Radiomics Nomogram of Contrast-Enhanced Spectral Mammography for Prediction of Axillary Lymph Node Metastasis in Breast Cancer: A Multicenter Study

Abstract

Background: Preoperative knowledge of axillary lymph node（ALN）status can potentially help in the clinical decision of breast cancer, nonetheless, there is a lack of method to determine preoperative tumour invasiveness. We developed the radiomics nomogram of contrast-enhanced spectral mammography (CESM), validated based on a multicenter dataset adopting a radiomic strategy, for pretreatment prediction of ALN metastasis in breast cancer. Methods: This retrospective study included 394 patients with breast cancer who underwent CESM examination from 2 hospitals. The least absolute shrinkage and selection operator(LASSO) algorithm were used to select the features. We incorporated the radiomics signature and independent risk factors built radiomics nomogram model. The performance of the nomogram was assessed in the training set and validation set(internal and external validation). The clinical usefulness of the nomogram was assessed using the decision curve analysis(DCA). Findings: The nomogram model included the radiomics signature, CESM-reported lymph node (LN) status. The model showed good calibration and discrimination, with an area under the receiver operator characteristic (AUC) of 0.778 [95% confidence interval (CI), 0.661-0.797]) in the training set, 0.772(95% CI, 0.667-0.871) in the internal validation set and 0.764 (95% CI, 0.677-0.773) in the external validation set. In the CESM-reported LNnegative (cN0) subgroup, the nomogram model also showed favorable discriminatory ability (AUC 0.79; 95% CI, 0.70-0.87). DCA indicated that the model was clinically useful. Interpretation: The radiomics nomogram model incorporates the radiomics signature and CESM-reported LN status, shows favorable predictive accuracy for ALN metastasis in patients with breast cancer. Funding Statement: The authors stated: None. Declaration of Interests: All authors have no conflicts of interest to declare. Ethics Approval Statement: This multicenter study was conducted in accordance with the Declaration of Helsinki and was approved by the ethics committee of each participating hospital, with the requirement for informed consent waived.