H&E to recurrence score: A step forward, but not yet a substitute for genomic testing
Shiqiong Zhou, Qinghua Ke · 2026
Read H&E to recurrence score: A step forward, but not yet a substitute for genomic testing by Shiqiong Zhou, Qinghua Ke (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13572740.txt.
Description
Shiqiong Zhou and Qinghua Ke comment on a deep learning model that predicts breast cancer recurrence scores from routine stained slides. Their 2026 commentary calls the work a step forward, but not yet a substitute for genomic testing.
The model combined slide images with clinical variables and was validated on a major trial plus six external cohorts, over five thousand patients. It flagged high recurrence scores well and even downgraded many clinically high-risk women to low risk. The commentators list limits: tumor heterogeneity yields discordant predictions, and benefit estimates lean on trial surrogates for menopausal status. Clinical use, they argue, must wait.
Catalog record
| CREATOR | Shiqiong Zhou, Qinghua Ke |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 14 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |