AI tool helps radiologists improve diagnoses of brain aneurysms

Register now

Stanford University researchers have developed an artificial intelligence algorithm that highlights areas of a brain scan that are likely to contain an intracranial aneurysm.

Head computed tomographic angiography (CTA) imaging was used to train and test the AI tool, which helps identify brain aneurysms—bulges or ballooning in blood vessels that can be fatal.

A study, published June 7 in JAMA Network Open, shows that the 3-dimensional convolutional neural network—called HeadXNet—improved the ability of clinicians to accurately identify aneurysms at a level equivalent to finding six more aneurysms in 100 scans that contain aneurysms.

In the study, eight clinicians tested HeadXNet by evaluating a set of 115 brain scans for aneurysm, once with the help of the algorithm and once without.

“The deep learning model developed successfully detected clinically significant intracranial aneurysms on CTA,” state the study’s authors. “This suggests that integration of an artificial intelligence–assisted diagnostic model may augment clinician performance with dependable and accurate predictions and thereby optimize patient care.”

Also See: AI helps to predict risk of a potentially fatal heart disease

According to Kristen Yeom, associate professor of radiology and co-senior author of the study, the search for an aneurysm is one of the most labor-intensive and critical tasks radiologists undertake.

“Given the potential catastrophic outcome of a missed aneurysm at risk of rupture, an automated detection tool that reliably detects and enhances clinicians’ performance is highly desirable,” contend the authors.

“In addition to significantly improving accuracy across clinicians while interpreting CTA examinations, an automated aneurysm detection tool, such as the one presented in this study, could also be used to prioritize workflow so that those examinations more likely to be positive could receive timely expert review, potentially leading to a shorter time to treatment and more favorable outcomes,” researchers add.

Nonetheless, they also note that major hurdles remain in integrating AI algorithms such as HeadXNet with daily clinical workflows in radiology at hospitals. Given that scan viewers aren’t currently designed to work with help from AI, researchers had to custom-build tools to integrate HeadXNet within scan viewers.

“Because of these issues, I think deployment will come faster not with pure AI automation, but instead with AI and radiologists collaborating,” said Andrew Ng, adjunct professor of computer science and co-senior author of the study. “We still have technical and non-technical work to do, but we as a community will get there and AI-radiologist collaboration is the most promising path.”

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