English(EN) Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration

联邦学习框架FedHD对齐WSI特征以实现协同病理学

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-01 11:25

研究人员推出FedHD，一个新颖的联邦学习框架，专为协同数字病理学设计。该框架通过对齐高斯混合特征，解决了机构间不同架构和特征提取器带来的挑战。FedHD不共享模型参数，而是生成全切片图像（WSIs）的合成特征表示，然后使用基于课程的策略将其整合到本地训练中。 AI

影响引入了一种新颖的医学影像联邦学习方法，有望改善机构间的协同研究和诊断。

排序理由该集群包含一篇详细介绍数字病理学新颖联邦学习框架的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Luru Jing, Cong Cong, Yanyuan Chen, Yongzhi Cao · 2026-05-04 04:00

Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration

arXiv:2605.00578v1 Announce Type: new Abstract: Federated learning (FL) offers a promising framework for collaborative digital pathology by enabling model training across institutions. However, real-world deployments face heterogeneity arising from diverse multiple instance learn…
arXiv cs.CV TIER_1 English(EN) · Yongzhi Cao · 2026-05-01 11:25

Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration

Federated learning (FL) offers a promising framework for collaborative digital pathology by enabling model training across institutions. However, real-world deployments face heterogeneity arising from diverse multiple instance learning (MIL) architectures and heterogeneous featur…