A computer tool measures childhood brain tumors more closely
Original title: Improved Deep Learning Segmentation of Pediatric Diffuse Midline Gliomas After Treatment.
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 already taken from patients, and it is not part of regular care yet.
The short version
Researchers built a computer tool that outlines a child's brain tumor on scans more closely than an older tool did.
What was studied. Researchers made a computer tool to outline diffuse midline 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, a type of brain tumor, on MRI scans. They trained it on scans from people aged 1-30 years, then tested it on 88 scans from 49 patients in a trial.
What they found. The new tool, called DMGtracker, matched the expert outlines more closely than the winning tool from a 2024 contest. The difference was biggest on scans taken after treatment. On those scans, the new tool gave a good enough outline in 64.0% of cases, and the older tool did so in 52.0% of cases.
What this means, and what it doesn't
What it could mean: Doctors measure a tumor on scans to see if it is growing or shrinking. Doing that by hand takes time, and people can measure it differently. A tool like this could make the measuring faster and steadier, above all after treatment.
What it doesn't mean: This is not a treatment, and it is not a cure. The tool measures tumors, it does not treat them. It was tested on scans that were already collected, not in day to day clinic care. It is research software, so you cannot ask for it at an appointment today.
Source: PubMed, August 26, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.