Table 2 Brain tumour segmentation performance metrics for baseline and proposed models.
From: Enhanced brain tumour segmentation using a hybrid dual encoder–decoder model in federated learning
Model | Training setup | Dice coefficient | IoU score | Training time per round |
|---|---|---|---|---|
U-Net | Federated | 0.82 | 0.80 | 12 min |
UNet + + | Federated | 0.88 | 0.79 | 13 min |
ResUNet | Federated | 0.87 | 0.79 | 15 min |
Proposed Model (EfficientNet + Swin + BASNet + MaskFormer) | Federated | 0.94 | 0.87 | 17 min |
