One computer tool that reads many kinds of MRI scans for tumors
Original title: MRICombo: a deep-learning-based framework for universal volumetric segmentation grading-staging and malignancy detection across heterogeneous MRI.
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 computer tool was only tested on past scans, not used in real care yet.
The short version
Researchers built a computer tool that reads MRI scans and helps spot and sort tumors.
What was studied. Researchers built a computer program that learns from examples. They trained it on 7,380 MRI image sets from 2,354 people, using 9 kinds of MRI scans.
What they found. The program could outline 14 key body parts and label 11 major tumor types on scans. It did well at judging how serious a brain tumor called glioma: A tumor that starts in the glial cells, the support cells of the brain and spinal cord. Gliomas are given a grade from 1 to 4 describing how the tumor is expected to behave. See the glossary was, and at some other cancers. It still worked on scans from 734 more people in four separate groups, and it could work even when some scans were missing.
What this means, and what it doesn't
What it could mean: Someday, one tool like this might help doctors read MRI scans faster. For people with glioma: A tumor that starts in the glial cells, the support cells of the brain and spinal cord. Gliomas are given a grade from 1 to 4 describing how the tumor is expected to behave. See the glossary, it could help doctors judge how serious the tumor is. It could also mean fewer separate tools are needed.
What it doesn't mean: This is not a treatment, and it is not a cure. The tool was tested on scans that were already taken, not in everyday care. It is not something your care team can use today. Doctors still read your scans and make the calls.
Source: PubMed, August 8, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.