A method that uses AI to translate between frozen sections and the gold-standard approach, which improves the quality of images for a rapid and accurate diagnosis, was developed by collaborators from Bogazici University in a recent study.
While the patient is on the operating table, surgeons frequently have to collect, analyze, and diagnose disease. For a quick and accurate examination, samples must be sent to the pathologist using one of two methods: the gold-standard method, which can take a long time and involves freezing tissue, which can make a diagnosis more difficult.
“We are using the power of artificial intelligence to address an age-old problem at the intersection of surgery and pathology,” stated co-author Faisal Mahmood, Ph.D., of BWH’s Division of Computational Pathology. It is difficult and requires specialized training to quickly diagnose from frozen tissue samples, but this type of diagnosis is essential to patient care during surgery.”
A tissue sample that has been paraffin-embedded and formalin-fixed is used by pathologists to preserve it and produce high-quality images. However, this procedure is time-consuming and can take anywhere from 12 to 48 hours.
The AI would be able to switch between frozen sections and FFPE tissue, which is more commonly used. Pathologists used AI-processed images and conventional cryosectioning images to test the method and make a diagnosis.
The study’s findings, which were published in Nature Biomedical Engineering, demonstrated that AI-enhanced diagnostic accuracy and image quality.
According to Mahmood, “Our work shows that AI has the potential to make a time-sensitive, critical diagnosis easier and more accessible to pathologists,” he is eager to test the method in a real hospital setting. Additionally, it might be applicable to any kind of cancer surgery. It opens up numerous opportunities for enhancing patient care and diagnosis.
Source: Express Tribune