HeadXNet algorithm tool can detect brain aneurysms

Researchers at Stanford University have developed an AI tool, built on an algorithm called HeadXNet, which can identify parts of the brain that might contain an aneurysm. The algorithm’s conclusions are overlaid on computerised tomography angiogram head scans as a semi-transparent highlight, so medical staff can still examine the underlying image. Eight clinicians tested HeadXNet by evaluating a set of 115 brain scans, with and without the AI tool. With the tool, the doctors successfully highlighted six more aneurysms per 100 scans that displayed the condition, therefore reducing the rate of missed diagnoses.
Christopher Chute, co-lead author of the paper, said: “We labelled, by hand, every voxel, the 3D equivalent to a pixel, with whether or not it was part of an aneurysm. Building the training data was a pretty gruelling task and there were a lot of data.”
Kristen Yeom, associate professor of radiology at Stanford and co-senior author of the paper, said: “Search for an aneurysm is one of the most labour-intensive and critical tasks radiologists undertake. Given inherent challenges of complex neurovascular anatomy and potential fatal outcome of a missed aneurysm, it prompted me to apply advances in computer science and vision to neuroimaging.”