Guo Xinyu, Song Jingjing, Zhu Lingyi, Liu Shuang, Huang Chaoming, Zhou Lingling, Chen Weiyue, Lin Guihan, Zhao Zhongwei, Tu Jianfei, Chen Minjiang, Chen Feng, Zheng Liyun, Ji Jiansong
Key Laboratory of Imaging Diagnosis and Minimally Invasive Intervention Research, Zhejiang Engineering Research Center of Interventional Medicine Engineering and Biotechnology, Zhejiang Key Laboratory of Imaging and Interventional Medicine, Lishui Hospital of Zhejiang University, Lishui, 323000, China.
Department of Radiology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, 310003, Zhejiang, China.
BMC Cancer. 2025 Apr 14;25(1):683. doi: 10.1186/s12885-025-14079-y.
This study was undertaken to develop and validate a radiomics model based on multiparametric magnetic resonance imaging (MRI) for predicting recurrence in patients with hepatocellular carcinoma (HCC) following postoperative adjuvant transarterial chemoembolization (PA-TACE).
In this retrospective study, 149 HCC patients (81 for training, 36 for internal validation, 32 for external validation) treated with PA-TACE were included in two medical centers. Multiparametric radiomics features were extracted from three MRI sequences. Least absolute shrinkage and selection operator (LASSO)-COX regression was utilized to select radiomics features. Optimal clinical characteristics selected by multivariate Cox analysis were integrated with Rad-score to develop a recurrence-free survival (RFS) prediction model. The model performance was evaluated by time-dependent receiver operating characteristic (ROC) curves, Harrell's concordance index (C-index), and calibration curve.
Fifteen optimal radiomic features were selected and the median Rad-score value was 0.434. Multivariate Cox analysis indicated that neutrophil-to-lymphocyte ratio (NLR) (hazard ratio (HR) = 1.49, 95% confidence interval (CI): 1.1-2.1, P = 0.022) and tumor size (HR = 1.28, 95% CI: 1.1-1.5, P = 0.001) were the independent predictors of RFS after PA-TACE. A combined model was established by integrating Rad-score, NLR, and tumor size in the training cohort (C-index 0.822; 95% CI 0.805-0.861), internal validation cohort (0.823; 95% CI 0.771-0.876) and external validation cohort (0.846; 95% CI 0.768-0.924). The calibration curve exhibited a satisfactory correspondence.
A multiparametric MRI-based radiomics model can predict RFS of HCC patients receiving PA-TACE and a nomogram can be served as an individualized tool for prognosis.
本研究旨在开发并验证一种基于多参数磁共振成像（MRI）的放射组学模型，用于预测肝细胞癌（HCC）患者术后辅助经动脉化疗栓塞术（PA-TACE）后的复发情况。
在这项回顾性研究中，两个医学中心纳入了149例接受PA-TACE治疗的HCC患者（81例用于训练，36例用于内部验证，32例用于外部验证）。从三个MRI序列中提取多参数放射组学特征。采用最小绝对收缩和选择算子（LASSO）-COX回归来选择放射组学特征。将多变量Cox分析选择的最佳临床特征与Rad-score相结合，以建立无复发生存期（RFS）预测模型。通过时间依赖性受试者操作特征（ROC）曲线、Harrell一致性指数（C-index）和校准曲线来评估模型性能。
选择了15个最佳放射组学特征，Rad-score中位数为0.434。多变量Cox分析表明，中性粒细胞与淋巴细胞比值（NLR）（风险比（HR）=1.49，95%置信区间（CI）：1.1-2.1，P=0.022）和肿瘤大小（HR=1.28，95%CI：1.1-1.5，P=0.001）是PA-TACE后RFS的独立预测因素。在训练队列（C-index 0.822；95%CI 0.805-0.861）、内部验证队列（0.823；95%CI 0.771-0.876）和外部验证队列（0.846；95%CI 0.768-0.924）中，通过整合Rad-score、NLR和肿瘤大小建立了一个联合模型。校准曲线显示出良好的一致性。
基于多参数MRI的放射组学模型可以预测接受PA-TACE的HCC患者的RFS，列线图可作为一种个体化的预后工具。
