cell pathology.

[9]  J. Taylor,et al.  Cytoplasmic and nuclear shape analysis for computerized cell recognition. , 1976, Acta cytologica.

[10]  J. Holmquist,et al.  Analysis of grey-level histograms as a method of classifying cells from the uterine cervix. , 1976, Computers in biology and medicine.

[11]  N. J. Pressman.  Markovian analysis of cervical cell images. , 1976, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[12]  A. Miller,et al.  Mortality from cancer of the uterus in canada and its relationship to screening for cancer of the cervix , 1976, International journal of cancer.

[13]  J. Holmquist,et al.  A microspectrophotometric study of Papanicolaou-stained cervical cells as an aid in computerized image processing. , 1976, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[14]  B Stenkvist,et al.  A software system to record and analyze digitized cell images. , 1977, Computer programs in biomedicine.