GE Healthcare, Fujitsu collaborate on brain aneurysm diagnosis

Register now

A new research collaboration in Australia will focus on ways to diagnose and monitor brain aneurysms quicker and more efficiently using artificial intelligence.

To launch the program, the Australian government has provided a grant of $2.1 million from the Department of Industry, Innovation and Science.

Fujitsu is leading the research and leveraging its artificial intelligence technology and digital solution capabilities. GE Healthcare brings medical imaging technology to the collaborative effort.

Macquarie University in Australia and Macquarie Medical Imaging offer clinical expertise to develop and test the technology, which in time is expected to be commercialized first in Australian radiology practices and then worldwide.

“As the consequences of brain aneurysm rupture often are fatal, effective and expedient detection is crucial,” says Matt Tucker, president and CEO at GE Healthcare in Australia and New Zealand. "Unfortunately, screening and monitoring takes time, and specialist expertise is not available to every radiology practice. The application of AI can give doctors better insights quicker and produce fewer variable results.”

Professor John Magnussen, an interventional radiologist at Macquarie Medical Imaging, believes the work being done is an opportunity to address the problem of accurate diagnosis of brain aneurysms. “Even in ideal circumstances, detecting brain aneurysms is time and expertise intensive, and missed aneurysms can have terrible outcomes. By creating an AI assistant to automatically flag potential aneurysms and allow for accurate follow-up, we can make a huge difference in patient care.”

Fujitsu will apply AI methods to images of the brain generated by GE’s Revolution CT scanner, and use a trained algorithm to look for abnormalities and aneurysms.

Researchers expect one of the outcomes of the program will be validation of an AI algorithm able to highlight blood vessels within the circle of what is known as Willis, which is an arterial ring at the base of the brain and that may have one or more aneurysms.

Addition technology supporting the research will include tracking of identified aneurysms over time, which will be a diagnostic support tool for clinicians, while also giving patients greater peace of mind that known aneurysms are being monitored. Also to be developed is a planning tool for surgical stent intervention that will use fluid dynamic modeling to predict risk of an aneurysm rupture.

For reprint and licensing requests for this article, click here.