Speckle Suppression in Medical Ultrasound Images Using Two Dimensional GARCH Model

Abstract

In this paper, we introduce a novel speckle suppression method for medical ultrasound images, based on statistical model of wavelet coefficients. We use two-dimensional generalized autoregressive conditional heteroscedasticity (GARCH) model for statistical modeling of images wavelet coefficients. By using two-dimensional GARCH model on the wavelet coefficients, we are capable of taking into account important characteristics of wavelet coefficients, such as non-stationarity, heavy tailed marginal distribution, and the dependencies between the coefficients. Furthermore, we use minimum mean square error (MMSE) estimator for estimating the clean image wavelet coefficients. Here, to prove the performance of this method in speckle suppression, we have compared our proposed method with various speckle suppression methods applied on actual ultrasound medical images and we verify the performance improvement in utilizing the new strategy.