Preoperative prediction of Ki-67 expression and prognosis in breast cancer based on contrast-enhanced cone-beam breast CT: a two-centre study
Wenxiu Guo, Binglin Lyu, Yue Ma, Yafei Wang, Keyi Bian, Jiaqi Wu, Yaopan Wu, Jie Jiang, Yueqiang Zhu, Zhaoxiang Ye · 2026
Read Preoperative prediction of Ki-67 expression and prognosis in breast cancer based on contrast-enhanced cone-beam breast CT: a two-centre study by Wenxiu Guo, Binglin Lyu, Yue Ma, Yafei Wang, Keyi Bian, Jiaqi Wu, Yaopan Wu, Jie Jiang, Yueqiang Zhu, Zhaoxiang Ye (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/PMC13576104.txt.
Description
Wenxiu Guo leads a 2026 two-centre study predicting a growth marker in breast cancer from a specialised breast CT scan. The marker, Ki-67, signals how fast tumour cells divide and helps guide treatment before surgery. The team built models from image patterns, deep learning, and clinical facts, testing two cut-off levels for high Ki-67.
The study enrolled 636 patients across training, validation, test, and prognosis groups. Pattern-based models did best, scoring 0.885 and 0.831 on the accuracy curve in the outside test set at the two cut-offs. Combined models scored slightly higher at 0.895 and 0.869 yet did not clearly beat the pattern models alone. A pattern score for the higher cut-off also predicted time without disease returning. The authors call the approach a non-invasive aid for planning.
Catalog record
| CREATOR | Wenxiu Guo, Binglin Lyu, Yue Ma, Yafei Wang, Keyi Bian, Jiaqi Wu, Yaopan Wu, Jie Jiang, Yueqiang Zhu, Zhaoxiang Ye |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 45323 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |