Federated Learning for Lung Ultrasound Classification Across Age-Diverse Patient Populations
Affiliation Type:
Academia
Keywords:
LUS Patterns, Federated learning, demographic heterogeneity, Deep learning
Abstract:
Deep learning (DL) has rapidly advanced lung ultrasound (LUS) image classification. However, traditional DL uses centralized learning (CL) to train models, which requires large datasets for effective model training. While combining data across hospitals could provide sufficient samples, patient privacy considerations may complicate direct data sharing. To solve this problem, federated learning (FL) can be employed. FL enables multiple clients to collaborate without exposing patient data, allowing each client to train models locally and share only weights for central aggregation. Both FL and CL face challenges from demographic heterogeneity in LUS datasets, particularly between adult and neonatal populations. This study investigates for the first time whether FL maintains robustness across hospitals, compared with CL, for the specific case of LUS data with diverse age distribution.
