FedAD: Adaptive Federated Disentanglement is presented, a unique framework that uses two key ideas to handle problems in a synergistic way in terms of generalization to unseen target domains, and outperforms current approaches in terms of generalization to unseen target domains.
Abstract
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.
A novel class-incremental continual learning model for a one-shot FL paradigm, in which each task introduces new classes, clients observe heterogeneous and evolving class distributions, and communication with the server occurs only once, substantially mitigates catastrophic forgetting while consistently enhancing recognition of newly introduced classes.
Pedro H. Barros, Omid Orang, Giulia Zanon de Castro et al.· 0 citations
STPFL builds an EMA-based aggregated teacher to accumulate historical global knowledge and provide consistent guidance and improves global accuracy and F1-score, while personalized models improve by 4–25% and 4–32%, respectively.
R. Semwal, Imlimaong Aier, P. Varadwaj· Intelligent Data Analysis· 0 citations
The qualitative and quantitative evaluations of the generated explanations verify that the Fed-XAI framework identifies genuine pathological biomarkers rather than exploiting spurious domain-specific artifacts, thereby establishing a verifiable foundation of trust for clinical decision support systems.
Kulathunga D. D. T. K.· International Journal of Com...· 0 citations
Deep learning in medical imaging is severely hindered by the "domain gap," where significant imaging discrepancies exist even among images of the same modality and anatomical structure due to heterogeneous scanning devices and diverse clinical environments. While major medical centers possess high-fidelity data, resource-constrained clinics often struggle with legacy hardware and severe data scarcity. This imbalance leads to a significant collapse in diagnostic performance and poor model generalization when deployed in low-resource settings. To address these challenges, we propose a novel few-shot Federated Low-Rank Adaptation (Fed-LoRA) framework for cross-domain generative feedback. By leveraging the lightweight nature of LoRA, our method enables the efficient transmission of global pathological priors from a high-resource Hub to decentralized Edge nodes with minimal communication overhead. Crucially, this mechanism facilitates cross-domain data generation while ensuring privacy by precluding the transmission of raw medical data. This allows local models to synthesize high-fidelity abnormal exemplars precisely tailored to specific institutional styles. Extensive experiments demonstrate that our synthetic images significantly enhance the performance of downstream anomaly detection tasks. This work provides a scalable and secure solution for mitigating data scarcity and achieving effective cross-domain adaptation in decentralized healthcare systems.
Federated learning enables medical-imaging models to be trained across hospitals, and privacy law, most explicitly the GDPR ``right to be forgotten'', turns removing a hospital's, a class's, or a patient's influence from such a model into a federated unlearning problem. This need is most acute in medicine, where patients withdraw consent and hospitals leave collaborations. Yet nearly all unlearning evidence comes from natural images, whose heterogeneity and task structure differ sharply from clinical data, so it is unclear whether existing methods transfer, and no shared protocol covers clinical data. We present Lethe, a benchmark for federated unlearning in medical imaging. It evaluates twelve methods across eight task families, from classification and segmentation to denoising, cross-modality synthesis, and vision-language question answering, at three forgetting granularities and against a retrained gold standard on utility, privacy, and cost. The central result is that what separates methods is the difficulty of the forgetting request, not the method itself. The easy removals that dominate the literature leave the methods that preserve utility indistinguishable, while only hard ones separate them. More striking, on the many medical tasks that generalize across sites, forgetting a client barely changes task performance, leaving residual membership as the signal that must be erased.
Shengchao Chen, Ting Shu· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
