Background: Mammography is the standard for breast cancer (BC) screening and diagnosis. However, its limited accuracy and false-positive results necessitate the identification of novel complementary biomarkers. Circulating microRNAs (c-miRNAs) represent a class of biomarkers with the potential of improving the diagnostic performance of current imaging analysis. Methods: C-miRNA profiles of paired pre- and post-operative serum samples from 402 patients with early-stage BC were analyzed by quantitative reverse transcriptase polymerase chain reaction. Wilcoxon and Mann-Whitney tests were used to identify significantly dysregulated c-miRNAs. Validation was performed on an independent cohort of BC samples (n = 160), in benign breast lesions (n = 60), and in healthy individuals (n= 50). A logistic regression model was used to identify diverse miRNA signatures with the highest diagnostic efficacy. Diagnostic performance of c-miRNA signatures and mammography was evaluated using Receiver Operating Characteristic (ROC) curves. Results: The expression of 15 miRNAs was able to cluster breast cancer patients from healthy donors, pre- and post-operative patients. Eleven miRNAs showed diagnostic potential (area under the curve (AUC) of 0.61 to 0.72). A combination of five miRNAs (miR-10b, miR-21, miR-133a, miR-148b, and miR-155) demonstrated a substantial higher diagnostic value compared with mammography (AUC = 0.89 vs AUC = 0.81, respectively). Importantly, the diagnostic performance of the miRNA signature was consistently better than mammography alone among women under the age of 50 (AUC = 0.91 vs AUC = 0.74, respectively). Of note, a single miRNA (miR-155) was significantly associated (P< 0.001) with lymph node involvement, potentially substantiating histologic evaluation in breast cancer (without biopsy). Conclusions: These results suggest the assessment of circulating miRNAs as useful non-invasive diagnostic markers that increase the diagnostic performance of mammography, particularly in young early-stage BC patients. All together these data motivate the development of a next-generation system that combines the use of molecular biomarkers with breast imaging techniques.