Artificial Intelligence Tool To Help Make Real Time Diagnosis During Surgery, Says Study

The study was published in the journal Nature Biomedical Engineering.

A new study has demonstrated the development of an artificial intelligence tool to aid in real-time diagnosis during surgery, boosting the quality of images to increase the accuracy of rapid diagnostics.

The study was published in Nature Biomedical Engineering and is titled ‘AI method can make time-sensitive, critical diagnosis easier and more accessible to pathologists.’ According to the research, artificial intelligence. used to translate between frozen sections and the gold standard approach.

Faisal Mahmood, PhD, corresponding author, Division of Computational Pathology at US-based Brigham and Women’s Hospital said in a press release: “We are using the power of artificial intelligence to tackle an age-old problem at the intersection of surgery and pathology speak. Making a rapid diagnosis from frozen tissue samples is challenging and requires specialized training, but this type of diagnosis is a critical step in the care of patients during surgery.”

According to the study, pathologists use formalin-fixed and paraffin-embedded (FFPE) tissue samples to make final diagnoses. This process preserves tissue in a way that produces high-quality images, but is labor intensive and can take several days. To ensure a quick diagnosis that takes minutes, cryosectioning is used which quickly freezes tissue, cuts sections and observes these thin slices under a microscope. The downside of this approach is that it can distort cellular details and damage or tear delicate tissue.

The researchers then created a deep learning model that could translate between frozen sections and more commonly used FFPE tissue. The team’s research showed that the method could subtype several types of cancer, including gliomas and non-small cell lung tumors.

Also read: Researchers in Israel develop AI tool that can predict heart failure with 80% accuracy

Furthermore, the authors say that prospective clinical studies in real hospital settings should be conducted in the future to confirm and validate the artificial intelligence method in terms of diagnostic accuracy and surgical decision-making.

“Our work shows that AI has the potential to make a time-sensitive, critical diagnosis easier and more accessible to pathologists. And it can potentially be applied to any type of cancer surgery. This opens up many possibilities for improving diagnosis and patient care,” Dr Mahmood said in the press release.