Automated feature extraction and classification of breast lesions in magnetic resonance images

We are developing computerized methods to distinguish between malignant and benign lesions in contrast-enhanced magnetic resonance (MR) images of the breast. In this study, we compare 2-D spatial analysis of lesions with 3-D spatial analysis. Our database consists of 28 lesions: 15 malignant and 13 benign. At 90 s intervals, 4 to 6 scans are obtained, and the spatial uptake of contrast agent is analyzed. Computer-extracted features quantify the inhomogeneity of uptake, sharpness of the margins, and shape of the lesion. Stepwise multiple regression is employed to obtain a subset of features, followed by linear discriminant analysis to estimate the likelihood of malignancy. Cross-validation and ROC analysis are used to evaluate the performance of the method in distinguishing between benign and malignant lesions. The procedures are performed in 3-D, and in 2-D from single and multiple slices. Shape and sharpness of the lesion were the most effective features. ROC analysis yielded an A, value of 0.96 for 3-D features, between 0.67 and 0.92 for single slices, and 0.88 for 2-D features from multiple slices. The performance of 2-D analysis on single slices depends strongly on the selected plane and may be significantly lower than the accuracy of full 3-D analysis.