Additional file 3 of Three-dimensional CT texture analysis of anatomic liver segments can differentiate between low-grade and high-grade fibrosis

Additional file 3. Univariate evaluation of the radiomic features. The table contains results of the ROC analysis of texture parameters for the classification of low-grade vs. high-grade fibrosis sorted by the AUC value; the coefficient of a univariate linear regression analysis performed against liver stiffness as the dependent variable, and feature importance scores calculated during cross-validated recursive feature elimination.

补充文件3：放射组学特征的单变量评估。本表格包含按曲线下面积（Area Under Curve，AUC）值排序的、用于区分低级别与高级别纤维化的纹理参数受试者工作特征（Receiver Operating Characteristic，ROC）分析结果；同时包含以肝脏硬度为因变量的单变量线性回归分析系数，以及交叉验证递归特征消除过程中计算得到的特征重要性得分。