A Novel Technique for Speckle Noise Reduction on Medical Images

One problem in processing ultrasound (US) images is the presence of speckle noise which is multiplicative and is a major limitation on image quality. The presence of the speckle noise affects image interpretation by human and the accuracy of computer-assisted diagnostic techniques. Low image quality is an obstacle for effective feature extraction, analysis, recognition and quantitative measurements. Image variances or speckle is a granular noise that inherently exists in and degrades the quality of the medical images. Before using ultrasound and magnetic resonance imaging, the very first step is to reduce the effect of Speckle noise. Most of speckle reduction techniques have been studied by researchers; however, there is no comprehensive method that takes all the constraints into consideration. Filtering is one of the common methods which is used to reduce the speckle noises. In this paper, a new filter has been proposed which works by passing an image through a filter which works by raising pixels that are darker than their surrounding neighbors, then complementarily lowering pixels that are brighter than their surrounding neighbors to reduce the speckle index of that image. The proposed method has been compared with mean, median, Local Region Filter, Lee and Diffusion Filter using quantitative parameters like MSE and SNR. It has been found that the proposed method performs better than all other methods while still retaining the structural details