Development and validation of a predictive model for thyroid nodule malignancy risk based on intralesional and perilesional ultrasound radiomic features
Wanying Liu, Ziran Zhang, Li Ling, Ying Zhao, Jiale Wu, Yongquan Chu · 2026
Read Development and validation of a predictive model for thyroid nodule malignancy risk based on intralesional and perilesional ultrasound radiomic features by Wanying Liu, Ziran Zhang, Li Ling, Ying Zhao, Jiale Wu, Yongquan Chu (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/PMC13561598.txt.
Description
Liu and colleagues build a model to judge whether thyroid nodules are cancerous without surgery, in 2026 medical imaging research. The study enrolled 147 patients whose nodules fell into the uncertain C-TIRADS 4a or 4b ultrasound categories. Radiomics, the mining of numeric patterns from images, captured features inside each nodule and in the ring of tissue around it. Three machine learning methods combined those features with clinical signs to estimate cancer risk.
Analysis identified microcalcification, a taller-than-wide shape, and irregular outline as independent predictors of cancer. The joint clinical-radiomics model using logistic regression performed best, reaching an accuracy score, measured as area under the curve, of 0.866. Its accuracy was 84.4 percent, with sensitivity of 91.3 percent and specificity of 77.3 percent in those cases. Features from the tissue around the nodule contributed most.
Catalog record
| CREATOR | Wanying Liu, Ziran Zhang, Li Ling, Ying Zhao, Jiale Wu, Yongquan Chu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |