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

By Qingsong Yang, Pingkun Yan, Yanbo Zhang, Hengyong Yu, Yongyi Shi, Xuanqin Mou, Mannudeep K. Kalra, Yi Zhang, Ling Sun, Ge Wang. IEEE Transactions on Medical Imaging, 2017

1,435 citations recorded by the source corpus.

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.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/125246099c1a21469af6735480bae2c426c31cd5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Low-dose CT image and projection dataset (2020, background): “A generative adversarial network (GAN) for low-dose CT denoising.(28,29) 4.”
Preparing Medical Imaging Data for Machine Learning (2020, background): “Workflow improvements include prioritizing worklists for radiologists (2,3), triaging screening mammograms (4), reducing or eliminating gadolinium-based contrast media for MRI (5,6), and reducing the radiation dose of CT imaging by advancing image noise reduction (7–9).”
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications (2020, background): “cal fields such as for generating and designing DNA [296], [297], drug discovery [298], generating multi-label discrete patient records [299], medical image processing [300], [301], [302], [303], [304], [305], [306], [307], and doctor recommen-”
Generative Adversarial Network in Medical Imaging: A Review (2018, methodology): “Traditionally, conditional random ﬁeld (CRF) and graph cut methods are usually adopted for segmentation reﬁnement by incorporating spatial correlation.”
Unsupervised Medical Image Translation With Adversarial Diffusion Models (2022, background): “The fast conditional diffusion process in SynDiff might also offer performance benefits over GANs in other applications such as denoising and super-resolution [49], [83], [84].”
Sharpness-Aware Low-Dose CT Denoising Using Conditional Generative Adversarial Network (2017, methodology): “[68] also employed GAN for CT denoising and some technical differences from ours have been highlighted in “Related Works”.”
A review of multimodal image matching: Methods and applications (2021, methodology): “uch as FlowNet [100], DVFNet [102], and U-Net [103,104].”
The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches (2018, methodology): “GANs for Medical Imagining and medical information processing [102], GANs for medical image de-noising with Wasserstein distance and perceptual loss [215].”
CT Super-Resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble (GAN-CIRCLE) (2018, background): “However, it has been pointed out in [81], [82] that high PSNR and SSIM values cannot guarantee a visually favorable result.”
Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstruction (2018, methodology): “To address this challenge, various noise reduction algorithms were proposed for LDCT, which can be categorized into the following categories: 1) sinogram filtration [8, 9, 10], 2) iterative reconstruction [11, 12, 13], and 3) image post-processing [14, 15, 16, 17].”
MedGAN: Medical Image Translation using GANs (2018, methodology): “Additionally, [49] utilized a pretrained network for the calculation of feature matching losses together with the Wasserstein distance loss.”
FISTA-Net: Learning a Fast Iterative Shrinkage Thresholding Network for Inverse Problems in Imaging (2020, background): “the ‘cosmetic improvements’ might result in over-smoothing and loss of critical structural details in certain cases [25].”
3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network (2018, neutral): “Different objective functions include the mean squared error (MSE) [5]–[8], the adversarial loss [7], [9], and the perceptual loss [9].”