A new way to read brain scans may help predict how a tumor will act
Original title: Physics-Informed Multiscale Decoding of Tissue Microstructure: The Gray Level Affinity Metrics (GLAM) Framework.
How far along is this research?
- Lab cells
- Animals
- Review
- Tested in people
This was done on cells in a lab, not in people. It is a very early step.
This was computer work on scans already collected from patients, not a treatment or a tool your doctor can use.
The short version
Researchers built a new computer method for reading brain scans that may help predict how a tumor will behave.
What was studied. Researchers created a new way for a computer to measure the texture and structure of a tumor on a scan. They call it GLAM. They tested it on scans from people with high grade 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 at more than one hospital.
What they found. GLAM picked up more information about the tumor's structure than the usual scan measures do. In tumors with a marker called MGMT that is switched off, which often respond better to treatment, GLAM worked best on its own. It sorted people into a higher risk group and a lower risk group that differed by 668 days of survival. In tumors where that marker was not switched off, mixing GLAM with the usual scan measures worked best, with a 267 day difference between the groups.
What this means, and what it doesn't
What it could mean: In the future, a scan might tell a care team more about what to expect. That could help with planning. It does not change any treatment you would get today.
What it doesn't mean: This is not a new treatment. It is a computer method for measuring scans, tested on scans that were already collected. It has not been used to make real decisions in a clinic. It cannot tell any one person how long they will live. It is not a cure, and it is not a promise of one.
Source: PubMed, July 20, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.