Diagnostic and Interventional Radiology
Breast Imaging - Original Article

Digital breast tomosynthesis (DBT)-based peritumoral radiomics approaches on differentiation of benign and malignant breast lesions


Department of Biomedical Engineering, China Medical University, Shenyang, China


Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, China

Diagn Interv Radiol 2020; 1: -
Read: 98 Published: 01 March 2021

PURPOSE: To evaluate Digital Breast Tomosynthesis (DBT)-based radiomics on differentiation of benign and malignant breast lesions in women.

METHODS: A total of 185 patients who underwent DBT scans were enrolled between December 2017 and June 2019. Radiomics handcrafted and deep learning-based features were extracted from the tumoral and peritumoral regions with different radial dilation distances outside the tumor. A three-step method was used to selected discriminative features and develop the radiomics signature. Discriminative clinical factors were identified by univariate logistic regression. The clinical factors with p < 0.05 were used to build a clinical model with multivariate logistic regression. The radiomics nomogram was developed integrating the radiomics signature and discriminative clinical factors. Discriminative performance of the radiomics signature, clinical model, nomogram and BI-RADS assessment were evaluated and compared with the receiver operating characteristic (ROC) and decision curves analysis (DCA).

RESULTS: A total of two handcrafted and two deep features were identified as the most discriminative features from the peritumoral regions with 2 mm dilation distances and used to develop the radiomics signature. The nomogram incorporating the radiomics signature, age and menstruation status showed the best discriminative performance with AUCs of 0.980 (95% CI, 0.960 to 1.000; SEN = 0.970, SPE = 0.946) in the training cohort and 0.985 (95% CI, 0.960 to 1.000; SEN = 0.909, SPE = 0.966) in the validation cohort. DCA confirmed the potential clinical usefulness of our nomogram. 

CONCLUSION: Our results illustrate that the radiomics nomogram integrating the DBT imaging features and clinical factors (age and menstruation status) can be considered as a useful tool in aiding clinical diagnosis of breast cancer.

EISSN 1305-3612