Image processing for mitoses in sections of breast cancer: a feasibility study.

This paper describes an image analysis technique for the counting of nuclei in mitosis in tissue sections. Five experienced pathologists scored mitoses in photographs of preselected areas of tissue sections of the breast. Objects consistently labelled as mitotic cells by all five pathologists were considered "mitoses" in the analysis. In total, there were 45 mitotic nuclei, 68 possible mitotic nuclei and 1,172 nonmitotic nuclei. The image analysis procedure was designed to give priority to a low false negative rate, i.e., misclassification of mitoses. The procedure consists of three steps: 1. Segmentation of the image. 2. Reduction of the number of nonmitotic nuclei by using feature values based on the brightness histogram of the objects. 3. Fully automatic classification of the remaining objects using contour features. The objects remaining after the first two steps were visualized in a composite display for interactive evaluation: 10% of the mitotic nuclei were missed, and 85% of the nonmitotic nuclei were eliminated. The result of the fully automatic procedure described in this paper is rather disappointing and gave a loss of 37% of the mitoses while 5% of the nonmitotic nuclei remained.

[1]  I. Young,et al.  Morphologic changes in rat urothelial cells during carcinogenesis: II. Image cytometry. , 1984, Cytometry.

[2]  M. Boon,et al.  Prognostic indicators in breast cancer‐morphometric methods , 1982, Histopathology.

[3]  Johan S. Ploem,et al.  The Use of LEYTAS in Analytical and Quantitative Cytology , 1982, IEEE Transactions on Biomedical Engineering.

[4]  Fixation induced variations in quantitative nuclear image features in sections. , 1981, Acta histochemica.

[5]  B Stenkvist,et al.  Correlation between cytometric features and mitotic frequency in human breast carcinoma. , 1981, Cytometry.

[6]  G. P. Vooys,et al.  Field test results using the BioPEPR cervical smear prescreening system. , 1980, Cytometry.

[7]  Jack Perkins,et al.  Pattern recognition in practice , 1980 .

[8]  N. Tanaka,et al.  Field test and experimental use of CYBEST model 2 for practical gynecologic mass screening. , 1979, Analytical and quantitative cytology.

[9]  J P Baak,et al.  Quantitative nuclear image analysis: differentiation between normal, hyperplastic, and malignant appearing uterine glands in a paraffin section. IV. The use of Markov chain texture features in discriminant analysis. , 1978, European journal of obstetrics, gynecology, and reproductive biology.

[10]  Jean Serra,et al.  “One, Two, Three,... Infinity” , 1978 .

[11]  J. F. Brenner,et al.  Two graph searching techniques for boundary finding in white blood cell images. , 1978, Computers in biology and medicine.

[12]  A. Gibbs,et al.  Histological discrimination of malignancy in mucinous ovarian tumours , 1977, Histopathology.

[13]  Bowie Je,et al.  An analysis technique for biological shape-III. , 1977 .

[14]  Henry J. Norris,et al.  Mitosis counting—III , 1976 .

[15]  K. R. Castleman,et al.  An Automated System for Chromosome Analysis , 1976 .

[16]  Azriel Rosenfeld,et al.  Digital Picture Processing , 1976 .

[17]  P. Bartels,et al.  Modeling of histologic images by computer. , 1976, Acta cytologica.

[18]  Ian T. Young,et al.  An Analysis Technique for Biological Shape. I , 1974, Inf. Control..

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

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