Skip to main content
. Author manuscript; available in PMC: 2021 Oct 20.
Published in final edited form as: IEEE Int Conf Comput Vis Workshops. 2020 Mar 5;2019:10.1109/iccvw.2019.00043. doi: 10.1109/iccvw.2019.00043

Table 3.

Joint learning results. Results of joint learning models and comparison with fully-supervised U-Net models on each modality.

Method CT tested DSC MR tested DSC
CT trained U-Net 0.901 (0.020) 0.260 (0.072)
MR trained U-Net 0.134 (0.091) 0.869 (0.044)
CT&MR trained U-Net 0.835 (0.035) 0.590 (0.098)
Joint CT&MR CycleGAN 0.870 (0.023) 0.846 (0.048)
Joint CT&MR TD-GAN 0.880 (0.018) 0.863 (0.029)
Joint CT&MR DADR 0.912 (0.012) 0.891 (0.040)
Joint CT&MR DALACE 0.911 (0.013) 0.907 (0.049)