FedWSIDD: Federated Whole Slide Image Classification via Dataset Distillation

2025/06/18 by Huaizhi Jin, Shenglin Liu, Jin, Haolong +11
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image Processing and 3D Reconstruction #Image and Video Processing (eess.IV) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2506.15365

openalex publication_date 2025/06/18 · openalex created_date 2025/10/19 · openalex updated_date 2026/07/28

Abstract

Federated learning (FL) has emerged as a promising approach for collaborative medical image analysis, enabling multiple institutions to build robust predictive models while preserving sensitive patient data. In the context of Whole Slide Image (WSI) classification, FL faces significant challenges, including heterogeneous computational resources across participating medical institutes and privacy concerns. To address these challenges, we propose FedWSIDD, a novel FL paradigm that leverages dataset distillation (DD) to learn and transmit synthetic slides. On the server side, FedWSIDD aggregates synthetic slides from participating centres and distributes them across all centres. On the client side, we introduce a novel DD algorithm tailored to histopathology datasets which incorporates stain normalisation into the distillation process to generate a compact set of highly informative synthetic slides. These synthetic slides, rather than model parameters, are transmitted to the server. After communication, the received synthetic slides are combined with original slides for local tasks. Extensive experiments on multiple WSI classification tasks, including CAMELYON16 and CAMELYON17, demonstrate that FedWSIDD offers flexibility for heterogeneous local models, enhances local WSI classification performance, and preserves patient privacy. This makes it a highly effective solution for complex WSI classification tasks. The code is available at FedWSIDD.

Citations

• Dataset Distillation for Histopathology Image Classification
• Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchors
• FedImpro: Measuring and Improving Client Update in Federated Learning
• Unlocking the Potential of Federated Learning: The Symphony of Dataset Distillation via Deep Generative Latents
• Accelerating Dataset Distillation via Model Augmentation
• Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments
• FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning
• Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning
• Dataset Distillation by Matching Training Trajectories
• Federated Learning Based on Dynamic Regularization
• FedProto: Federated Prototype Learning across Heterogeneous Clients
• Model-Contrastive Federated Learning
• Federated Learning for Computational Pathology on Gigapixel Whole Slide\n Images
• Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images
• From Detection of Individual Metastases to Classification of Lymph Node Status at the Patient Level: The CAMELYON17 Challenge
• Dataset Distillation
• Deep Residual Learning for Image Recognition

Related

• Federated Distillation for Medical Image Classification: Towards Trustworthy Computer-Aided Diagnosis
• Federated Learning for Computational Pathology on Gigapixel Whole Slide\n Images
• Image Distillation for Safe Data Sharing in Histopathology
• FedDropoutAvg: Generalizable federated learning for histopathology image classification
• A New One-Shot Federated Learning Framework for Medical Imaging Classification with Feature-Guided Rectified Flow and Knowledge Distillation