Abstract：
To develop and validate a random forest model based on radiomic features in Gd-EOB-DTPA enhanced MRI for predicting the Ki-67 expression in solitary HCC.
This retrospective study analyzed 258 patients with solitary HCC. Significant clinicoradiological factors were identified through univariate and multivariate analyses for distinguishing HCC with high (>20%) and low (≤20%) Ki-67 expression. Radiomic features were extracted at Gd-EOB-DTPA enhanced MRI. The recursive feature elimination (RFE) strategy was employed to screen robust radiomic features, and the Random Forest (RF) algorithm was utilized to rank radiomic features and construct prediction models. The AUC, accuracy, precision, recall, and f1-score were used to evaluate the performance of RF models.
Multivariate analysis identified serum AFP level, tumor size, growth type, and peritumoral enhancement as independent predictors for HCC with high Ki-67 expression. The clinicoradiological-radiomic model that incorporated the clinicoradiological predictors and the top ten radiomic features outperformed the clinicoradiological model in the training set (AUCs 0.876 vs. 0.780; p < 0.001), though the test set did not have a statistical significance (AUCs 0.809 vs. 0.723; p = 0.123). The addition of clinicoradiological predictors did not yield a significant improvement in the performance of radiomic features in both sets (training, p = 0.692; test, p = 0.229). Decision curve analysis further confirmed the clinical utility of the RF models.
The RF models based on radiomic features of Gd-EOB-DTPA enhanced MRI achieved satisfactory performance in preoperatively predicting Ki-67 expression in HCC.
This retrospective study analyzed 258 patients with solitary HCC. Significant clinicoradiological factors were identified through univariate and multivariate analyses for distinguishing HCC with high (>20%) and low (≤20%) Ki-67 expression. Radiomic features were extracted at Gd-EOB-DTPA enhanced MRI. The recursive feature elimination (RFE) strategy was employed to screen robust radiomic features, and the Random Forest (RF) algorithm was utilized to rank radiomic features and construct prediction models. The AUC, accuracy, precision, recall, and f1-score were used to evaluate the performance of RF models.
Multivariate analysis identified serum AFP level, tumor size, growth type, and peritumoral enhancement as independent predictors for HCC with high Ki-67 expression. The clinicoradiological-radiomic model that incorporated the clinicoradiological predictors and the top ten radiomic features outperformed the clinicoradiological model in the training set (AUCs 0.876 vs. 0.780; p < 0.001), though the test set did not have a statistical significance (AUCs 0.809 vs. 0.723; p = 0.123). The addition of clinicoradiological predictors did not yield a significant improvement in the performance of radiomic features in both sets (training, p = 0.692; test, p = 0.229). Decision curve analysis further confirmed the clinical utility of the RF models.
The RF models based on radiomic features of Gd-EOB-DTPA enhanced MRI achieved satisfactory performance in preoperatively predicting Ki-67 expression in HCC.
摘要：
目的：开发并验证基于Gd-EOB-DTPA增强MRI影像组学特征的随机森林模型，以预测孤立性HCC中Ki-67的表达。
方法：这项回顾性研究分析了258例单发HCC患者。通过单变量和多变量分析确定了重要的临床放射因素，以区分高（>20％）和低（≤20％）Ki-67表达的HCC。在Gd-EOB-DTPA增强MRI中提取影像组学特征。采用递归特征消除(RFE)策略筛选稳健的放射学特征，并利用随机森林（RF）算法对放射学特征进行排序并构建预测模型。AUC,准确度,精度,召回，和f1评分用于评估射频模型的性能。
结果：多变量分析确定了血清AFP水平，肿瘤大小,生长类型,瘤周增强是Ki-67高表达HCC的独立预测因子。结合了临床放射放射学预测因子和十大放射学特征的临床放射放射学模型优于训练集中的临床放射放射学模型（AUCs0.876与0.780；p<0.001)，尽管测试集没有统计学意义(AUCs0.809与0.723；p=0.123）。增加临床放射学预测因子并没有显着改善两组放射学特征的性能（训练，p=0.692;试验,p=0.229）。决策曲线分析进一步证实了RF模型的临床实用性。
结论：基于Gd-EOB-DTPA增强MRI影像组学特征的RF模型在术前预测HCC中Ki-67表达方面取得了令人满意的表现。
方法：这项回顾性研究分析了258例单发HCC患者。通过单变量和多变量分析确定了重要的临床放射因素，以区分高（>20％）和低（≤20％）Ki-67表达的HCC。在Gd-EOB-DTPA增强MRI中提取影像组学特征。采用递归特征消除(RFE)策略筛选稳健的放射学特征，并利用随机森林（RF）算法对放射学特征进行排序并构建预测模型。AUC,准确度,精度,召回，和f1评分用于评估射频模型的性能。
结果：多变量分析确定了血清AFP水平，肿瘤大小,生长类型,瘤周增强是Ki-67高表达HCC的独立预测因子。结合了临床放射放射学预测因子和十大放射学特征的临床放射放射学模型优于训练集中的临床放射放射学模型（AUCs0.876与0.780；p<0.001)，尽管测试集没有统计学意义(AUCs0.809与0.723；p=0.123）。增加临床放射学预测因子并没有显着改善两组放射学特征的性能（训练，p=0.692;试验,p=0.229）。决策曲线分析进一步证实了RF模型的临床实用性。
结论：基于Gd-EOB-DTPA增强MRI影像组学特征的RF模型在术前预测HCC中Ki-67表达方面取得了令人满意的表现。
