Differential diagnosis of thyroid nodules through a combination of multiple ultrasonography techniques: A decision-tree model

The present study aimed to establish a decision tree (DT) model by combining the parameters of conventional gray-scale ultrasonography (US), elastosonography (ES), color Doppler US (CDUS) and contrast-enhanced US (CEUS) for the differential diagnosis of thyroid nodules. A single-center, retrospective study of 321 thyroid nodules was conducted. For 222 nodules, parameters of conventional gray-scale US, CDUS, ES and CEUS were evaluated using univariate logistic regression. Factors for with P<0.10 were further assessed using multivariate logistic regression. Significant factors (P<0.05) were used to establish a DT. The diagnostic accuracy of this DT was then evaluated by its application to the other 99 nodules. After univariate logistic analysis, factors including gender, number of nodules and diffuse disease were excluded, due to P>0.10. The results of multivariate logistic analysis determined that the following factors were required for the DT: Extent of blood flow determined by CDUS (P=0.002), area ratio determined by ES (P=0.033), peak phase patterns determined by CEUS (P<0.001) and micro-calcification determined by conventional gray-scale US (P=0.015). When compared to the pathological or cytological results of 99 nodules, the resulting DT had a sensitivity of 98.6%, specificity of 80.1%, positive predictive value of 93.5% and negative predictive value of 95.5%. These results suggested that a DT combining conventional gray-scale US, ES, CDUS and CEUS may be helpful for differentiating between types of thyroid nodules.