Full Breakdown
AI-Assisted Neurosurgery Saves Patient’s Sight
8/27/2026, 8:15:01 PM
The Pioneering Operation
In May 2026, neurosurgeons at the National Hospital for Neurology and Neurosurgery (NHNN), part of the University College London Hospitals NHS Foundation Trust, performed the world’s first successful brain operation that used live artificial-intelligence assistance. The patient, 48-year-old Rhys Hibbert of Bedfordshire, underwent an endoscopic removal of an 11 mm (0.433 in) non-cancerous pituitary tumour that was pressing on his optic nerves and threatening blindness. Surgeons inserted a thin camera through the nose to reach the tumour, while a bespoke AI system analysed the live video feed, highlighted hidden vessels and nerves, and suggested the safest paths for tissue removal. The AI acted only as an advisory tool; the surgical team retained full control throughout the procedure.
Background & Context
Pituitary tumours sit at the base of the skull near the carotid arteries and optic nerves, making their removal especially delicate. Conventional endoscopic surgery relies on pre-operative scans and the surgeon’s experience; in the UK, an average surgeon performs only 10–20 of these operations annually. Reported complication rates for pituitary tumour removal range from a 25–50 % chance of incomplete resection to a 0.5–2 % risk of injuring a major blood vessel, which can lead to blindness, stroke, or death.
Data & Statistics
- Tumour size: 11 mm (0.433 in).
- Typical surgeon case load: 10–20 operations per year.
- Complication risk: 25–50 % incomplete removal; 0.5–2 % major vessel injury.
- AI training set: hundreds of recorded pituitary tumour surgeries, with anatomical structures manually annotated to teach the system to recognise critical anatomy in real time.
Official Statements & Responses
Prof Hani Marcus, a professor of neurosurgery at UCL who helped develop the AI tool, emphasized that the system is designed to act as an “expert second pair of eyes” and operates in real time, unlike earlier experimental AI aids. The research team, funded by the National Institute for Health and Care Research (NIHR) and Google, stressed that the AI merely assists; surgeons maintain ultimate decision-making authority. NIHR scientific director Prof Mike Lewis described the operation as “pioneering” and highlighted the potential for advanced AI to support surgeons and improve patient care.
Verbatim Quotes
- “From a patient safety perspective, I can see absolutely the benefit. There are no road signs inside our head,” — Hibbert. Until
- “It is trained on more operations than most surgeons see or do in a lifetime and can act like an expert second pair of eyes,” — Prof Hani Marcus
- “When I opened my eyes after the operation it felt like I had got 360-degree vision - I hadn't seen that clearly for a year,” — Hibbert. And, an associate professor
- “When I came round … I could see everything in the room clearly,” — Rhys Hibbert
What’s Next
Following the successful case, the UCL team is preparing a larger clinical trial to evaluate the AI system across multiple centres. Their long-term ambition, as stated by Prof Marcus, is to develop a “ChatGPT for surgeons” that can be consulted for advice or ignored at the surgeon’s discretion, expanding the role of real-time AI assistance in complex operations.
