摘要
目的 探讨基于CT、MRI增强门静脉期的影像组学和临床指标预测模型预测单发肝细胞癌(HCC)切除术后早期复发(≤2年)的价值。方法 回顾性搜集2016年4月至2020年2月徐州市中心医院手术切除并经病理证实的单发HCC患者88例,其中术后早期复发患者40例。按4∶1将88例单发HCC患者随机分为训练集(n=70)和验证集(n=18)。在CT及MRI增强门静脉期图像上手动分割整个肿瘤,获得感兴趣区,提取影像组学特征。在训练集中,采用单变量选择法、最小绝对收缩和选择算子算法(LASSO)、斯皮尔曼相关性分析(Spearman)对组学特征进行降维,筛选最佳特征集。采用单因素、多因素分析确定HCC患者术后早期复发的高危临床因素。联合影像组学特征和临床高危因素分别构建CT-临床模型、MR-临床模型、CT-MR-临床模型。采用受试者工作特征(ROC)曲线下面积(AUC)和Delong检验评估模型的预测价值,并生成预测模型可视化列线图,使用校准曲线评估列线图效能,决策曲线分析(DCA)评估列线图的临床应用价值。结果 临床单因素、多因素分析显示天冬氨酸氨基转移酶(AST)是预测HCC早期复发的独立危险因素(P<0.05)。基于CT、MRI增强门静脉期,共筛选9个CT影像组学特征、4个MRI最佳影像组学特征,与临床独立危险因素分别构建MR-临床模型、CT-临床模型、CT-MR-临床模型。在训练集和验证集中AUC分别为0.919、0.959、0.971和0.844、0.850、0.875,CT-临床模型对HCC术后早期复发预测效能明显优于MR-临床模型(P<0.05),且训练集中CT-MR-临床模型的预测效能明显优于CT-临床模型(P<0.05),DCA显示训练集中阈值概率为>30%,CT-MR-临床模型临床净收益更高。结论 基于CT、MRI增强门静脉期影像组学特征联合临床因素AST构建的预测模型(CT-MR-临床模型)对HCC患者术后早期复发具有更好的预测效能,CT-临床模型预测效能优于MR-临床模型。
Objective To explore the value of predicting early recurrence(≤ 2 years) after resection of single hepatocellular carcinoma(HCC) based on CT and MRI enhanced portal phase imaging and clinical index prediction models. Methods From April 2016 to February 2020,88 patients with single episode HCC who underwent general surgical resection and were pathologically confirmed at Xuzhou Central Hospital were retrospectively collected. Among them, 40 patients with early postoperative recurrence were randomly divided into a training set(n=70) and a validation set(n=18) based on a 4∶1 ratio. Manually segment the entire tumor on CT and MRI enhanced portal phase images to obtain regions of interest and extract imaging features. In the training set, the univariate selection method, least absolute shrinkage and selection operator(LASSO),and Spearman correlation analysis(Spearman) were used to reduce the dimensions of the histological features and select the best feature set. Single factor and multiple factor analysis was used to determine the high-risk clinical factors for early postoperative recurrence in HCC patients. The CT clinical model, MR clinical model, and CT MR clinical model were constructed by combining imaging characteristics and clinical high-risk factors. The prediction value of the model was evaluated using the area under the subject working characteristic(ROC) curve(AUC) and Delong test, and a visual nomogram of the prediction model was generated. Calibration curves were used to evaluate the efficacy of the nomogram, and decision curve analysis(DCA) was used to evaluate the clinical application value of the nomogram. Results Clinical univariate and multivariate analysis showed that aspartate aminotransferase(AST) was an independent risk factor for predicting early recurrence of HCC(P<0.05).Based on CT and MRI enhanced portal phase, a total of 9 CT imaging features and 4 MRI optimal imaging features were selected, and a CT clinical model, an MR clinical model, and a CT MR clinical model were constructed respect
作者
杨宁
夏平
师毅冰
梁弦弦
钱宝鑫
YANG Ning;XIA Ping;SHI Yibing(Department of CT Room,Xuzhou Center Hospital,Xuzhou,Jiangsu Province 221000,P.R.China)
出处
《临床放射学杂志》
北大核心
2024年第5期746-752,共7页
Journal of Clinical Radiology
基金
江苏省卫生健康委医学科研项目(编号:M2021014)。
关键词
计算机体层成像
磁共振成像
影像组学
肝细胞癌
肝切除术
早期复发
Computed tomography
Magnetic resonance imaging
Radiomics
Hepatocellular carcinoma
Liver resection
Early recurrence
