Can AI read scans to predict how immune therapy works?
Original title: Radiomics and deep learning for immune checkpoint inhibitor outcomes: imaging-derived immune phenotyping and clinical translation across solid tumors.
How far along is this research?
- Lab cells
- Animals
- Review
- Tested in people
This looks across many earlier studies rather than running a new one.
This is a review of where the research is heading, not a new treatment you can get.
The short version
Researchers looked at AI tools that study scans, and say these tools are not ready for your care yet.
What was studied. This was a review paper, not a new study. The authors went through past research that used AI on CT, MRI, and PET scans. They wanted to know if AI could predict how well immune therapy drugs work in solid tumors.
What they found. CT scans have the most research behind them, mostly in lung cancer. MRI added useful extra detail in liver cancer and in cancer that had spread to the brain. The scan patterns did line up with signs of immune activity inside tumors. But the authors say this does not prove the tools can guide a treatment choice.
What this means, and what it doesn't
What it could mean: Nothing about your care changes today. Your doctor still uses regular scans, lab tests, and tissue samples. Someday AI may help read scans, but it would add to those tests, not take their place.
What it doesn't mean: This is not a new treatment, and it is not a cure. It is a summary of where the research stands, not a new result. Most of the studies were small and looked back at old records. Results also shifted with different scan machines and settings. The authors call these tools investigational, which means still being tested. They are not part of everyday care.
Source: PubMed, September 21, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.