UvA-DARE (Digital Academic Repository) A method for counting mitoses by image processing in Feulgen stained breast cancer sections

This study describes an image processing method for the assessment of the mitotic count in Feulgen-stained breast cancer sections. The segmentation procedure was optimized to eliminate 95-98% of the nonmitoses, whereas 11% of the mitoses did not survive the segmentation procedure. Contour features and optical density measurements of the remaining objects were computed to allow for classification. Twelve specimens were analyzed, nine used to serve as a training set, and three put aside for later use as independent test set. The fully automatic image processing method correctly classified 81% of the mitoses at the specimen level while inserting 30% false positives. The automatic procedure strongly correlated with the interactive counting procedure (r = 0.98). Although the fully automatic method provided satisfactory results, it is not yet suited for clinical practice. The automated method with an interactive evaluation step gave an accurate reflection of the mitotic count showing an almost perfect correlation with the results of the interactive morphometry (r = 0.998). Therefore this semiautomated method may be useful as prescreening device.

[1]  Fu Ys,et al.  DNA ploidy measurements in tissue sections. , 1985 .

[2]  Y. Collan,et al.  Volume corrected mitotic index (M/V-INDEX). The standard of mitotic activity in neoplasms. , 1989, Pathology, research and practice.

[3]  S. Silverberg,et al.  Reproducibility of the mitosis count in the histologic diagnosis of smooth muscle tumors of the uterus. , 1976, Human pathology.

[4]  A W Smeulders,et al.  Evaluation of automated estimation of epithelial volume and its prognostic value in ovarian tumors. , 1989, Laboratory investigation; a journal of technical methods and pathology.

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

[6]  J. Baak,et al.  Obtaining Quantitative Data , 1983 .

[7]  B H Mayall,et al.  Characterization of chromatin distribution in cell nuclei. , 1986, Cytometry.

[8]  R. Kempson,et al.  Mitosis counting—II , 1976 .

[9]  A W Smeulders,et al.  Quantification of epithelial volume by image processing applied to ovarian tumors. , 1987, Cytometry.

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

[11]  K. Donhuijsen,et al.  Mitosis counts: reproducibility and significance in grading of malignancy. , 1986, Human pathology.

[12]  C Busch,et al.  Differential staining of mitoses in tissue sections and cultured cells by a modified methenamine-silver method. , 1988, Laboratory investigation; a journal of technical methods and pathology.

[13]  P S Ellis,et al.  Mitosis counting--a need for reappraisal. , 1981, Human pathology.

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

[15]  G. Sterrett,et al.  Feulgen DNA cytophotometry in histologic sections of mammary neoplasms. , 1984, Analytical and quantitative cytology.

[16]  V. Budach,et al.  Changes in mitotic rate and cell cycle fractions caused by delayed fixation. , 1990, Human pathology.

[17]  Pesce Cm.  Defining and interpreting diseases through morphometry. , 1987 .

[18]  A. Smeulders,et al.  Image processing for mitoses in sections of breast cancer: a feasibility study. , 1984, Cytometry.

[19]  Bidyut Baran Chaudhuri,et al.  Characterization and featuring of histological section images , 1988, Pattern Recognit. Lett..

[20]  D Ellis,et al.  Hypocomplementemic idiopathic membranous glomerulopathy. , 1981, Human pathology.

[21]  T. W. Ridler,et al.  Picture thresholding using an iterative selection method. , 1978 .

[22]  J. Peterse,et al.  Reproducibility of mitosis counting in 2,469 breast cancer specimens: results from the Multicenter Morphometric Mammary Carcinoma Project. , 1992, Human pathology.

[23]  J. Baak,et al.  Mitosis counting in tumors. , 1990, Human pathology.

[24]  Arnold W. M. Smeulders,et al.  SCILAIM: A multi-level interactive image processing environment , 1990, Pattern Recognit. Lett..

[25]  C Sowter,et al.  Morphometry of bladder carcinoma: I. The automatic delineation of urothelial nuclei in tissue sections using an ibas II image array processor , 1987, The Journal of pathology.

[26]  T L Hall,et al.  DNA ploidy measurements in tissue sections. , 1985, Analytical and quantitative cytology and histology.

[27]  J. Baak,et al.  The value of morphometry to classic prognosticators in breast cancer , 1985, Cancer.

[28]  P H Bartels,et al.  Image analysis in quantitative cytopathology and histopathology. , 1989, Human pathology.

[29]  H. Levin,et al.  Mitosis counting in seminoma: an exercise of questionable significance. , 1988, Human pathology.

[30]  C. Cornelisse,et al.  DNA image cytometry on machine-selected breast cancer cells and a comparison between flow cytometry and scanning cytophotometry. , 1985, Cytometry.

[31]  A W Smeulders,et al.  Quantification of epithelial area by image processing applied to endometrial carcinomas: a comparison with ovarian tumors. , 1989, Human pathology.

[32]  C M Pesce.  Defining and interpreting diseases through morphometry. , 1987, Laboratory investigation; a journal of technical methods and pathology.

[33]  M. Bond,et al.  The significance of mitotic rate: a retrospective study of 127 thyroid carcinomas. , 1985, Human pathology.