Computer-aided Diagnosis Of Breast Tumor Based On Ultrasonic Image

Breast cancer is the most prevalent cancer among women. The fatality ratio is keeping rising in these years. Sonography has been widely used for diagnosis of breast cancer because of its non-invasive and low cost for the patients. However, it heavily depends on operator's experience, which leads to a high false positive predictive value. That means large number of unnecessary biopsies, which are painful and economical burden to the patients.Computer-aided diagnosis of breast cancer can reduce breast biopsies and improve breast cancer diagnosis accuracy and objectivity. And it also can largely reduce the doctors'work. This research focused on developing a computer-aided diagnosis system, improving the system's accuracy of both malignant and benign breast diagnosis and offering the secondary opinion to the doctors.A computer-aided diagnosing Method based on B-mode grayscale and color Doppler image analysis and Back Propagation artificial neural network was proposed. Firstly, seven contour features and two gray level features of the tumors were extracted from the regions of interest of the ultrasonic images. Second, gray ratio, Fourier descriptor, circularity and roughness were selected through comparing the classification distance of all the features. And then an optimal feature vector consisted of gray ratio, Fourier and circularity with high sensitivity was created, using K-means cluster algorithm. Finally, based on the result of the feature select, gray ratio, Fourier descriptor and circularity were input to a three-layer Back Propagation (BP) artificial neural network to distinguish the benign and malignant cases. According to the rich blood supplying characteristics...