Automatic Assessment of Knee Osteoarthritis Severity in Portable Devices based on Deep Learning 

Abstract

Background For knee osteoarthritis, the commonly used radiology severity criteria Kellgren-Lawrence lead to variability among surgeons. And most existing diagnosis models require pre-processed radiographs and specific equipment. Methods All enrolled patients diagnosed as KOA who met the criteria were obtained from **** hospital. This study included 2579 images shot from posterior-anterior X-rays of 2378 patients. We used the RefineDet to train and validate this deep learning-based diagnostic model. After developing it, 823 images of 697 patients were enrolled as test set. The whole test set were assessed by up to 5 surgeons and this diagnostic model respectively. To evaluate the model’s performance. we compared the results of model with the KOA severity diagnoses of surgeons based on K-L scales. Results Compared to diagnoses of surgeons, the model achieved an overall accuracy of 0.977. Its sensitivity(recall) for K-L 0 to 4 was 1.0, 0.972, 0.979, 0.983 and 0.989 respectively; for these diagnoses, the specificity of this model was 0.992, 0.997, 0.994, 0.991 and 0.995. The precision and F1-score were 0.5 and 0.667 for K-L 0, 0.914 and 0.930 for K-L 1, 0.978 and 0.971 for K-L 2, 0.981 and 0.974 for K-L 3, 0.988 and 0.985 for K-L 4. And all K-L scales perform AUC > 0.90.The quadratic weighted Kappa coefficient between the diagnostic model and surgeons was 0.815(P＜0.01, 95%CI 0.727–0.903). The performance of the model is comparable to clinical diagnosis of KOA. This model improved the effciency and avoid the cumbersome image-preprocessing. Conclusion The deep learning-based diagnostic model can be used to assess the severity of knee osteoarthritis in portable devices according to Kellgren-Lawrence scales. On the premise of improving the diagnostic efficiency, The results are high-reliability and reproducibility.