Medical image blind denoising using context bilateral filter

Edge and detail preserving is a very important requirement in blind medical denoising since the details can help doctors diagnosis diseases. Bilateral filter (BF) is a famous filter in preserving details while smoothing. However, its performance in image denoising is unsatisfied. The main reason for this situation is that the bilateral filter uses gray levels of pixels directly, which causes the propagation of noise (PoN). In this paper, we propose a method, named context bilateral filter (CBF), which conditions the bilateral filter on the context. That is, the range filter is not defined on the gray levels directly while it is defined on the context! Since context can be defined as a smoother version for the image, the PoN can be suppressed greatly. In order to demonstrate the good performance for our method, experimental results using real medical images are given.