Kim BS, et al. Ann Rehabil Med. 2015 Feb;39(1):52-55. http://dx.doi.org/10.5535/arm.2015.39.1.52

Purpose: The aim of this study was to develop a neural network that accurately and effectively segments the median nerve in ultrasound (US) images.Methods: In total, 1,305 images of the median nerve of 123 normal subjects were used to train and evaluate the model. Four datasets from two measurement regions (wrist and forearm) of the nerve and two US machines were used. The neural network was designed for high accuracy by combining information at multiple scales, as well as for high efficiency to prevent overfitting. The model was designed in two parts (cascaded and factorized convolutions), followed by selfattention over scale and channel features. The precision, recall, dice similarity coefficient (DSC), and Hausdorff distance (HD) were used as performance metrics. The area under the receiver operating characteristic curve (AUC) was also assessed.Results: In the wrist datasets, the proposed network achieved 92.7% and 90.3% precision, 92.4% and 89.8% recall, DSCs of 92.3% and 89.7%, HDs of 5.158 and 4.966, and AUCs of 0.9755 and 0.9399 on two machines. In the forearm datasets, 79.3% and 87.8% precision, 76.0% and 85.0% recall, DSCs of 76.1% and 85.8%, HDs of 5.206 and 4.527, and AUCs of 0.8846 and 0.9150 were achieved. In all datasets, the model developed herein achieved better performance in terms of DSC than previous U-Net-based systems.Conclusion: The proposed neural network yields accurate segmentation results to assist clinicians in identifying the median nerve.

Kim DK, et al. Ann Rehabil Med. 2017 Feb;41(1):58-65. https://doi.org/10.5535/arm.2017.41.1.58

Objective: Primary frozen shoulder causes significant pain and progressively restricts shoulder movements. Diagnosis is primarily clinically based on patient history and physical examination. Management is mainly non-invasive owing to its self-limiting clinical course. However, clinical practice guidelines for frozen shoulder have not yet been developed in Korea. The developed guidelines aim to provide evidence-based recommendations for the diagnosis and treatment of frozen shoulder.Methods: A guideline development committee reviewed the literature from four databases (PubMed, Embase, Cochrane Library, and KMbase). Using the PICO (Population, Intervention, Comparator, and Outcome) framework, the committee formulated two backgrounds and 16 key questions to address common clinical concerns. Recommendations were made using the Grading of Recommendations, Assessment, Development, and Evaluation framework.Results: Diabetes, thyroid disease, and dyslipidemia significantly increase the risk of developing a frozen shoulder. Although frozen shoulder is often self-limiting, some patients may experience long-term disabilities. Ultrasound and magnetic resonance imaging should be used as adjunctive tools alongside clinical diagnosis, and not as independent diagnostic methods. Noninvasive approaches, such as medications, physical modalities, exercises, electrical stimulation, and manual therapy, may reduce pain and improve shoulder function. Other noninvasive interventions have limited evidence, and their application should be based on clinical judgment. Intra-articular steroid injections are recommended for treatment, and physiotherapy or hydrodilatation with steroid injections can also be beneficial.Conclusion: These guidelines provide evidence-based recommendations for diagnosing and treating primary frozen shoulder.

Yang J, et al. Korean Circ J. 2009 May;39(5):198-204. http://dx.doi.org/10.4070/kcj.2009.39.5.198