Breast Tumor Ultrasound Image Recognition Based On Wavelet Transform

Wavelet transform is very important in digital image processing, including the image compression, the image goes chirp, image fusion, image dissection, image enhancement etc. 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. In this paper, we analyze the normal breast ultrasonic image and distempered breast ultrasonic image using the theory of wavelet transform and also image de-noising using the theory and feature extraction too. we analyze the statistic of the feature parameter of ultrasonic image of breast though the methods of Probabilistic neural network., and distinguish the two kinds of ultrasonic image, we can know which is the breast tumor result from the image. Research results show that the method has higher accuracy rate to the custom experience. Image Segmentation, image de-noising and then extracting feature parameter by Wavelet Transform can distinguish two kinds of images, doctors diagnose according to quantized feature parameter and improve accuracy rating of clinical diagnosis Breast Tumor.