机器人外科学杂志（中英文）2025，Vol.6Issue(11)：1860-1865,6.DOI:10.12180/j.issn.2096-7721.2025.11.008
人工智能辅助下多模态超声联合TRAb及VEGF检测对甲状腺结节的精准诊断及临床价值评估
Precise diagnosis and clinical value assessment of thyroid nodules using AI-assisted multimodal ultrasound combined with TRAb and VEGF detection
摘要
Abstract
Objective:To investigate the precise diagnosis and clinical value of AI-assisted multimodal ultrasound combined with thyrotropin receptor antibody(TRAb)and vascular endothelial growth factor(VEGF)detection in thyroid nodules.Methods:129 patients with thyroid nodule admitted to Tangshan People's Hospital from January 2023 to September 2024 were enrolled.AI-assisted multimodal ultrasound[conventional AI ultrasound+color Doppler flow imaging(CDFI)+real-time shear wave elastography(SWE)+contrast-enhanced ultrasound(CEUS)]was performed,with postoperative pathological results as the gold standard.The patients were divided into the benign group(n=82)and the malignant(n=47)group.Serum levels of TRAb and VEGF were measured,and ultrasound and serum indicators were compared between the two groups.The diagnostic value of AI-assisted multimodal ultrasound combined with serum markers was analyzed.Results:The combined detection of AI-assisted multimodal ultrasound with TRAb and VEGF achieved a complete compliance rate of 98.45%(127/129)with pathological results.Its sensitivity,specificity,positive predictive value(PPV),and negative predictive value(NPV)in diagnosing thyroid nodules were significantly higher than those of TRAb or VEGF alone(P<0.05).Based on pathological results,the diagnostic efficacy(AUC,95%CI)of TRAb,VEGF,AI-assisted multimodal ultrasound,and their combination were(0.849,0.773-0.926),(0.883,0.814-0.952),(0.927,0.872-0.982),and(0.983,0.956-1.000),respectively,all significantly different with AZ=0.5(P<0.05).Conclusion:In the diagnosis of benign and malignant thyroid nodules,integrating AI-assisted multimodal ultrasound features with serum TRAb and VEGF levels can significantly improve diagnostic accuracy,which has certain clinical value.关键词
甲状腺结节/人工智能/多模态超声/促甲状腺激素受体抗体/血管内皮生长因子/临床价值Key words
Thyroid Nodule/Artificial Intelligence/Multimodal Ultrasound/Thyrotropin Receptor Antibody/Vascular Endothelial Growth Factor/Clinical Value分类
医药卫生引用本文复制引用
郑薇薇,周宇微,李慧芳,王泱,白立洁..人工智能辅助下多模态超声联合TRAb及VEGF检测对甲状腺结节的精准诊断及临床价值评估[J].机器人外科学杂志（中英文）,2025,6(11):1860-1865,6.基金项目
河北省医学科学研究课题(20251223) Hebei Provincial Medical Science Research Project(20251223) （20251223）
