BI-RADS Lesion Characteristics Predict Likelihood of Malignancy in Breast MRI for Masses But Not for Nonmasslike Enhancement

Abstract

Combinations of BI-RADS lesion descriptors can predict the probability of malignancy for breast MRI masses but not for NMLE. If our model is validated, masses with a low probability of malignancy may be eligible for short-interval follow-up rather than biopsy. Further research focused on predictive features of NMLE is needed.