基于CT影像组学的局部进展期直肠癌新辅助放化疗效果的预测模型研究  

A study on predictive models for the efficacy of neoadjuvant chemoradiotherapy in locally advanced rectal cancer based on CT radiomics

作　　者：胡义銧 刘碧瑶 张雯迪 蒲瑞芳 孔慧珍 田峻奇 王勇[1] 汪晓东[1] HU Yiguang;LIU Biyao;ZHANG Wendi;PU Ruifang;KONG Huizhen;TIAN Junqi;WANG Yong;WANG Xiaodong(Division of Gastrointestinal Surgery,Department of General Surgery,West China Hospital,Sichuan University,Chengdu 610041,P.R.China;West China School of Medicine,Sichuan University,Chengdu 610041,P.R.China;School of Computer Science,Sichuan University,Chengdu 610065,P.R.China)

机构地区：[1]四川大学华西医院普外科,胃肠外科病房,成都610041 [2]四川大学华西临床医学院,成都610041 [3]四川大学计算机学院,成都610065

出　　处：《中国普外基础与临床杂志》2025年第2期205-212,共8页Chinese Journal of Bases and Clinics In General Surgery

基　　金：四川省科技厅重点研发项目(项目编号:2024YFHZ0060);四川大学大学生创新创业计划项目(项目编号:S202410610509)。

摘　　要：目的基于增强CT影像特征构建多模态影像组学模型,预测局部进展期直肠癌(locally advanced rectal cancer,LARC)患者接受新辅助放化疗(neoadjuvant chemoradiotherapy,NCRT)后的肿瘤退缩分级(tumor regression grade,TRG)。方法回顾性分析2016年10月至2023年10月期间四川大学华西医院收治的符合纳入排除标准的199例LARC患者的临床资料,纳入患者皆在NCRT后联合全直肠系膜切除术。收集患者的临床病理信息,并提取NCRT前CT图像的影像组学特性。使用Python 3.13.0进行特征降维,并采用单因素logistic回归和Lasso回归5倍交叉验证方法筛选影像组学特征。将所有患者按照7∶3的比例随机分为训练集和测试集进行机器学习并构建联合模型,计算准确率、灵敏度、特异度、曲线下面积(area under curve,AUC),并绘制受试者工作特征曲线、混淆矩阵、临床决策曲线(decision curve analysis,DCA)以评估模型性能。结果199例患者中,疗效不良155例(77.89%),疗效良好44例(22.11%)。使用单因素logistic回归(logistic regression,LR)和Lasso回归筛选出8个临床病理特征和5个影像组学特征(包括1个形状特征,2个一阶统计特征,2个纹理特征),分别建立LR模型、支持向量机(support vector machine,SVM)模型、随机森林(random forest,RF)模型、分布式梯度增强库(eXtreme gradient boosting,XGBoost)模型。训练集中,LR、SVM、RF和XGBoost模型的AUC分别为0.99、0.98、1.00、1.00,准确率分别为0.94、0.93、1.00、1.00,灵敏度分别为0.98、1.00、1.00、1.00,特异度分别为0.80、0.67、1.00、1.00。测试集中,4个模型的AUC分别为0.97、0.92、0.96、0.95,准确率分别为0.87、0.87、0.88、0.90,灵敏度分别为1.00、1.00、1.00、0.95,特异度分别为0.50、0.50、0.56、0.75;其中XGBoost模型的效能最佳,其准确率和特异度最高。DCA显示4个模型均有临床获益。结论基于增强CT的多模态影像组学模型在预测LARC行NCRT的疗效上具有良好Objective To construct a multimodal imaging radiomics model based on enhanced CT features to predict tumor regression grade(TRG)in patients with locally advanced rectal cancer(LARC)following neoadjuvant chemoradiotherapy(NCRT).Methods A retrospective analysis was conducted on the Database from Colorectal Cancer(DACCA)at West China Hospital of Sichuan University,including 199 LARC patients treated from October 2016 to October 2023.All patients underwent total mesorectal excision after NCRT.Clinical pathological information was collected,and radiomics features were extracted from CT images prior to NCRT.Python 3.13.0 was used for feature dimension reduction,and univariate logistic regression(LR)along with Lasso regression with 5-fold cross-validation were applied to select radiomics features.Patients were randomly divided into training and testing sets at a ratio of 7∶3 for machine learning and joint model construction.The model’s performance was evaluated using accuracy,sensitivity,specificity,and the area under the curve(AUC).Receiver operating characteristic curve(ROC),confusion matrices,and clinical decision curves(DCA)were plotted to assess the model’s performance.Results Among the 199 patients,155(77.89%)had poor therapeutic outcomes,while 44(22.11%)had good outcomes.Univariate LR and Lasso regression identified 8 clinical pathological features and 5 radiomic features,including 1 shape feature,2 first-order statistical features,and 2 texture features.LR,support vector machine(SVM),random forest(RF),and eXtreme gradient boosting(XGBoost)models were established.In the training set,the AUC values of LR,SVM,RF,XGBoost models were 0.99,0.98,1.00,and 1.00,respectively,with accuracy rates of 0.94,0.93,1.00,and 1.00,sensitivity rates of 0.98,1.00,1.00,and 1.00,and specificity rates of 0.80,0.67,1.00,and 1.00,respectively.In the testing set,the AUC values of 4 models were 0.97,0.92,0.96,and 0.95,with accuracy rates of 0.87,0.87,0.88,and 0.90,sensitivity rates of 1.00,1.00,1.00,and 0.95,and specificity rates of 0

关 键 词：直肠癌 肿瘤退缩分级 机器学习 影像组学 新辅助放化疗 

分 类 号：R735.37[医药卫生—肿瘤]