Predicting neoadjuvant chemotherapy efficacy among different breast cancer subtypes based on MR radiomics
10.3969/j.issn.1002-1671.2024.12.010
- VernacularTitle:基于MR影像组学预测不同亚型乳腺癌新辅助化疗疗效
- Author:
Jia DING
1
;
Biyun HUANG
;
Qinghong DUAN
Author Information
1. 贵州医科大学医学影像学院,贵州 贵阳 550000
- Keywords:
breast cancer;
predictive model;
radiomics;
magnetic resonance imaging
- From:
Journal of Practical Radiology
2024;40(12):1979-1983
- CountryChina
- Language:Chinese
-
Abstract:
Objective To investigate the value of radiomics model based on multiple sequences MR in predicting the efficacy of neoadjuvant chemotherapy(NAC)among different breast cancer subtypes.Methods Two hundred breast cancer patients undergoing NAC treatment were retrospectively selected,and then randomly divided into training group and validation group at a ratio of 7:3,as well as divided into responsive and non-responsive according to the therapeutic response.Radiomics features were selected and filtered from multiple sequences MR.The model was established by using machine learning,and validated in the validation group.The predictive performance of the model was evaluated by using receiver operating characteristic(ROC)curve,and the clinical application value of the model was assessed by clinical decision curve analysis(DCA).Results The area under the curve(AUC)of hormone receptor(HR)-positive with human epidermal growth factor receptor-2(HER-2)-negative breast cancer patients in training and validation groups were 0.881 and 0.682,respectively,while the AUC of HER-2-positive breast cancer patients were 0.831 and 0.636,respectively.The AUC of triple-negative breast cancer patients were 0.969 and 0.708,respectively.The clinical DCA showed significant clinical benefits.Conclusion The MR radiomics model can predict the efficacy of NAC among different breast cancer subtypes.
