摘要
目的 基于多房样肝囊肿及肝黏液性囊性肿瘤(MCN)的CT及MRI特征建立Logistic回归模型,并分析其对两者鉴别诊断的价值。方法 回顾性分析65例多房样肝囊性病变的CT及MRI资料,其中男13例、女52例。根据手术病理结果将其分为肝囊肿病变(39例)与肝MCN病变(26例)。采用卡方检验比较2组影像特征,对组间差异有统计学意义的CT及MRI征象进行多因素分析,建立二元Logistic回归模型。采用受试者操作特征(ROC)曲线评估模型预测效能,并计算其曲线下面积(AUC)、敏感度、特异度及准确度。结果 肝囊肿及肝MCN间的囊性病变数量、囊壁及分隔外观、囊壁或分隔结节样凸起、实性部分厚度>10 mm、分隔类型、分隔位置、分隔与囊壁的关系,其差异均具有统计学意义(均P<0.05)。多因素Logistic回归分析显示,分隔类型、分隔与囊壁的关系是肝囊肿及肝MCN的独立预测因素(P<0.05),采用这2个因素构建二元Logistic回归模型,该回归模型的诊断效能(AUC=0.871)比单独使用分隔类型、分隔与囊壁的关系的要高(AUC分别为0.699、0.795)。结论 基于分隔类型、分隔与囊壁的关系联合构建的Logistic回归模型能够较好地鉴别多房样肝囊肿及肝MCN,有助于提高肝囊肿及肝MCN术前影像诊断水平。
Objective To establish a logistic regression model based on CT and MRI features of multilocular hepatic cysts and mucinous cystic tumors(MCN),and analyze its value in differential diagnosis between the two entities.Methods A retrospective analysis was conducted on CT and MRI data from 65 cases of multilocular hepatic cystic lesions,including 13 males and 52 females.According to surgical pathology results,the cases were divided into hepatic cyst lesions(39 cases)and hepatic MCN lesions(26 cases).Chi-square tests were used to compare imaging findings between the two groups.Statistically significant CT and MRI features were further analyzed using multivariate logistic regression to construct a binary logistic regression model.The predictive performance of the model was evaluated using the receiver operating characteristic(ROC)curve,and the area under the curve(AUC),sensitivity,specificity,and accuracy were calculated.Results Significant differences were observed between hepatic cysts and hepatic MCNs in terms of the number of hepatic cystic lesions,the appearance of cyst wall and septa,nodular protrusions of cyst wall or septa,the thickness of solid components greater than 10 mm,types of septa,septa location,and the relationship between septa and cyst walls between hepatic cysts and hepatic MCNs(all P<0.05).Multivariate logistic regression analysis identified that septal type,and the relationship between septa and cyst walls as independent predictive factors(P<0.05).A logistic regression model constructed using these two factors achieved higher diagnostic performance(AUC=0.871)compared to using septal type(AUC=0.699)or the relationship between septa and cyst walls (AUC=0.795) alone. Conclusion A logistic regression model incorporating septal type, and the relationship between septa and cyst walls can effectively distinguish multilocular hepatic cysts from hepatic MCN, improving the preoperative imaging diagnostic accuracy for these lesions.
作者
刘洪杰
李永元
郑嘉铭
魏凯
叶露
李艳博
崔建民
孙浩然
LIU Hongjie;LI Yongyuan;ZHENG Jiaming;WEI Kai;YE Lu;LI Yanbo;CUI Jianmin;SUN Haoran(Department of Radiology,The Fifth Central Hospital of Tianjin,Tianjin 300450,China;Department of General Surgery,Tianjin Fifth Central Hospital;West China School of Medicine,Sichuan University;Department of Radiology,Tianjin Medical University Cancer Hospital;Department of Radiology,Tianjin Medical University General Hospital.)
出处
《国际医学放射学杂志》
2024年第6期669-674,共6页
International Journal of Medical Radiology
