A deep transfer learning radiomics nomogram using chest CT for differentiating anterior mediastinal cysts from low-grade thymomas
Li Zhao, Dengwang Zhao, Tong Zhou, Xueqing Sui, Pei Nie, Chongfeng Duan · 2026
Read A deep transfer learning radiomics nomogram using chest CT for differentiating anterior mediastinal cysts from low-grade thymomas by Li Zhao, Dengwang Zhao, Tong Zhou, Xueqing Sui, Pei Nie, Chongfeng Duan (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/pmc-13581725.txt.
Description
Li Zhao and co-authors built a prediction chart that joins clinical traits with image based learning to tell chest cysts apart from low grade tumors, in work published in 2026. The two growths sit in the same chest region and can look alike on scans. Cases were split into training and test sets.
Three clinical traits entered the model, along with scores from image texture analysis and from a deep learning model. The combined chart performed best in the test set, with high accuracy and balanced sensitivity and balance across classes. The deep model alone was close behind. The authors say the chart shows promise as decision support, though more validation is needed before clinical use.
Catalog record
| CREATOR | Li Zhao, Dengwang Zhao, Tong Zhou, Xueqing Sui, Pei Nie, Chongfeng Duan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 32 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |