Federated deep multiple instance learning for histopathological whole-slide image classification

Yumeng Wang

doi:10.1016/j.bspc.2025.109059

Federated deep multiple instance learning for histopathological whole-slide image classification

2025-11-13

0

PRE

AI

DOI：10.1016/j.bspc.2025.109059

Original

Original request for help

Save

Abstract

En 中文

• Federated deep MIL is developed for histopathology WSI classification. • A dynamic weight aggregation scheme is designed to solve the heterogeneity issue. • Multi-scale attention-based MIL is used for weakly-supervised learning on clients. • We evaluated our FedDMIL on the two popular and publicly available WSI datasets.

Federated deep multiple instance learning for histopathological whole-slide image classification

Abstract

Journal

Organization