Quantitative Analysis of Lesion Morphology and Texture Features for Diagnostic Prediction in Breast MRI

Abstract

To investigate the feasibility using quantitative morphology/texture features of breast lesions for diagnostic prediction, and to explore the association of computerized features with lesion phenotype appearance on magnetic resonance imaging. Forty-three malignant/28 benign lesions were used in this study. A systematic approach from automated lesion segmentation, quantitative feature extraction, diagnostic feature selection using an artificial neural network (ANN), and lesion classification was carried out. Eight morphologic parameters and 10 gray level co-occurrence matrix texture features were obtained from each lesion. The diagnostic performance of selected features to differentiate between malignant and benign lesions was analyzed using receiver-operating characteristic analysis. Six features were selected by an ANN using leave-one-out cross validation, including compactness, normalized radial length entropy, volume, gray level entropy, gray level sum average, and homogeneity. The area under the receiver-operating characteristic curve was 0.86. When dividing the database into half training and half validation set, a classifier of five features selected in the half training set achieved an area under the curve of 0.82 in the other half validation set. The selected morphology feature "compactness" was associated with shape and margin in the Breast Imaging Reporting and Data System lexicon, round shape and smooth margin for the benign lesions, and more irregular shape for the malignant lesions. The selected texture features were associated with homogeneous/heterogeneous patterns and the enhancement intensity. The malignant lesions had higher intensity and broader distribution on the enhancement histogram (more heterogeneous) compared to the benign lesions. Quantitative analysis of morphology/texture features of breast lesions was feasible, and these features could be selected by an ANN to form a classifier for differential diagnosis. Establishing the link between computer-based features and visual descriptors defined in the BI-RADS lexicon will provide the foundation for the acceptance of quantitative diagnostic features in the development of computer-aided diagnosis.