Scholarlink

<p>Collaborative learning across medical institutions is essential for building robust and generalisable digital pathology models. Federated learning (FL) enables collaboration without centralising data, yet its adoption is limited by high communication costs, model heterogeneity, and privacy concerns. We propose Federated Deep Feature Prompting (FedDFP), an efficient FL framework tailored for heterogeneous clinical environments. FedDFP introduces lightweight, client-specific learnable prompts applied to patch-level embeddings from whole-slide images. By sharing only these compact prompts, FedDFP reduces communication overhead by over 99.9% compared to standard FL while improving classification accuracy. Extensive experiments on TCGA-IDH, CAMELYON16 and CAMELYON17 show that FedDFP consistently outperforms standard and personalised FL baselines, achieving mean AUC gains of 0.11–0.13 over local-only training and up to 0.10 over the strongest federated methods. FedDFP also converges 2–4× faster and remains effective across diverse feature extractors and multiple-instance learning architectures, demonstrating scalability, flexibility and privacy-aware collaboration.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Flexible and scalable federated learning with deep feature prompts for digital pathology

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月14日

查看全文
  • Cong Cong,
  • Yang Song,
  • Antonio Di Ieva,
  • Angela Chou,
  • Anthony J. Gill,
  • Enrico Coiera,
  • Sidong Liu

摘要

Collaborative learning across medical institutions is essential for building robust and generalisable digital pathology models. Federated learning (FL) enables collaboration without centralising data, yet its adoption is limited by high communication costs, model heterogeneity, and privacy concerns. We propose Federated Deep Feature Prompting (FedDFP), an efficient FL framework tailored for heterogeneous clinical environments. FedDFP introduces lightweight, client-specific learnable prompts applied to patch-level embeddings from whole-slide images. By sharing only these compact prompts, FedDFP reduces communication overhead by over 99.9% compared to standard FL while improving classification accuracy. Extensive experiments on TCGA-IDH, CAMELYON16 and CAMELYON17 show that FedDFP consistently outperforms standard and personalised FL baselines, achieving mean AUC gains of 0.11–0.13 over local-only training and up to 0.10 over the strongest federated methods. FedDFP also converges 2–4× faster and remains effective across diverse feature extractors and multiple-instance learning architectures, demonstrating scalability, flexibility and privacy-aware collaboration.