A weighted feature transfer gan for medical image synthesis

Recent studies have shown that CycleGAN is a highly influential medical image synthesis model. However, the lack of sufficient constraints and the bottleneck layer in auto-encoder network usually lead to blurry image and meaningless features, which may affect medical judgment. In order to synthesize accurate and meaningful medical images, weighted feature transfer GAN (WFT-GAN) is proposed to improve the quality of generated medical image, which is applied to the synthesis of unpaired multi-modal data. WFT-GAN adopts weighted feature transfer (WFT) instead of traditional skip connection to reduce the interference of encoding information on image decoding, while retaining the advantage of skip connection to the information transmission of the generated image. Moreover, the local perceptual adversarial loss combines the VGG feature map and adversarial model to make the local features of the image more meaningful. Experiments in three data sets show that the method in this paper can synthesize higher-quality medical images.

Automated summary

Recent research introduces a new medical image synthesis model, WFT-GAN, which improves the quality of generated medical images by adopting weighted feature transfer and local perceptual adversarial loss. This approach aims to avoid the negative impact of blurry and meaningless features on medical judgment, and has shown promising results in synthesizing higher-quality medical images across three different datasets.