Ultrasonography is an acceptable modality to evaluate median nerve (MN) in patients with carpal tunnel syndrome (CTS). Additional investigations are needed to evaluate sonographic parameters and compare their performances with artificial intelligence (AI) methods. The aim of this study is to compare the performance of shear wave elastography, morphometry, and AI techniques to predict MN entrapment accurately. 200 wrists including 100 CTS and 100 control wrists were included. Twelve morphological and five elasticity parameters were measured from each MN. Two AI techniques namely, support vector machine (SVM), and convolutional neural network (CNN) were used to diagnose CTS. MN area with area under receiver-operating characteristic curve (AUC) of 0.949 and mean elasticity with AUC of 0.942 showed the highest performance to differentiate CTS from control wrists among morphological and elasticity parameters, respectively. The CNN achieved the best performance with AUC of 0.980, while SVM obtained AUC of 0.943 in testing dataset to diagnose CTC. MN is larger, stiffer, more irregular and extended in CTS patients. Deep learning technique yielded the highest performance in diagnosing CTS automatically. AI methods have vast potential to be implemented in clinical practice as an auxiliary tool for the assessment of CTS with high accuracy.

超声检查是评估腕管综合症（CTS）患者中位神经（MN）的可接受方式。需要进行其他调查以评估超声参数，并将其性能与人工智能（AI）方法进行比较。这项研究的目的是比较剪切波弹性成像，形态计量学和AI技术的性能，以准确预测MN的夹带。包括200个手腕，包括100个CTS和100个控制手腕。从每个MN测量了十二个形态学参数和五个弹性参数。支持向量机（SVM）和卷积神经网络（CNN）这两种AI技术被用于诊断CTS。MN区域，接收器工作特性曲线（AUC）下的面积为0.949，平均弹性为AUC为0。942在区分形态和弹性参数方面分别表现出从对照腕部区分CTS的最高性能。CNN以0.980的AUC取得最佳性能，而SVM在测试数据集中诊断CTC的AUC为0.943。在CTS患者中，MN更大，更僵硬，更不规则并且延伸。深度学习技术在自动诊断CTS中产生了最高的性能。AI方法具有巨大的潜力，可以在临床实践中作为高精度评估CTS的辅助工具。深度学习技术在自动诊断CTS中产生了最高的性能。AI方法具有巨大的潜力，可以在临床实践中作为高精度评估CTS的辅助工具来使用。深度学习技术在自动诊断CTS中产生了最高的性能。AI方法具有巨大的潜力，可以在临床实践中作为高精度评估CTS的辅助工具来使用。