AI Performs Better Than Pathologists Inside the Operating Room
Wed, April 21, 2021

AI Performs Better Than Pathologists Inside the Operating Room

AI has taken operating rooms by storm / Photo Credit: Motortion Films (via Shutterstock)

 

According to a research by Todd C. Hollon and colleagues published in the journal portal Nature Medicine, brain surgeons are bringing AI and new imaging techniques to the operating room to diagnose tumors faster and more accurately than pathologists, wrote Denise Grady of New York City-based newspaper The New York Times. This approach optimizes the standard practice of analyzing tissue samples while the patient is on the operating table, guiding brain surgery and later treatment. The traditional approach requires tissue samples to be sent to a lab, freezing and staining it, and looking at it through a microscope. The whole process takes 20 to 30 minutes or even longer. But the new technique only takes two-and-a-half minutes. While it also requires tissue to be removed from the brain, the new approach uses lasers to create images and a computer to read them.

Dr. Daniel A. Orringer, a neurosurgeon at N.Y.U. Langone Health and the senior author of the report, said, “Although we often have clues based on preoperative MRI, establishing a diagnosis is a primary goal of almost all brain tumor operations, whether we’re removing a tumor or just taking a biopsy.”

Aside from making the process faster, the technique can also detect some details that traditional methods may miss such as the spread of a tumor along nerve fibers, Orringer noted. Furthermore, the new method does not destroy the sample. Hence, the tissue can be used again for further testing.

 This may also aid doctors who perform head and neck, breast, skin, and gynecologic surgeries. The report emphasized that there is a shortage of neuropathologists, recommending that the new technology may help in addressing the skills gap in medical centers.

The study used brain tissue from 278 patients, analyzed them while surgery was taking place. Each sample was split equally with the AI and neuropathologists. They were judged if they were right or wrong based on whether they are in line with findings of lengthier and more extensive tests undertaken after surgery. The result? Humans were 93.9% correct while AI scored 94.6%.

 “It won’t change brain surgery, but it’s going to add a significant new tool, more significant than they’ve stated,” said Dr. Joshua Bederson, the chairman of neurosurgery for the Mount Sinai Health System, who was not involved in the study.