A web-based semi-supervised deep learning platform for automated AS-OCT assessment and monitoring of infectious keratitis
Yiming Sun, Peng Jin, Jingxuan Cai, Pengjie Chen, Nuliqiman Maimaiti, Yaqi Wang, Xianwen Liu, Zhichao Hu, Guiping Qian, Gangyong Jia, Peifang Xu, Juan Ye · 2026
Read A web-based semi-supervised deep learning platform for automated AS-OCT assessment and monitoring of infectious keratitis by Yiming Sun, Peng Jin, Jingxuan Cai, Pengjie Chen, Nuliqiman Maimaiti, Yaqi Wang, Xianwen Liu, Zhichao Hu, Guiping Qian, Gangyong Jia, Peifang Xu, Juan Ye (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/PMC13635184.txt.
Description
Yiming Sun and eleven colleagues published this 2026 paper on a web platform that grades eye infections automatically. Infectious keratitis, an infected sore on the cornea, blinds millions, and judging its severity by eye is subjective. Their system reads cross-section eye scans, outlines the cornea and the infected tissue, and measures the lesion's depth and width. It then rebuilds the cornea in three dimensions so doctors can watch the disease change.
The system learned from more than three thousand scans using a partly self-taught method robust to artifacts and fuzzy borders. Its outlines matched expert markings closely. Its depth and width grades agreed with reference readings more tightly than the human experts agreed with each other. Width classification was especially strong. The authors present the platform as an objective, non-invasive way to stage these infections and follow them visit by visit, reducing dependence on scarce specialist judgment.
Catalog record
| CREATOR | Yiming Sun, Peng Jin, Jingxuan Cai, Pengjie Chen, Nuliqiman Maimaiti, Yaqi Wang, Xianwen Liu, Zhichao Hu, Guiping Qian, Gangyong Jia, Peifang Xu, Juan Ye |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 42184 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |