Radiomics features predict equivocal HER2 status in breast cancer patients with high accuracy

ObjectiveIdentification of Human epidermal growth factor receptor 2 (HER2) status is significant for the treatment and prognosis of breast cancer patients. The study aimed to evaluate the equivocal HER2 (IHC 2+) status of breast cancer using intra- and peritumoral radiomics features of contrast-enhanced mammography (CEM).MethodsA total of 131 breast cancer patients with equivocal HER2 (IHC 2+) status of breast cancer were enrolled in the study and divided into training (n=84), internal test (n=22) and prospective test (n=25) cohorts. Radiomics features were extracted from intratumoral and peritumoral regions on CEM and were selected using low variance and least absolute shrinkage and selection operator regression (LASSO). Five radiomics signatures were established based on different intratumoral and peritumoral regions. The nomogram was constructed using the selected signatures and clinical factors by logistic regression analysis. Its predictive performance was compared with the radiomics model and the clinical model. The area under the receiver operator characteristic curve (AUC), sensitivity, specificity, accuracy, the calibration curve, and decision curve analysis (DCA) were used to evaluate predictive performance of the models.ResultsThe intratumoral signature, 5mm-peritumoral signature, and tumor diameter were used to establish nomogram. Compared to the radiomics model and the clinical model, the nomogram achieved optimal predictive performance, with an AUC of 0.893 in the internal test cohort and an AUC of 0.840 in the prospective test cohort. The calibration curves and DCA showed favorable predictive performance of the nomogram.ConclusionsThe nomogram incorporated the intratumoral and peritumoral radiomics signatures of CEM and clinical risk variables has the potential to predict equivocal HER2 (IHC 2+) status of breast cancer preoperatively.