A computer tool that may help tell tumor regrowth from treatment changes on MRI
Original title: Integrating chemotherapy, radiotherapy, and O6-methylguanine-DNA methyltransferase (MGMT) status with deep-learning cellular tumor volumetry sharpens prediction of glioblastoma recurrence on postoperative 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.
Researchers tested this on old scans from real patients, but it is not used in care yet.
The short version
Researchers built a computer tool that reads brain scans and adds treatment details to help doctors tell regrowth from treatment effects.
What was studied. Researchers looked back at 135 MRI scans taken after surgery from 97 people with glioblastoma: A glioma that is given grade 4. Grade 4 is the highest grade there is. The tumor grows fast. Treatment usually starts soon after it is found. It often means surgery, and then radiation and chemotherapy. See the glossary treated between January 2008 and December 2022. Of these scans, 105 were confirmed regrowth and 30 were changes caused by treatment.
What they found. The tool measured the tumor area on 5 types of MRI pictures. It also used whether the person had chemotherapy or radiation, and their MGMT promoter methylation: MGMT is a gene whose protein repairs damage to a tumor's DNA. Methylation turns it down. Your report says how much, and your team uses that when they choose chemotherapy. The line between high and low is not settled. See the glossary status. Adding all of that information made the tool better at telling regrowth apart from treatment changes than using the scan details alone.
What this means, and what it doesn't
What it could mean: After treatment, an MRI can be hard to read. Swelling and scarring from treatment can look like a tumor growing back. Work like this may one day give doctors a better tool to sort that out. That could mean fewer anxious waits and clearer next steps.
What it doesn't mean: This is not a treatment, and it is not a cure. Nothing here changes what medicine or radiation a person gets. The team looked back at old scans in one group of patients. The tool was not tested in real time in the clinic, and it is not something a doctor can use today. It also made mistakes. It is a research tool, not a final answer about anyone's scan.
Source: PubMed, July 9, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.