UCL Surgeons Pioneer Groundbreaking AI-Assisted Brain Tumour Removal

University College London neuroscientists have broken new ground by applying technology to one of the most sensitive challenges in medicine: the safe removal of a brain tumour.

Rhys Hibbert, 48, had a pituitary gland tumour that affected his balance and ultimately threatened his eyesight. Diagnosed in 2024, he embraced the new experimental treatment to resolve the condition.

“If patients are not prepared to join research, how can doctors ever learn and how can medicine ever progress?” he said. “To me, it's a really important and vital part of what these top specialist hospitals do.”

Blood vessels and the nerves controlling vision are tightly packed together in the brain. According to UCL, one tiny slip could lead to blindness, a stroke, or even the death of the patient.

Former UK prime minister Keir Starmer talks at UCL about AI opportunities in medicine. Getty Images Show caption: Former UK prime minister Keir Starmer talks at UCL about AI…

Developers of the technology included Sophia Bano, associate professor in robotics and AI. She said of the technology: “It is designed to help recognise critical anatomy, surgical instruments and tissue interactions in real time, supporting the surgeon during highly delicate procedures.”

UCL officials described how the AI analysed the live surgical video feed, giving real-time support to the operating team that allowed for more precise decisions. A statement added that the system ran on an Nvidia Clara IGX platform tailored to deliver AI in medical device settings.

The surgical team was led by Hani Marcus, consultant neurosurgeon at UCL's National Hospital for Neurology and Neurosurgery. Danyal Khan was the surgical resident leading the work.

In an interview during the research phase, Mr Khan talked about the distilled experience the system brought to the theatre. “As I progress as a surgeon there might be stages where I wonder have I done enough of a particular part of the procedure and should I move on?” he said. “Having that sort of assistant in the background as a reassurance to say actually at this stage, out of the hundreds of videos of experts that this algorithm has watched, the experts would probably start moving on to the next phase.”