Abstract
Radiomics has been used as a non-invasive medical image analysis technique for diagnosis and prognosis prediction of breast cancer. This study intended to use radiomics based on preoperative Doppler ultrasound images to classify four molecular subtypes of breast cancer. A total of 565 female breast cancer patients diagnosed by postoperative pathology in a hospital between 2014 and 2022 were included in this study. Radiomic features extracted from preoperative ultrasound images and clinical features were used to construct models for the classification of molecular subtypes of breast cancer. The least absolute shrinkage and selection operator (LASSO) regression was applied for the final screening of radiomic features and clinical features. Three classifiers including Logistic regression, support vector machine (SVM), and XGBoost were utilized to construct model. Model performance was assessed primarily by the area under the receiver operating characteristic curve (AUC) and 95% confidence interval (CI). The mean age of these patients was 54.58 (± 11.27) years. Of these 565 patients, 130 (23.01%) were Luminal A subtype, 329 (58.23%) were Luminal B subtype, 65 (11.50%) were human epidermal growth factor receptor-2 (HER-2) subtype, and 41 (7.26%) were triple negative (TN) subtype. A total of 12 clinical features and 8 radiomic features were selected for model construction. The AUC of the SVM model [0.826 (95%CI 0.808-0.845)] was higher than that of the Logistic regression model [0.776 (95%CI 0.756-0.796)] and the XGB model [0.800 (95%CI 0.779-0.821)] in the multiple classification of breast cancer. For the single classification of breast cancer, the AUC of the SVM model was 0.710 (95%CI 0.660-0.760) for Luminal A subtype, 0.639 (95%CI 0.592-0.685) for Luminal B subtype, 0.754 (95%CI 0.695-0.813) for HER-2 subtype, and 0.832 (95%CI 0.771-0.892) for TN subtype. The SVM model with radiomic features combined with clinical features shows good performance in classifying four molecular subtypes of breast cancer.