London Surgeons Remove 11mm Brain Tumour With Live AI Anatomy Mapping
The system color-coded critical anatomy during a delicate pituitary procedure, but the reported result is one patient case within a clinical trial—not a demonstrated safety advantage over standard surgery.
Listen to this story
The audio brief
Story brief
3 key pointsAt London’s National Hospital for Neurology and Neurosurgery, an AI system moved from research into a patient clinical trial during a May operation, overlaying live footage with color-coded anatomy as surgeons removed Rhys Hibbert’s 11mm pituitary tumour. It recognized glands, nerves, vessels, instruments, and tissue interactions, but made no decisions; surgeons retained control. Hibbert recovered and returned to...
- 01
Pituitary surgery risks damage to vision-related nerves and vessels; officials said a one-millimetre error can mean blindness, stroke, or death.
- 02
AI was trained on hundreds of surgical videos, exposing it to a breadth of cases beyond a single surgeon’s experience.
- 03
The National Institute for Health and Care Research funded the procedure as a clinical trial and the hospital’s first patient use.
London neurosurgeons used a live AI video-analysis system to help remove an 11mm pituitary tumour from 48-year-old Rhys Hibbert. Health officials described the May procedure as the world’s first successful AI-assisted operation to remove a brain tumour; the surgical team remained in control throughout.
A live view of structures surgeons need to protect
The operation took place at the National Hospital for Neurology and Neurosurgery in London. The AI analyzed live camera footage, identifying the pituitary gland, nerves, blood vessels, surgical instruments, and interactions between tissue and instruments in real time.
Its interface color-coded critical anatomy that surgeons needed to avoid. The tool therefore acted as a recognition layer over the surgical field, rather than making surgical decisions or directing the operation. The hospital had previously used the technology as a research tool; this was its first use on a patient.
By learning from hundreds of surgical videos, [the system] has been exposed to a breadth of surgical examples that would take a surgeon many years to encounter.
Dr Sophia Bano, associate professor in robotics and AI at UCL and technical lead for the system
The anatomy leaves little room for error
The pituitary gland sits close to blood vessels and nerves that control vision. Health officials said going a millimetre wrong can make a critical difference, with blindness, stroke, or death among the potential consequences. Hibbert’s hormone imbalance and vision problems had worsened after his 2024 diagnosis and initial nonsurgical management; officials said he faced blindness without surgery.
A clinical-trial milestone, not a proven outcome advantage
Within a week, Hibbert could walk independently without glasses or sticks, and he later returned to work. That recovery documents the result for this patient, not whether real-time AI labeling improves surgical safety or outcomes across a broader group.
The National Institute for Health and Care Research funded the operation as part of a clinical trial. The immediate shift is from a hospital research tool into patient care under that setting. Evidence from more patients or a comparison with standard practice would be needed to show whether the visual guidance changes outcomes.
Sources
- theguardian.comLondon neurosurgeons perform first successful AI-assisted operation to remove brain tumour
