Purpose: To develop and validate a radiomics nomogram based on intratumoral and peritumoral multiparametric MRI for preoperative prediction of N2-3 stage axillary lymph node (ALN) in invasive breast cancer. Methods: We retrospectively analyzed 320 invasive breast cancer patients (training: n=224; validation: n=96) who underwent pre-treatment breast MRI from January 2018 to December 2019. Pathological ALN metastases < 4 or ≥4 differentiated N0-1 and N2-3 stage ALN groups. Radiomics features associated with ALN stage were selected from five MRI sequences in three regions (intratumor, peritumor, and intratumor+peritumor), and Random Forest (RF) built three radiomics models and calculated the radiomics signature (Radscore), respectively. Univariate and multivariate logistic regression identified clinical parameters related to N2-3 stage ALN, and then constructed a clinical model. Features from the optimal radiomics model and clinical model were integrated to build a combined model and visualized as a nomogram. Using the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA), the predictive performance and clinical usefulness of each model were assessed and compared. Results: The Intra&Peri- (intratumor + peritumor) model performed best among the three radiomics models, with an AUC (area under the curve) of 0.911 and 0.858 in the training and validation datasets, respectively. The nomogram integrating Intra&Peri- radiomics features and clinical features (i.e., peritumoral edema and lesion enhancement pattern) had the best predictive efficacy of N2-3 stage ALN among all models, with an AUC of 0.923 and 0.892 in the training and validation datasets, respectively. Calibration curves showed that the predicted values of the nomogram were in good agreement with the actual observed values. DCA demonstrated that the high clinical utility of nomogram. Conclusions: A nomogram constructed by multiregion multiparametric MRI radiomics features and clinical features has high value for personalized prediction of N2-3 stage ALN in invasive breast cancer.