Enhanced Wiener filter for ultrasound image denoising

Speckle phenomenon strongly affects Ultra-Sound (US) images. Over the past last years, several efforts have been done in order to provide an effective denoising methodology. Although good results have been achieved in terms of noise reduction effectiveness, most of the proposed approaches are characterized by a high computational load and require the supervision of an external operator for tuning the input parameters. Within this manuscript, a novel approach for noise reduction is investigated, based on Wiener filter. With respect to classical Wiener filter, the proposed Enhanced Wiener filter is able to locally adapt itself. By automatically tuning its kernel a good combination of edges and details preservation with effective noise reduction can be reached. This behavior is achieved by implementing a Local Gaussian Markov Random Field for modeling the image. Due to its intrinsic characteristics, the computational burden of the algorithm is sensibly low compared to other widely adopted filters and the parameter tuning effort is minimal. Results on a simulated dataset are reported, showing the interesting performances of the approach.