cs.LGNov 10, 2026

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

Authors: Moon-Il Joo, Md Ariful Islam Mozumder, Hee-Cheol Kim

Organizations: Institute of Digital Anti-Aging Healthcare, Inje University, Republic of Korea · College of AI & Computer Engineering, Inje University, Republic of Korea

Abstract

Classification of lung adenocarcinoma into poorly differentiated (PD) and well-to-moderately differentiated (WMD) subtypes plays an important role in patient survival; however, consistent classification is difficult due to inter-observer variability among pathologists. Collecting data from multiple hospitals is also challenging due to patient privacy concerns. This study proposes a web-based federated learning system that shares only locally trained model weights without sharing patient data between institutions. The UNI2 foundation model and CLAM-SB were used to classify pathological whole slide images. A four-client federated learning system was constructed, and the NLST cohort was reserved exclusively for external validation. In centralized evaluation, joint training with CPTAC and TCGA outperformed single-institution training on external validation, confirming the necessity of multi-institutional data integration. FedAvg, FedProx, FedBN, and FedNova were compared as federated learning algorithms under identical experimental conditions. Test AUC ranked as FedBN, FedProx, FedNova, and FedAvg. FedNova showed the most balanced classification performance between PD and WMD. L1-norm structural pruning at 20%, 30%, and 40% sparsity was applied to reduce model transmission size. FedAvg, FedProx, and FedBN showed a tendency of decreasing Test AUC under pruning, while FedNova achieved improved Test AUC across all sparsity levels. A web-based application was developed supporting slide upload, local training, AI classification, and attention heatmap-based visualization. The combination of FedNova and 40% pruning was confirmed as a practical approach that improves communication efficiency and classification performance while protecting patient privacy.

Explore similar work

CardsList
  1. FedHisto-PAST: Parameter-Efficient Stain-Aware Federated Learning for Cross-Site Lung Histopathology Classification

    Sep 25, 2026Muhammad Muhtasim Shahriar, M. M. Golam Hafiz, Saad Aloteibi +1Histopathology Image ClassificationFederated Learning

  2. FedDRAW: Federated Dual Reputation Annealing Weighting for Heterogeneous Multi-Institutional Chest Radiograph Classification

    Sep 4, 2026Maryam Moradpour, Anne-Christin HauschildFederated Learning AggregationHeterogeneous Federated Learning

  3. Federated Survival Analysis in Healthcare: A Multi-Model Evaluation on Cross-Institutional Heterogeneous Breast Cancer Data

    Jun 22, 2026Natalia Moreno-Blasco, Anusha Ihalapathirana, Pekka Siirtola +1Cancer Survival PredictionSurvival Analysis