Deep learning-based multiclass classification for the diagnosis of hand arthritis on digital radiography: a multicenter study
Chao Deng, Dan Yan, Cong Tang, Xuemei Deng, Chuanyu Li, Xikui Chen, Lihua Deng, Zhe Wu · 2026
Read Deep learning-based multiclass classification for the diagnosis of hand arthritis on digital radiography: a multicenter study by Chao Deng, Dan Yan, Cong Tang, Xuemei Deng, Chuanyu Li, Xikui Chen, Lihua Deng, Zhe Wu (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-13619487.txt.
Description
Deng and co-authors build in 2026 a deep learning system that sorts hand arthritis types from digital X rays. Four classes are covered, osteoarthritis, rheumatoid arthritis, gouty arthritis, and normal hands. The study drew 1,179 radiographs from 520 people at four centers.
Three centers formed a training cohort checked by patient level cross validation. Four model families were trained on the same pipeline. The vision transformer won inside the cohort, at about 0.937 accuracy. On a held out fourth center it classified 133 of 178 images right, accuracy 0.747, with strong area under curve scores per class. The drop outside the home centers bounds the claim.
Catalog record
| CREATOR | Chao Deng, Dan Yan, Cong Tang, Xuemei Deng, Chuanyu Li, Xikui Chen, Lihua Deng, Zhe Wu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 36 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |