The accuracy of the diagnosis is comparable to conventional human diagnosis.

A new optical imaging technique used together with an artificial intelligence, or AI, algorithm accurately diagnoses the presence, or otherwise, of a brain tumour in under two minutes, reports The Hill.

New research published Monday in Nature Medicine said the AI-based diagnosis was 94.6% accurate compared to the 93.9% accuracy from the standard lab-based procedure. Besides, the lab procedure carried out by an expert pathologist could take as much as 20 to 30 minutes. This is a significant interval of time during brain surgery.

The AI-based system also went a step further and detected details that the human system may miss completely. For example, the spread of a brain tumor along nerve fibers. Additionally, the AI system did not destroy the brain tissue, unlike conventional practice.

AI faster, more accurate on diagnosis of brain tumour

The new procedure uses images from an optical imaging technique called stimulated Raman histology (SRH). An AI algorithm scans these images and delivers a diagnosis of the presence of a brain tumor within 150 seconds. Surgeons take the tissue sample and send it for analysis while the patient is still on the operating table.

Daniel A. Orringer, associate professor of Neurosurgery at New York University Grossman School of Medicine, helped develop the revolutionary technique with colleagues at the University of Michigan.

“As surgeons, we’re limited to acting on what we can see; this technology allows us to see what would otherwise be invisible, to improve speed and accuracy in the [operating room], and reduce the risk of misdiagnosis,” Orringer said in a statement. “With this imaging technology, cancer operations are safer and more effective than before.”

Related Story:  Artificial Intelligence (AI) Improves MRI Detection of ADHD