Brain tumor segmentation data enhancement method based on generative adversarial network

Abstract

The invention relates to the technical field of brain tumor image processing, and specifically discloses a brain tumor segmentation data enhancement method based on a generative adversarial network. According to the method, an image-to-image conversion framework-Tumor GAN network architecture (comprising a generator, a global discriminator and a local discriminator) is constructed; n2-n virtual image pairs can be synthesized from n real data pairs (a multi-modal brain tumor picture set with segmentation tags), and a data enhancement model is obtained through training, so that the quality and authenticity of an image synthesized by the data enhancement model are ensured; on the basis of an attention region provided by a semantic tag, a region perception loss function and a region loss function are added in a generator, training of an image with authenticity to an image translation model is assisted, image details can be reserved, and the generalization performance of the model is improved; by applying the local discriminator to be used in cooperation with the global discriminator, the discrimination efficiency can be improved, and the model is helped to generate a medical image pairwith more real texture details.

Description

technical field [0001] The invention relates to the technical field of brain tumor image processing, in particular to a brain tumor segmentation data enhancement method based on a generative adversarial network. Background technique [0002] Brain tumor is a common nervous system disease. In China, as a common high-incidence disease, its incidence rate has reached 1.34 / 100,000. In the United States, more than 200,000 patients are diagnosed with primary or metastatic disease every year. brain tumors. In the incidence of systemic tumors, the incidence of brain tumors is second only to tumors in the stomach, uterus, breast, and esophagus, accounting for about 2% of systemic tumors, and the death rate has exceeded 2%. According to the survey, brain tumors account for the highest proportion of children, followed by young adults aged 20-50, among which the number of glioma patients is the largest. Among childhood malignancies, the incidence of brain tumors ranks second, after le...

AI Technical Summary

Problems solved by technology

[0007] The invention provides a brain tumor segmentation data enhancement method based on a generative confrontation network, which solves the technical problem that the existing brain tumor image segmentation enhancement method cannot obtain pixel-level real medical images

Images