Mix of advanced imaging, AI accurately IDs brain tumors
Researchers have found a new technique for brain tumor image classification that combines advanced optical imaging with AI and published their findings in Nature Medicine.
The current technique for achieving an intraoperative diagnosis during cancer surgeries uses up a number of resources and depends on a “contracting, unevenly distributed pathology workforce,” wrote lead author Todd C. Hollon, MD, University of Michigan, and colleagues. The team hoped this new method could result in a streamlined process “independent of a traditional pathology laboratory.”
The alternative workflow developed by Hollon et al. began with stimulated Raman histology (SRH), an imaging technique that identifies tumor movement in tissue using laser light. The SRH images are then scanned by an AI algorithm that provides a predicted brain tumor diagnosis.
The team developed its algorithm by training a deep convolutional neural network with more than 2.5 million tissue samples from 415 patients. Another 278 patients were then recruited for a prospective clinical trial, and the algorithm achieved an overall accuracy of 94.6%.
“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 OR, and reduce the risk of misdiagnosis,” senior author Daniel A. Orringer, MD, NYU Grossman School of Medicine, said in a prepared statement. “With this imaging technology, cancer operations are safer and more effective than ever before.”
“SRH will revolutionize the field of neuropathology by improving decision-making during surgery and providing expert-level assessment in the hospitals where trained neuropathologists are not available,” study co-author Matija Snuderl, MD, associate professor in the department of pathology at NYU Grossman School of Medicine, said in the same prepared statement.
Michael has more than 18 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.