Personalized and privacy-preserving federated heterogeneous medical image analysis with PPPML-HMI

Abstract

Heterogeneous data is endemic due to the use of diverse models and settings of devices by hospitals in the field of medical imaging. However, there are few open-source frameworks for federated heterogeneous medical image analysis with personalization and privacy protection simultaneously without the demand to modify the existing model structures or to share any private data. In this paper, we proposed PPPML-HMI, an open-source learning paradigm for personalized and privacy-preserving federated heterogeneous medical image analysis. To our best knowledge, personalization and privacy protection were achieved simultaneously for the first time under the federated scenario by integrating the PerFedAvg algorithm and designing our novel cyclic secure aggregation with the homomorphic encryption algorithm. To show the utility of PPPML-HMI, we applied it to a simulated classification task namely the classification of healthy people and patients from the RAD-ChestCT Dataset, and one real-world segmentation task namely the segmentation of lung infections from COVID-19 CT scans. For the real-world task, PPPML-HMI achieved $\sim$5\% higher Dice score on average compared to conventional FL under the heterogeneous scenario. Meanwhile, we applied the improved deep leakage from gradients to simulate adversarial attacks and showed the solid privacy-preserving capability of PPPML-HMI. By applying PPPML-HMI to both tasks with different neural networks, a varied number of users, and sample sizes, we further demonstrated the strong robustness of PPPML-HMI.

References in corpus (24)

• The Future of Digital Health with Federated Learning
• An overview of deep learning in medical imaging focusing on MRI
• Federated Learning with Non-IID Data
• A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises
• Improving Federated Learning Personalization via Model Agnostic Meta Learning
• Personalized Federated Learning: A Meta-Learning Approach
• Adaptive Personalized Federated Learning
• Three Approaches for Personalization with Applications to Federated Learning
• FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation
• Agnostic Federated Learning
• Personalized Federated Learning with Moreau Envelopes
• Decentralized Federated Learning through Proxy Model Sharing
• Federated Learning: Opportunities and Challenges
• Peer-to-peer Federated Learning on Graphs
• Do Gradient Inversion Attacks Make Federated Learning Unsafe?
• Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes
• Lower Bounds and Optimal Algorithms for Personalized Federated Learning
• Central Server Free Federated Learning over Single-sided Trust Social Networks
• NVIDIA FLARE: Federated Learning from Simulation to Real-World
• SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks
• A Novel Attribute Reconstruction Attack in Federated Learning
• Sharing Models or Coresets: A Study based on Membership Inference Attack
• SAFE: Secure Aggregation with Failover and Encryption
• Model-Agnostic Federated Learning