星形细胞瘤病理分级与MRI影像表现的有序回归模型研究  

A study of ordinal regression models in evaluating the pathological grading of astrocytoma with MR image characteristics

作　　者：彭宗清[1] 余水[1] 曾令春[1] 曾义军[1] 王强平[1] 杜德明[1] 李自强[1] 淡冰[1] 

机构地区：[1]都江堰市人民医院神经外科,四川都江堰611830

出　　处：《现代肿瘤医学》2012年第12期2488-2491,共4页Journal of Modern Oncology

摘　　要：目的:探讨星形细胞瘤病理分级与MRI影像学特征参数的有序回归模型的价值和意义。方法:回顾分析我院2009年7月至2011年7月符合本研究纳入标准和排除标准的星形细胞瘤患者与四川大学华西医院2010年3月至2011年7月符合本研究纳入排出标准的星形细胞瘤患者共163例,使用χ2检验(蒙特卡罗法)或Fisher确切概率法对其8项影像学参数进行统计学分析,将筛选出与病理分级有关的MRI特征参数纳入有序回归模型并分析,最终建立有序回归模型并使用ROC(receiver operating characteristic)曲线对模型的预测准确性进行分析。结果:星形细胞瘤MRI增强情况和水肿程度与病理分级关系最密切;建立的有序回归模型预测准确性为73.56%。结论:有序回归模型对星形细胞瘤病理分级和MRI影像学表现的研究有意义,可为临床提供参考。Objective：To evaluate the association between pathological grading of astrocytoma and MR image characteristics by using ordinal regression model.Methods： A total of 163 patients with astrocytoma were enrolled.8 MR image characteristics were evaluated by Chi-square test or Fisher＇s exact test,and then the ordinal regression model was built using the pathological grading and the MR image characteristics which were filtered out.Finally the predictive accuracy of the regression model was assessed using the area under the receiver operating characteristic（ROC） curve.Results： Enhancement of T1 weighted imaging and edema were the best general predictors of malignacy in this study,and the prediction accuracy of ordinal regression model was 73.56%.Conclusion： The ordinal logistic regression is a meaningful model to evaluate the grading of astrocytoma with MR image characteristics.

关 键 词：星形细胞瘤 磁共振成像 病理学 有序回归模型 

分 类 号：R739.41[医药卫生—肿瘤]