Zeng Hanqiu, Ma Zichang, Tao Yuxi, Cheng Ci, Lin Junyu, Fang Jiayu, Wei Yuhan, Liu Huajin, Zou Feixiang, Cui Enming, Zhang Yaqin
Department of Radiology, the Fifth Affiliated Hospital, Sun Yat-Sen University, Zhuhai, China.
Department of Radiology, People's Hospital of Wuchuan Gelao and Miao Autonomous County, Zunyi 5643000 Guizhou, China.
Eur J Radiol. 2025 Jul;188:112130. doi: 10.1016/j.ejrad.2025.112130. Epub 2025 Apr 23.
To develop and validate a comprehensive model for predicting postoperative early recurrence of hepatocellular carcinoma (HCC) based on gadoxetate disodium (Gd-EOB-DTPA)-enhanced MRI.
239 patients with HCC who underwent curative surgical resection were recruited from two centers between April 2017 and December 2022. Radiomics features were extracted from the region of interest (ROI) on preoperative Gd-EOB-DTPA-enhanced MR images, and consistency analysis was performed to select stable radiomics features. Significant variables in the univariate and multivariate logistic regression analysis were included in clinical-radiologic model. Nomograms were constructed by combining the best performing radiologic and clinical-radiologic characteristics. Recurrence-free survival (RFS) comparisons were conducted using the log-rank test based on high versus low model-derived scores.
The radiomics model based on multiple phases MR outperformed all other radiomics models and had the best discrimination for early recurrence, with AUC of 0.799 and 0.743 in the training and validation sets, respectively. In the entire cohort, high-risk patients exhibited significantly lower RFS compared to low-risk patients.
The nomogram integrating Gd-EOB-DTPA enhanced MRI radiomics features and clinical-radiologic characteristics demonstrate superior predictive performance with postoperative early recurrence in patients with HCC. The model can identify patients at high risk and provide support for individualized treatment planning.
基于钆塞酸二钠（Gd-EOB-DTPA）增强磁共振成像（MRI）开发并验证一种预测肝细胞癌（HCC）术后早期复发的综合模型。
2017年4月至2022年12月期间，从两个中心招募了239例行根治性手术切除的HCC患者。从术前Gd-EOB-DTPA增强MR图像的感兴趣区域（ROI）提取影像组学特征，并进行一致性分析以选择稳定的影像组学特征。单因素和多因素逻辑回归分析中的显著变量被纳入临床-影像模型。通过结合表现最佳的影像组学和临床-影像特征构建列线图。基于模型衍生分数的高低，使用对数秩检验进行无复发生存期（RFS）比较。
基于多期MR的影像组学模型优于所有其他影像组学模型，对早期复发具有最佳的鉴别能力，训练集和验证集的AUC分别为0.799和0.743。在整个队列中，高风险患者的RFS明显低于低风险患者。
整合Gd-EOB-DTPA增强MRI影像组学特征和临床-影像特征的列线图在预测HCC患者术后早期复发方面表现出卓越的性能。该模型可以识别高风险患者，并为个体化治疗计划提供支持。
