Development and validation of a deep learning model for automatic severity grading of hip osteoarthritis: a multi-center study

Abstract Background Hip osteoarthritis (HOA) profoundly impairs individuals’ quality of life. Accurate Kellgren–Lawrence (KL) grading is essential for guiding interventions to delay the progression of HOA. However, manual KL grading is constrained by inherent subjectivity and low interobserver reliability. This study aimed to develop and validate a deep learning–based model for the automated grading of HOA. Methods We retrospectively collected 20,745 hip radiographs from two Chinese hospitals for model development, 1,928 radiographs from a third hospital for external validation, and 1,249 hips from the Osteoarthritis Initiative (OAI) dataset. A ResNet-50 network with a Convolutional Block Attention Module was trained and evaluated. Comprehensive performance was evaluated across multiple metrics and compared with orthopedic surgeons of varying clinical experience. In addition, Gradient-weighted Class Activation Mapping (Grad-CAM) was used for interpretability. Results The model achieved 90.83% (95% confidence interval [CI]: 89.96–91.72) accuracy (area under the receiver operating characteristic curve [AUC]: 0.94) on the internal dataset, 86.67% (95% CI: 85.11–88.12) accuracy (AUC: 0.93) externally, and 82.29% (95% CI: 80.22–84.39) accuracy (AUC: 0.90) on the OAI dataset, with most misclassifications confined to adjacent KL grades. In the reader comparison study, it matched deputy chief surgeons. Grad-CAM confirmed that the model predominantly attended to clinically relevant anatomical features associated with KL grading. Conclusions The developed model enables automatic and objective assessment of HOA severity using KL grading across diverse populations and imaging conditions. This tool shows potential to support disease monitoring, and large-scale epidemiologic research to enhance standardization and reproducibility in HOA assessment.

• Publication year

  2025

• Venue

  Annals medicus

• Publication date

  2025-11-09

• Fields of study

  Medicine

• Identifiers
  DOI 10.1080/07853890.2025.2584361PMID 41208350PMCID 12604132
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Deep learning for automated hip fracture detection and classification : achieving superior accuracy.

  2025cited by this paper
• Deep learning-based automated measurement of hip key angles and auxiliary diagnosis of developmental dysplasia of the hip

  2024cited by this paper
• Interobserver Agreement and Performance of Concurrent AI Assistance for Radiographic Evaluation of Knee Osteoarthritis.

  2024cited by this paper
• American Academy of Orthopaedic Surgeons Clinical Practice Guideline Summary Management of Osteoarthritis of the Hip.

  2024cited by this paper
• Evaluation of Osteoarthritis Disease Burden in China During 1990–2019 and Forecasting Its Trend Over the Future 25 Years

  2024cited by this paper
• Automatic hip osteoarthritis grading with uncertainty estimation from computed tomography using digitally-reconstructed radiographs

  2023cited by this paper
• Ensemble deep-learning networks for automated osteoarthritis grading in knee X-ray images

  2023cited by this paper
• A fully automatic target detection and quantification strategy based on object detection convolutional neural network YOLOv3 for one-step X-ray image grading.

  2023cited by this paper
• Development and Validation of An Automated Classification System for Osteonecrosis of the Femoral Head Using Deep Learning Approach: A Multi-Center Study.

  2023cited by this paper
• Assessment of a novel deep learning-based software developed for automatic feature extraction and grading of radiographic knee osteoarthritis

  2023cited by this paper
• Global, regional, and national burden of osteoarthritis, 1990–2020 and projections to 2050: a systematic analysis for the Global Burden of Disease Study 2021

  2023cited by this paper
• When are patients with osteoarthritis referred for surgery?

  2023cited by this paper
• Diagnostic performance for severity grading of hip osteoarthritis and osteonecrosis of femoral head on radiographs: deep learning model vs. board-certified orthopaedic surgeons

  2023cited by this paper
• Deep Learning Approach for Diagnosing Early Osteonecrosis of the Femoral Head Based on Magnetic Resonance Imaging.

  2022cited by this paper
• Osteoarthritis of the hip: is radiography still needed?

  2022cited by this paper
• Imaging of Osteoarthritis of the Hip.

  2022cited by this paper
• Consensus Guidelines on Interventional Therapies for Knee Pain (STEP Guidelines) from the American Society of Pain and Neuroscience

  2022cited by this paper
• Development and Validation of an Artificial Intelligence–Powered Platform for Prostate Cancer Grading and Quantification

  2021cited by this paper
• Diagnosis and Treatment of Hip and Knee Osteoarthritis: A Review.

  2021cited by this paper
• Automating classification of osteoarthritis according to Kellgren-Lawrence in the knee using deep learning in an unfiltered adult population

  2021cited by this paper
• Development and Validation of a Multitask Deep Learning Model for Severity Grading of Hip Osteoarthritis Features on Radiographs.

  2020cited by this paper
• Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study.

  2020cited by this paper
• Deep Learning-Based End-to-End Diagnosis System for Avascular Necrosis of Femoral Head

  2020cited by this paper
• Application of a deep learning algorithm for detection and visualization of hip fractures on plain pelvic radiographs

  2019cited by this paper
• Performance of a Deep Learning Algorithm in Detecting Osteonecrosis of the Femoral Head on Digital Radiography: A Comparison With Assessments by Radiologists.

  2019cited by this paper
• Deep learning predicts hip fracture using confounding patient and healthcare variables

  2018cited by this paper
• Management of Osteoarthritis of the Hip

  2018cited by this paper
• Applying Densely Connected Convolutional Neural Networks for Staging Osteoarthritis Severity from Plain Radiographs

  2018cited by this paper
• Automatic Knee Osteoarthritis Diagnosis from Plain Radiographs: A Deep Learning-Based Approach

  2017cited by this paper
• A preliminary examination of the diagnostic value of deep learning in hip osteoarthritis

  2017cited by this paper
• Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

  2016cited by this paper
• Classifications in Brief: Kellgren-Lawrence Classification of Osteoarthritis

  2016cited by this paper
• US Spending on Personal Health Care and Public Health, 1996-2013.

  2016cited by this paper
• Atlas of individual radiographic features in osteoarthritis, revised.

  2007cited by this paper
• Socioeconomic impact of osteoarthritis in Hong Kong: utilization of health and social services, and direct and indirect costs.

  2003cited by this paper
• Radiological Assessment of Osteo-Arthrosis

  1957cited by this paper

• Non-Imaging Differential Diagnosis of Lower Limb Osteoarthritis: An Interpretable Machine Learning Framework

  2026influential citation