University of Michigan researchers use Artificial Intelligence to speed up brain tumor diagnosis

Michigan
A new system uses optical imaging and artificial intelligence that are making brain tumor diagnosis quicker and more accurate. This technology is allowing them to quickly see diagnostic tissue and tumor margins in near-real time.

ANN ARBOR, Mich. (WLNS) – A team of researchers trained a computer in the operating room to receive a diagnosis that rivals the accuracy of an expert pathologist.

The team which includes University of Michigan researchers are using new artificial intelligence technology to provide neurosurgeons with valuable, real-time information about what type of brain tumor is present, while the patient is still on the operating table.

Traditionally, sending out a biopsy to an expert pathologist and getting back a diagnosis under the best case scenario takes about 40 minutes, but on average the computer can do it in under 3 minutes.

The time saved helps to inform surgeons how to proceed with their delicate surgery and make immediate and potentially life-saving treatment decisions to assist their patients.

The advance comes from a clinical trial of 278 patients undergoing brain surgery.

Using another technological advance called stimulated Raman histology which requires teaching a computer using large datasets of examples on how to perform a given task.

The team trained the computer to classify tissues samples into one of 13 categories commonly found in a brain tumor sample.

Overall, the machine’s performance was quite impressive, returning the right answer about 95 percent of the time.

The machine made a correct diagnosis in all 17 cases that a pathologist got wrong, while the pathologist got the right answer in all 14 cases in which the machine slipped up.

The findings show that the combination of SRH and AI can be used to make real-time predictions of a patient’s brain tumor diagnosis to inform surgical decision-making. That may be especially important in places where expert neuropathologists are hard to find, according to the Director of the National Institutes of Health.

Ultimately, the researchers suggest that AI may add greater precision to a diagnosis while similar approaches will help surgeons operating on patients with other types of cancer such as skin or breast.

Copyright 2020 Nexstar Broadcasting, Inc. All rights reserved. This material may not be published, broadcast, rewritten, or redistributed.

Michigan Headlines

More Michigan

StormTracker 6 Radar