EUVIMEDEUVIMED entdecken
Crossref

Deep contrastive learning improves identification of early‐stage knee osteoarthritis across multicohort X‐ray datasets

Ligan Jia, Guangyuan Du, Zijuan Fan, Xiaoke Li, Haifeng Liu, Jing Zhang, Dijun Li, Lei Yan, Jingwei Jiu, Ruoqi Li, Songyan Li, Yiqi Yang und 7 weitere

Knee Surgery, Sports Traumatology, Arthroscopy · 2026

DOI: 10.1002/ksa.70191 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Knee Surgery, Sports Traumatology, Arthroscopy, 2026. Verfasst von Ligan Jia und 18 weiteren Autor:innen. Beteiligte Einrichtung: Department of Orthopaedic Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. Hauptthemen laut MEDLINE: Osteoarthritis, Knee, Deep Learning. Die Arbeit nennt 18 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Zhejiang Medical and Health Science and Technology Project, Natural Science Foundation of Zhejiang Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

To develop a Kellgren–Lawrence (K–L) grading recognition framework for knee osteoarthritis (KOA) with enhanced capability for early‐stage detection and to validate its transferability across three independent cohorts.

Methods

Weight‐bearing anteroposterior knee radiographs were obtained from three datasets: the osteoarthritis initiative (OAI), Wuchuan and Shunyi. The OAI dataset included baseline, 72‐month, and 96‐month follow‐up images, while the Wuchuan and Shunyi datasets were collected from Wuchuan (China) and Shunyi District (Beijing), respectively. Contrastive learning was incorporated into model training to construct the Augmented Dataset‐Wide‐ResMRnet‐Contrastive Loss‐Cross Entropy (AW2C) framework.

Results

The AW2C framework achieved overall classification accuracies of 83.0%, 82.0% and 80.5% on the OAI, Wuchuan and Shunyi datasets, respectively, with corresponding area under the curve (AUC) of 97.0%, 96.7% and 95.6%. Compared with the baseline model, accuracy for K–L grade 2 improved from 64% to 80%, and discrimination between K–L grades 1 and 2 was notably enhanced.

Conclusions

The proposed AW2C framework demonstrated robust and transferable performance for automated radiographic K–L grading of KOA, particularly improving recognition of early‐stage and suspected disease. With further optimisation, it holds promise as a reliable tool for large‐scale studies and clinical decision support. Level of Evidence Level III.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Osteoarthritis, KneeDeep LearningHumansMiddle AgedFemaleMaleRadiographyAgedEarly Diagnosis

Stichwörter der Autor:innen

K‐L gradingcontrastive learningdeep learning modelknee osteoarthritisradiographic analysis

Autor:innen und Institutionen

  • Department of Orthopaedic Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
  • School of Computer Science and Technology, Xinjiang University, Urumchi, China.
  • Department of Health Statistics, School of Public Health, Sun Yat-sen University, Guangzhou, China.
  • Department of Orthopaedic Surgery, Shanxi Medical University Second Affiliated Hospital, Taiyuan, China.
  • Department of Emergency Surgery, The Affiliated Hospital of Guizhou Medical University, Guiyang, China.
  • Department of Orthopedics, Orthopedic Research Institute, West China Hospital, Sichuan University, Chengdu, Sichuan Province, China.

ORCID-Profile: Bin Wang

Förderung

  • National Natural Science Foundation of China
  • Zhejiang Medical and Health Science and Technology Project
  • Natural Science Foundation of Zhejiang Province
  • Education Reform Project of Zhejiang University School of Medicine
  • Medical Education Research Project of The First Affiliated Hospital, Zhejiang University School of Medicine
  • Special Fund Project for Clinical Medical Research of Zhejiang Medical Association

Zitieren

APA

Jia, L., Du, G., Fan, Z., Li, X., Liu, H., Zhang, J., Li, D., Yan, L., Jiu, J., Li, R., Li, S., Yang, Y., Liu, H., Ren, Y., Liu, X., Li, J. J., Zhang, Y., Lin, J., & Wang, B. (2026). Deep contrastive learning improves identification of early‐stage knee osteoarthritis across multicohort X‐ray datasets. Knee Surgery, Sports Traumatology, Arthroscopy. https://doi.org/10.1002/ksa.70191

Vancouver

Jia L, Du G, Fan Z, Li X, Liu H, Zhang J, et al. Deep contrastive learning improves identification of early‐stage knee osteoarthritis across multicohort X‐ray datasets. Knee Surgery, Sports Traumatology, Arthroscopy. 2026. doi:10.1002/ksa.70191

BibTeX
@article{Jia2026,
  author = {Jia, Ligan and Du, Guangyuan and Fan, Zijuan and Li, Xiaoke and Liu, Haifeng and Zhang, Jing and Li, Dijun and Yan, Lei and Jiu, Jingwei and Li, Ruoqi and Li, Songyan and Yang, Yiqi and Liu, Huachen and Ren, Yijia and Liu, Xuanbo and Li, Jiao Jiao and Zhang, Yuqing and Lin, Jianhao and Wang, Bin},
  title = {Deep contrastive learning improves identification of early‐stage knee osteoarthritis across multicohort X‐ray datasets},
  journal = {Knee Surgery, Sports Traumatology, Arthroscopy},
  year = {2026},
  doi = {10.1002/ksa.70191}
}
Kostenlos starten →