A scan reading tool tries to predict a meningioma marker before surgery
Original title: Preoperative prediction of progesterone receptor expression in meningiomas based on diffusion weighted imaging habitat analysis and Transformer-Based deep learning.
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 only tested on scans already taken from people, not used in real care yet.
The short version
Researchers built a computer tool that studies MRI scans to guess one trait of a meningioma before an operation.
What was studied. Researchers looked back at records from people with meningioma at two hospitals, treated between January 2014 and April 2024. They trained computer programs to read a type of MRI scan and predict whether the tumor carried a marker called the progesterone receptor.
What they found. The team kept 13 scan features and 4 patient and imaging features that lined up best with the marker. A combined program, which used both the scan pattern data and the deep learning model, predicted the marker better than a program built from patient and imaging details alone. It also held up when tested on scans from a separate group of patients.
What this means, and what it doesn't
What it could mean: This marker is normally checked in the lab after surgery removes tumor tissue. A tool like this might one day give doctors a hint from a scan alone. That could help with planning before an operation.
What it doesn't mean: This is not a treatment. It does not shrink a tumor, and it is not a cure. The study only looked back at scans that were already taken. The tool was not used to guide anyone's real care. No one has shown that it helps people feel better or live longer. It is not something you can ask for at an appointment today.
Source: PubMed, July 17, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.