Application Of The Binary Regression Mode In Analyzing The Ultrasonograp Hic Features Of Solid Thyroid Micronodules

Objective:To apply the binary Logistic regression model and evaluate the value of grey scale ultrasonography(US), ultrasond elastography(UE) and Contrast-enhanced ultrasound imaging mode(CEUS).Methods:US, UE and CEUS were performed in130patients with142solid thyroid micronodules (The largest diameter less than10mm). Pathology was followed up as golden diagnosis criteria. A Logistic model on the basis of ultrasonographic features was obtained. A receiver operating characteristic(ROC) curve was used to assess the performance of Logistic model.Results:Four ultrasonic indexes were finally entered into the Logisic regression model including microcalcification, acpect ratio, advanced CEUS mode and elasticity score.The percentage correction of prediction was92.1%(129/142). The area under the ROC curve was0.944.Conclusion:The multivariate analysis model of binary Logistic regression can describe and analyze the process of differential diagnosis ofmalignant and benign solid thyroid micronodules by ultrosonography, and select out the valuable indexes for differential diagnosis.