Addressing data heterogeneity in distributed medical imaging with heterosync learning

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.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2025-10-24
DOI
https://doi.org/10.1038/s41467-025-64459-y
Citations
2
Primary Topic
AI in cancer detection
Type
article
Field-Weighted Citation Impact
4.96

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Addressing data heterogeneity in distributed medical imaging with heterosync learning

Muyan Cai, Wenjuan Tong, Li‐Da Chen, Ming Kuang et al.
2 citations
Nature Communications
AI in cancer detection
4.96
article

Addressing data heterogeneity in distributed medical imaging with heterosync learning

Muyan Cai, Wenjuan Tong, Li‐Da Chen, Ming Kuang, Shaohong Wu, Jinbo Hu, Xin-Xin Lin, Qinghua Huang, Feng Ye, Wei-Ping Ke, Hong Yang, Haibo Wang, Wei Wang, Ming-De Lu, Guangjian Liu, Shuai Liu, Ming‐De Li
article en
2 citations

Abstract

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.

Nature CommunicationsVol. 16(1)
Minzu University of China (CN), Sun Yat-sen University (CN), Guangxi Medical University (CN), Northwestern Polytechnical University (CN), Sixth Affiliated Hospital of Sun Yat-sen University (CN), First Affiliated Hospital of GuangXi Medical University (CN), The First Affiliated Hospital, Sun Yat-sen University (CN), Northwestern Polytechnic University (US)
National Natural Science Foundation of China
Openalex Percentile: Top 4%
AI in cancer detection
4.96
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.