We introduce Federated Medical Data Augmentation with Differential Privacy for Medical Assistance(FMDADP-MA),addressing the challenge of limited medical data sharing due to privacy regulations and data isolations.Unli...We introduce Federated Medical Data Augmentation with Differential Privacy for Medical Assistance(FMDADP-MA),addressing the challenge of limited medical data sharing due to privacy regulations and data isolations.Unlike traditional Generative adversarial networks assuming Independent and Identically Distributed(IID)data,FMDADP-MA facilitates data augmentation in non-IID environments using federated learning.This framework enables medical institutions collaboration across different locations to enrich datasets without centralizing data,overcoming collection and computational constraints.By organizing edge nodes and selecting groups for global training,we minimize data transmission to a central server.Each local model uses two convolutional neural networks to generate and label data,incorporating local differential privacy to safeguard against gradient-based privacy breaches.Our experiments show that increasing participant institutions enhances the global model’s accuracy,boosts local model performance,and diversifies data generation,tackling real-world issues of medical data privacy,imbalance,and under-labeling.展开更多
基金supported by the National Key R&D Program(No.2024YFB3310202)the Key R&D Program of Jilin Province(No.20250201076GX).
文摘We introduce Federated Medical Data Augmentation with Differential Privacy for Medical Assistance(FMDADP-MA),addressing the challenge of limited medical data sharing due to privacy regulations and data isolations.Unlike traditional Generative adversarial networks assuming Independent and Identically Distributed(IID)data,FMDADP-MA facilitates data augmentation in non-IID environments using federated learning.This framework enables medical institutions collaboration across different locations to enrich datasets without centralizing data,overcoming collection and computational constraints.By organizing edge nodes and selecting groups for global training,we minimize data transmission to a central server.Each local model uses two convolutional neural networks to generate and label data,incorporating local differential privacy to safeguard against gradient-based privacy breaches.Our experiments show that increasing participant institutions enhances the global model’s accuracy,boosts local model performance,and diversifies data generation,tackling real-world issues of medical data privacy,imbalance,and under-labeling.
