Skin Lesion Segmentation on University of Waterloo skin cancer database
| Rank | Model | Dice Score | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | DTP-Net | 0.884 ±0.100 | DTP-Net: A convolutional neural network model to predict threshold for localizing the lesions on dermatological macro-images | VipinBioLab/DTP-Net | 2022 |
| 2 | DeepLabV3+ | 0.883 ±0.108 | |||
| 3 | FCN-8s | 0.870 ±0.063 | |||
| 4 | SegNet | 0.854 ±0.088 | |||
| 5 | U-Net | 0.836 ±0.132 | |||
| 6 | DTP-Net | 0.884 ±0.100 | DTP-Net: A convolutional neural network model to predict threshold for localizing the lesions on dermatological macro-images | VipinBioLab/DTP-Net | 2022 |
| 7 | DeepLabV3+ | 0.883 ±0.108 | |||
| 8 | FCN-8s | 0.870 ±0.063 | |||
| 9 | SegNet | 0.854 ±0.088 | |||
| 10 | U-Net | 0.836 ±0.132 |