Automatic screening system and automatic screening method using thin-prep cytology test

Abstract

The invention discloses an automatic screening system and an automatic screening method using a thin-prep cytology test. The system comprises an image acquisition module, an image segmentation module, a target recognition module and a comprehensive analysis module. The method provided by the invention respectively adopts a three-point evolutionary uniform sampling method to guarantee the reliability of automatic focusing, the coarse-to-fine segmentation algorithm to improve the segmentation accuracy of pathological cell nucleuses, a series of filters to rapidly filter various impurities, and a cascade classifier training method to greatly reduce the false positive rate, and uses relative features to conduct comprehensive analysis. The method disclosed by the invention has the advantages of high sensitivity over pathological cells, high specificity over normal cells, high recognition speed and high automation degree, so that the diagnostic accuracy can be improved and the workload of a cytopathologist is reduced at the same time.

Description

technical field [0001] The invention relates to cytopathology, image processing and pattern recognition, in particular to an automatic screening method and system for diseased cells in cervical liquid-based smears. Background technique [0002] Cervical cancer is the most threatening malignant tumor disease for women. Worldwide, nearly 250,000 people die from cervical cancer each year. With the development of cervical cancer screening methods, in 1996, the US FDA approved an improved cytology sample preparation technology - thin-layer liquid-based cytology. Compared with the traditional Pap smear method, this method can evenly distribute the cells on the glass slide, which improves the sensitivity of detecting low-grade and high-grade lesions. It has been reported in the literature that thin-layer liquid-based cytology can detect 92.9% of high-grade lesions And 100% tumor cancer, compared with 77.8% and 90.9% of traditional smears, there is a significant difference. On th...

AI Technical Summary

Problems solved by technology

[0003] Although thin-layer liquid-based technology has reduced the phenomenon of a large number of overlapping cells in traditional smears, due to the complexity of actual images, there are still many difficulties in the automatic identification of diseased cells in cervical liquid-based smears, which are often overlooked by traditional methods. These problems: nuclei overlap or touch each other; nuclei vary in shape and size (normal nuclei in some people are larger than diseased nuclei in others); nuclei, especially diseased nuclei, stain unevenly (this often results in under-segmentation, increasing the probability of false negatives); the contrast between the nucleus and its background is altered due to uneven illumination or cytoplasmic stacking; stacking of impurities (eg, inflammatory cells, cell debris) may exhibit features resembling diseased nuclei

Images