EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access · CC BY-NC-ND 4.0

Development and Validation of an Interpretable Deep Learning Model for Automated Kellgren–Lawrence Grading of Knee Osteoarthritis Using X‐Ray Imaging

Zhen Dai, Chengcheng Feng, Meng Ni, Zhi Tang, Fangyue Cheng, Jinling Zhang iD

Journal of Orthopaedic Research · 2026

DOI: 10.1002/jor.70276 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift Journal of Orthopaedic Research, 2026. Verfasst von Zhen Dai und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopedics, The First Affiliated Hospital of AnhuiMedical University, Hefei, China. Hauptthemen laut MEDLINE: Deep Learning, Osteoarthritis, Knee. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate and reproducible Kellgren–Lawrence grading of radiographic knee osteoarthritis remains challenging, particularly for intermediate grades and anatomically heterogeneous compartments. We present X‐VIG, an interpretable deep learning framework integrating paired anteroposterior and lateral knee radiographs via view‐specific backbones with deformable convolutions, attention‐based feature fusion, and dual classification–regression optimization aligned with five‐grade clinical practice. Grad‐CAM++ visualizations enhance model transparency and support clinical interpretation. In a retrospective cohort ( n = 229) with consensus reference‐standard KL labels established by double‐blinded expert review and patient‐level splitting (70%/30%), X‐VIG achieved AUCs of 0.9646–0.9945 across five anatomical subregions. Multimodal fusion yielded a mean AUC gain of 5.6 percentage points over single‐view models. In a reader study of 50 held‐out patients comprising 100 individual radiographs, X‐VIG outperformed junior radiologists, matched or surpassed senior performance in most subregions, and reduced reading time by 82% (27 s per case). These results position X‐VIG as a credible second reader for standardizing the reporting of knee osteoarthritis in routine clinical workflows.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningOsteoarthritis, KneeHumansRetrospective StudiesRadiographyFemaleMaleMiddle AgedAged

Stichwörter der Autor:innen

KL gradingclassification–regressiondeep learningknee osteoarthritisradiographic assessment

Autor:innen und Institutionen

  • Department of Orthopedics, The First Affiliated Hospital of AnhuiMedical University, Hefei, China.
  • Department of Rheumatology, The First Affiliated Hospital of AnhuiMedical University, Hefei, China.

ORCID-Profile: Jinling Zhang

Zitieren

APA

Dai, Z., Feng, C., Ni, M., Tang, Z., Cheng, F., & Zhang, J. (2026). Development and Validation of an Interpretable Deep Learning Model for Automated Kellgren–Lawrence Grading of Knee Osteoarthritis Using X‐Ray Imaging. Journal of Orthopaedic Research. https://doi.org/10.1002/jor.70276

Vancouver

Dai Z, Feng C, Ni M, Tang Z, Cheng F, Zhang J. Development and Validation of an Interpretable Deep Learning Model for Automated Kellgren–Lawrence Grading of Knee Osteoarthritis Using X‐Ray Imaging. Journal of Orthopaedic Research. 2026. doi:10.1002/jor.70276

BibTeX
@article{Dai2026,
  author = {Dai, Zhen and Feng, Chengcheng and Ni, Meng and Tang, Zhi and Cheng, Fangyue and Zhang, Jinling},
  title = {Development and Validation of an Interpretable Deep Learning Model for Automated Kellgren–Lawrence Grading of Knee Osteoarthritis Using X‐Ray Imaging},
  journal = {Journal of Orthopaedic Research},
  year = {2026},
  doi = {10.1002/jor.70276}
}
Kostenlos starten →