Morphology analysis of breast tumor angiogenesis for 3-D power Doppler ultrasound

Angiogenesis provides blood supply for tumor expansion and increases the opportunity for tumor metastasis For decades, the value of angiogenesis as a prognostic indicator for a wide range of cancers has now been demonstrated. In cancer, tumor vasculature is highly disorganized, tortuous, dilated, and excessive branching. This paper presents a computer-aided diagnostic (CAD) system that can quantify these features using 3-D power Doppler ultrasound (US) on breast tumors. Our scheme utilizes 3-D thinning algorithm for examining the morphology of blood vessels, and neural network for inspecting its relation with tumor malignacy. Investigations into 221 solid breast tumors including 110 benign and 111 malignant cases, the p values of the Student's t-test for all features are less than 0.05, indicating that the proposed features are statistically significant. The experimental results also show that the proposed method is feasible, and have a good agreement with the diagnosis of the pathologists.