Clinical utility of CT-based deep learning for differentiating pulmonary aspergillosis from bacterial pneumonia: a multicenter retrospective study
Tianyu Li, Ronger Zhang, Huanyao Zhang, Deyan Chen, Junnan Pan, Jiejia Chen, Wei Wang, Chengbao Peng, Fan Yang, Xia Zhang, Zhengtu Li, Jinping Zheng, Feng Ye, Yun Li · 2026
Read Clinical utility of CT-based deep learning for differentiating pulmonary aspergillosis from bacterial pneumonia: a multicenter retrospective study by Tianyu Li, Ronger Zhang, Huanyao Zhang, Deyan Chen, Junnan Pan, Jiejia Chen, Wei Wang, Chengbao Peng, Fan Yang, Xia Zhang, Zhengtu Li, Jinping Zheng, Feng Ye, Yun Li (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-13655879.txt.
Description
Li and co-authors build computer tools that read chest scans to tell two lung infections apart. One is caused by a fungus and the other by common bacteria. The two look alike on scans and in symptoms, and lab tests can be slow or need invasive sampling.
The team trained learning models on scans from one hospital in Guangzhou and tested them on patients from a second hospital. A tool that holds up at a new site is more likely to help in real clinics. The models are meant to support doctors, not replace lab proof. A fast, fair guess early in care can steer the first choice of drugs. The study checks whether the tools stay accurate outside their home hospital, a step many such models fail.
Catalog record
| CREATOR | Tianyu Li, Ronger Zhang, Huanyao Zhang, Deyan Chen, Junnan Pan, Jiejia Chen, Wei Wang, Chengbao Peng, Fan Yang, Xia Zhang, Zhengtu Li, Jinping Zheng, Feng Ye, Yun Li |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 70 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |