A new artificial intelligence (AI) tool called Charm has been developed to assist doctors in combating aggressive brain tumors by identifying key features that provide guidance during surgery. Charm, or Cryosection Histopathology Evaluation and Review Machine, efficiently analyzes im ages to identify genetic characteristics of gliomas , which are aggressive brain tumors. Currently, this process can take days or weeks. Surgeons heavily rely on detailed diagnoses to guide their operations, and Charm aims to expedite this process, according to Kun-Hsing Yu, the senior author of a report public wasted in the July 7 issue of Medicine.
While Charm cannot match the accuracy of current genetic tests, it is capable of quickly predicting a tumor's profile. This rapid analysis enables doctors to prescribe appropriate treatment without the need for additional surgeries, saving valuable time. Additionally, Ch arm has the ability to differentiate between malignant and benign tumor cells and determine the tumor's grade, which indicates its level of aggressiveness. These assessments are typically performed by human pathologists during surgery. By eliminating the wait time or the need for an on-call pathologist, Charm can streamline the decision- making process and contributing to better outcomes for patients with gliomas, including the aggressive subtype known as glioblastoma.
The research team trained a machine learning algorithm using images of brain surgery samples and validated its accuracy against patient diagnoses. Charm demonstrated superior performance compared to other AI systems in identifying tumor genetic profiles. Given the critical n nature of decisions regarding tissue resection and potential treatment options , such as drug-coated wafers, surgeons heavily rely on the genetic characteristics of the tumor. However, obtaining this information currently takes a significant amount of time.
This study by Yu and his team is part of a broader initiative to leverage artificial intelligence in improving cancer diagnosis and treatment. The use of AI systems to accurately identify individuals at higher risk of pancreatic, lung, and breast cancer has been highlighted in a notable editorial published in the June edition of The Lancet Oncology. These comprehensive efforts aim to harness the potential of AI to enhance various aspects of cancer care and ultimately improve patient outcomes.
