The value of radiomics nomogram based on multiparameter MRI in predicting human epidermal growth factor receptor 2 status in endometrial cancer
10.3969/j.issn.1002-1671.2025.06.020
- VernacularTitle:基于多参数MRI的影像组学列线图预测子宫内膜癌人表皮生长因子受体2状态的价值
- Author:
Jing SONG
1
;
Haiping LI
;
Li LI
;
Zengxin LIANG
;
Yongqiang PU
Author Information
1. 青海大学附属医院肿瘤妇科,青海 西宁 810000
- Publication Type:Journal Article
- Keywords:
endometrial cancer;
magnetic resonance imaging;
human epidermal growth factor receptor 2;
radiomics
- From:
Journal of Practical Radiology
2025;41(6):989-993
- CountryChina
- Language:Chinese
-
Abstract:
Objective To explore the predictive value of radiomics nomogram based on multiparameter MRI for the status of human epidermal growth factor receptor 2(HER-2)in endometrial cancer(EC).Methods A total of 154 patients with pathologically proved EC were retrospectively selected and randomly divided into training set(108 cases)and validation set(46 cases)according to the ratio of 7∶3.Radiomics features were extracted from the preoperative multiparameter MRI images of the patients.The predictive performance of different machine learning algorithms was evaluated by receiver operating characteristic(ROC)curves,and the nomogram was constructed in combination with clinical risk factors.Results The degree of differentiation and depth of myometrial invasion were clinical risk factors for predicting HER-2 positivity in EC patients.The support vector machine(SVM)was selected as the best radiomics model.The nomogram showed the highest predictive performance in the training and validation sets,with area under the curve(AUC)of 0.926 and 0.897,respectively.Conclusion The radiomics nomogram based on multiparameter MRI can accurately predict the HER-2 status of EC patients before surgery and can be used to guide clinical treatment decisions.
