Clinically integrated multi-modal transformer framework with cross-modal gated fusion and clinical nomogram for automated Kellgren-Lawrence grading of knee osteoarthritis on x-ray images
Yingying Huang, Zihan Shao, Renfang Wang, Hong Qiu · 2026
Read Clinically integrated multi-modal transformer framework with cross-modal gated fusion and clinical nomogram for automated Kellgren-Lawrence grading of knee osteoarthritis on x-ray images by Yingying Huang, Zihan Shao, Renfang Wang, Hong Qiu (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/PMC13281478.txt.
Description
Yingying Huang and colleagues built a smart grading tool for knee arthritis in a 2026 study. Doctors grade knee wear on X-rays with a five-step scale, but grades vary by reader. The team gathered more than two thousand seven hundred knee X-rays from three hospitals, spanning 2018 to 2024. Their tool reads the image and also uses facts like age and weight. A new fusion step blends the two streams and weighs how sure it is.
On a fresh hospital's images, set aside for testing, the tool matched expert grades at a very high level. It beat eight rival designs, including image-only and facts-only tools. It caught most severe cases while rarely flagging healthy knees. A chart version of its logic also sorted risk cleanly. The authors say such tools could make knee grading faster and more even across clinics.
Catalog record
| CREATOR | Yingying Huang, Zihan Shao, Renfang Wang, Hong Qiu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 51127 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |