A New Frontier in Neurosurgery: How Real-Time AI is Protecting Patient Vision During Brain Surgery

Neurosurgeons in London have performed the world’s first AI-assisted operation to remove a brain tumour, successfully saving a patient’s sight. This groundbreaking procedure represents a significant milestone in medical technology, demonstrating how artificial intelligence can work alongside skilled surgeons to navigate some of the body’s most delicate anatomical regions with enhanced precision and safety.

Rhys Hibbert, 48, from Bedfordshire, was the first patient at UCLH to undergo surgery supported by the AI system, which runs on an NVIDIA Clara IGX platform designed to support real-time AI in medical device settings. His condition was discovered by chance in December 2024 when he collapsed during a walk and suffered a seizure. The discovery led to tests that revealed a tumor on his pituitary gland that threatened his vision and required urgent intervention.

The challenge of operating in this region of the brain cannot be overstated. The pituitary gland, blood vessels and nerves controlling vision are tightly packed together in this part of the brain, with the pituitary gland itself around the size of a marble. Damage to these structures during surgery can cause serious complications, including blindness, stroke or death. This extreme density of critical structures demands exceptional surgical precision and awareness.

What makes this procedure revolutionary is the approach to real-time guidance. Rather than relying solely on pre-operative imaging, the AI analysed the live surgical video feed, highlighting critical structures at the base of the brain to support the surgical team’s decision-making and help identify areas to avoid while they removed as much tumour as safely possible. While the surgeon remained in full control, the AI system analysed live camera footage during the procedure, helping identify critical structures such as nerves and blood vessels. This real-time integration represents a fundamental shift in how technology can augment surgical expertise.

The AI system was developed at the UCL Hawkes Institute, a research center dedicated to advancing healthcare technologies. Researchers trained and evaluated the system using a large collection of annotated endoscopic pituitary surgery videos from previous operations. By learning from extensive surgical records, the AI developed the ability to recognize anatomical structures that surgeons needed to protect during the delicate work of tumor removal.

The outcome for Hibbert has been remarkably positive. Hibbert reports significantly improved vision and energy eight weeks after surgery. More specifically, when he opened his eyes after the operation it felt like he had 360-degree vision and he hadn’t seen that clearly for a year. The removal of the tumor not only eliminated the threat to his vision but restored capabilities he had lost to the growing mass.

This procedure should not be understood as AI replacing surgical expertise. Rather, it acted as a real-time guide, giving the surgical team an additional set of eyes while they worked around some of the brain’s most sensitive structures. The fact that an AI system can identify structures in surgical video does not automatically mean it can improve patient outcomes. Researchers will need to demonstrate that using it actually reduces complications, improves tumor removal or produces other meaningful benefits.

The team behind this breakthrough has plans to advance the research further. The team plans a larger clinical trial to determine whether the technology can safely improve outcomes. These future studies will provide crucial evidence about whether real-time AI guidance can consistently enhance patient safety and surgical success across a broader patient population.

This achievement signals an exciting new chapter in surgical medicine, where artificial intelligence serves as a sophisticated tool that enhances rather than replaces human skill. As this technology matures through rigorous clinical testing, it may become standard practice in some of the most challenging surgical procedures, ultimately helping surgeons protect vital structures and improve outcomes for patients facing complex brain pathologies.