Li H, et al. - In this retrospective study, researchers investigated a new approach for improving the performance of benign and malignant breast lesion classification by combining bilateral time–intensity curve (TIC) differentiation features with other effective characteristics. The study sample consisted of 112 DCE-MRI biopsy-proven breast examinations. The use of only unilateral TIC features or conventional features achieved an accuracy of 0.7321 or 0.8482 in terms of accuracy. When bilateral TIC differentiation features were included, however, the accuracy increased to 0.9196. Findings suggested that bilateral differentiation TIC features can be a stronger indicator in the differentiation of benign and malignant breast lesions than unilateral TIC features calculated from only one side of the breast and some conventional features commonly used in MR image analysis.