AI that labels anatomy during pituitary surgery, tested in people
Original title: First-in-human evaluation of real-time pixel-level AI-assisted anatomical segmentation in neurosurgery: pituitary surgery as an exemplar.
How far along is this research?
- Lab cells
- Animals
- Review
- Tested in people
This was tested in people. That is the most reliable kind of research we share.
This was the first test in people, and it only checked whether the tool could work.
The short version
Surgeons tried an AI tool that labels anatomy on live surgery video.
What was studied. Eight people with pituitary tumors had surgery done with a camera scope. Doctors tested an AI tool that marks body parts on the live video as the surgeon works.
What they found. The AI ran as planned in six of the eight surgeries. In two cases it would not start, because of a setup problem on its computer. The team saw no harm to patients, no problems caused by the AI, and no real distraction for the main surgeon.
What this means, and what it doesn't
What it could mean: Nothing about your care changes today. If tools like this keep working, they may one day help surgeons see key parts more clearly during surgery.
What it doesn't mean: This was a first, very small test to see if the tool could work at all. It does not show that surgery becomes safer or that people do better. The tool is not in regular use in hospitals, and it is not a cure for a tumor.
Source: PubMed, October 3, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.