剪切波弹性成像在甲状腺结节良恶性鉴别诊断中的Logistic回归分析

目的 应用Logistic回归模型评价剪切波弹性成像(SWE)技术在甲状腺结节良恶性鉴别诊断中的价值。方法 对239例患者行常规超声及SWE检查,建立Logistic回归模型,绘制ROC曲线,评价回归模型的预报准确性,通过比较各超声特征变量的似然比,评价SWE技术在甲状腺结节良恶性中的鉴别诊断价值。结果 经过Logistic回归分析,进入回归模型有统计学意义的超声特征变量包括边界、钙化、弹性模量最大值(Emax)及平均值(Emean)。Logistic回归模型对甲状腺结节定性诊断正确率为91.60%,敏感性为92.90%,特异性为89.90%。结论 SWE对甲状腺结节的良恶性鉴别诊断有价值。

Evaluation of shear wave elastography in differentiation diagnosis of thyroid nodules using logistic regression

Objective To evaluate the value of conventional ultrasonic and shear wave elastography in the diagnosis of thyroid nodules by applying the binary Logistic regression model. Methods Totally 239 cases of thyroid solitary nodules were examined by conventional ultrasonic and shear wave elastography.A Logistic model was obtained on the basis of ultrasonographic features. A receiver operator characteris(ROC) curve was constructed to assess the performance of the Logistic model. The differential diagnosis value of shear wave elastography in thyroid nodules was evaluated. Results Four ultrasonographic features including boundary, calcification, Emax and Emean finally entered into the Logistic model. The percentage of correct prediction, the sensitivity and specificity were 91.60％, 92.90% and 89.90%. Conclusion Shear wave elastography plays important role in the differential diagnosis of thyroid nodules.