Imaging-based development and validation of artificial intelligence models for lung adenocarcinoma precursor lesions and early lung adenocarcinoma presenting as pulmonary nodules

Junbao Zhang, Yanyi Hou, Yikang Yang, Ziyan Zhang, Yi Gao, Ping Xu · 2026

Read Imaging-based development and validation of artificial intelligence models for lung adenocarcinoma precursor lesions and early lung adenocarcinoma presenting as pulmonary nodules by Junbao Zhang, Yanyi Hou, Yikang Yang, Ziyan Zhang, Yi Gao, Ping Xu (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-13619932.txt.

Description

Junbao Zhang and co-authors published this lung study in 2026. Lung nodules found on scans may be early, mild growths or true invasive cancer, and telling them apart before surgery is hard. The team built an AI system that joins CT image traits with clinical facts. They gathered 1,179 nodules with known outcomes from one center.

Image traits came from a frozen vision model, then a trained probe summed each nodule's slices. A fusion step let image and clinic data weigh each other before the call. Across held-out folds, the system scored well, with accuracy near eighty-one percent. It beat a clinic-only model and a standard score, though not image-only builds by a clear edge. The authors require tests at other centers before clinic use.

Catalog record

CREATORJunbao Zhang, Yanyi Hou, Yikang Yang, Ziyan Zhang, Yi Gao, Ping Xu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE60 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13619932

Browse the full library · About the Tower of Babel