AI, imaging system able to accurately identify brain tumors
A new laser-based imaging system combined with artificial intelligence is able to provide accurate, real-time intraoperative diagnosis of brain tumors.
A new laser-based imaging system combined with artificial intelligence is able to provide accurate, real-time intraoperative diagnosis of brain tumors.
That’s the finding of a new study, published on Monday in the journal Nature Medicine, which assessed the diagnostic accuracy of brain tumor image classification using machine learning vs. pathologist interpretation of conventional histologic images.
Researchers discovered that the accuracy of the AI-based diagnosis was comparable to the pathologist-based interpretation (94.6 percent and 93.9 percent, respectively).
Convolutional neural networks (CNNs) “learned a hierarchy of recognizable histologic feature representations to classify the major histopathologic classes of brain tumors,” according to the study’s authors.
In addition to CNNs, the study leveraged stimulated Raman histology (SRH), an advanced optical imaging technique that reveals tumor infiltration in human tissue by collecting scattered laser light and illuminating essential features not typically seen in standard histologic images.
“We implemented a semantic segmentation method to identify tumor-infiltrated diagnostic regions within SRH images,” contend the authors. “These results demonstrate how intraoperative cancer diagnosis can be streamlined, creating a complementary pathway for tissue diagnosis that is independent of a traditional pathology laboratory.”
CNNs were trained using more than 2.5 million SRH images and predicted brain tumor diagnosis in the operating room in under two and a half minutes—an order of magnitude faster than conventional techniques.
“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,” says senior author Daniel Orringer, MD, associate professor in the Department of Neurosurgery at NYU Langone, who helped develop SRH. “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,” adds co-author Matija Snuderl, MD, associate professor in the Department of Pathology at NYU Langone.
That’s the finding of a new study, published on Monday in the journal Nature Medicine, which assessed the diagnostic accuracy of brain tumor image classification using machine learning vs. pathologist interpretation of conventional histologic images.
Researchers discovered that the accuracy of the AI-based diagnosis was comparable to the pathologist-based interpretation (94.6 percent and 93.9 percent, respectively).
Convolutional neural networks (CNNs) “learned a hierarchy of recognizable histologic feature representations to classify the major histopathologic classes of brain tumors,” according to the study’s authors.
In addition to CNNs, the study leveraged stimulated Raman histology (SRH), an advanced optical imaging technique that reveals tumor infiltration in human tissue by collecting scattered laser light and illuminating essential features not typically seen in standard histologic images.
“We implemented a semantic segmentation method to identify tumor-infiltrated diagnostic regions within SRH images,” contend the authors. “These results demonstrate how intraoperative cancer diagnosis can be streamlined, creating a complementary pathway for tissue diagnosis that is independent of a traditional pathology laboratory.”
CNNs were trained using more than 2.5 million SRH images and predicted brain tumor diagnosis in the operating room in under two and a half minutes—an order of magnitude faster than conventional techniques.
“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,” says senior author Daniel Orringer, MD, associate professor in the Department of Neurosurgery at NYU Langone, who helped develop SRH. “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,” adds co-author Matija Snuderl, MD, associate professor in the Department of Pathology at NYU Langone.
More for you
Loading data for hdm_tax_topic #better-outcomes...