Medical Image Segmentation On 2018 Data
Métriques
Dice
Precision
Recall
mIoU
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Dice | Precision | Recall | mIoU |
|---|---|---|---|---|
| msrf-net-a-multi-scale-residual-fusion | 0.9224 | 0.9022 | 0.9402 | 0.8534 |
| emcad-efficient-multi-scale-convolutional | 0.9274 | - | - | - |
| trans2unet-neural-fusion-for-nuclei-semantic | 0.9225 | - | - | 0.8614 |
| unet-a-nested-u-net-architecture-for-medical | 0.8974 | - | - | 0.9255 |
| fanet-a-feedback-attention-network-for | 0.9176 | 0.9194 | 0.9222 | 0.8569 |
| doubleu-net-a-deep-convolutional-neural | 0.9133 | 0.9596 | 0.6407 | 0.8407 |
| dcsau-net-a-deeper-and-more-compact-split | - | - | 0.9240 | 0.8501 |
| stepwise-feature-fusion-local-guides-global | 0.9230 | - | - | 0.8614 |
| duat-dual-aggregation-transformer-network-for | 0.926 | - | - | 0.870 |