Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss

Abstract

The continuous development and extensive use of computed tomography (CT) in medical practice has raised a public concern over the associated radiation dose to the patient. Reducing the radiation dose may lead to increased noise and artifacts, which can adversely affect the radiologists' judgment and confidence. Hence, advanced image reconstruction from low-dose CT data is needed to improve the diagnostic performance, which is a challenging problem due to its ill-posed nature. Over the past years, various low-dose CT methods have produced impressive results. However, most of the algorithms developed for this application, including the recently popularized deep learning techniques, aim for minimizing the mean-squared error (MSE) between a denoised CT image and the ground truth under generic penalties. Although the peak signal-to-noise ratio is improved, MSE- or weighted-MSE-based methods can compromise the visibility of important structural details after aggressive denoising. This paper introduces a new CT image denoising method based on the generative adversarial network (GAN) with Wasserstein distance and perceptual similarity. The Wasserstein distance is a key concept of the optimal transport theory and promises to improve the performance of GAN. The perceptual loss suppresses noise by comparing the perceptual features of a denoised output against those of the ground truth in an established feature space, while the GAN focuses more on migrating the data noise distribution from strong to weak statistically. Therefore, our proposed method transfers our knowledge of visual perception to the image denoising task and is capable of not only reducing the image noise level but also trying to keep the critical information at the same time. Promising results have been obtained in our experiments with clinical CT images.

Data‐driven synthetic MRI FLAIR artifact correction via deep neural network

“…For the loss function, we used a combination of the mean absolute error (MAE) loss and the perceptual loss . Addition of the perceptual loss has been shown to perform better at reconstructing fine details than using MAE alone in medical image applications . The perceptual loss was composed of the early layers of the VGG‐16 network pretrained on the ImageNet dataset (Fig.…”

“…Recently, deep learning (DL) using a neural network has shown remarkable potential for similar problems in which model‐based analytical approaches are difficult to apply . The method can learn a nonlinear mapping from an input space to an output space when enough dataset pairs are given.…”

A performance comparison of convolutional neural network‐based image denoising methods: The effect of loss functions on low‐dose CT images

“…Perceptual loss is calculated from the pixel‐level loss for feature maps, which contain hierarchical features of images, extracted by a pretrained CNN classifier . It greatly improves the perceptual quality of denoised images but often changes the brightness . Adversarial loss is formulated with Kullback–Leibler divergence, Jensen–Shannon divergence, or the Wasserstein distance as a measure of the distance between distributions of a denoised LDCT image and a NDCT image.…”

“…Therefore, adversarial loss prevents aggressive noise reduction and helps preserve the fine detail . However, it needs to be combined with pixel‐level loss or perceptual loss because using it alone might alter the image content due to its nature …”

“…In addition to the network designs and loss functions, reliable and objective image quality assessment is essential to derive a meaningful conclusion from a comparative study on different image denoising methods. The image quality metrics like the root‐mean‐squared error (RMSE) and the structural similarity index (SSIM) are widely used for the quantitative evaluation of LDCT denoising . However, regarding perceptual similarity, these simple metrics often do not match the qualitative evaluation .…”