What if computers could diagnose certain kinds of cancer using artificial intelligence in only a couple of minutes?

A recent study conducted by a team of neurosurgeons at the University of Michigan details how AI technology was successfully used to diagnose brain tumors during surgery — as the patients were still on the operating table.

“AI is invaluable in the operating room,” said Dr. Daniel Orringer, one of the neurosurgeons who co-authored the study. “Often the distinction between tissue containing tumor and tissue free of tumor is impossible with the naked eye and can even be challenging on a microscopic scale.”

After surgery, it usually takes around 30 minutes for a pathologist to study the biopsy results under a microscope and provide a diagnosis. In that time, the patient is sewed up and returned to the recovery room to await the results.

With AI, the results were delivered within an average of two and a half minutes. This allowed the surgeons to understand the patient’s full medical condition and determine the best care while they were still in the operating room.

Orringer explained that different tumors are treated in different ways — some are best treated with surgery, while others respond best to chemotherapy and radiation.

“Being able to match the tumor with the right treatment is essential for patient care,” he said.

Plus, AI and human pathologists scored around the same number of successful diagnoses of 278 patients in the study. Using only AI, the cancer diagnosis rate was 94.6 percent, while pathologists scored 93.9 percent.

“We are very optimistic about the power of AI in tumor diagnosis,” Orringer concluded. “Better diagnosis means better care. Better care opens the possibility for more effective treatment of cancer.”