基于MRI影像组学模型预测乙型肝炎病毒相关性肝细胞癌的价值  

Value of MRI radiomics model in predicting hepatocellular carcinoma associated with hepatitis B virus infection

作　　者：李思琪 杨存霞 吴春梅 崔景景 殷小平[1,2,3,4] LI Siqi;YANG Cunxia;WU Chunmei;CUI Jingjing;YIN Xiaoping(Department of Radiology,Affiliated Hospital of Hebei University,Baoding 071000,China;College of Clinical Medical of Hebei University;College of Nursing of Hebei University;Hebei Key Laboratory of precise imaging of inflammation related tumors;Beijing United Imaging Healthcare Co.,Ltd.)

机构地区：[1]河北大学附属医院放射科,保定071000 [2]河北大学临床医学院 [3]河北大学护理学院 [4]河北省炎症相关肿瘤精准影像诊断学重点实验室 [5]联影智能医疗科技(北京)有限公司

出　　处：《国际医学放射学杂志》2025年第1期28-35,共8页International Journal of Medical Radiology

摘　　要：目的探讨多序列MRI影像组学模型预测乙型肝炎病毒(HBV)感染病人相关性肝细胞癌(HCC)的价值。方法回顾性纳入住院治疗的147例HCC病人和癌症影像档案(TCIA)公共数据库中行肝切除术的20例HCC病人。将病人分为HBV感染(HBV)组和非HBV感染(n-HBV)组。将医院病人按照7∶3的比例随机分为训练集(102例)和测试集(45例)。将TCIA来源的病人作为独立验证集。收集全部病人的临床资料以及术前T2WI、扩散加权成像(DWI)、增强MRI影像资料。由2位放射医师手动勾画病灶ROI,利用5折交叉验证、Pearson相关系数和最小绝对收缩和选择算子(LASSO)算法提取和筛选影像组学特征。分别采用支持向量机(SVM)、逻辑回归(LR)分类器构建T2WI、DWI、增强MRI、多模态MRI(mpMRI:T2WI+DWI+增强MRI)影像组学模型。采用受试者操作特征(ROC)曲线评估模型的预测效能,并计算曲线下面积(AUC)、敏感度和特异度,计算模型的Brier分数。在独立验证集中验证最佳模型的泛化能力。结果训练集和测试集中,基于SVM、LR分类器的mpMRI模型预测效能均良好[SVM:AUC值分别为0.991和0.941,LR:AUC值分别为0.993和0.936]。测试集中,SVM模型的预测效能优于LR模型;基于SVM的模型敏感度较高,基于LR的模型的特异度较高。基于SVM-mpMRI模型的诊断效能最佳,其在独立验证集中的AUC值为0.792。校准曲线分析显示,基于LR分类器的mpMRI模型较基于SVM分类器模型(Brier分数分别为0.006、0.069)的预测曲线与实际曲线的拟合度更好。结论基于多序列MRI影像组学模型可辅助临床无创性预测HCC病人是否存在HBV感染,有助于临床决策,能为HCC的精准诊断提供附加信息。Objective To explore the value of a multi-sequence MRI radiomics model in predicting hepatocellular carcinoma(HCC)associated with hepatitis B virus(HBV)infection.Methods A retrospective study included 147 HCC patients hospitalized for treatment and 20 HCC patients from the Cancer Imaging Archive(TCIA)public database who underwent liver resection.Patients were divided into HBV infection(HBV)and non-HBV infection(n-HBV)groups.The hospital patients were randomly assigned into a training set(102 cases)and a testing set(45 cases)in a 7∶3 ratio.The TCIA patients were used as an independent validation set.Clinical data,preoperative T2-weighted imaging(T2WI),diffusion-weighted imaging(DWI),and contrast-enhanced MRI data were collected.Two radiologists manually delineated the regions of interest(ROIs)of the lesions.Five-fold cross-validation,Pearson correlation coefficients,and the least absolute shrinkage and selection operator(LASSO)algorithm were used to extract and select radiomics features.Support vector machine(SVM)and logistic regression(LR)classifiers were employed to construct radiomics models based on T2WI,DWI,contrast-enhanced MRI,and multi-modal MRI(mpMRI:T2WI+DWI+contrast-enhanced MRI).Receiver operating characteristic(ROC)curves were used to evaluate the prediction performance of the models,and the area under the curve(AUC),sensitivity,specificity,and Brier score were calculated.The generalization ability of the best model was validated in the independent validation set.Results In both the training and testing sets,the mpMRI models based on SVM and LR classifiers performed well in predicting HCC associated with HBV infection(SVM:AUC values of 0.991 and 0.941;LR:AUC values of 0.993 and 0.936).In the testing set,the SVM model performed better than the LR model,with higher sensitivity in the SVM-based model and higher specificity in the LR-based model.The SVM-mpMRI model showed the best diagnostic performance,with an AUC of 0.792 in the independent validation set.Calibration curve analysis showed that the mpM

关 键 词：肝细胞癌 磁共振成像 影像组学 乙型肝炎病毒 

分 类 号：R735.7[医药卫生—肿瘤] R445.2[医药卫生—临床医学]