Lesion Segmentation On Isic 2018
評価指標
mean Dice
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | mean Dice |
|---|---|
| doubleu-net-a-deep-convolutional-neural | 0.8962 |
| promise-promptable-medical-image-segmentation | 0.921 |
| bi-directional-convlstm-u-net-with-densley | 0.847 |
| msrf-net-a-multi-scale-residual-fusion | 0.8813 |
| inconsistency-masks-removing-the-uncertainty | 0.85 |
| a-novel-focal-tversky-loss-function-with | 0.829 |
| a-novel-focal-tversky-loss-function-with | 0.806 |
| mobileunetr-a-lightweight-end-to-end-hybrid | 0.9074 |
| exploring-dual-attention-mechanism-with-multi | 0.9152 |
| multi-level-context-gating-of-embedded | 0.895 |
| bi-directional-convlstm-u-net-with-densley | - |
| training-on-polar-image-transformations | 0.9253 |
| a-novel-focal-tversky-loss-function-with | 0.856 |
| dermosegdiff-a-boundary-aware-segmentation | 0.9005 |
| duat-dual-aggregation-transformer-network-for | 0.923 |
| boundary-aware-transformers-for-skin-lesion | 0.912 |