基于乳腺X线摄影及DCE-MRI机器学习模型预测乳腺癌新辅助治疗后病理完全缓解:双中心研究  

Machine learning model based on mammography and DCE-MRI to predict pathological complete response after neoadjuvant therapy in breast cancer:a dual center research

作　　者：刘晶晶[1] 庞婧[2] 赵晓丹[2] 林昕 付敏[1] 陈静静[2] LIU Jingjing;PANG Jing;ZHAO Xiaodan;LIN Xin;FU Min;CHEN Jingjing(Qingdao Medical College of Qingdao University,Qingdao 266071,Shandong,China;Department of Radiology,The Affiliated Hospital of Qingdao University,Qingdao 266000,Shandong,China)

机构地区：[1]青岛大学青岛医学院,山东青岛266071 [2]青岛大学附属医院放射科,山东青岛266000

出　　处：《山东大学学报(医学版)》2025年第1期60-72,共13页Journal of Shandong University:Health Sciences

基　　金：国家自然科学基金(8207071895)。

摘　　要：目的探讨基于乳腺X线摄影及动态增强磁共振成像(dynamic contrast-enhanced magnetic resonance imaging,DCE-MRI)的机器学习模型预测乳腺癌患者新辅助治疗(neoadjuvant therapy,NAT)后病理完全缓解(pathological complete response,pCR)的价值。方法回顾性分析2016年8月至2023年7月于青岛大学附属医院(机构1)及烟台毓璜顶医院(机构2)接受NAT后行手术的396例乳腺癌患者资料,来自机构1的320例患者按7∶3比例随机分为训练集和验证集,来自机构2的76例患者作为独立的外部验证集。对患者NAT前乳腺X线摄影及DCE-MRI图像进行感兴趣区域(region of interest,ROI)勾画、特征提取、特征筛选,使用支持向量机(support vector machine,SVM)机器学习算法构建影像组学模型。对临床特征进行单因素-多因素逻辑回归分析,保留具有统计学意义的临床独立预测因子并构建临床模型。将联合影像组学模型与临床独立预测因子使用SVM机器学习算法联合构建综合模型。采用受试者工作特征(receiver operating characteristic,ROC)曲线的曲线下面积(area under the curves,AUC)、准确性、敏感性、特异性和F1-score评价模型的性能,绘制校准曲线评价模型的拟合优度,采用决策曲线分析(decision curve analysis,DCA)评估模型的临床应用价值。结果联合影像组学模型预测性能高于临床模型、乳腺X线摄影影像组学模型和MRI影像组学模型,其在训练集、验证集和外部验证集AUC分别为0.899、0.850及0.765。综合模型预测性能最佳,其在训练集、验证集和外部验证集AUC分别为0.918、0.856、0.795,且该模型具有良好的校准能力和临床收益。Delong检验示临床模型与综合模型的AUC的差异有统计学意义(P<0.05)。结论基于乳腺X线摄影及DCE-MRI的机器学习模型可以预测乳腺癌患者NAT后pCR,且具有较高的预测性能。Objective To investigate the value of machine learning models based on mammography and dynamic contrast-enhanced magnetic resonance imaging(DCE-MRI)in predicting pathological complete response(pCR)in breast cancer patients after neoadjuvant therapy(NAT).Methods A retrospective analysis of 396 breast cancer patients who underwent NAT followed by surgery from August 2016 to July 2023 at the Affiliated Hospital of Qingdao University(Institution 1)and Yantai Yuhuangding Hospital(Institution 2)was performed.A total of 320 patients from Institution 1 were randomly divided into a training set and a validation set in a ratio of 7∶3,and 76 patients from Institution 2 served as an independent external validation set.Regions of interest(ROI)were delineated on pre-NAT mammography and DCE-MRI images,followed by feature extraction and feature selection.The radiomics model was constructed using the support vector machine(SVM)algorithm.Clinical features underwent univariate and multivariate analyses,and statistically significant independent predictors were used to construct the clinical model.The comprehensive model integrating the radiomics signature and clinical predictors was constructed using the SVM algorithm.The performance of the models was evaluated using the area under the receiver operating characteristic(AUC)curve,accuracy,sensitivity,specificity,and F1-score.The calibration efficiency of the predictive models was evaluated by drawing calibration curves and decision curve analysis(DCA)was performed to evaluate the clinical utility of the predictive models.Results The combined radiomics model demonstrated better predictive performance than the clinical model,mammography radiomics model and MRI radiomics model,with AUCs of 0.899,0.850,and 0.765 in the training,validation,and external validation sets,respectively.The comprehensive model showed the best predictive performance,with AUCs of 0.918,0.856,and 0.795 in the training,validation,and external validation sets,respectively.The comprehensive model exhibited good cal

关 键 词：乳腺癌 影像组学 新辅助治疗 乳腺X线摄影 磁共振成像 

分 类 号：R737.9[医药卫生—肿瘤] R814.41[医药卫生—临床医学]