Fig. 1From: A 4D-CBCT correction network based on contrastive learning for dose calculation in lung cancerArchitecture and module details of the CLCGAN network: a illustrates the overall architecture of CLCGAN; and b showcases the detailed principle of contrastive learning, where (b−1) and (b−2) show the internal diagrams of the generator and discriminator, respectivelyBack to article page