Addressing data heterogeneity in distributed medical imaging with heterosync learning
Hang-Tong Hu, Ming‐De Li, Xin-Xin Lin, Meng-Yao Cai, Shuai Liu, Shaohong Wu, Wenjuan Tong, Feng-Yu Ye, Jinbo Hu, Wei-Ping Ke, Li‐Da Chen, Hong Bo Yang, Guang-Jian Liu, Haibo Wang, Ming-De Lu, Qinghua Huang, Ming Kuang, Wei Wang · Nature Communications · 2025
Data heterogeneity critically limits distributed artificial intelligence (AI) in medical imaging. We propose HeteroSync Learning (HSL), a privacy-preserving framework that addresses heterogeneity through: (1) Shared Anchor Task (SAT) for cross-node representation alignment, and (2) an Auxiliary Learning Architecture coordinating SAT with local primary tasks. Validated via large-scale simulations (feature/label/quantity/combined heterogeneity) and a real-world multi-center thyroid cancer study, HSL outperforms local learning, 12 benchmark methods (FedAvg, FedProx, SplitAVG, FedRCL, FedCOME, etc.), and foundation models (e.g., CLIP) by better stability and up to 40% in area under the curve (AUC), matching central learning performance. HSL achieves 0.846 AUC on the out-of-distribution pediatric thyroid cancer data (outperforming others by 5.1-28.2%), demonstrating superior generalization. Visualizations confirm HSL successfully homogenizes heterogeneous distributions. This work provides an effective solution for distributed medical AI, enabling equitable collaboration across institutions and advancing healthcare AI democratization. Data heterogeneity presents a challenge in distributed artificial intelligence (AI) for medical imaging across diverse clinical settings. Here, the authors develop HeteroSync Learning, a privacy-preserving distributed learning framework that mitigates data heterogeneity and outperforms classical, state-of-the-art, and foundation models.