The utilisation of artificial intelligence in medicine and healthcare has led to successful clinical applications in several domains. The conflict between data usage and privacy protection requirements in such systems must be resolved for optimal results as well as ethical and legal compliance. This calls for innovative solutions such as privacy-preserving machine learning (PPML). We present PriMIA (Privacy-preserving Medical Image Analysis), a software framework designed for PPML in medical imaging. In a real-life case study we demonstrate significantly better classification performance of a securely aggregated federated learning model compared to human experts on unseen datasets. Furthermore, we show an inference-as-a-service scenario for end-to-end encrypted diagnosis, where neither the data nor the model are revealed. Lastly, we empirically evaluate the framework's security against a gradient-based model inversion attack and demonstrate that no usable information can be recovered from the model.
@article{arxiv.2012.06354,
title = {Privacy-preserving medical image analysis},
author = {Alexander Ziller and Jonathan Passerat-Palmbach and Théo Ryffel and Dmitrii Usynin and Andrew Trask and Ionésio Da Lima Costa Junior and Jason Mancuso and Marcus Makowski and Daniel Rueckert and Rickmer Braren and Georgios Kaissis},
journal= {arXiv preprint arXiv:2012.06354},
year = {2020}
}
Comments
Accepted at the workshop for Medical Imaging meets NeurIPS, 34th Conference on Neural Information Processing Systems (NeurIPS) December 11, 2020