Preoperative prediction of thymoma risk classification with machine learning-based computed tomography radiomics features

Kai Zhao, Yiming Liu, Honghao Xu, Wenhan Cai, Jiamei Jin, Leilei Shen, Zirui Zhu, Herui Han, Mingchuan Hu, Qiang Lu, Zhiqiang Xue · 2026

Read Preoperative prediction of thymoma risk classification with machine learning-based computed tomography radiomics features by Kai Zhao, Yiming Liu, Honghao Xu, Wenhan Cai, Jiamei Jin, Leilei Shen, Zirui Zhu, Herui Han, Mingchuan Hu, Qiang Lu, Zhiqiang Xue (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/PMC13471461.txt.

Description

Kai Zhao and co-authors build in 2026 a prediction model that sorts thymus tumors by risk before surgery using only plain CT scans. Thymomas are graded into low and high risk types, but scan features overlap between them, so surgeons often learn the grade only after removal. Records of 436 patients with proven thymomas, gathered over thirteen years, were split into training and validation sets.

The team extracted hundreds of texture features from each tumor outline and narrowed them to eleven that separated the risk groups best. Two ordinary clinical imaging features joined them in a combined scoring chart. That chart outperformed every single model at telling low risk tumors from high risk ones. The authors propose the tool for planning how aggressive surgery should be before the chest is opened.

Catalog record

CREATORKai Zhao, Yiming Liu, Honghao Xu, Wenhan Cai, Jiamei Jin, Leilei Shen, Zirui Zhu, Herui Han, Mingchuan Hu, Qiang Lu, Zhiqiang Xue
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE36283
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13471461

Browse the full library · About the Tower of Babel