Table 9 Results of proposed methodology trained and tested on combined dataset.The results presented in this table are resulted from the models trained on combined dataset.
From: Melanoma segmentation using deep learning with test-time augmentations and conditional random fields
Method | Dice | Jaccard | Precision | Recall |
|---|---|---|---|---|
Trained and tested on combined dataset | ||||
UNet | 87.26 | 84.60 | 89.18 | 86.10 |
ResUNet | 83.59 | 81.07 | 84.61 | 85.06 |
ResUNet++ | 83.73 | 85.44 | 86.11 | 93.85 |
Trained on the combined dataset and tested on the ISIC-2016 dataset | ||||
UNet | 93.74 | 89.59 | 95.03 | 90.21 |
ResUNet | 90.70 | 86.64 | 91.38 | 89.31 |
ResUNet++ | 92.71 | 90.02 | 94.34 | 92.19 |
Trained on the combined dataset and tested on the ISIC-2017 dataset | ||||
UNet | 83.74 | 80.65 | 85.00 | 85.15 |
ResUNet | 79.83 | 77.89 | 81.33 | 83.37 |
ResUNet++ | 82.43 | 80.73 | 86.37 | 87.01 |
