A computer tool may tell two brain tumors apart on MRI scans
Original title: Radiomics-guided multimodal MRI fusion framework for non-enhanced glioblastoma noninvasive identification.
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 a computer test on scans people already had, not a treatment you can get.
The short version
A computer program read brain scans and often picked the right tumor type.
What was studied. Doctors looked at MRI scans from 118 people with brain tumors. A computer program tried to tell a glioblastoma: The fastest-growing type of glioma (grade 4). Treatment usually starts soon after diagnosis: surgery first, then radiation and chemotherapy. See the glossary that does not light up on scans from a slower growing astrocytoma. Of the 118 people, 47 had the glioblastoma and 71 had the astrocytoma.
What they found. The program used the person's age plus many small measurements taken from the scans. In one test group of 22 people, it picked the right tumor type 91.0% of the time. In a second test group of 12 people from another hospital, it was right 90.0% of the time.
What this means, and what it doesn't
What it could mean: This is a tool to help with diagnosis. It is not a treatment. Right now these two tumors are told apart by testing a piece of the tumor. A tool like this might one day help doctors tell them apart from scans alone.
What it doesn't mean: This does not change anyone's care today. The scans were old ones the doctors looked back at, not scans read as people came in. The test groups were very small. This is not a treatment and it is not a cure. Much more testing is needed before a tool like this is used in a clinic.
Source: PubMed, August 21, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.