基于增强磁共振成像影像组学的肝细胞癌靶向联合免疫治疗疗效预测研究  

Radiomics analysis on contrast-enhanced magnetic resonance imaging for predicting treatment response of targeted-immune systemic therapy in hepatocellular carcinoma

作　　者：姚致远 赵文超 张恭 柳俨哲 李悦[2,3,4,6] 肖朝辉 夏念信 刘荣 YAO Zhiyuan;ZHAO Wenchao;ZHANG Gong;LIU Yanzhe;LI Yue;XIAO Chaohui;XIA Nianxin;LIU Rong(Chinese PLA Medical School,Beijing 100853,China;Faculty of Hepato-Pancreato-Biliary Surgery,the First Medical Center,Chinese PLA General Hospital,Beijing 100853,China;Institute of Hepatobiliary Surgery of PLA,Beijing 100853,China;Key Laboratory of Digital Hepatobiliary Surgery of PLA,Beijing 100853,China;Department of Hepato-Pancreato-Biliary Surgery,the Sixth Medical Center,Chinese PLA General Hospital,Beijing 100048,China;Medical School of Nankai University,Tianjin 300071,China)

机构地区：[1]解放军医学院,北京100853 [2]解放军总医院第一医学中心肝胆胰外科医学部,北京100853 [3]解放军肝胆胰外科研究所,北京100853 [4]解放军数字肝胆外科重点实验室,北京100853 [5]解放军总医院第六医学中心肝胆胰外科,北京100048 [6]南开大学医学院,天津300071

出　　处：《解放军医学院学报》2024年第8期817-823,831,共8页Academic Journal of Chinese PLA Medical School

基　　金：科技创新2030重大项目(2021ZD0113301)。

摘　　要：背景靶向联合免疫治疗是目前肝细胞癌的一线系统治疗方案,临床缺乏可靠的生物标志物用于疗效预测及识别潜在获益人群。目的探讨利用增强磁共振成像(magnetic resonance imaging,MRI)影像组学特征进行疗效预测的可行性。方法纳入2019年1月—2023年1月在解放军总医院肝胆胰外科医学部接受靶向免疫治疗的肝细胞癌患者191例,以7∶3的比例随机分为训练集和验证集。所有患者在治疗前和随诊期间均接受了动态增强MRI检查,根据RECIST 1.1标准评估疗效,达到客观缓解(objective response,OR)视为治疗有效。在治疗前的动态增强MRI图像上勾画肿瘤区域并提取影像组学特征,使用最小绝对收缩和选择算子(least absolute shrinkage and selection operator,LASSO)算法筛选有意义的影像组学特征。采用多种机器学习算法,包括逻辑回归、K-最近邻、朴素贝叶斯、人工神经网络、支持向量机、决策树、XGBoost、随机森林分别构建影像组学预测OR的模型,使用受试者工作特征(receiver operator characteristic,ROC)曲线和混淆矩阵评估各模型效能。使用Cox回归和Kaplan-Meier曲线分析模型的预后预测价值。结果共收集191例患者,其中男性患者163例(85.3%),女性患者28例(14.7%),中位年龄为55(范围:24~74)岁,整体客观缓解率30.4%,纳入训练集133例,验证集58例,两组性别和年龄差异无统计学意义(P>0.05),训练集和验证集的客观缓解率分别为30.1%和31.0%。基于筛选后的影像组学特征成功构建了8个机器学习模型,其中K-近邻、朴素贝叶斯和支持向量机模型的AUC值在10折交叉验证的训练集中分别达到了0.826、0.810、0.801,在验证集中分别达到了0.830、0.836、0.825。生存分析显示上述3个模型预测治疗有效的患者无进展生存期显著延长(P<0.05)。结论基于机器学习算法的增强MRI影像组学模型能够准确预测肝细胞癌患者靶向免疫治疗的疗效,具有�Background Targeted-immune systemic therapy(TIST)is currently the first-line systemic treatment for hepatocellular carcinoma(HCC).However,there is a lack of reliable biomarkers for predicting efficacy and identifying potential beneficiaries.Objective To explore the feasibility of using Magnetic Resonance Imaging(MRI)radiomic features for response prediction.Methods This study included 191 HCC patients who received targeted immunotherapy at the Department of Hepatobiliary and Pancreatic Surgery,Chinese PLA General Hospital,from January 2019 to January 2023.The patients were randomly divided into training cohort and validation cohort at a 7:3 ratio.All patients underwent dynamic contrast-enhanced MRI before treatment and during follow-up.Treatment efficacy was assessed according to RECIST1.1 criteria,with complete or partial response considered effective.Tumor regions were delineated on pre-treatment dynamic contrast-enhanced MRI images,and radiomic features were extracted.Meaningful radiomic features were selected using the Least Absolute Shrinkage and Selection Operator(LASSO)algorithm.Various machine learning algorithms,including logistic regression,k-nearest neighbor(KNN),naive Bayes,neural network,support vector machine(SVM),decision tree,XGBoost,and random forest were used to construct radiomic prediction models.The performance of each model was evaluated using receiver operating characteristic(ROC)curves and confusion matrices.The prognostic predictive value of the models was analyzed using Cox regression and Kaplan-Meier curves.Results Medical data of 191 patients were collected,including 163 male patients(85.3%)and 28 female patients(14.7%),with a median age of 55(range:24-74)years.The overall objective response rate was 30.4%.There were 133 cases in the training set and 58 cases in the validation set,with no statistically significant differences in gender and age between the two groups(P>0.05),the objective response rates in training cohort and validation cohort were 30.1% and 31.0%,respectively.Eight ML

关 键 词：肝细胞癌 免疫治疗 影像组学 预测模型 

分 类 号：R657.3[医药卫生—外科学]