The technology can cut testing times to days or weeks, and widespread efforts are focused on using artificial intelligence to diagnose and treat cancer. Researchers have created an artificial intelligence tool that has the potential to help doctors treat aggressive brain tumors by identifying the characteristics that guide surgery.
Harvard Medical School (HMS) researchers have developed this AI tool to quickly decode the DNA of brain tumors during surgery.
The tool, called CHARM (Cryosection Histopathology Assessment and Review Machine), is freely available to other researchers.
The magic tool studies the images to quickly pick out the genetic profile of a type of tumor called a glioma, a process that currently takes days or weeks, said Kun-Hsing Yu, lead author of the report published Friday in the journal Med.
Surgeons use detailed diagnoses to guide them during surgery, Yu said, and being able to get them quickly could improve patient outcomes and save them from multiple surgeries.
It still needs to be clinically validated through real-world testing and approved by the FDA before being deployed in hospitals, the research team said.
“Right now, even state-of-the-art clinical practice cannot molecularly profile tumors intraoperatively. Our tool overcomes this problem by extracting previously untapped biomedical signals from frozen pathology slides,” said lead study author Kun-Hsing Yu, assistant professor of biomedical informatics at the Blavatnik Institute at HMS. Knowing the tumor’s molecular identity during surgery is also valuable because some tumors benefit from on-the-spot treatment using drug-coated wafers placed directly into the brain at the time of surgery, Yu said.
“The ability to determine real-time intraoperative molecular diagnosis during surgery can drive the development of real-time precision oncology,” added Yu.