Gastric cancer lymph node staining pathological image automatic identification method and system based on deep neural network

Abstract

The invention relates to a gastric cancer lymph node staining pathological image automatic recognition system based on a deep neural network, and the system comprises a first module which removes a background region of a slice image, and extracts a tissue region as a region of interest; a second module which is used for cutting the slice image into small imagesand inputting the small images into adeep neural network, wherein the deep neural network comprises a first unit, a second unit, a third unit, a fourth unit and a fifth unit, the first unit is used for calculating a tumor probability score of each small image; the second unit synthesizes a tumor thermodynamic diagram of the whole tissue slice image according to the tumor probability scores of the plurality of small images; the thirdunit binarizes the tumor thermodynamic diagram to generate a monochrome mask diagram, the fourth unit uses median filtering to remove false positive points, and the fifth unit is used for calculatingthe number of positive points in the whole mask graph. The system can automatically identify the slice image of the gastric cancer metastatic lymph node, and can improve the efficiency of the diagnosis process in histopathology.

Description

technical field [0001] The present invention relates to the field of deep neural networks, in particular to a deep neural network-based automatic recognition method for stained pathological images of gastric cancer lymph nodes, and also relates to an automatic recognition system for gastric cancer lymph node stained pathological images based on deep neural networks, and also relates to an electronic device , and also relates to a computer-readable storage medium. Background technique [0002] Gastric cancer is one of the most common malignant tumors in the world, with a poor prognosis and a serious threat to human health. According to the latest statistics from GLOBOCAN, in 2018, there were about 1.033 million new cases of gastric cancer worldwide, and about 783,000 deaths, ranking fifth in terms of incidence and second in mortality among malignant tumors. According to the latest cancer statistics in my country, there are about 679,000 new cases of gastric cancer each year,...

AI Technical Summary

Problems solved by technology

[0006] The present invention proposes an automatic identification method, system, electronic equipment, and computer-readable storage medium for gastric cancer lymph node staining pathological images based on a deep neural network, which can train a deep neural network to identify digital pathology, and solves the need for manual identification in the prior art The problem of identification in digital pathology

Images