Mammary glandular cell segmentation method based on multi-scale growth and double-strategy adhesion-removing model

Abstract

The invention discloses a mammary glandular cell segmentation method based on a multi-scale growth and double-strategy adhesion-removing model. The method comprises the following steps: firstly, inputting a mammary glandular tissue image and converting the image into a gray image; secondly, enhancing the contrast ratio; thirdly, carrying out cell positioning by using wavelet decomposition; fourthly, carrying out multi-scale region growth; fifthly, realizing primary segmentation of a cell region through voting and selecting; sixthly, judging whether the segmented region has cell adhesion or not; if the cell adhesion does not exist, determining that the segmented region is a single cell region, and outputting a segmentation result; if the cell adhesion exists, determining that the segmented region is an adhesion region, and carrying out adherent cell segmentation; and finally, carrying out adherent cell segmentation by using the double-strategy adhesion-removing model constructed by morphological corrosion-expansion operation and a corner detection segmentation algorithm until all the cells are segmented. By virtue of the method, the influences on mammary glandular cell segmentation, caused by a complicated background of a mammary glandular tissue slice image, are effectively inhibited; and the identification precision of an adherent cell segmentation line is improved and the segmentation precision of the adherent cells is further improved.

Description

technical field [0001] The invention relates to image processing technology, in particular to a breast cell segmentation method based on a multi-scale growth and dual-strategy de-adhesion model. Background technique [0002] According to the data of the International Agency for Research on Cancer (Iarc), breast cancer has become the most common malignant tumor in women, and its morbidity and mortality both occupy the first place in women's diseases. It is very difficult to cure breast cancer, and realizing its early diagnosis is the key means to improve the curative effect. Currently, the only way to diagnose breast cancer is through pathological analysis of microscopic images of tissue sections. The traditional way of manual pathological analysis has strong subjectivity. In order to improve the objectivity of diagnosis, computer-aided analysis of microscopic images of breast tissue sections is the current development trend. [0003] Accurate segmentation is an important ...

AI Technical Summary

Problems solved by technology

In foreign related research, the most widely used segmentation method is based on the morphological watershed algorithm, which has achieved certain results in the segmentation of adherent cells in mammary gland cells. However, these algorithm studies usually have more misplaced positioning and cannot effectively separate adherent cells.

The study found that the main reason for the low segmentation accuracy of existing algorithms is that the influence of complex backgrounds is not completely suppressed when extracting cell regions, and the segmentation line is not obtained accurately when separating cohesive overlapping cells.

Images