google life image: de-identifying patient information in medical imaging data
September 10, 2019

De-Identification Solution for Google Cloud Healthcare API

Life Image Service Achieves Highly Accurate, Highly Scalable, Enterprise-Class Results When Combined with the Google Cloud Healthcare API De-Identification Solution

Newton, Mass. – September 10, 2019 – Life Image, one of the world’s largest global networks for sharing clinical and imaging data that is powered by leading interoperability standards, today announced the launch of a new enhancement and validation service that optimizes the de-identification functionality of the Google Cloud Healthcare API, which helps to power healthcare insights for security and compliance-focused environments.

Protected health information (PHI) embedded in images has traditionally been extremely difficult to de-identify at scale. Specifically, Life Image provided third-party evaluation of the Google Cloud Healthcare API and found that it outperformed other tools in the market in its accuracy at de-identifying PHI contained in imaging pixels, metadata tags and associated notes.

In addition, Life Image will also offer a value-add service that uses a combination of machine learning and human validators to further augment the tool in order to achieve accuracy levels consistent with some of the most stringent compliance requirements and beyond those operating in healthcare today. Combined, the Life Image service and Google Cloud Healthcare API can help protect patient information and promote accelerated research development.

The Google Cloud Healthcare API was built to store and process imaging data across modalities, manufacturers and site locations. It is capable of enabling and supporting medical imaging workflows across clinical, analytical, research and other use cases. In addition, the Google Cloud Healthcare API provides capabilities that can help remove PHI from this data at scale while retaining useful information, such as demographics and clinical content, without the need for extensive custom configuration that is required by other tools in the market.

Life Image leveraged its access to one of the world’s largest sets of medical images to internally evaluate the Google Cloud Healthcare API’s performance. Life Image determined the de-identification tool can remove PHI from millions of imaging files within just hours, and sometimes minutes, across all the major global manufacturers and modalities, and for a wide range of clinical use cases.

Life Image’s value-added service will further optimize the Google Cloud Healthcare API’s de-identification performance to a high level of accuracy by applying its own advanced machine learning capabilities, in-depth imaging expertise and a service validation layer to closely filter and distinguish imaging data.

“Given the intricacies of imaging data, and the myriad places where PHI can exist, the process of de-identifying is often extremely cumbersome, expensive and requires specialized and custom programming as well as manual human intervention,” said Matthew A. Michela, CEO and President, Life Image. “Working with Google Cloud on this advanced de-identification solution allowed Life Image to bring our knowledge of the intricacies of imaging data, as well as our advanced machine learning capabilities, to bear so that together we could help solve one of the most complex issues in healthcare.”

While the value of reusing clinical trial imaging data for other research initiatives is well-known, de-identifying this data has long posed a problem due to privacy concerns, extremely high costs and a lack of adequate tools to accomplish this at scale. Life Image’s enhancement services, on top of the capabilities of the Google Cloud Healthcare API, overcome these hurdles by offering an enterprise solution that allows large de-identified datasets of images to be repurposed to accelerate new clinical research and discoveries, train machine learning models, carry out additional analysis and spark new ideas for research — while ensuring PHI in diagnostic images and reports is protected. Leveraging this de-identification technology, organizations can make imaging data from prior studies serviceable faster and easier, increase public availability of trial imaging data for use in other studies, improve access for real-world evidence applications, dramatically reduce the cost of de-identifying trial data, and more.

About Life Image
Life Image is world’s largest medical evidence network providing access to points of care and curated clinical and imaging data. It is the only company in the market today with Real World Imaging™ that provides large scale, heterogenous, de-identified imaging sets that are linkable to other longitudinal data. Founded in 2008, Life Image has created a digital platform using industry leading interoperability standards to connect 10,000 facilities with more than 150,000 U.S. providers and 58,000 global clinics. Its network of hospitals, physicians, patients, life sciences, medical devices and telehealth is interconnected with a technical ecosystem of EHRs, PACS, AI solutions, cloud environments and analytics platforms.

For more information about Life Image, please visit, visit its blog and follow the company on Twitter, Facebook, and LinkedIn.

Media Contact
Ashley Owen
Aria Marketing for Life Image
(617) 332-9999 x 216