Multi-institution encrypted medical imaging AI validation without data sharing

TL;DR

This paper demonstrates that CrypTFlow2 enables secure, privacy-preserving AI inference on multi-institutional medical imaging data without performance loss, facilitating safe collaboration between healthcare providers and AI developers.

Contribution

It introduces a framework using CrypTFlow2 for secure 2-party computation in medical imaging, showing no performance degradation across multiple institutions and datasets.

Findings

Secure inference matched insecure AUROC performance.

Model outputs were distributionally equivalent in secure and insecure modes.

CrypTFlow2 enables scalable, privacy-preserving model evaluation.

Abstract

Adoption of artificial intelligence medical imaging applications is often impeded by barriers between healthcare systems and algorithm developers given that access to both private patient data and commercial model IP is important to perform pre-deployment evaluation. This work investigates a framework for secure, privacy-preserving and AI-enabled medical imaging inference using CrypTFlow2, a state-of-the-art end-to-end compiler allowing cryptographically secure 2-party Computation (2PC) protocols between the machine learning model vendor and target patient data owner. A common DenseNet-121 chest x-ray diagnosis model was evaluated on multi-institutional chest radiographic imaging datasets both with and without CrypTFlow2 on two test sets spanning seven sites across the US and India, and comprising 1,149 chest x-ray images. We measure comparative AUROC performance between secure and insecure inference in multiple pathology classification tasks, and explore model output distributional shifts and resource constraints introduced by secure model inference. Secure inference with CrypTFlow2 demonstrated no significant difference in AUROC for all diagnoses, and model outputs from secure and insecure inference methods were distributionally equivalent. The use of CrypTFlow2 may allow off-the-shelf secure 2PC between healthcare systems and AI model vendors for medical imaging, without changes in performance, and can facilitate scalable pre-deployment infrastructure for real-world secure model evaluation without exposure to patient data or model IP.