IE-CycleGAN: improved cycle consistent adversarial network for unpaired PET image enhancement.
Jianan CuiYi LuoDonghe ChenKuangyu ShiXinhui SuHuafeng LiuPublished in: European journal of nuclear medicine and molecular imaging (2024)
The proposed unpaired PET image enhancement method outperforms NLM, BM3D, and DIP. Moreover, it performs better than the Unet (supervised) and CycleGAN (supervised) when implemented on local hospital datasets, which demonstrates its excellent generalization ability.