Early predictive value of dynamic contrast-enhanced MRI radiomics combined with Magee equation 3 for pathological response of HR+/HER2-breast cancer after neoadjuvant chemotherapy
10.3969/j.issn.1002-1671.2025.09.014
- VernacularTitle:动态对比增强MRI影像组学联合Magee方程3对HR+/HER2-乳腺癌新辅助化疗后病理反应的早期预测价值
- Author:
Siye LIU
1
;
Ming YANG
;
Huiling LI
;
Zhaodong AI
;
Xiaorong OU
;
Jun LIU
Author Information
1. 湖南省肿瘤医院 中南大学湘雅医学院附属肿瘤医院放射影像科,湖南 长沙 410006
- Publication Type:Journal Article
- Keywords:
breast cancer;
neoadjuvant chemotherapy;
pathological response;
radiomics
- From:
Journal of Practical Radiology
2025;41(9):1487-1493
- CountryChina
- Language:Chinese
-
Abstract:
Objective To investigate the predictive value of dynamic contrast-enhanced magnetic resonance imaging(DCE-MRI)radiomics combined with Magee equation 3(ME3)for pathological response following neoadjuvant chemotherapy(NAC)in patients with hormone receptor-positive/human epidermal growth factor receptor 2-negative(HR+/HER2-)breast cancer.Methods A ret-rospective analysis was performed on 325 breast cancer patients diagnosed with HR+/HER2-in two hospitals.Patients from the first hospital were randomly divided into training and internal validation sets at a ratio of 7∶3.Patients from the second hospital served as external validation set.The volume of interest(VOI)of breast cancer was delineated on DCE-MRI images.Then the rele-vant radiomics features were extracted and selected,and the Radiomics score(Radscore)was calculated.The statistically significant clinical and pathological features and Radscore were incorporated into a multivariate analysis.The combined radiomics-clinical model and nomogram were established,and the prediction performance was evaluated by using the receiver operating characteristic(ROC)curve,calibration curve,and decision curve analysis(DCA).Results In the training set,seven radiomics features were selected to construct the radiomics model.ME3 score emerged as the independent factor for pathological complete response(pCR)(P＜0.001).By integrating ME3 score and Radscore,a combined radiomics-clinical model was developed.This model demonstrated robust predictive accuracy,with area under the curve(AUC)of 0.88[95％confidence interval(CI)0.80-0.95],0.90(95％CI 0.82-0.98),and 0.82(95％CI 0.70-0.93)in the training,internal validation,and external validation sets,respectively.The nomogram construc-ted from the combined model exhibited excellent discrimination and calibration,with P-values of 0.455,0.312 and 0.062 in the train-ing,internal validation,and external validation sets.Conclusion DCE-MRI radiomics combined with ME3 can be used to predict the pathological response of NAC in HR+/HER2-breast cancer.
