高频超声在甲状腺良恶性结节鉴别诊断中的应用研究  

High-resolution ultrasonography for distinguishing benign from malignant thyroid nodules

作　　者：田付丽[1] 刘春蕊[1] 杨斌[1] 

机构地区：[1]南京大学医学院附属金陵医院(南京军区南京总医院)超声诊断科,南京医学硕士研究生210002

出　　处：《医学研究生学报》2016年第8期841-844,共4页Journal of Medical Postgraduates

基　　金：南京军区医药卫生科研基金(15ZD031)

摘　　要：目的高频超声的广泛应用增加了甲状腺结节的检出率，但良恶性结节的超声特征存在交叉，尚无定论。文中旨在比较良恶性结节的不同超声表现特征，探讨鉴别甲状腺恶性结节超声特征的危险因素。方法回顾性分析2015年1月至2016年1月南京军区南京总医院确诊为甲状腺结节患者64例，甲状腺结节共119枚（良性63枚，恶性56枚）。对性别、年龄、结节位置等变量先进行单因素分析，再利用多元Logistic回归分析筛选甲状腺恶性结节的危险因素，并通过ROC曲线分析检测模型拟合效果。结果Logistic回归分析结果显示，形态不规则（OR：6．166，95％CI：1．681～22．617）、微钙化（OR：3．593，95％CI：1．800～7．169）、纵横比≥1（OR：17．577，95％CI：1．739～166．468）是恶性结节的危险因素。ROC曲线AUC为0．922（0．868～0．976）。结论超声特征指标中形态不规则、微钙化、纵横比（≥1）对鉴别甲状腺结节性质具有诊断价值。Objective The extensive use of high-resolution thyroid uhrasonography has markedly improved the detection rate of thyroid nodules （TNs）. However, the uhrasonographie features of benign and malignant TNs usually overlap and have yet to be de- fined. This study aimed to investigate the uhrasonographic features and risk factors of malignant TNs by comparing their uhrasonograph- ic manifestations with those of benign TNs. Methods A total of 119 TNs （63 benign and 56 malignant） in 64 patients were includ- ed in this retrospective study. The gender, age, location of the TNs, and other variables were subjected to univariate analysis, the risk factors of malignant TNs were screened by multivariate logistic regression analysis, and the predictive value of the logistic regression model was assessed using the ROC curve. Results Multivariate logistic regression analysis indicated that the risk factors of malig- nant TNs in ultrasonography were irregular shape （OR： 6. 166, 95% CI： 1. 681 -22. 617）, micro calcification （OR： 3. 593, 95% CI： 1. 800 -7. 169）, and A/T ratio ≥1 （OR： 17. 577, 95% CI： 1. 739 - 166. 468）. ROC curve analysis showed the area under the curve （AUC） to be 0. 922 （95%CI： 0. 868 -0.976）. Conclusion Such ultrasonographic manifestations as irregular shape, micro- calcification, and A/T ratio ≥ 1 are valuable in identifying the nature of TNs.

关 键 词：高频超声 甲状腺结节 良性 恶性 LOGISTIC回归分析 

分 类 号：R736.1[医药卫生—肿瘤]