Nima Torbati - Iran University of Science and Technology, Tehran, Iran
Ahmad Ayatollahi
Ali Kermani

Ultrasound (US) image segmentation is a difficult task because of its heavy speckle noise, low quality and blurry boundaries. In this paper, a new neural network based method isproposed for ultrasound images segmentation. A modified self organizing map (SOM) network, named finite impulse responseSOM (FIR-SOM), is utilized to segment ultrasound images. A two dimensional (2D) discrete wavelet transform (DWT) is usedto build the input feature space of the network. Experimentalresults show that FIR-SOM discovers the pattern of the input image properly and is robust against noise. Segmentation resultsof breast ultrasound images (BUS) demonstrate that there is a strong correlation between tumor region selected by a physician and the tumor region segmented by our proposed method

Artificial neural network (ANN), ultrasound image (US) segmentation, computer aided diagnosis (CAD)systems