SAM-Fed: SAM-Guided Federated Semi-Supervised Learning for Medical Image Segmentation
This addresses data privacy and annotation cost issues in medical imaging for healthcare applications, but it is incremental as it builds on existing federated and semi-supervised learning approaches.
The paper tackled the problem of improving pseudo-label reliability and handling computational constraints in federated semi-supervised learning for medical image segmentation by proposing SAM-Fed, which uses a segmentation foundation model to guide lightweight clients, resulting in consistent outperformance over state-of-the-art methods in experiments on skin lesion and polyp segmentation.
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.