Skip to main content
. 2021 Feb 22;38(3):749–762. doi: 10.1007/s00371-021-02075-9

Table 7.

Performance comparison of the proposed network and the state-of-the-art methods on ISIC 2018 dataset

Method F1-score Sensitivity Specificity Accuracy AUC
Unet 85.07 80.65 96.44 91.95 88.54
R2U-Net 84.90 78.47 97.46 92.06 87.97
Attention Unet 84.97 79.57 96.93 91.99 88.25
BCDU 85.44 83.56 95.21 91.89 89.39
Unet++ 87.86 83.35 97.46 93.45 90.41
DeeplabV3+ 85.85 80.28 97.32 92.47 88.80
Ours 86.27 86.28 94.54 92.19 90.41

Bold values indicate the best result of each metric