Predicting Ki-67 expression levels in non-small cell lung cancer using an explainable CT-based deep learning radiomics model
Shize Qin, Qing Jia, Chunmei Zhang, Man Li, Xiufu Zhang, Xue Zhou, Dan Su, Yongying Liu, Jun Zhou · 2025
Read Predicting Ki-67 expression levels in non-small cell lung cancer using an explainable CT-based deep learning radiomics model by Shize Qin, Qing Jia, Chunmei Zhang, Man Li, Xiufu Zhang, Xue Zhou, Dan Su, Yongying Liu, Jun Zhou (2025) 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-12727595.txt.
Description
Shize Qin and eight co-authors present a 2025 study on predicting a tumor growth marker from CT scans in lung cancer, without a biopsy. The marker, Ki-67, guides treatment choices. The team built models for two hundred fifty-nine patients at one center and tested them on one hundred twelve at another. Inputs mixed ordinary clinical features with image texture scores and deep learning scores from the scans.
The combined model won clearly on the outside test set, with an accuracy measure near zero point eight nine, beating each single-source model by a significant margin. An explanation method ranked the deep learning score, tumor type, and texture score as the top drivers. The authors present the explainable model as imaging evidence to help clinicians personalize therapy. It offers a noninvasive peek at tumor biology before treatment starts.
Catalog record
| CREATOR | Shize Qin, Qing Jia, Chunmei Zhang, Man Li, Xiufu Zhang, Xue Zhou, Dan Su, Yongying Liu, Jun Zhou |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 34 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |