弹性成像在甲状腺单发结节良恶性鉴别诊断中的Logistic回归分析

目的：建立以甲状腺结节超声诊断特征为变量的回归模型,评价常规超声及弹性成像在甲状腺单发结节良恶性鉴别诊断中的价值.方法：对139例患者行常规超声及弹性成像检查,以病理诊断为金标准建立Logistic回归模型.绘制ROC曲线图,评价建立回归模型的预报准确性,比较各变量的似然比,评价弹性成像在甲状腺结节良恶性中的鉴别诊断价值.结果：经过二分类Logistic回归分析,筛选出对甲状腺结节良恶性鉴别诊断中有统计学意义的特征变量包括钙化、CDFI及弹性评分.Logistic回归模型对甲状腺单发结节良恶性预报的正确率为91.40％,敏感性为91.80％,特异性为91.10％.结论：弹性成像较常规超声检查更有助于甲状腺单发结节的良恶性鉴别诊断.

Evaluation of ultrasonic elastography in differential diagnosis of thyroid solitary nodules using Logistic regression

Objective ：To evaluate the value of conventional ultrasonic and ultrasonic elastography in the diagnosis of thyroid solitary nodules by applying the binary Logistic regression model. Methods：Total of 139 cases of thyroid solitary nodules were examed by conventional ultrasonic and ultrasonic elastography, which were confirmed by surgical pathology. A Logistic model was obtained on the basis of ultrasonographic features. Receiver operator characteris （ROC） curve was constructed to assess the performance of the Logistic model to evaluate the differential diagnosis value of ultrasonic elastography in thyroid solitary nodules. Results：Three ultrasonographic features including calcifi- cation, CDFI and elastic score were finally entered into the Logistic model. The percentage of correct prediction was 91.40%. Conclusion：Uhrasonic elastography plays more important role in the differential diagnosis of thyroid solitary nodules.