Background and Objectives To investigate accuracy of magnetic resonance imaging (MRI) for measuring residual tumor size in breast cancer patients receiving neoadjuvant chemotherapy (NAC). Methods Ninety-eight patients were studied. Several MRI were performed during NAC for response monitoring, and the residual tumor size was measured on last MRI after completing NAC. Covariates, including age, tumor characteristics, biomarkers, NAC regimens, MRI scanners, and time from last MRI to operation, were analyzed. Univariate and Multivariate linear regression models were used to determine the predictive value of these covariates for MRI-pathology size discrepancy as the outcome measure. Results The mean (±SD) of the absolute difference between MRI and pathological residual tumor size was 1.0 ± 2.0 cm (range, 0-14 cm). Univariate regression analysis showed tumor type, morphology, HR status, HER2 status, and MRI scanner (1.5 T or 3.0 T) were significantly associated with MRI-pathology size discrepancy (all P < 0.05). Multivariate regression analyses demonstrated that only tumor type, tumor morphology, and biomarker status considering both HR and HER-2 were independent predictors (P = 0.0014, 0.0032, and 0.0286, respectively). Conclusion The accuracy of MRI in evaluating residual tumor size depends on tumor type, morphology, and biomarker status. The information may be considered in surgical planning for NAC patients. J. Surg. Oncol. 2014 109:158-167. © 2013 Wiley Periodicals, Inc. © 2013 Wiley Periodicals, Inc.