A computer tool reads tumor slide images to guess gene activity
Original title: DeepPathway: Predicting Pathway Expression from Histopathology Images.
How far along is this research?
- Lab cells
- Animals
- Review
- Tested in people
This was done on cells in a lab, not in people. It is a very early step.
This is early computer work on tissue images, not a treatment for people.
The short version
Scientists built a computer tool that studies tumor slide pictures to guess how groups of genes are acting.
What was studied. Researchers made a tool called DeepPathway. It learns from regular stained tissue slides, the kind labs already make. They tested it on several cancer data sets, on images from a large public cancer image library, and on brain tumor samples.
What they found. The tool could tell apart certain gene group activity in normal tissue and in tumor tissue. In brain tumor samples, it predicted signs of low oxygen in the tissue. The team could check that work against a special stain that shows low oxygen areas. The paper reports these results without giving numbers in the summary.
What this means, and what it doesn't
What it could mean: Gene tests on tissue can cost a lot, so most people never get them. A tool like this might one day pull some of that information from slides labs already make. For now it may help researchers study tumors, not guide your care.
What it doesn't mean: This is not a treatment and it is not a cure. Nobody was treated or tested in a trial here. This is early computer work on tissue images. It has not been shown to help doctors make better choices for patients. It is a long way from anything you would see at your own clinic.
Source: PubMed, August 26, 2026 · Read the original
This plain-language summary was written by AI and published automatically after passing our automatic safety checks. How we write.