Towards Privacy-Preserving Medical Imaging: Federated Learning with Differential Privacy and Secure Aggregation Using a Modified ResNet Architecture

TL;DR

This paper presents a federated learning framework with differential privacy and secure aggregation, using a modified ResNet architecture, to enable privacy-preserving medical image classification across hospitals.

Contribution

It introduces DPResNet and combines differential privacy with secure multi-party computation for federated medical imaging, improving privacy without sacrificing accuracy.

Findings

Achieves accuracy close to non-private models

Outperforms traditional privacy-preserving methods

Demonstrates effectiveness on BloodMNIST dataset

Abstract

With increasing concerns over privacy in healthcare, especially for sensitive medical data, this research introduces a federated learning framework that combines local differential privacy and secure aggregation using Secure Multi-Party Computation for medical image classification. Further, we propose DPResNet, a modified ResNet architecture optimized for differential privacy. Leveraging the BloodMNIST benchmark dataset, we simulate a realistic data-sharing environment across different hospitals, addressing the distinct privacy challenges posed by federated healthcare data. Experimental results indicate that our privacy-preserving federated model achieves accuracy levels close to non-private models, surpassing traditional approaches while maintaining strict data confidentiality. By enhancing the privacy, efficiency, and reliability of healthcare data management, our approach offers substantial benefits to patients, healthcare providers, and the broader healthcare ecosystem.