JUN 11, 2019 08:57 AM PDT

Artificial Intelligence May Soon Detect Brain Aneurysms

WRITTEN BY: Nouran Amin

Artificial intelligence (AI) may soon help doctors diagnose brain aneurysms which are bulges in blood vessels that can lead to stroke, brain damage, and death. However, with the new AI tool developed by researchers at Stanford University, problem areas can be detected on brain scans that likely contain an aneurysm.

Learn more about brain (cerebral) aneurysms:

"There's been a lot of concern about how machine learning will actually work within the medical field," said Allison Park, a Stanford graduate student in statistics and co-lead author of the paper. "This research is an example of how humans stay involved in the diagnostic process, aided by an artificial intelligence tool."

Findings of the study were published in JAMA Network Open.

"Search for an aneurysm is one of the most labor-intensive and critical tasks radiologists undertake," said Kristen Yeom, associate professor of radiology and co-senior author of the paper. "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."

The new AI tool was developed around an algorithm called HeadXNet—which improves clinicians' ability to correctly identify aneurysms at a level equal to detecting six more aneurysms in 100 brain scans that contain aneurysms. The tool also improved consensus among the interpreting clinicians.

"We labelled, by hand, every voxel -- the 3D equivalent to a pixel -- with whether or not it was part of an aneurysm," said Chute, who is also co-lead author of the paper. "Building the training data was a pretty grueling task and there were a lot of data."

Stanford University: In this brain scan, the location of an aneurysm is indicated by HeadXNet using a transparent red highlight. (Image credit: Allison Park)

"We were interested how these scans with AI-added overlays would improve the performance of clinicians," said Pranav Rajpurkar, a graduate student in computer science and co-lead author of the paper. "Rather than just having the algorithm say that a scan contained an aneurysm, we were able to bring the exact locations of the aneurysms to the clinician's attention."

Source: Stanford University

About the Author
  • Nouran enjoys writing on various topics including science & medicine, global health, and conservation biology. She hopes through her writing she can make science more engaging and communicable to the general public.
You May Also Like
DEC 08, 2019
DEC 08, 2019
Paper-based technology can sense iron levels in fortified foods
In many low-income nations, mass food fortification programs have grown to address issues surrounding poor nutrition address nutrient in their populations....
DEC 08, 2019
Chemistry & Physics
DEC 08, 2019
Record-making Nuclear Fusion Device to Rescue Dwindling Medical Isotope Supply
Neutron generators are a type of nuclear fusion device that can produce a stream of neutrons through merging hydrogen atoms. Because of the intri...
DEC 08, 2019
Space & Astronomy
DEC 08, 2019
How Much Do You Know About NASA's Voyager Missions?
NASA’s Voyager 1 and 2 spacecraft each launched in 1977 for a unique opportunity to explore the solar system’s outermost planets in unprecedent...
DEC 08, 2019
Genetics & Genomics
DEC 08, 2019
Can CRISPR Replace Antibiotics?
Antibiotic-resistant infections claim around 700,000 lives per year, with estimates saying that this number could swell to 10 million by 2050 (Jacobs: 2019...
DEC 08, 2019
DEC 08, 2019
Algorithm Predicts Response to HIV Immunotherapy
Blood samples from HIV patients produced the data necessary for two scientists to build a mathematical model for predicting how HIV patients will respond t...
DEC 08, 2019
Space & Astronomy
DEC 08, 2019
Will ISRO Succeed At Building its Own Space Station?
When hearing the words “space station,” the International Space Station probably comes to mind; but the International Space Station wasn’...
Loading Comments...