The framework of the proposed denoising method. (IMAGE)
Caption
The author proposes Ves-GAN, a novel unsupervised vessel-targeted denoising framework based on the architecture of Cycle-GAN. Ves-GAN achieves global denoising of LDCTA images while selectively enhancing vascular features, maintaining structural consistency, and improving the CTA clinical diagnostic reliability.
Credit
Li Lab@NCUT.
Usage Restrictions
News organizations may use or redistribute this image, with proper attribution, as part of news coverage of this paper only.
License
Original content