The study, led by researchers from Michigan Medicine, tested a new system to improve diagnostic accuracy and efficiency using technology developed at the Ann Arbor-based institution. The system used both a technique called stimulated Raman histology to generate images of tumor tissue in near-real-time and a deep convolutional neural network — a type of AI algorithm — to predict a brain cancer diagnosis from the imaging data.
Together, the two techniques provided neurosurgeons with more accurate diagnoses within minutes at the bedside, allowing for more rapid treatment of potential brain tumors. Not only did the AI system achieve diagnostic accuracy of nearly 95 percent, but it was also able to identify human pathologists’ misdiagnoses.
“We’re transforming brain tumor diagnosis. … It’s a highly standardized tool that can deliver accurate diagnoses to a broad swath of brain tumor patients,” said lead author Todd Hollon, MD, chief neurosurgical resident at Michigan Medicine. “It’s another way to help the pathologists and surgeons increase certainty while making important decisions in the operating room.”
More articles on AI:
Banner Health integrates AI-powered digital triage tool to improve patient experience
World Economic Forum: 3 ways AI will transform healthcare in the next decade
Advocate Health Care implements AI tech to detect stroke more quickly
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.