Skip to main content
. Author manuscript; available in PMC: 2021 Oct 1.
Published in final edited form as: Med Image Anal. 2020 Jul 18;65:101785. doi: 10.1016/j.media.2020.101785

Table 1.

Training parameters in Tumor-CIFAR and CT datasets

Initial Learning Rate Decreased Epochs Decreased Ratio Max Epoch Optimizer Weight Decay
0.01 [50, 70, 80] 0.4 100 Adam 0

3D RPN and 3DDLNN are the CNNs borrowed from Liao et al. (Liao et al., 2019) to extract scan-level feature.