May 21, 2024

New AI Tool Revolutionizes Brain Tumor Classification with 95% Accuracy

Researchers in Australia and the United States have developed a new artificial intelligence tool that significantly speeds up and improves the accuracy of brain tumor classification.

The traditional method for identifying different types of brain tumors, known as DNA methylation-based profiling, is accurate but can take several weeks to deliver results and is not widely available in many hospitals globally.

To overcome these limitations, a research team from the Australian National University, in collaboration with the U.S. National Cancer Institute, has devised a way to predict DNA methylation, which regulates gene activity.

Their approach classifies brain tumors into 10 major categories using a deep learning model, a type of artificial intelligence inspired by the human brain's data processing capabilities.

The U.S.-Australian system, called DEPLOY, utilizes histopathology images-microscopic pictures of a patient's tissue. Researchers view DEPLOY as a complement to initial diagnoses made by pathologists or physicians.

Danh-Tai Hoang, a research fellow at the Australian National University, told VOA that AI will enhance existing diagnostic methods, which are often slow. "The technique is very time consuming," Hoang said. "It often takes around two to three weeks to obtain a result from the test, whereas patients with high-grade brain tumors often require immediate treatment because time is crucial for brain tumors, so they need to get treatment as soon as possible.