UK Surgeons Perform World's First Real-Time AI-Assisted Brain Surgery
Surgeons at University College London Hospitals successfully performed the world's first real-time AI-assisted brain surgery to remove a pituitary tumor from a 48-year-old patient. The custom AI system analyzed live endoscopic footage to help surgeons navigate around critical blood vessels and nerves. This milestone demonstrates the practical application of real-time computer vision in high-stakes surgeries, potentially reducing complications and improving tumor removal rates. It paves the way for "surgeon-assistant" AI systems that act as an extra pair of expert eyes in the operating room. The AI system was trained on hundreds of endoscopic pituitary surgery videos to recognize anatomical landmarks that are often hidden behind bone and tissue. It operates on a second screen, tracking surgical instruments and highlighting safe entry zones without taking control of the procedure.
## BACKGROUND
Pituitary tumors are located at the base of the brain, close to critical structures like the carotid artery and optic nerves, making surgery highly delicate with risks of vision loss or severe bleeding. Endoscopic transsphenoidal surgery (eTSA) involves inserting a camera through the nasal cavity, where surgeons must navigate complex, patient-specific anatomy. Real-time AI assistance helps bridge the gap by identifying landmarks and tracking instruments during the procedure.