AI-Powered Model Shows Promise in Finding Residual Brain Tumor After Surgeries

Researchers have developed an AI powered model that is able to determine within 10 seconds during surgery “if any part of a cancerous brain tumor that could be removed remains.”

The technology “outperformed conventional methods for identifying what remains of a tumor by a wide margin.” Oftentimes, “residual tumor” remains after a tumor is removed from a patient’s brain because “the residual tumor may resemble healthy brain.” There are limitations regarding procedures to determine if residual tumor remains.

This new tool, called FastGlioma, was able to detect and calculate “how much tumor remained with an average accuracy of approximately 92%.” The AI technology, when guiding surgeries, missed “high-risk, residual tumor just 3.8% of the time” compared to a “nearly 25% miss rate for conventional methods.”

FastGlioma “combines microscopic optical imaging with a type of artificial intelligence called foundation models,” which can “classify images, act as chatbots, reply to emails and generate images from text descriptions.” DeepGlioma is another “AI based diagnostic screening system that detects a brain tumor’s genetic mutations in under 90 seconds.” The full resolution model “achieved accuracy up to 92%, with the fast mode slightly lower at approximately 90%.”