Purpose. To determine the diagnostic accuracy of DOBIComfortScan in patients with Breast Imaging Reporting suspect breast lesions (BI-RADS) 4-5 breast lesions. Materials and Methods. One-hundred and thirteen patients underwent DOBIComfortScan examination before surgery. Twelve parameters were taken into consideration to define DOBI findings. Results. Twenty-seven radical mastectomies, 47 quadrantectomies and 39 wide excisions, were performed. Overall, 65 invasive cancer, 9 in situ carcinoma and 39 nonmalignant lesions, were observed. Ten out of 12 considered parameters resulted significantly in association with histology at discriminant analysis. A summation score of 30.5 resulted to be the best cut off at ROC analysis, giving a sensitivity and specificity of 80% and 87%, respectively, and a positive predictive value of 92.2%. Finally the following DOBI-BI-RADS model was developed: malignant B5 ≥ 38 score); possibly malignant (B4 = 25 - 37 score); benign but the possibility of malignancy cannot be excluded (B3 = 20 - 24 score); benign (B2 < 20 score). Conclusion. definition of other parameters permits to improve the accuracy of this procedure. Further studies are warranted to define the potential role of DOBIComfortScan in breast cancer imaging.