A radiomics-based machine learning model for the preoperative differentiation of lung adenocarcinoma subtypes
Fengjuan Tian, Jing Ding, Zhenyu Cao, Dengfa Yang, Hengfeng Shi, Jian Wang, Hongjie Hu · 2026
Read A radiomics-based machine learning model for the preoperative differentiation of lung adenocarcinoma subtypes by Fengjuan Tian, Jing Ding, Zhenyu Cao, Dengfa Yang, Hengfeng Shi, Jian Wang, Hongjie Hu (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/PMC13545612.txt.
Description
Tian and colleagues built in 2026 a machine learning model that tells lung adenocarcinoma subtypes apart before surgery using CT scans. Subtype guides personal treatment, but standard imaging reads it poorly. The team gathered 3,038 patients from four hospitals, split into training, test, and checking sets. Radiologists outlined tumors, and the model blended clinical details, image texture measures from the tumor and its rim, and deep learning features.
Tian's fused model beat every single-source model, with discrimination scores that held up from the training set to the separate checking set. It separated the lepidic subtype, the slowest-growing pattern, most reliably, while middle and fast patterns were harder. Explanation tools showed which features drove each call, and checks of calibration and clinical benefit supported real-world use. The authors present the model as an aid for planning care before an operation.
Catalog record
| CREATOR | Fengjuan Tian, Jing Ding, Zhenyu Cao, Dengfa Yang, Hengfeng Shi, Jian Wang, Hongjie Hu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |