An artificial intelligence (AI) tool has emerged to help doctors combat aggressive brain tumors. It helps to identify important characteristics that provide guidance during the operation.
The Cryosection Histopathology Assessment and Review Machine (Charm) is an advanced tool that effectively analyzes images to determine 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 accuracy of the tool cannot match current genetic tests, it can easily predict the tumor profile. This quick analysis enables doctors to continue the appropriate treatment without having to schedule and perform additional operations, saving valuable time, explained Yu.
In addition, Charm can distinguish between malignant and benign tumor cells and determine the grade of the tumor, which indicates its level of aggressiveness. These are tests that human pathologists usually perform 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 surgery.
Glioma – especially the aggressive subtype known as glioblastoma – poses a major threat, with untreated cases leading to death in less than six months. Unfortunately, only 17% of individuals diagnosed with glioblastoma survive beyond the second year, according to the American Association of Neurological Surgeons.
Related: AI has the potential to send Bitcoin price over $750K – Arthur Hayes
Yu and his team trained a machine learning algorithm using images of brain surgery samples and verified its accuracy against patient diagnoses. Charm did better at identifying tumor genetic profiles than other AI systems.
When making critical decisions about the extent of tissue removal and the potential use of drug-coated wafers in the treatment of glioma tumors, surgeons rely heavily on the tumor’s genetic profile. Unfortunately, getting this information is a time-consuming process at the moment.
The research conducted by Yu and his team contributes to a comprehensive range of initiatives that use AI to improve cancer diagnosis and treatment. In a famous editorial published in the June edition of Lancet Oncology, the capabilities of specific systems are highlighted for their accurate identification of individuals at high risk of pancreatic, lung and breast cancer.
Magazine: AI travel booking hilariously bad, 3 weird uses for ChatGPT, crypto plugins