影像科学与光化学2025，Vol.43Issue(5)：53-59,67,8.DOI:10.7517/issn.1674-0475.2025.05.07
基于多模态超声构建分化型甲状腺癌术后复发的定量预测模型
Quantitative Prediction Model of Postoperative Recurrence of Differentiated Thyroid Cancer Based on Multimodal Ultrasound
摘要
Abstract
Objective:This study aimed to develop a quantitative prediction model for postoperative recurrence of differentiated thyroid cancer(DTC)using multimodal ultrasound technology,with the goal of improving the accuracy of assessing postoperative recurrence risk.Methods:We retrospectively analyzed the clinical data of 106 DTC patients who underwent surgery at our hospital between April 2018 and April 2021.All patients underwent multimodal ultrasound examinations,including 2D ultrasound,color Doppler ultrasound,and elastic imaging.Based on follow-up results within two years after surgery,patients were divided into recurrence and non-recurrence groups.Logistic regression analysis was performed to identify independent risk factors for postoperative recurrence,and a quantitative prediction model was constructed based on these factors.The predictive performance of the model was validated using receiver operating characteristic(ROC)curves and calibration curves.Results:Among the 106 patients,32(30.19%)experienced postoperative recurrence.Multivariate Logistic regression analysis revealed that marginal echo,calcification,acoustic halo thickness,elasticity score,blood flow classification,and orientation were independent risk factors for postoperative recurrence of DTC.ROC curve analysis showed that the constructed nomogram model exhibited good predictive performance,with an AUC value of 0.858.Conclusion:This study successfully established a quantitative prediction model for postoperative recurrence of DTC based on multimodal ultrasound technology.The model demonstrated high predictive accuracy and discrimination ability,providing valuable reference for clinical practice and facilitating early identification of patients at high risk of recurrence,enabling the implementation of preventive measures accordingly.关键词
多模态超声/分化型甲状腺癌/复发/列线图Key words
multimodal ultrasound/differentiated thyroid cancer/recurrence/nomograph分类
医药卫生引用本文复制引用
高净,邱爽,刘晓玲..基于多模态超声构建分化型甲状腺癌术后复发的定量预测模型[J].影像科学与光化学,2025,43(5):53-59,67,8.基金项目
河北省医学科学研究重点课题计划项目(20240608). （20240608）
