Table 1 Federated training hyperparameters for all models.
From: Enhanced brain tumour segmentation using a hybrid dual encoder–decoder model in federated learning
Hyperparameter | U-Net | UNet + + | ResUNet | Proposed model |
|---|---|---|---|---|
Number of clients (M) | 5 | 5 | 5 | 5 |
Rounds (R) | 30 | 30 | 30 | 20 |
Local epochs (LE) | 5 | 5 | 5 | 5 |
Batch size | 8 | 8 | 8 | 8 |
Optimizer | Adam | Adam | Adam | Adam |
Learning rate (LR) | 0.001 | 0.001 | 0.001 | 0.001 |
Loss function | Dice + BCE | Dice + BCE | Dice + BCE | Dice + BCE + attention-based refinement |
Differential privacy | ✗ | ✗ | ✓ | ✓ |
Secure aggregation | ✗ | ✗ | ✓ | ✓ |
