Clinical value of artificial intelligence assisted score combined with shear wave elastography in the differential diagnosis of benign and malignant thyroid nodules
Clinical value of artificial intelligence assisted score combined with shear wave elastography in the differential diagnosis of benign and malignant thyroid nodules
Objective To explore the clinical value of artificial intelligence assisted score(AIAS)combined with shear wave elastography(SWE)in the differential diagnosis of benign and malignant thyroid nodules.Methods A total of 231 patients with thyroid nodules(327 nodules)confirmed by surgery or needle biopsy in our hospital were enrolled,including 135 benign nodules and 192 malignant nodules.The differences of SWE parameter[ratio of strain rate(SR)]and AIAS in benign and malignant thyroid nodules were compared.Receiver operating characteristic(ROC)curve was drawn to analyze the diagnostic efficacy of SR,AIAS alone and in combination in the differential diagnosis of benign and malignant thyroid nodules.Results SR and AIAS in malignant thyroid nodules were significantly higher than those in benign nodules(both P<0.05).ROC curve analysis showed that the area under the curve of SR and AIAS for differentiating benign and malignant thyroid nodules were 0.885 and 0.845,the sensitivity were 75.00%and 78.12%,and the specificity were 97.78%and 93.33%,respectively.The area under the curve,sensitivity and specificity of SR and AIAS combined for differentiating benign and malignant thyroid nodules were 0.917,82.81%and 91.11%,respectively,which were higher than those of individual application,and the differences were statistically significant(all P<0.05).Conclusion AIAS combined with SWE has certain clinical value for differentiating benign and malignant thyroid nodules.
关键词
剪切波弹性成像/人工智能辅助评分/甲状腺结节,良恶性/诊断价值
Key words
Shear wave elastography/Artificial intelligence assisted score/Thyroid nodule,benign and malignant/Diagnostic value
维普
万方数据