A new automated software system to evaluate breast MR examinations: improved specificity without decreased sensitivity

Abstract

Objective: We sought to compare the accuracy of breast MRI interpretations with and without a new software application (CADstream) that provides automated evaluations of breast MR examinations.

Materials and methods: Thirty-three consecutive lesions seen only on MRI (nine malignant, 24 benign) were evaluated with and without the automated software system. Automated analyses of kinetic enhancement for each lesion were recorded at 50%, 80%, and 100% enhancement thresholds. Computer-assisted analyses included presence or absence of "significant" enhancement and classification of enhancement patterns into percent volumes of washout, plateau, and persistent enhancement. Fisher's exact tests were performed to compare the likelihood of malignancy based on the presence of software-defined significant enhancement at the three thresholds. Enhancement profiles of malignant versus benign lesions were compared using the Student's t test.

Results: All malignant lesions showed significant enhancement at all thresholds. Compared with the unassisted interpretations, the computer-assisted analyses yielded false-positive rates that were reduced by 25% at a 50% threshold (not significant [NS]), 33% at an 80% threshold (p = 0.05), and 50% at a 100% threshold for enhancement (p < 0.01). There were no significant differences between enhancement profiles of benign and malignant lesions, with all lesions showing a wide range of washout, plateau, and persistent patterns of enhancement.

Conclusion: New automated software applied to interpret breast MR examinations accurately showed significant enhancement in all the malignant lesions while depicting 12 of 24 benign lesions as showing insignificant enhancement. If these results are validated by a larger study, the number of unnecessary biopsies of MR lesions could be reduced without a concomitant decrease in cancer detection.