Researchers at the Australian National University (ANU) have developed a new AI tool to classify brain tumours more quickly and accurately. The research was recently published in Nature Medicine.
In collaboration with experts from the National Cancer Institute in the United States, the ANU researchers developed DEPLOY, a way to predict DNA methylation and subsequently classify brain tumours into ten major subtypes. The model was trained and validated on large datasets of approximately 4,000 US and European patients. DEPLOY draws on microscopic pictures of a patient’s tissue called histopathology images.
“DNA methylation-based profiling is the current gold standard for identifying different kinds of brain tumours,” said ANU’s Dr Danh-Tai Hoang. “DNA methylation acts like a switch to control gene activity and which genes are turned on or off. But the time it takes to do this kind of testing can be a major drawback, often requiring several weeks or more when patients might be relying on quick decisions on therapies. There’s also a lack of availability of these tests in nearly all hospitals worldwide.”
Hoang said DEPLOY achieved an unprecedented accuracy rate of 95% and, when dealing with particularly difficult samples, was able to provide a diagnosis that was more clinically relevant than what pathologists initially offered.
“This shows the potential future role of DEPLOY as a complementary tool, adding to a pathologist’s initial diagnosis or even prompting re-evaluation in the case of disparities,” said Hoang.
The researchers believe DEPLOY could eventually be used to help classify other types of cancer.
