Digital breast tomosynthesis radiomics combined with clinical data for predicting molecular type of breast invasive ductal carcinoma
10.13929/j.issn.1672-8475.2025.02.006
- VernacularTitle:数字乳腺断层摄影影像组学联合临床预测乳腺浸润性导管癌分子类型
- Author:
Qi CHEN
1
;
Mengyao GU
1
;
Li LIU
1
;
Jiajia QI
1
;
Wanhu LI
1
Author Information
1. 山东省肿瘤防治研究院(山东省肿瘤医院),山东第一医科大学(山东省医学科学院)影像科,山东 济南 250117
- Publication Type:Journal Article
- Keywords:
breast neoplasms;
mammography;
radiomics;
molecular typing
- From:
Chinese Journal of Interventional Imaging and Therapy
2025;22(2):107-111
- CountryChina
- Language:Chinese
-
Abstract:
Objective To observe the value of digital breast tomosynthesis(DBT)radiomics combined with clinical data for predicting molecular type of breast invasive ductal carcinoma(IDC).Methods Totally 309 female patients with Luminal type and 97 with non-Luminal type breast IDC were retrospectively enrolled and divided into training set(n=284)and test set(n=122)at a ratio of 7∶3.Multivariate logistic regression analysis was performed to screen independent impact factors related to Luminal expression of breast IDC based on clinical data and DBT manifestations,then a clinical-imaging model was constructed.The radiomics model was established based on mediolateral oblique position of DBT images,and a combined model was conducted combining with clinical-imaging model and radiomics model.Receiver operating characteristic curves were drawn,and the area under the curves(AUC)were calculated to evaluate the efficacy of each model for predicting molecular type of breast IDC.Results Histopathological grade and lesion margin showed on DBT was the clinical and imaging independent impact factor associated with Luminal expression of breast IDC,respectively(both P＜0.05).AUC of combined model for predicting molecular type of breast IDC in training set and test set was 0.821 and 0.715,respectively,both higher than clinical-imaging model(0.727 and 0.665)and radiomics model(0.776 and 0.663)(all P＜0.05),while no significant difference was found between clinical-imaging model and radiomics model(both P＞0.05).Conclusion DBT radiomics combined with clinical data was helpful for predicting molecular type of breast IDC.
