SAM-Fed: SAM-Guided Federated Semi-Supervised Learning for Medical Image Segmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918208149127168 |
|---|---|
| author | Nasirihaghighi, Sahar Ghamsarian, Negin Li, Yiping Breeuwer, Marcel Sznitman, Raphael Schoeffmann, Klaus |
| author_facet | Nasirihaghighi, Sahar Ghamsarian, Negin Li, Yiping Breeuwer, Marcel Sznitman, Raphael Schoeffmann, Klaus |
| contents | Medical image segmentation is clinically important, yet data privacy and the cost of expert annotation limit the availability of labeled data. Federated semi-supervised learning (FSSL) offers a solution but faces two challenges: pseudo-label reliability depends on the strength of local models, and client devices often require compact or heterogeneous architectures due to limited computational resources. These constraints reduce the quality and stability of pseudo-labels, while large models, though more accurate, cannot be trained or used for routine inference on client devices. We propose SAM-Fed, a federated semi-supervised framework that leverages a high-capacity segmentation foundation model to guide lightweight clients during training. SAM-Fed combines dual knowledge distillation with an adaptive agreement mechanism to refine pixel-level supervision. Experiments on skin lesion and polyp segmentation across homogeneous and heterogeneous settings show that SAM-Fed consistently outperforms state-of-the-art FSSL methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_14302 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SAM-Fed: SAM-Guided Federated Semi-Supervised Learning for Medical Image Segmentation Nasirihaghighi, Sahar Ghamsarian, Negin Li, Yiping Breeuwer, Marcel Sznitman, Raphael Schoeffmann, Klaus Computer Vision and Pattern Recognition Artificial Intelligence Medical image segmentation is clinically important, yet data privacy and the cost of expert annotation limit the availability of labeled data. Federated semi-supervised learning (FSSL) offers a solution but faces two challenges: pseudo-label reliability depends on the strength of local models, and client devices often require compact or heterogeneous architectures due to limited computational resources. These constraints reduce the quality and stability of pseudo-labels, while large models, though more accurate, cannot be trained or used for routine inference on client devices. We propose SAM-Fed, a federated semi-supervised framework that leverages a high-capacity segmentation foundation model to guide lightweight clients during training. SAM-Fed combines dual knowledge distillation with an adaptive agreement mechanism to refine pixel-level supervision. Experiments on skin lesion and polyp segmentation across homogeneous and heterogeneous settings show that SAM-Fed consistently outperforms state-of-the-art FSSL methods. |
| title | SAM-Fed: SAM-Guided Federated Semi-Supervised Learning for Medical Image Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.14302 |