RESUMEN
Background: Rotator cuff pathology is a common cause of pain and shoulder dysfunction. Several nonoperative treatment modalities have been developed for rotator cuff lesions, but their relative efficacy is not well-established. Purpose/Hypothesis: The purpose of this systematic review and meta-analysis was to evaluate the efficacy and safety of sodium hyaluronate (SH) in the treatment of patients with rotator cuff lesions. It was hypothesized that SH would be found to be more effective than other nonoperative regimens. Study Design: Systematic review; Level of evidence, 3. Methods: We searched various databases to identify eligible studies that evaluated the effects of SH on the pain and shoulder dysfunction attributed to rotator cuff lesions. Outcome measures were pain visual analog scale (VAS) score; Constant score; University of California, Los Angeles (UCLA) score; satisfaction rate; complications; and factors affecting the pain VAS score. Outcomes were reported as weighted mean difference (WMD) or risk ratio. Results: A total of 9 studies were identified for data analysis. Compared with patients treated with other nonoperative treatments (controls), those treated with SH had significantly improved pain VAS scores at 1 week (WMD = -0.95; 95% CI, -1.75 to -0.16; P = .019), 2 weeks (WMD = -1.05; 95% CI, -2.07 to -0.03; P = .044), 3 weeks (WMD = -1.49; 95% CI, -2.88 to -0.11; P = .035), and 4 weeks (WMD = -2.12; 95% CI, -4.05 to -0.19; P = .031). The Constant score was significantly improved in the SH group versus controls at 2 weeks (WMD = 3.25; 95% CI, 2.36 to 4.13; P < .001), 3 months (WMD = 20.28; 95% CI, 0.54 to 40.03; P = .044), and 6 months (WMD = 5.58; 95% CI, 0.94 to 10.21; P = .018). The UCLA score and satisfaction rate did not differ significantly between the 2 groups. No complications associated with SH were reported in the included studies. Metaregression analysis showed that, except for study design (coefficient = -1.64; 95% CI, -2.64 to -0.63; P = .002), none of the variables (sample size, tear type, control treatments) significantly predicted the difference in VAS pain score between SH and other treatments. Conclusion: The present meta-analysis demonstrated that SH was effective in treating patients with rotator cuff lesions.
RESUMEN
Ultrasonography is one of the main imaging methods for diagnosing thyroid nodules. Automatic differentiation between benign and malignant nodules in ultrasound images can greatly assist inexperienced clinicians in their diagnosis. The key of problem is the effective utilization of the features of ultrasound images. In this study, we propose a method that is based on the combination of conventional ultrasound and ultrasound elasticity images based on a convolutional neural network and introduces richer feature information for the classification of benign and malignant thyroid nodules. First, the conventional network model performs pretraining on ImageNet and transfers the feature parameters to the ultrasound image domain by transfer learning so that depth features may be extracted and small samples may be processed. Then, we combine the depth features of conventional ultrasound and ultrasound elasticity images to form a hybrid feature space. Finally, the classification is completed on the hybrid feature space, and an end-to-end CNN model is implemented. The experimental results demonstrate that the accuracy of the proposed method is 0.9470, which is better than that of other single data-source methods under the same conditions.