An artificial intelligence (AI) tool has emerged to assist doctors in combating aggressive brain tumors. It aids in identifying crucial characteristics that provide guidance during surgery.
The Cryosection Histopathology Assessment and Review Machine (CHARM) is an advanced tool that efficiently analyzes images to identify the genetic profile of gliomas, a type of aggressive brain tumor. Currently, this process takes days or weeks. Kun-Hsing Yu, the senior author of a July 7 report in Med, explained that surgeons rely on detailed diagnoses to guide their operations.
Although the tool’s accuracy may not match current genetic tests, it has the ability to predict a tumor’s profile swiftly. This quick analysis enables doctors to proceed with appropriate treatment without the need for scheduling and performing additional surgeries, saving valuable time, as explained by Yu.
In addition, CHARM can distinguish between malignant and benign tumor cells and determine the tumor’s grade, indicating its level of aggressiveness. These are assessments that human pathologists typically make during surgery. However, according to Yu, CHARM could eliminate the need for a 10-to-15-minute wait or the presence of a pathologist on standby during the operation.
Glioma, particularly the aggressive subtype known as glioblastoma, poses a significant threat, with untreated cases leading to death in less than six months. Tragically, only 17% of individuals diagnosed with glioblastoma survive beyond the second year, as reported by the American Association of Neurological Surgeons.
Yu and his team trained a machine-learning algorithm using images of brain surgery samples and validating its accuracy against patient diagnoses. CHARM showed superior performance in identifying tumor genetic profiles compared to other AI systems.
When making critical decisions about the extent of tissue removal and the potential use of drug-coated wafers in treating glioma tumors, surgeons heavily rely on the tumor’s genetic profile. Unfortunately, obtaining this information is a time-consuming process at present.
The research conducted by Yu and his team is contributing to a comprehensive range of initiatives that utilize AI to enhance the diagnosis and treatment of cancer. In a notable editorial published in the June edition of the Lancet Oncology, the capabilities of certain systems were underscored for their accurate identification of individuals with an elevated risk of pancreatic, lung and breast cancer.