PURPOSE: The purpose of this study was to assess the ability of Micro Computed Tomography (Micro CT) to measure primary tumor size in breast lumpectomy specimens, as compared to the histopathological measurement. METHODS: This was a diagnostic study involving women who were scheduled to have breast lumpectomy surgery at the Massachusetts General Hospital (MGH) Department of surgery from June 2011 - September 2011. Those who met the study eligibility criteria were recruited to participate in the study. The study was approved by the MGH Institutional Review Board (IRB). All the participants provided consent prior to their participation in the study. The lumpectomy specimens of 45 subjects were scanned by Micro CT scan for no longer than 15 minutes, they were then delivered to the gross pathology lab for processing via the standard pathological protocol. Later on, the maximum dimension of the invasive breast tumor was obtained from the Micro CT image and was compared to the corresponding pathology report for each subject. RESULTS: We found that Micro CT tends to overestimate the breast malignant tumor size. However, there were few differences in T-stage classification between Micro CT and pathology. Overall, Micro CT demonstrated good agreement with pathological tumor size and staging. For Invasive ductal carcinoma, Micro CT showed a substantial agreement with pathological tumor size and staging. However, Micro CT showed no agreement with pathological tumor size and staging for invasive lobular carcinoma. CONCLUSIONS: Micro CT is a promising modality in measuring and staging the invasive ductal carcinoma.