UPDATED 12:00 EDT / MAY 29 2020

hui-xue-2 AI

NIH employs Docker software containers to improve medical diagnosis

The mobility and flexibility of container technology are being used by the National Institutes of Health to improve medical diagnosis. The institution adopts the technology from the software container company Docker Inc. to quickly deliver imaging software to more than 40 hospitals worldwide, curate data from these sites, and use artificial intelligence to help inform doctors’ decisions.

“If we are, for example, developing a new AI-based image analysis for the heart image, what we do with Docker is we can put our model and software into the Docker, so that our collaboration sites will pull the software that contains the latest technology, then use them for the patients, of course under the research agreement at NIH,” said Hui Xue (pictured), principal deputy director of the Medical Signal and Image Processing Program at the National Heart, Lung, and Blood Institute, the third largest institute of the National Institutes of Health.

Xue spoke with Stu Miniman, host of theCUBE, SiliconANGLE Media’s livestreaming studio, during DockerCon Live. They discussed the NHLBI experience with Docker, the progress made so far in using container technology in the diagnosis process, the importance of process automation, and the prospects for the future. (* Disclosure below.)

Security is critical

The global reach and security offered by Docker are fundamental characteristics that enable NHLBI researchers and developers to use containers for new imaging technologies, according to Xui.

“Because Docker i s… available globally, we can actually implement a continuous integration and testing [and] update the framework based on our collaborators, [who] would have the latest technology,” he explained. “It gives us the flexibility we never had before to reach our customers, to reach other people in the world, to help them. They also help us.”

To meet the security demands of the highly regulated medical field, all the communication between the container and the imaging equipment is encrypted. “We also have all the paperwork … to allow us to provide technology to our clinician,” he pointed out.

In addition, any new version of the software runs through a rigorous automated integration test. “The basic principle is we don’t allow any version of the software to be delivered to customers without testing Docker,” Xue stated.

NHLBI is also using this continuous testing framework to automate many other processes. For example, an open-source Python tool is usually configured on the service, which watches the GitHub repository.

“Whenever I make a change or someone in the team makes a change — for example, fix a bug, add a new feature, or maybe update a new AI model — we push the change to GitHub. Then there’s a continuous building system that will … trigger the integration test run all inside the Docker environment,” Xue  explained.

Cloud now and in the future

Another way the NHLBI is using Docker is to deploy containers in the Microsoft Azure cloud. That way, the same container works for customers anywhere in the cloud or on-site. “This actually reduces the development cost [and] also improves our efficiency a lot,” Xue said.

For the future, the idea is to move many applications into the cloud only, Xue added. This would be the case, for example, with new AI applications. “If a customer is waiting to use them, they will have to be willing to connect to the cloud and maybe send data there and receive, for example, the AI apps from our running Docker image in the cloud,” he said.

To achieve this, the price is a key element. “If we have one data center and 50 hospitals using it every day … the average price for one patient comes to a few dollars per patient,” Xue explained. “The ideal costs of using cloud computing can be truly trivial, but what we can offer to patients and doctors has never happened. I believe that’s the future.”

Watch the complete video interview below, and be sure to check out more of SiliconANGLE’s and theCUBE’s coverage of DockerCon Live. (* Disclosure: TheCUBE is a paid media partner for DockerCon Live. Neither Docker Inc., the sponsor for theCUBE’s event coverage, nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: Hui Xue

Since you’re here …

Show your support for our mission with our one-click subscription to our YouTube channel (below). The more subscribers we have, the more YouTube will suggest relevant enterprise and emerging technology content to you. Thanks!

Support our mission:    >>>>>>  SUBSCRIBE NOW >>>>>>  to our YouTube channel.

… We’d also like to tell you about our mission and how you can help us fulfill it. SiliconANGLE Media Inc.’s business model is based on the intrinsic value of the content, not advertising. Unlike many online publications, we don’t have a paywall or run banner advertising, because we want to keep our journalism open, without influence or the need to chase traffic.The journalism, reporting and commentary on SiliconANGLE — along with live, unscripted video from our Silicon Valley studio and globe-trotting video teams at theCUBE — take a lot of hard work, time and money. Keeping the quality high requires the support of sponsors who are aligned with our vision of ad-free journalism content.

If you like the reporting, video interviews and other ad-free content here, please take a moment to check out a sample of the video content supported by our sponsors, tweet your support, and keep coming back to SiliconANGLE.