Dec. 23 (UPI) -- A new study has found a way to use artificial intelligence to diagnose the tissues of patients during surgery, improving rapid diagnosis during critical moments.
In a paper published Friday in the journal Nature Biomedical Engineering, investigators from the Mahmood Lab at Brigham and Women's Hospital and collaborators from Bogazici University developed a method that allows AI to translate between frozen sections of tissue and the gold standard approach to examining tissue during surgery to improve the accuracy of rapid analysis.
The method has the potential of improving patient outcomes when doctors have to make quick diagnoses and determinations in the middle of surgeries and slash the time it takes to examine tissue during those critical periods.
"We are using the power of artificial intelligence to address an age-old problem at the intersection of surgery and pathology," said corresponding author Faisal Mahmood in a statement.
"Making a rapid diagnosis from frozen tissue samples is challenging and requires specialized training, but this kind of diagnosis is a critical step in caring for patients during surgery."
Currently, for rapid diagnosis, pathologists use an approach known as cryosectioning, which involves fast-freezing tissue, cutting sections, and observing these thin slices under a microscope. Cryosectioning takes minutes but can distort cellular details and compromise or tear delicate tissue.
The new AI study says that a deep-learning model that can be used to translate between frozen sections and more commonly used formalin-fixed and paraffin-embedded tissue samples.
The research team validated their findings by recruiting pathologists to a reader study in which they were asked to make a diagnosis from images that had gone through the AI method and traditional cryosectioning images.
The AI method improved image quality and improved diagnostic accuracy among experts.
"Our work shows that AI has the potential to make a time-sensitive, critical diagnosis easier and more accessible to pathologists," Mahmood said. "And it could potentially be applied to any type of cancer surgery. It opens up many possibilities for improving diagnosis and patient care."