Tumor area capillary segmentation method and device

Abstract

The invention relates to a tumor area capillary segmentation method and device. The method comprises the following steps: acquiring an image block containing a tumor area and microvessels; and inputting the image block into a tumor area microvessel segmentation model to obtain a prediction probability graph of the tumor area and the microvessels, wherein the prediction probability graph comprises a capillary region, a tumor region and a background region, and the tumor area capillary segmentation model comprises two convolution layers with preset scales, a plurality of dense connection blocks and a sigmoid activation module. By adopting the method, the accuracy of tumor area capillary segmentation can be improved.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular to a method and device for segmenting microvessels in tumor regions. Background technique [0002] With the development of image processing technology, automatic recognition and segmentation of target objects through image processing has been applied to various industries. In medical clinical diagnosis, pathologists need to manually segment the microvessels in the tumor area of ​​the breast CD34-stained digital pathological section, and then perform quantitative analysis on the morphological characteristics of each microvessel, and finally classify the patients according to the quantitative analysis results diagnosis. [0003] The existing microvessel segmentation methods in the tumor region of breast CD34 images can often roughly segment the microvessels in the slice. However, these methods are often not accurate enough for the segmentation of microvessels in t...

AI Technical Summary

Problems solved by technology

However, these methods are often not accurate enough for the segmentation of microvessels in tumor regions because the microvessel segmentation in tumor regions has smaller surface features compared with tissue regions, and tumor regions are not easy to observe.

Incorrect positioning of the tumor area can easily result in the segmentation of microvessels outside the tumor area, coupled with inaccurate microvessel boundary segmentation, which will affect the final morphological information statistics and cancer grade diagnosis

Images