Unsupervised domain adaptation system and method based on generative adversarial network

Abstract

The invention discloses an unsupervised domain adaptation system and method based on a generative adversarial network, and a storage medium. The system comprises a feature extraction module used for extracting high-dimensional feature maps of a first sample and a second sample that are slice images with different dyeing styles, a dimension reduction module used for performing dimension reduction on the high-dimensional feature maps of the first sample and the second sample to convert the high-dimensional feature maps into low-dimensional feature maps, a discriminator used for receiving the low-dimensional feature maps of the first sample and the second sample, and enabling the low-dimensional feature maps output by the dimension reduction module to have consistency through adversarial training, a dimension raising module used for raising the dimensions of the low-dimensional feature maps of the first sample and the second sample to regenerate high-dimensional feature maps of the firstsample and the second sample, and a classification module used for receiving the regenerated high-dimensional feature maps of the first sample and the second sample and outputting an image analysis result. The system has good analysis capability for slice images with different dyeing styles.

Description

technical field [0001] The invention belongs to the technical field of medical cytopathological image analysis, and more specifically relates to an unsupervised domain adaptation system, method and storage medium based on a generative confrontation network. Background technique [0002] In recent years, artificial intelligence technology has developed rapidly, and the combination of artificial intelligence and medical care can alleviate the problem of shortage of doctor resources. In the field of medical cytopathology, the accumulation of a large amount of pathological slice data provides a big data background for the analysis of medical cytopathological images. In the processing of large data samples, because the analysis and processing capabilities of deep learning algorithms are generally stronger than other traditional analysis algorithms, depth Learning is widely used in the field of big data medical cytopathology image analysis. [0003] Using deep learning to analyze...

AI Technical Summary

Problems solved by technology

Although the generalization ability of the model can be improved to a certain extent only through data enhancement, no

Images