Low-dose CT denoising using a Progressive Wasserstein generative adversarial network

Abstract

Low-dose computed tomography (LDCT) imaging can greatly reduce the radiation dose imposed on the patient. However, image noise and visual artifacts are inevitable when the radiation dose is low, which has serious impact on the clinical medical diagnosis. Hence, it is important to address the problem of LDCT denoising. Image denoising technology based on Generative Adversarial Network (GAN) has shown promising results in LDCT denoising. Unfortunately, the structures and the corresponding learning algorithms are becoming more and more complex and diverse, making it tricky to analyze the contributions of various network modules when developing new networks. In this paper, we propose a progressive Wasserstein generative adversarial network to remove the noise of LDCT images, providing a more feasible and effective way for CT denoising. Specifically, a recursive computation is designed to reduce the network parameters. Moreover, we introduce a novel hybrid loss function for achieving improved results. The hybrid loss function aims to reduce artifacts while better retaining the details in the denoising results. Therefore, we propose a novel LDCT denoising model called progressive Wasserstein generative adversarial network with the weighted structurally-sensitive hybrid loss function (PWGAN-WSHL), which provides a better and simpler baseline by considering network architecture and loss functions. Extensive experiments on a publicly available database show that our proposal achieves better performance than the state-of-the-art methods.