A computer tool tries to tell apart types of slow-growing meningioma from MRI scans
Original title: Multimodal Radiomics Combined with Habitat Analysis for Precise Preoperative Differentiation of WHO Grade I Meningioma Subtypes.
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 tested on scans from real patients, but only by looking back at old records, and it is not used in care today.
The short version
Researchers built a computer tool that looks at MRI scans and tries to guess which type of a slow-growing brain lining tumor a person has, before surgery.
What was studied. Researchers looked back at MRI scans from 334 patients who had a WHO Grade I meningioma. There were 162 with the fibrous type, 91 with the transitional type, and 81 with the meningothelial type. A computer program measured details in the scans, then tried to sort the tumors into those three types. The tool was then checked on a separate group of 67 patients.
What they found. The scans held patterns that the computer could pick up on. The version of the tool that used two kinds of MRI images plus a map of different zones inside the tumor did the best. It did better than the versions that used only one kind of image, or only the tumor zone map. The tumor zones the computer found lined up with real differences in the tumor tissue.
What this means, and what it doesn't
What it could mean: Right now, doctors usually learn the exact type of a meningioma after surgery, when the tissue is looked at under a microscope. A tool like this might one day give a doctor a better idea from the scan alone. That could help with planning surgery. For now, it is a research tool, not something in your clinic.
What it doesn't mean: This is not a treatment. It does not shrink a tumor, and it is not a cure. It also does not mean the tool is accurate enough to trust on its own. It was built by looking back at scans that were already taken, not by testing it in real time with patients. It was not right every time. It has not been approved or put into everyday care, and more testing in more hospitals would be needed first.
Source: PubMed, August 5, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.