Hsieh, Yu HsingYu HsingHsiehLi, Jia DaJia DaLiLee, Yao ChihYao ChihLeeCHU-SONG CHENWu, Li FuLi FuWuCheng, Skye H.Skye H.Cheng2023-10-062023-10-062023-01-019798350339840https://scholars.lib.ntu.edu.tw/handle/123456789/635955Metal artifacts (MA) reduction is crucial for clinical application yet often lacks paired training data. Learning MA reduction from unpaired data and enforcing fidelity seems a trade-off. The study proposed an improved contrastive unpaired translation solution to address the issues and demonstrate its efficacy.constrastive learning | CT | metal artifacts reduction | negative learningconference paper10.1109/CAI54212.2023.001522-s2.0-85168678322https://api.elsevier.com/content/abstract/scopus_id/85168678322