基于IVIM-DWI功能图像的影像组学模型术前预测肝细胞癌的分化程度  

IVIM-DWI-based radiomic model for preoperative prediction of hepatocellular carcinoma differentiation

作　　者：庄羽翔 李晓凤 周代全 旷连勤 严敏 ZHUANG Yuxiang;LI Xiaofeng;ZHOU Daiquan;KUANG Lianqin;YAN Min(Department of Radiology,the Third Affiliated Hospital of Chongqing Medical University,Chongqing,401120,China)

机构地区：[1]重庆医科大学附属第三医院放射科,重庆401120

出　　处：《陆军军医大学学报》2024年第20期2322-2329,共8页Journal of Army Medical University

基　　金：重庆市教育委员会科学技术研究项目(KJQN202300452);重庆市临床重点专科建设项目(SLCZDZK202202)。

摘　　要：目的 基于体素内不相干运动扩散加权成像(intravoxel incoherent motion diffusion-weighted imaging, IVIM-DWI)功能图像构建影像组学相关模型,探讨其术前预测肝细胞癌(hepatocellular carcinoma, HCC)分化程度的价值。方法 纳入2018年6月至2024年1月于重庆医科大学附属第三医院接受手术治疗的187例HCC患者的临床及影像学资料,根据术后病理结果分为低分化组(n=58)和非低分化组(n=129),以8∶2的比例随机分为训练组149例和验证组38例。采用单因素分析评估与HCC分化程度相关的临床资料并构建临床模型;应用Pyradiomics软件提取IVIM-DWI功能图像的组学特征,采用最小绝对收缩和选择算子逻辑回归算法筛选出与HCC分化程度高度相关的影像组学特征,分别运用支持向量机(support vector machine, SVM)、逻辑回归(logistic regression, LR)、随机森林(random forest, RF)算法构建不同的影像组学模型;采用SVM算法构建影像组学-临床联合模型。采用10折交叉验证进行模型内部验证;运用受试者工作特征曲线(receiver operating characteristic curve, ROC)、曲线下面积(area under the curve, AUC)、校准曲线、决策曲线分析(decision curve analysis, DCA)评价临床模型、影像组学模型、影像组学-临床联合模型的诊断价值和临床收益。结果 共提取4 060个影像组学特征,经过特征筛选及降维后,最终纳入24个特征进行模型构建。结果显示,影像组学模型、影像组学-临床联合模型的预测性能优于临床模型。运用SVM算法构建的影像组学模型、影像组学-临床联合模型间进行比较,在训练集中影像组学模型AUC=0.954(0.908~1.000),影像组学-临床联合模型AUC=0.943(0.905~0.982),二者间差异无统计学意义;在验证集中影像组学模型AUC=0.807(0.640~0.975),影像组学-临床联合模型AUC=0.876(0.743~1.000),二者间差异具有统计学意义(P<0.05)。校准曲线显示影像组学模型和影像组学-临床联合ObjectiveTo construct a radiomic model based on intravoxel incoherent motion diffusion-weighted imaging(IVIM-DWI)for preoperative prediction of hepatocellular carcinoma(HCC)differentiation and validate its clinical value.MethodsClinical and imaging data of 187 HCC patients who received surgical treatment in the Third Affiliated Hospital of Chongqing Medical University from June 2018 to January 2024 were collected and retrospectively analyzed.According to the postoperative pathological results,they were divided into low-differentiation group(n=58)and non-low-differentiation group(n=129),and randomly divided into the training group(n=149)and the validation group(n=38)with the ratio of 8∶2.Univariate analysis was used to assess the clinical indicators related to HCC differentiation,and then a clinical model was constructed.Pyramidimics software was used to extract the radiomic features of IVIM-DWI functional images,and minimum absolute contraction and selection operator logistic regression algorithm were employed to screen those highly correlated indicators with HCC differentiation.Support vector machine(SVM),logistic regression(LR)and random forest(RF)algorithms were utilized to construct different image omics models.SVM algorithm was applied to construct the combined imaging omics and clinical model.The internal verification of the model was carried out by using ten-fold cross-validation.Receiver operating characteristic(ROC)curve,area under the curve(AUC),calibration curve,and decision curve analysis(DCA)were used to evaluate the diagnostic value and clinical benefits of clinical model,radiomic model,and their combination.ResultsA total of 4060 radiological features were extracted,and after feature screening and dimensionality reduction,24 features were finally included to construct the model.Among all models,the predictive performance of the radiomic model and the radiomic-clinical combined model was better than that of the clinical model.In the comparison between the radiomic model constructed by SVM algorith

关 键 词：肝细胞癌 体素内不相干运动 磁共振成像 影像组学 

分 类 号：R445.2[医药卫生—影像医学与核医学] R730.21[医药卫生—诊断学] R735.7[医药卫生—临床医学]