Estimation of the performance of an array-processor oriented system for automatic Pap smear analysis.

The rapid progress in computer technology makes possible the automatic analysis of thousands of cells on a slide in the field of automatic uterine cancer cytology. Our approach starts with the high-resolution scanning of visually selected and classified single cells determining the training set for discriminant analysis. On the basis of more than 15 morphologic and textural features measured, correct classification results of 95% are reached. Our aim is to speed up our image processing system by means of an Array-Processor, the model AP 120 B from Floating Point Systems. In this study a realistic time estimation of the scanning, segmentation, feature extraction and classification of about 40,000 cells on a slide is performed.

[1]  P.H. Bartels,et al.  Computer analysis and biomedical interpretation of microscopic images: Current problems and future directions , 1977, Proceedings of the IEEE.

[2]  F. Meyer.  Iterative image transformations for an automatic screening of cervical smears. , 1979, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[3]  A M van Driel-Kulker,et al.  Automated analysis of cervical specimens using the T.A.S. , 1980, Microscopica acta. Supplement.

[4]  W Abmayr,et al.  Progress report of the TUDAB project for automated cancer cell detection. , 1979, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[5]  R Nawrath,et al.  Quantitative image analysis: applications using sequential transformations. , 1979, Microscopica acta.

[6]  W. Abmayr,et al.  A thresholding method for automatic cell image segmentation. , 1979, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[7]  J. E. Green.  Rapid analysis of hematology image data: the ADC-500 preprocessor. , 1979, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[8]  J. Ploem,et al.  Acriflavine-Feulgen stilbene staining: a procedure for automated cervical cytology with a television based system (LEYTAS). , 1979, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[9]  F Meyer,et al.  Automatic screening of Papanicolaou stained cervical smears with the T. A. S. , 1980, Microscopica acta. Supplement.

[10]  P Schwarzmann,et al.  Structure analysis and classification of cervical cells using a processing system based on TV. , 1979, Analytical and quantitative cytology.