ObjectiveTo observe the accuracy of location and operation of traditional blind acupotomy lysis in the treatment of scapulohumeral periarthritis by using the high-frequency ultrasound.MethodsForty-two patients with scapulohumeral periarthritis diagnosed in the First Affiliated Hospital of Xinjiang Medical University and Urumqi Hospital of Traditional Chinese Medicine from February to April 2018 were selected. Four common sites of needle knife in the treatment of scapulohumeral periarthritis were operated blindly, and the process of the needle insertion points location and needle perform were both observed by high-frequency ultrasound.ResultsUsing high-frequency ultrasound to observe and confirm the bare-handed positioning point and needle-knife operating point, we found that the accuracy rate of bare-handed positioning needle-point was 100.0% (42/42). In the process of needling, the accuracies of needle insertion at the point of small tubercle of humerus and the point of bursa of deltoid muscle were high, which was 95.2% (40/42) and 100.0% (42/42), respectively. However, because of the deviation of the needle depth and direction, the accuracies of needle insertion at the coracoid point and the sulcus point between the humeral tubercles were low, which was 45.2% (19/42) and 4.8% (2/42), respectively.ConclusionsTraditional acupotomy lysis is a commonly used method of needle knife treatment. Using high-frequency ultrasound, it is found that even by experienced needle knife doctors, there may still be positioning deviation when using blind method to insert needles. Because the visualization of clinical needle knife is difficult to be carried out universally due to the limitations of time and technology, it is suggested that high-frequency ultrasound could be used as a visualization teaching tool in the training of needle knife operation to assist the training of blind needle knife operation technology, which may improve the accuracy of blind needle knife operation.
Ultraviolet radiation is a primary external factor contributing to skin photoaging, as it induces cellular deoxyribonucleic acid damage and collagen degeneration, thereby accelerating skin aging and increasing the risk of skin cancer. Currently, skin aging assessment mainly relies on dermatologists’ empirical judgment, which is inherently subjective and inefficient. To address these limitations, this study proposes a deep learning–driven intelligent skin aging classification method based on high-frequency ultrasound images. The proposed model employs efficient network version 2 (EfficientNetV2) as the backbone network and introduces the Gaussian error linear unit (GELU) activation function and layer normalization to enhance nonlinear feature representation and training stability. In addition, a global-aware temporal hierarchical network is integrated to enable efficient multi-scale feature extraction of skin tissue. A dual enhancement attention mechanism, combining parallel channel–spatial attention and squeeze-and-excitation modules, is further designed to improve the model’s sensitivity to key aging-related regions. Moreover, a multi-scale path dropout regularization strategy is adopted to effectively alleviate overfitting. Experiments conducted on a facial high-frequency ultrasound dataset collected from subjects aged 25~55 years demonstrate that the proposed method achieves an accuracy of 87.66%, a precision of 88.27%, a recall of 87.66%, an F1 score of 87.80%, and a specificity of 97.94%, consistently outperforming existing mainstream models. These results indicate that the proposed approach enables high-precision identification of skin aging levels and provides an efficient and objective auxiliary diagnostic tool for skincare, anti-aging treatment, and the prevention of photoaging-related skin diseases.