Application of Homomorphic Encryption in Medical Imaging

A technical 20-page report for next-generation data governance models

Authors :

  • Francis Dutil, Applied Research Scientist
  • Alexandre See, Applied Research Scientist
  • Lisa Di Jorio, Director of AI Research and Strategy
  • Florent Chandelier, Chief Technology Officer

Application of Homomorphic Encryption in Medical Imaging

For evaluation, we consider two types of baselines: single latent variable models that infer a single variable, and double

Healthcare research is primordial for improving patient management & care strategies, and greatly benefits society at multiple levels. However, most of this research requires access to large quantities of medical data, eventually including direct or indirect personal information. Privacy is of the utmost importance and personal health information should be accessed on a need-to-know basis in order to remain as confidential and secure as possible.

Ideally, no health data should leave its fiduciary healthcare organization. Thus, research groups – either public, such as universities, or private, such as pharmaceutical companies – that wish to make use of such data need to design distributed processing strategies that mitigate the risk of exposing proprietary information (e.g. a proprietary machine learning model).

Homomorphic Encryption (HE) is an emerging technology designed to process data that remains encrypted. Moreover, these operations produce encrypted results that can only be decrypted by the party holding the original encryption key. Using an appropriate design, HE can solve both the privacy & governance challenges described above.

In this technical report, we explore the use of homomorphic encryption (HE) in the context of training and predicting with deep learning (DL) models to deliver strict Privacy by Design services, and to enforce a zero-trust model of data governance.

Download the free report, now available to subscribers!

Related posts

How we developed an AI-driven discovery platform that transforms real-world healthcare data into clinically actionable insights

How we developed an AI-driven discovery platform that transforms real-world healthcare data into clinically actionable insights

It seems self-evident that healthcare research could gain tremendous value from using artificial intelligence to derive insights and solutio

...
Read more
How AI could improve lung cancer screening—and help to save lives

How AI could improve lung cancer screening—and help to save lives

Lung cancer is the deadliest cancer in Canada—and the world. Every year, lung cancer kills more than 20,000 Canadians. Of those who receiv

...
Read more
Application of Homomorphic Encryption in Medical Imaging

Application of Homomorphic Encryption in Medical Imaging

A technical 20-page report for next-generation data governance models. Authors: Francis Dutil, Alexandre See, Lisa Di Jorio and Florent Chan

...
Read more