Development and validation of a radiomics-based nomogram for predicting two subtypes of HER2-negative breast cancer.

Background: Breast cancer is the most common malignant tumor among women, with an increasing incidence each year. The subtypes of human epidermal growth factor receptor 2 (HER2)-negative breast cancer, classified as HER2-low and HER2-zero based on HER2 receptor expression, show differences in clinical characteristics, therapeutic approaches, and prognoses. Distinguishing between these subtypes is clinically valuable as it can impact treatment strategies, including the use of next-generation antibody-drug conjugates (ADCs) targeting HER2-low tumors. This study aimed to develop a nomogram based on dynamic magnetic resonance imaging (MRI) and clinical indicators to differentiate between HER2-low and HER2-zero subtypes in HER2-negative breast cancer patients. Methods: This study included 214 breast cancer patients from two centers, Hospital A (Affiliated Hospital of Jining Medical University, n=178) and Hospital B (Ningyang No. 1 People's Hospital, n=36). HER2 status was determined by immunohistochemistry (IHC) and fluorescence in situ hybridization (FISH). Among the participants, 112 cases were identified as HER2-low and 102 as HER2-zero. Patients from Hospital A were split into a training set and an internal test set in an 8:2 ratio, while the 36 patients from Hospital B were used as an external test set. Regions of interest (ROI) were delineated on phase 2 enhanced scans and diffusion weighted imaging (DWI) images, with features selected via Pearson correlation coefficients and least absolute shrinkage and selection operator (LASSO) regression. A K-Nearest Neighbor (KNN) model was employed to calculate the rad score, and clinical predictors (tumor maximum diameter and CA153) were identified through logistic regression analysis. These predictors, combined with the rad score, were incorporated into the final nomogram model. The model's accuracy was evaluated using area under curve (AUC) values in both the internal and external validation sets. Results: The nomogram achieved AUC values of 0.873 and 0.859 in the internal and external validation sets, respectively, demonstrating superior performance over single-feature models. Decision curve analysis (DCA) indicated substantial net clinical benefits, and calibration curves displayed strong alignment between the model's predictions and actual outcomes in both sets. Conclusions: This nomogram shows high accuracy and stability in differentiating HER2-low and HER2-zero subtypes among HER2-negative breast cancer patients, suggesting potential clinical utility in refining treatment decisions and identifying candidates for ADC therapy in HER2-low cases.