How blurry MRI scans affect a computer tool that outlines tumors
Original title: Evaluation of the image quality index with MRI motion artifacts on tumor segmentation using 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.
This was a computer test on scan images, not a treatment for people.
The short version
Small movements during an MRI can blur the scan and change how a computer marks a tumor.
What was studied. Doctors traced brain tumors by hand on MRI scans from 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. A computer tool then marked the tumors. The team added fake blur from movement and checked the results.
What they found. The picture quality scores did not line up well with how the computer outlined the tumor. One score, called SSIM, matched what people saw with their own eyes better than the others. An SSIM of 0.8 matched a visual score of 2 or higher. At that level, people could still tell where the tumor edges were.
What this means, and what it doesn't
What it could mean: This is early work on quality checks for brain MRI scans. In time it may help teams judge when a scan is too blurry to trust. Holding still during your scan still helps.
What it doesn't mean: This is not a treatment, and it does not change your care today. The blur was made by computer, not by real patients moving. The team says the results may change with more cases and other computer tools. More testing with real scans is needed first. It is not a cure or a promise of one.
Source: PubMed, September 22, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.