Classification of Breast Masses Using Color Doppler Flow Imaging

Color Doppler flow imaging takes a great value in diagnosing and classifying benign and malignant breast tumors. However, previous computer aided diagnosis (CAD) systems have not analyzed blood flow information. In this paper, we present a new approach to classify benign or malignant masses based on two dimensional (2D) ultrasound plus Color Doppler flow imaging in CAD system. In the proposed method, geometric features, textural features and blood flow features are extracted automatically. The experimental results show that the proposed system can improve true positive (TP) and decrease false positive (FP) detection rates greatly, and it will useful for breast cancer control.