One-Shot Federated Class-Incremental Learning for Medical Imaging via Variational Feature Transfer

FedAD: adaptive federated disentanglement for domain generalization in unlabeled medical imaging

Three barriers significantly hinder the use of deep learning in medical imaging: poor generalization to new clinical domain shifts, label scarcity, and data privacy. A unified framework that learns from unlabeled, decentralized data while optimizing for generalization is desperately needed, even if Federated Learning (FL), Self-Supervised Learning (SSL), and Domain Generalization (DG) provide partial solutions that often operate under contradictory assumptions. We present FedAD: Adaptive Federated Disentanglement, a unique framework that uses two key ideas to handle these problems in a synergistic way. First, a federated semantic disentanglement objective (FedSD) explicitly distinguishes between the domain-invariant semantic characteristics and domain-specific variants using a non-adversarial orthogonality constraint. Second, in order to prevent premature convergence and enhance resilience, an adaptive teacher-student alignment (ATSA) curriculum dynamically modifies the generalization pressure based on the stability of the global model. This dual technique creates a strong feature encoder by forcing the model to learn what it sees as opposed to where it sees it. FedAD outperforms current approaches in terms of generalization to unseen target domains, as demonstrated by its validation on publicly available medical datasets. Our strategy concurrently addresses privacy, label scarcity, and domain change, paving the road for useful, reliable, and fair medical AI.

STPFL: Stable teacher-guided personalized federated learning for heterogeneous multi-institution medical imaging

Multi-institutional medical imaging data are distributed across sites and cannot be pooled for centralized training due to privacy and governance constraints. Federated learning enables collaborative training without sharing raw data; however, under non-IID client distributions, it often faces unstable optimization and weak global-local knowledge transfer. Personalized federated learning mitigates this issue through client-specific adaptation, but many regularization-, meta-learning-, or distillation-based methods still degrade under highly skewed partitions. To address this, we propose STPFL, a stable teacher-guided personalized federated learning framework. STPFL builds an EMA-based aggregated teacher to accumulate historical global knowledge and provide consistent guidance. Each client optimizes a unified objective combining supervised learning with temperature-scaled KL distillation from the teacher model. On the server side, STPFL applies validation-driven performance weighting as a reliability signal and performs Adam-style aggregation to improve convergence under cross-silo/multi-institutional client distributions. We evaluate STPFL under controlled data heterogeneity (α = 0–1) and cross-silo client-count scalability (1–10 clients) on three benchmark datasets (PathMNIST, BloodMNIST, TissueMNIST) and three real-world medical imaging datasets (brain tumour MRI, blood cell cancer, and Kermany2018 OCT). Compared with FedAvg, FedProx, MetaFed, and FedLFP, STPFL achieves 4–23% and 6–29% improvements in global accuracy and F1-score, while personalized models improve by 4–25% and 4–32%, respectively. Under cross-silo client-count scalability, STPFL further improves global accuracy and F1-score by 5–30% and 5–40%, with corresponding personalized gains of up to 13–33% and 17–47%.

Fed-LoRA: Cross-Domain Generative Knowledge Feedback for Few-Shot Medical Anomaly Detection

Federated learning for medical image classification based on prototype alignment

Federated Learning with Global Model Hint for Medical Image Object Detection.

Building an ideal medical image object detection model often requires sufficient training data, which can be challenging to obtain in practical scenarios. Manual annotation is labor-intensive, and sharing datasets may raise data privacy concerns. Although federated learning can partially address these issues, we find an amplified feature drift problem when it is directly applied to medical image object detection. Motivated by the observation that the global model's parameters tend to align more closely with those of the oracle model than with those of the client models, we propose FedMHDet: Model Hint Federated Learning Detection Model, a novel federated learning detection framework. During the training phase, FedMHDet leverages multi-scale feature consistency as a global model hint to guide client models, thus mitigating the feature drift problem. Extensive experiments on pulmonary lesion and brain tumor detection tasks show that FedMHDet achieves favorable overall performance. Compared to the strongest baseline under each corresponding metric, it improves average AP by 1.05 and 0.19, and average sensitivity by 1.10 and 0.43 on the two tasks, respectively. We also provide in-depth analyses to support the practical use of our method. The code is available at https://github.com/bbamai/FedMHDet.

FedProIn: Mitigating Client Drift for Learnable Prototypes in Federated Medical Imaging

Federated learning (FL) is severely hindered by statistical heterogeneity due to variations in scanners, acquisition protocols, and patient populations. Such non-IID data induces client drift during local optimization, leading to unstable convergence and suboptimal global models when parameter-based aggregation is applied. We propose a prototype-based, influence-aware federated learning framework (FedProIn) that uses multiple learnable class prototypes to capture shared semantic structures across heterogeneous clients. We introduce feature divergence loss and prototype contrastive loss to mitigate client drift by decomposing it into feature drift and prototype drift. In addition, we propose a normalized influence aggregation strategy that adaptively weights client prototypes according to their contribution to the global representation, reducing the impact of biased or low-quality updates. Experimental results on two publicly available medical datasets, HAM10000 and Matek-19, demonstrate that FedProIn achieves accuracies of (83.5% IID, 81.1% non-IID) on HAM10000 and (96.2% IID, 95.8% non-IID) on Matek-19, respectively, outperforming existing baselines in both conditions. Our code is available at https://github.com/harsh-kmr/FedProIn.