Objective To investigate the value of a nomogram based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics combined with clinical factors in predicting preoperative axillary lymph node (ALN) metastasis of breast cancer. Methods The data of 80 patients with breast cancer confirmed by pathology in Pingdingshan First People’s Hospital from January 2023 to May 2025 were collected retrospectively, and randomly divided into training set (56 cases) and internal validation set (24 cases) according to the ratio of 7 vs. 3. All patients were examined by DCE-MRI before surgery, and the region of interest (ROI) was delineated layer by layer on the T1-weighted imaging (T1WI) enhanced sequence to extract the radiomics features. A multivariate Logistic regression model was established based on clinical and pathological factors, and a nomogram was drawn. In addition, the receiver operator characteristic (ROC) curve was used to evaluate the discrimination of the model. Results There were 27 positive cases and 29 negative cases of ALN metastasis in the training set, 12 positive cases and 12 negative cases in the internal validation set. Finally, 9 radiomics features most relevant to ALN metastasis were screened. The area under the curve (AUC) of the combined model (ALN status reported by Radscore＋MRI) in the training set and the internal validation set were 0.912 (95%CI: 0.841?0.983) and 0.873 (95%CI: 0.754?0.992), respectively, which were superior to the single clinical model or the radiomics model. Conclusion The nomogram based on DCE-MRI radiomics combined with clinical factors can effectively improve the accuracy of preoperative prediction of ALN metastasis in breast cancer, providing a non-invasive auxiliary tool for individualized treatment decisions.