• BACKGROUND
    • The diagnosis of rotator cuff tears using radiographs alone is clinically challenging; thus, the utility of deep learning algorithms based on convolutional neural networks has been remarkable in the field of medical imaging recognition. We aimed to evaluate the diagnostic performance of artificial intelligence (a deep learning algorithm; a convolutional neural network) to detect and classify rotator cuff tears using shoulder radiographs, and compare its diagnostic performance with that of orthopedic surgeons.
  • METHODS
    • A total of 1,169 plain shoulder anteroposterior radiographs (one image per shoulder) were included in the total dataset and divided into four groups: intact, small, medium, and large to massive tear groups. The sensitivity, specificity, positive predictive value, negative predictive value, accuracy, and area under the receiver operating curve were measured for the detection of rotator cuff tears through binary classification. The average accuracy, recall, precision, and F1-score were divided into four groups by cuff tear size for multiclass classification.
  • RESULTS
    • The convolutional neural network demonstrated a high performance, with 92% sensitivity, 69% specificity, 86% accuracy, and an AUC of 0.88 for the detection of rotator cuff tears. The average accuracy, recall, precision, and F1-score of the convolutional neural network for classification were 60%, 0.42, 0.49, and 0.45, respectively. The accuracy of the convolutional neural network for the detection and classification of rotator cuff tears was significantly better than that of orthopedic surgeons.
  • CONCLUSION
    • The convolutional neural network demonstrated the diagnostic ability to detect and classify rotator cuff tears using plain shoulder radiographs, and the diagnostic performance exhibited equal to superior accuracy when compared with those of shoulder experts.