中国临床医学影像杂志2025，Vol.36Issue(3)：162-167,6.DOI:10.12117/jccmi.2025.03.003
多模态影像特征联合临床因素列线图模型预测乳腺癌新辅助化疗疗效
A nomogram model based on multimodal imaging features combined with clinical factors predicts the efficacy of neoadjuvant chemotherapy for breast cancer
摘要
Abstract
Objective:To explore the predictive value of the nomogram model based on full-field digital mammography(FFDM),ultrasound(US)and clinical-pathological factors in predicting the efficacy of neoadjuvant chemotherapy(NAC)in breast cancer patients.Methods:The clinical and imaging data of 202 breast cancer patients were retrospectively analyzed,and the patients were randomly divided into training set(n=141)and test set(n=61)at a ratio of 7∶3.In the training set,Lasso regres-sion and multivariate Logistic regression analysis were used to screen predictors and establish a nomogram prediction model,and the model was validated using data from the testing set.The area under the receiver operating characteristic(ROC)curve(AUC),calibration curve and clinical decision curve analysis(DCA)were used to evaluate the diagnostic efficacy of the nomo-gram model.Results:A total of 202 breast cancer patients were divided into pathologic complete response(PCR)group(n=53)and non-PCR group(n=149)according to the pathological results after NAC.The results of Lasso regression combined with multivaritae Logistic regression analysis showed that ER status,HER-2 status,FFDM tumor maximum diameter and US tumor margin were predictors of PCR after NAC in breast cancer,and a nomogram model was constructed to predict the efficacy of NAC.In the training set and validation set,the AUC of the model was 0.913 and 0.881,respectively,and the nomogram model had good discrimination.The optimal threshold of the nomogram based on the ROC curve of the training set was 132.33.The calibration curve showed that the actual probability of the nomogram model was close to the predicted probability,and the model fitted well.The clinical decision curve showed that the model had good clinical applicability.Conclusion:The nomogram model based on FFDM,US imaging features and clinical factors can accurately predict the efficacy of NAC in breast cancer,providing a valuable reference for the clinical formulation of individualized treatment plans.关键词
乳腺肿瘤/放射摄影术/超声检查Key words
Breast Neoplasms/Radiography/Ultrasonography分类
临床医学引用本文复制引用
阮野,刘兴远,曹思薇,金彦桐,张五岳,赵明明,王扬,高波..多模态影像特征联合临床因素列线图模型预测乳腺癌新辅助化疗疗效[J].中国临床医学影像杂志,2025,36(3):162-167,6.基金项目
国家自然科学基金资助项目(编号62172129). （编号62172129）
