AI algorithm IDs head abnormalities in CT scans with 95% accuracy
A new artificial intelligence (AI) technology from healthcare startup Qure.ai can accurately identify serious abnormalities in head CT scans with more than 95 percent accuracy, according to an April 26 release.
"Qure.ai's new head CT scan technology rapidly screens scans in under 10 seconds to detect, localize and quantify abnormalities, as well as assess their severity," said Prashant Warier, co-founder and CEO of Qure.ai, in a prepared statement. "This enables patient prioritization and the appropriate clinical intervention."
Imaging data from 313,318 randomized head CT scans and corresponding clinical reports were used to train the AI. Some 491 CT scans were then used to clinically validate the algorithms, and three senior radiologists compared results. Overall, they found the algorithm to be 95 percent accurate in identifying abnormalities in head CT scans.
"This is important new technology," said Norbert G. Campeau, MD, a senior neuro-radiologist from the Mayo Clinic and panel radiologist for the study, in a prepared statement. "The strong results of the deep learning system support the feasibility for use of automated head CT scan interpretation as an adjunct to medical care. This improves the quality and consistency of radiologic interpretation."
A recent graduate from Dominican University (IL) with a bachelor’s in journalism, Melissa joined TriMed’s Chicago team in 2017 covering all aspects of health imaging. She’s a fan of singing and playing guitar, elephants, a good cup of tea, and her golden retriever Cooper.