Abstract：
BACKGROUND: To develop and compare machine learning models based on triphasic contrast-enhanced CT (CECT) for distinguishing between benign and malignant renal tumors.
METHODS: In total, 427 patients were enrolled from two medical centers: Center 1 (serving as the training set) and Center 2 (serving as the external validation set). First, 1781 radiomic features were individually extracted from corticomedullary phase (CP), nephrographic phase (NP), and excretory phase (EP) CECT images, after which 10 features were selected by the minimum redundancy maximum relevance method. Second, random forest (RF) models were constructed from single-phase features (CP, NP, and EP) as well as from the combination of features from all three phases (TP). Third, the RF models were assessed in the training and external validation sets. Finally, the internal prediction mechanisms of the models were explained by the SHapley Additive exPlanations (SHAP) approach.
RESULTS: A total of 266 patients with renal tumors from Center 1 and 161 patients from Center 2 were included. In the training set, the AUCs of the RF models constructed from the CP, NP, EP, and TP features were 0.886, 0.912, 0.930, and 0.944, respectively. In the external validation set, the models achieved AUCs of 0.860, 0.821, 0.921, and 0.908, respectively. The \"original_shape_Flatness\" feature played the most important role in the prediction outcome for the RF model based on EP features according to the SHAP method.
CONCLUSIONS: The four RF models efficiently differentiated benign from malignant solid renal tumors, with the EP feature-based RF model displaying the best performance.
METHODS: In total, 427 patients were enrolled from two medical centers: Center 1 (serving as the training set) and Center 2 (serving as the external validation set). First, 1781 radiomic features were individually extracted from corticomedullary phase (CP), nephrographic phase (NP), and excretory phase (EP) CECT images, after which 10 features were selected by the minimum redundancy maximum relevance method. Second, random forest (RF) models were constructed from single-phase features (CP, NP, and EP) as well as from the combination of features from all three phases (TP). Third, the RF models were assessed in the training and external validation sets. Finally, the internal prediction mechanisms of the models were explained by the SHapley Additive exPlanations (SHAP) approach.
RESULTS: A total of 266 patients with renal tumors from Center 1 and 161 patients from Center 2 were included. In the training set, the AUCs of the RF models constructed from the CP, NP, EP, and TP features were 0.886, 0.912, 0.930, and 0.944, respectively. In the external validation set, the models achieved AUCs of 0.860, 0.821, 0.921, and 0.908, respectively. The \"original_shape_Flatness\" feature played the most important role in the prediction outcome for the RF model based on EP features according to the SHAP method.
CONCLUSIONS: The four RF models efficiently differentiated benign from malignant solid renal tumors, with the EP feature-based RF model displaying the best performance.
摘要：
背景：开发和比较基于三相对比增强CT（CECT）的机器学习模型，以区分良性和恶性肾脏肿瘤。
方法：总共，427名患者来自两个医疗中心:中心1(用作训练集)和中心2(用作外部验证集)。首先,从皮质髓质期(CP)中单独提取1781个放射学特征，肾图相位（NP），和排泄期（EP）CECT图像，之后，通过最小冗余最大相关性方法选择10个特征。第二,随机森林(RF)模型由单相特征(CP，NP,和EP）以及来自所有三个阶段（TP）的特征组合。第三，在训练集和外部验证集中评估RF模型.最后,模型的内部预测机制由SHapley加法扩张(SHAP)方法解释。
结果：共纳入了来自中心1的266例肾脏肿瘤患者和来自中心2的161例患者。在训练集中，从CP构建的RF模型的AUC，NP,EP,TP特征分别为0.886、0.912、0.930和0.944。在外部验证集中，模型的AUC分别为0.860,0.821,0.921和0.908.根据SHAP方法,“original_shape_flatness”特征在基于EP特征的RF模型的预测结果中起着最重要的作用。
结论：四种RF模型可有效区分良性和恶性实体肾肿瘤，基于EP特征的RF模型显示最佳性能。
方法：总共，427名患者来自两个医疗中心:中心1(用作训练集)和中心2(用作外部验证集)。首先,从皮质髓质期(CP)中单独提取1781个放射学特征，肾图相位（NP），和排泄期（EP）CECT图像，之后，通过最小冗余最大相关性方法选择10个特征。第二,随机森林(RF)模型由单相特征(CP，NP,和EP）以及来自所有三个阶段（TP）的特征组合。第三，在训练集和外部验证集中评估RF模型.最后,模型的内部预测机制由SHapley加法扩张(SHAP)方法解释。
结果：共纳入了来自中心1的266例肾脏肿瘤患者和来自中心2的161例患者。在训练集中，从CP构建的RF模型的AUC，NP,EP,TP特征分别为0.886、0.912、0.930和0.944。在外部验证集中，模型的AUC分别为0.860,0.821,0.921和0.908.根据SHAP方法,“original_shape_flatness”特征在基于EP特征的RF模型的预测结果中起着最重要的作用。
结论：四种RF模型可有效区分良性和恶性实体肾肿瘤，基于EP特征的RF模型显示最佳性能。
