London Surgeons Use AI to Remove Brain Tumor, Saving Patient's Sight

In a groundbreaking medical achievement, neurosurgeons in London have successfully conducted the world's first operation to remove a brain tumor with the aid of artificial intelligence. The procedure, performed in May at the National Hospital for Neurology and Neurosurgery (NHNN), part of University College London Hospitals NHS, was aimed at saving the sight of a 48-year-old patient, Rhys Hibbert.

While the surgical team maintained full control throughout the procedure, an AI system was employed to analyze live camera footage during the operation. Its function was to help identify vital structures, such as nerves and blood vessels, located near the 11-millimeter tumor situated in Hibbert's pituitary gland. This real-time analysis provided an additional layer of precision, crucial for navigating the delicate area surrounding the tumor.

Hibbert reported a remarkable recovery, stating he could see everything clearly upon waking and experienced a "360-degree panoramic view." Within a week, he was able to walk unaided and without glasses or a cane, and has since returned to his work as a customer service manager. The surgery utilized a new AI technology that identifies small anatomical structures by assigning color codes to critical areas, thereby assisting surgeons in avoiding them more safely.

“

When I woke up from surgery, I could see everything in the room clearly. It felt like I had a 360-degree panoramic view of everything around me.

This marks the first time the technology, previously used as a research tool at the hospital, was applied in a patient surgery. The pituitary gland, along with surrounding blood vessels and nerves controlling vision, are in close proximity. Health officials noted that even a millimeter's error in this region could lead to critical consequences, including blindness, stroke, or death.

Associate Professor Dr. Sophia Bano, a specialist in Robotics and AI at University College London and the technical lead for the AI system, explained that the system was trained using hundreds of surgical video recordings. "By learning from hundreds of surgical videos, this system is exposed to a variety of procedural examples that might take a surgeon years to encounter," she stated. This extensive training allows the AI to recognize and highlight complex anatomical details with a high degree of accuracy.

“

By learning from hundreds of surgical videos, this system is exposed to a variety of procedural examples that might take a surgeon years to encounter.