CycleSGAN: A cycle-consistent and semantics-preserving generative adversarial network for unpaired MR-to-CT image synthesis

Runze Wang, Alexander F. Heimann, Moritz Tannast, Guoyan Zheng

Abstract: Highlights•CycleSGAN features a novel and generic way to incorporate semantic information into CycleGAN.•CycleSGAN is a semantics-preserving image synthesis network.•Comprehensive evaluation on two hip datasets.