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.

Objectives: The aim of this study was to investigate the effect of hyperglycaemia on oxidative stress markers and inflammatory and matrix gene expression within tendons of normal and diabetic rats and to give insights into the processes involved in tendinopathy. Methods: Using tenocytes from normal Sprague-Dawley rats, cultured both in control and high glucose conditions, reactive oxygen species (ROS) production, cell proliferation, messenger RNA (mRNA) expression of NADPH oxidase (NOX) 1 and 4, interleukin-6 (IL-6), matrix metalloproteinase (MMP)-2, tissue inhibitors of matrix metalloproteinase (TIMP)-1 and -2 and type I and III collagens were determined after 48 and 72 hours in vitro. In an in vivo study, using diabetic rats and controls, NOX1 and 4 expressions in Achilles tendon were also determined. Results: In tenocyte cultures grown under high glucose conditions, gene expressions of NOX1, MMP-2, TIMP-1 and -2 after 48 and 72 hours, NOX4 after 48 hours and IL-6, type III collagen and TIMP-2 after 72 hours were significantly higher than those in control cultures grown under control glucose conditions. Type I collagen expression was significantly lower after 72 hours. ROS accumulation was significantly higher after 48 hours, and cell proliferation after 48 and 72 hours was significantly lower in high glucose than in control glucose conditions. In the diabetic rat model, NOX1 expression within the Achilles tendon was also significantly increased. Conclusion: This study suggests that high glucose conditions upregulate the expression of mRNA for NOX1 and IL-6 and the production of ROS. Moreover, high glucose conditions induce an abnormal tendon matrix expression pattern of type I collagen and a decrease in the proliferation of rat tenocytes. Cite this article: Y. Ueda, A. Inui, Y. Mifune, R. Sakata, T. Muto, Y. Harada, F. Takase, T. Kataoka, T. Kokubu, R. Kuroda. The effects of high glucose condition on rat tenocytes in vitro and rat Achilles tendon in vivo. Bone Joint Res 2018;7:362–372. DOI: 10.1302/2046-3758.75.BJR-2017-0126.R2

Fascia lata augmentation of massive rotator cuff tears has shown good clinical results. However, its biological effect during the early healing process is not clearly understood. The purpose of the study was to evaluate the biological efficacy of fascia lata augmentation during the early healing process of rotator cuff tears using a rabbit rotator cuff defect model. The infraspinatus tendon was resected from the greater tuberosity of a rabbit to create a rotator cuff tear. The tendon edge was directly sutured to the humeral head. The rotator cuff repaired site was augmented with a fascia lata autograft (augmentation group, group A). The rotator cuff defect in the contralateral shoulder was repaired without augmentation (reattachment group, group R). A group with intact rotator cuff was set as the control group. Histological examinations and mechanical analysis were conducted 4 and 8 weeks postoperatively. In the HE staining, the tendon maturing score of group A was higher than that of group R at 4 weeks postoperatively. In the safranin O staining, proteoglycan staining at the repaired enthesis in group A at 4 weeks postoperatively was stronger than that in group R. Picrosirius red staining showed that type III and type I collagen in group A was more strongly expressed than that in group R at 4 weeks postoperatively. The ultimate failure load of the infraspinatus tendon–humeral head complex in group A was statistically higher than that in group R at 4 weeks postoperatively. The ultimate failure load of group A was similar to that of the control group. The biological and mechanical contribution of fascia lata augmentation for massive rotator cuff tears was analyzed in this study. Type III collagen was reported to be expressed during the tendon healing process. Although the biological action similar to natural ligament healing occurred around the fascia lata grafts, type III collagen was gradually replaced by type I collagen as the tissue matured. Our results suggest that fascia lata augmentation could stimulate biological healing and provide initial fixation strength of the repaired rotator cuff.

Substantial advancements in markerless motion capture accuracy exist, but discrepancies persist when measuring joint angles compared to those taken with a goniometer. This study integrates machine learning techniques with markerless motion capture, with an aim to enhance this accuracy. Two artificial intelligence-based libraries—MediaPipe and LightGBM—were employed in executing markerless motion capture and shoulder abduction angle estimation. The motion of ten healthy volunteers was captured using smartphone cameras with right shoulder abduction angles ranging from 10° to 160°. The cameras were set diagonally at 45°, 30°, 15°, 0°, −15°, or −30° relative to the participant situated at a distance of 3 m. To estimate the abduction angle, machine learning models were developed considering the angle data from the goniometer as the ground truth. The model performance was evaluated using the coefficient of determination R² and mean absolute percentage error, which were 0.988 and 1.539%, respectively, for the trained model. This approach could estimate the shoulder abduction angle, even if the camera was positioned diagonally with respect to the object. Thus, the proposed models can be utilized for the real-time estimation of shoulder motion during rehabilitation or sports motion.