Predicting Helicobacter pylori Antibiotic Resistance from Routine Hematoxylin and Eosin Histopathology Using a Vision-Language Model-Guided Foundation Model Framework
Siping Xiong, Shuguang Liu, Wei Zhang, Degui Liao, Tian Tang, Chao Zeng, Yimin Guo · 2026
Read Predicting Helicobacter pylori Antibiotic Resistance from Routine Hematoxylin and Eosin Histopathology Using a Vision-Language Model-Guided Foundation Model Framework by Siping Xiong, Shuguang Liu, Wei Zhang, Degui Liao, Tian Tang, Chao Zeng, Yimin Guo (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/PMC13436092.txt.
Description
Siping Xiong and colleagues built a computer system that predicts stomach bacteria drug resistance from routine biopsy slides, without lab cultures. Their 2026 study tackles Helicobacter pylori, a common stomach infection that is growing harder to treat with standard antibiotics.
Vision software first filtered slide patches for quality and for the right tissue type, and a large image model then read the kept patches. The team trained and tested the system on biopsy slides from 755 patients across several hospitals, with lab test results as the check. In a test group of 151 patients, the system scored 0.903 for clarithromycin and 0.959 for fluoroquinolones on a standard accuracy scale, where one means perfect. Xiong suggests such tools could flag risky cases early where lab testing is scarce.
Catalog record
| CREATOR | Siping Xiong, Shuguang Liu, Wei Zhang, Degui Liao, Tian Tang, Chao Zeng, Yimin Guo |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 30 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |