The study developed a radiomics model to predict the efficacy of neoadjuvant chemotherapy in patients with HER2-low breast cancer using pretreatment DCE-MRI imaging. Data from female patients were analyzed, from which conventional radiomic features were extracted, including those based on wavelets and the Hessian matrix. The clinical-pathological model achieved the best performance with the Random Forest algorithm. The radiomic model with conventional and Hessian features had an AUC of 0.84 in the training cohort and an AUC of 0.74 in the validation cohort. A nomogram combining the best Random Forest models from clinical and radiomic data showed an AUC of 0.89 in the training cohort and 0.79 in the validation cohort. Decision curve analysis confirmed the clinical advantages of the nomogram over separate models. The model offers a strategy for predicting treatment response.