An Asynchronous Federated Learning Platform for Lung Adenocarcinoma Grading via Foundation Models and Structural Pruning

A web-based federated learning system was proposed to classify lung adenocarcinoma into poorly differentiated (PD) and well-to-moderately differentiated (WMD) subtypes. The system shares only locally trained model weights without sharing patient data between institutions. Joint training with CPTAC and TCGA outperformed single-institution training on external validation.