First live AI-assisted brain surgery removes tumour, restores patient's vision

University College London Hospital (UCL) announced that Rhys Hibbert, a 48‑year‑old father from Bedfordshire, underwent the world’s first live, artificial‑intelligence–assisted brain surgery and successfully had a pituitary tumour removed. The operation, performed on 23 March, avoided damage to critical blood vessels and nerves and preserved Hibbert’s vision.

Hibbert’s tumour, measuring 11 mm, was located on the pituitary gland at the base of the skull. The gland regulates hormones that control growth, metabolism and blood pressure. Because of its proximity to the carotid arteries and the optic nerves, the tumour began to press on the optic nerves, narrowing Hibbert’s peripheral vision and causing dizziness, fatigue and occasional tripping. “I didn’t want this tumour to stop me from making my wife a cup of coffee,” Hibbert said. “I didn’t want to be a burden.”

The surgical team, led by neurosurgeons Prof Hani Marcus and Mr Danyal Khan, used a trans‑nasal endoscopic approach. An endoscope was inserted through the nose to reach the base of the skull, where the tumour lay behind bone and a tough membrane. Identifying a safe route for tumour removal was complicated by individual variations in anatomy and the risk of damaging major vessels or nerves. Conventional practice relies on pre‑operative scans and the surgeon’s experience, but the UCL team added a real‑time AI assistant to the procedure.

The AI system, developed by UCL researchers and funded by the National Institute for Health and Care Research and Google, analyzes a live video feed from the operating microscope. It tracks surgical instruments and highlights areas where vessels and nerves are most likely to be, based on a database of hundreds of previously recorded pituitary tumour surgeries. “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 Marcus explained. Unlike other experimental AI tools, the system works in real time, providing continuous guidance while the surgeon works.

During the operation, the AI marked a safe corridor for tumour removal, allowing the surgeons to excise as much of the tumour as possible without compromising the carotid arteries or optic nerves. The patient’s vision improved markedly in the weeks that followed. “When I opened my eyes after the operation it felt like I had 360‑degree vision – I hadn’t seen that clearly for a year,” Hibbert said. He reports that his energy levels and overall health have returned to normal.

The AI tool is intended to assist, not replace, surgeons. “We want to develop a type of ChatGPT for surgeons, so there can be ‘another expert in the room they can turn to for advice if they want it – or leave if they disagree with it,’” Prof Marcus added.

James Frith, the UK Health Innovation Minister, welcomed the operation as a “life‑changing surgery” that demonstrates the potential of AI in medicine. “AI needs proper safeguards and we will always ensure that safety is taken seriously, but we will also ensure we benefit from the opportunities it brings,” he said.

The team plans to expand the technology into a larger trial and to refine the AI’s real‑time analysis capabilities. If successful, the system could become a standard adjunct in pituitary and other complex neurosurgeries, improving outcomes for patients with tumours near critical structures.