Characterization of benign and malignant solid breast masses using vascular morphology in 3D power Doppler ultrasound images

摘要

Angiogenesis is a popular issue and indicator in the assessment of tumor's growth and metastasis. Three-dimensional (3-D) power Doppler ultrasound images could characterize benign and malignant breast masses. Therefore, this study extracts the features vascularization from 3-D ultrasound images and selects seven morphological features to diagnose benign and malignant breast tumors by using support vector machine (SVM). These features are trained by the Az value under the receiver operating characteristic (ROC) curve to distinguish the more important features from others. The simulations evaluate 30 benign and 30 malignant breast tumor cases by using the morphological features. The classification performance of the proposed method in term of Az value for the ROC curve of the features derived from 3-D power Doppler is 0.8423. The result shows that the vascular morphology in 3-D power Doppler ultrasound images could be used to diagnose benign and malignant breast tumors.