A computer tool that measures meningioma size on MRI scans
Original title: A deep learning algorithm for fully automated volumetric measurement of meningioma burden.
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.
It was tested on scans from real patients, but it is a research tool that doctors are not using in regular care yet.
The short version
Researchers built a computer program that outlines meningioma tumors on MRI scans on its own, and it worked better on some tumors than others.
What was studied. Researchers used 450 brain MRI scans from 104 people with meningiomas at two hospitals. They trained a computer program to find and outline the tumors, then checked it against outlines drawn by hand. They also tested it on 1000 scans from 944 patients in a public scan collection.
What they found. The computer outlines came close to the hand-drawn ones for low grade tumors. They matched less well for high grade tumors. The program had the most trouble picking out each separate tumor spot in high grade cases. It did well on the 1000 outside scans.
What this means, and what it doesn't
What it could mean: Measuring how much tumor is there takes time, and two doctors can measure it differently. A tool like this could help make those measurements faster and more consistent. The team put the tool and the code online so others can test it.
What it doesn't mean: This is not a treatment. It does not shrink a tumor or help you live longer. It is a research tool that was tested on scans that were already taken. It is not a cure and it is not part of regular care today. It still needs more testing before doctors would use it on your scans.
Source: PubMed, May 25, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.