A Computer Tool Judges Glioma Grade From MRI Scans
Original title: Glioma Grade Classification Using Machine Learning and MRI Radiomics: A Single-Center Prospective Study Comparing Original and Wavelet-Transformed Features From Anatomical, Diffusion-Weighted, and Post-Contrast Imaging.
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 people, but it is not used in clinics yet.
The short version
Researchers tested a computer tool that reads MRI scans to tell how fast-growing a glioma: A tumor that starts in the glial cells, the support cells of the brain and spinal cord. Gliomas are graded 1 to 4 by how fast they tend to grow. See the glossary is.
What was studied. The study included 92 people with gliomas confirmed by lab tests on tumor tissue. Each person had MRI scans, and the scan details were fed into several computer models to sort the tumor grade.
What they found. Adding a second way of measuring the scan images helped every model do better. The best setup paired a model called Random Forest with a scan map called eADC. On the held-out test group, it reached an accuracy of 0.97.
What this means, and what it doesn't
What it could mean: Right now, tumor grade is confirmed by testing tissue from surgery or a biopsy. A tool like this might one day help doctors judge grade from scans alone. For some people, that could mean fewer procedures.
What it doesn't mean: This does not mean the tool is ready for your care. It was built and tested at a single center with 92 people. It has not been tested in a large trial, and it has not been approved for everyday use. It is a way to read scans, not a treatment, and it is not a cure. Your care team still needs lab results to be sure of the grade.
Source: PubMed, August 11, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.