Nomogram for Predicting HER-2 Expression in Invasive Breast Carcinoma of No Specific Type Based on Radiomics of DCE-MRI
10.3969/j.issn.1005-5185.2025.04.008
- VernacularTitle:基于DCE-MRI影像组学列线图预测非特殊型浸润性乳腺癌HER-2表达
- Author:
Mengyi SHEN
1
;
Li ZHANG
1
;
Dingyi ZHANG
1
;
Xin HE
1
;
Xiaohua HUANG
1
Author Information
1. 川北医学院附属医院放射科,四川 南充 637000
- Publication Type:Journal Article
- Keywords:
Breast neoplasms;
Magnetic resonance imaging;
Radiomics;
Nomograms;
Receptor,ErbB-2
- From:
Chinese Journal of Medical Imaging
2025;33(4):381-389
- CountryChina
- Language:Chinese
-
Abstract:
Purpose To explore the value of a nomogram for predicting human epidermal growth factor receptor 2(HER-2)expression in invasive breast carcinoma of no specific type(IBC-NST)based on radiomics of intratumoral and peritumoral dynamic contrast-enhanced MRI(DCE-MRI)in combination with clinical characteristics.Materials and Methods The information of 136 patients with IBC-NST confirmed by pathology in the Affiliated Hospital of North Sichuan Medical College were retrospectively collected from April 2021 to June 2023 on the basis of inclusion and exclusion criteria,and all patients were randomly divided into a training cohort of 95 cases and a validation cohort of 41 cases according to 7∶3.The region of interest(ROI)of breast tumor(intratumor)was manually delineated on the second phase of DCE-MRI,then the intratumoral region was automatically expanded by 5 mm and adjusted,through which the peritumoral ROI was obtained.Features of intratumoral and peritumoral ROI were extracted and screened respectively,intratumoral and peritumoral model,intratumoral and peritumoral combination model were established,then the radiomics signature’s score(Radscore)was calculated.Multivariate Logistic regression analysis was used to screen the independent risk factors and after that,a clinical model was constructed.The nomogram was constructed using Radscore and the independent risk factor.The predictive performance of each model was mainly evaluated by the area under receiver operating characteristic curve(AUC).Results In the training cohort,the AUC of intratumoral and peritumoral model,intratumoral and peritumoral combination model,clinical model,nomogram were 0.822,0.751,0.869,0.578 and 0.870,respectively.In the validation cohort,the AUC were 0.755,0.790,0.817,0.626 and 0.821,respectively.The nomogram achieved the highest predictive performance.Conclusion The nomogram based on radiomics of intratumoral and peritumoral DCE-MRI in combination with the clinical characteristic can effectively predict HER-2 expression in IBC-NST and provides a reference for classifications and clinical treatment decisions of IBC-NST.
