Medical Image Denoising Using Two-stage Iterative Down- up CNN and SURF FEATURES

Abstract

Most of existing medical image denoising methods focus on estimating either the image or the residual noise. Moreover, they are usually designed for one specific noise with a strong assumption of the noise distribution. Explicitly modeling the distributions of these complex noises in the medical image is extremely hard. They cannot be accurately held by the Gaussian or mixture of Gaussian model. To overcome the two drawbacks, in this work, we propose a deep iterative down-up convolutional neural network (DIDN) for image denoising, which repeatedly decreases and increases the resolution of the feature maps. To better cope with the gradient vanishing problem in this very deep network, we introduce speeded up robust features (SURF) which is a patented local feature detector and descriptor. Extensive experiments have been performed on several kinds of medical noise images, such as the computed tomography and ultrasound images, and the proposed method has consistently outperformed stateof-the-art denoising methods.