Corticosteroid injections are widely used to treat enthesopathy and tendinitis, but are also associated with possible side effects, such as tendon degeneration or rupture. However, the mechanism of tendon degeneration or rupture after corticosteroid injection remains controversial. The purpose of this study was to reveal the mechanism of tendon degeneration or rupture after injection of triamcinolone acetonide (TA) or prednisolone (PSL). Forty‐two rats were divided into 3 groups: A normal saline injection group (control group), a TA injection group, and a PSL injection group; the normal saline or corticosteroid was injected around the Achilles tendon. One or 3 weeks after injection, the tendons were subjected to biomechanical testing and histological analysis. At 1 week, the biomechanical strength was significantly lower in the corticosteroid groups. Histological analysis, at 1‐week post‐injection, showed collagen attenuation, increased expression of MMP‐3 and apoptotic cells in the corticosteroid groups. The histological changes and biomechanical weaknesses of the tendon were not seen at 3 weeks. These alterations appeared to be involved in tendon degeneration or rupture after corticosteroid injection. © 2014 Orthopaedic Research Society. Published by Wiley Periodicals, Inc. J Orthop Res 32:1297–1304, 2014.

Background: Screening for elbow osteochondritis dissecans (OCD) using ultrasound (US) is essential for early detection and successful conservative treatment. The aim of the study is to determine the diagnostic accuracy of YOLOv8, a deep-learning-based artificial intelligence model, for US images of OCD or normal elbow-joint images. Methods: A total of 2430 images were used. Using the YOLOv8 model, image classification and object detection were performed to recognize OCD lesions or standard views of normal elbow joints. Results: In the binary classification of normal and OCD lesions, the values from the confusion matrix were the following: Accuracy = 0.998, Recall = 0.9975, Precision = 1.000, and F-measure = 0.9987. The mean average precision (mAP) comparing the bounding box detected by the trained model with the true-label bounding box was 0.994 in the YOLOv8n model and 0.995 in the YOLOv8m model. Conclusions: The YOLOv8 model was trained for image classification and object detection of standard views of elbow joints and OCD lesions. Both tasks were able to be achieved with high accuracy and may be useful for mass screening at medical check-ups for baseball elbow.