Revealing the evolution law of wear conditions and mechanisms is critical for assessing the health status of artificial joints and thereby extending their service life. Notably, high-precision wear particle recognition plays a pivotal role in the intelligent wear analysis of joint implants. However, insufficient and imbalanced particle samples often lead to inadequate recognition accuracy, which fails to meet the requirements of reliable wear particle analysis. Such limitations highlight the urgent need for a robust solution to address sample scarcity and imbalance. To this end, an intelligent wear particle recognition method based on a generative adversarial network is proposed to enhance the accuracy of artificial joint wear analysis. Specifically, a multiscale coordinated attention-based generative adversarial network is designed to produce high-quality wear particle samples, which are used to supplement scarce sample categories and balance the particle distribution. Subsequently, a wear particle classifier is constructed using a neural network, and the training strategy for this classification model is further optimized to ensure high-precision wear particle recognition. Ablation experiments demonstrate that the proposed method achieves an accuracy, precision, recall, and F1-score of 0.90 for wear particle recognition when using the generated samples. All metrics represent a significant improvement compared with the results obtained from the original sample dataset. Meanwhile, the recognition performance of the proposed method outperforms that of other state-of-the-art algorithms. Based on the recognition results of wear particles from joint implants, the particle size and type distributions are derived to evaluate the wear evolution of artificial joints. These findings hold great value for advancing artificial joint wear analysis and enabling reliable failure prediction.
- Article type
- Year
- Co-author
Open Access
Research Article
Online First
Artificial joint replacement is an important technology for treating bone and joint disorders. However, the long-term wear loss of joint prosthesis and periprosthetic osteolysis induced by wear debris causes aseptic loosening, leading to early failure of the prosthesis. Investigating the wear behaviors of artificial joint combination interfaces, including sliding and immobile interfaces, forms the foundation for exploring the formation mechanism of wear debris, studying loosening and failure mechanisms, and improving the abrasion performance of artificial joints. Such an investigation represents a fundamental approach to elucidate the mechanisms behind wear debris formation, explore the factors contributing to loosening and failure, and enhance the abrasion resistance of artificial joints. The literatures on the wear behaviors of artificial joints has been meticulously reviewed and summarized using resources from the Web of Science and China's national knowledge network databases. The primary aim of this study is to provide references for research on the wear behaviors of artificial joint combination interfaces.
Sliding and fretting wear of artificial joints were studied. Sliding wear was produced on the sliding interface between artificial joint prosthesis pairs, and a large amount of wear particles were generated, which were the main cause of prosthesis loosening and failure. Fretting wear occurred at the fixed interface between the prosthesis and bone, leading to the early loosening of artificial joints. Adhesive, abrasive, and fatigue wear were the three main wear mechanisms of artificial joints. The wear of artificial joints was caused by several factors, such as prosthesis structure, material, lubrication, wear debris, operation, and patient. Summarizing the factors influencing the wear behaviors of artificial joints revealed that the design of prosthesis structures and surface modification technologies will be crucial for optimizing and enhancing artificial joints. However, these influencing factors were interrelated; thus, the mechanisms affecting wear behaviors needed to be further discussed. To evaluate the friction and wear performance of artificial joints, researchers mainly used friction and wear experimental machines and joint simulators to obtain wear parameters through in vitro simulation tests. Some scholars had designed novel devices with special functions to implement complex and specific wear research. The sliding wear behaviors of artificial joints were commonly characterized by friction coefficient, abrasion loss, surface morphology, wear debris features, and material composition. By contrast, fretting wear was generally analyzed by the friction coefficient, dissipated energy, and fretting corrosion conditions. Based on the applications of computer vision and artificial intelligence technology, the automation and intelligence levels of wear monitoring had been considerably improved.
Material modification technology is effective in improving the wear performance of artificial joints and is a hotspot in the research field. A novel design of wear devices can provide an in vitro simulation experimental platform for complex and specific wear behavior testing. Further, a comparative analysis of various wear parameters can also comprehensively describe wear behaviors. Moreover, the efficiency and accuracy of artificial joint simulation tests in vitro can be effectively improved using computer vision and artificial intelligence techniques. The friction coefficient, wear surface, wear debris, and material composition are important factors in the wear behaviors of artificial joints, and multiple information fusion is required to study these wear behaviors. The applications of computer vision and artificial intelligence technology provide more solutions for wear debris and mechanism analysis of artificial joints, which are the future directions of wear behavior investigation on artificial joint combination interfaces.
京公网安备11010802044758号