机器人外科学杂志（中英文）2025，Vol.6Issue(6)：910-915,6.DOI:10.12180/j.issn.2096-7721.2025.06.006
人工智能辅助超声弹性成像在甲状腺结节良恶性鉴别中的应用
Application of AI-assisted ultrasound elastography in differentiating benign and malignant thyroid nodules
摘要
Abstract
Objective:To investigate the application of AI-assisted ultrasound elastography in differentiating benign and malignant thyroid nodules.Methods:81 patients with pathologically confirmed thyroid nodules at Ankang Central Hospital from July 2019 to February 2024 underwent AI-assisted ultrasound elastography.The results were compared with pathological findings(the gold standard),with the Kappa test used to evaluate consistency.ROC curves were plotted to assess diagnostic efficacy.Results:Among 96 nodules from 81 patients,pathology identified 66 malignant and 30 benign nodules.AI-assisted elastography findings matched pathological results in 76 nodules(concordance rate:79.16%;missed diagnosis rate:4.54%),showing strong consistency(Kappa value=0.785,P<0.001).Malignant nodules showed distinct morphology,hardness,and texture features,primarily classified as grade Ⅲ～Ⅳ,while benign nodules were grade 0～Ⅰ.The sensitivity,specificity,and AUC of AI-assisted elastography for differentiation were 93.42%,91.55%,and 0.920(95%CI:0.859～0.939),respectively,surpassing standalone AI or elastography(P<0.05).Conclusion:AI-assisted ultrasound elastography has significant advantages in differentiating benign and malignant thyroid nodules.Its core clinical value lies in leveraging deep learning algorithms to accurately analyze elastographic features,enabling efficient benign-malignant differentiation.This approach provides reliable diagnostic references while reducing subjectivity and uncertainty.关键词
人工智能/甲状腺结节/超声弹性成像Key words
Artificial Intelligence/Thyroid Nodules/Ultrasound Elastography分类
医药卫生引用本文复制引用
周伟,王闯,詹文涛,梁汝娜..人工智能辅助超声弹性成像在甲状腺结节良恶性鉴别中的应用[J].机器人外科学杂志（中英文）,2025,6(6):910-915,6.基金项目
陕西省卫生健康科研项目(2018C005)Shaanxi Provincial Health Research Project(2018C005) （2018C005）
