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

Abstract

In this paper, we introduce 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 transform theory, and promises to improve the performance of the GAN. The perceptual loss compares the perceptual features of a denoised output against those of the ground truth in an established feature space, while the GAN helps migrate the data noise distribution from strong to weak. Therefore, our proposed method transfers our knowledge of visual perception to the image denoising task, is capable of not only reducing the image noise level but also keeping the critical information at the same time. Promising results have been obtained in our experiments with clinical CT images.

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)
• Improved Training of Wasserstein GANs
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Perceptual Losses for Real-Time Style Transfer and Super-Resolution
• A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction
• Wasserstein GAN
• GPU-based Low Dose CT Reconstruction via Edge-preserving Total Variation Regularization
• Neural Photo Editing with Introspective Adversarial Networks
• A Taxonomy of Deep Convolutional Neural Nets for Computer Vision
• Image Super-Resolution Using Deep Convolutional Networks
• Medical Image Synthesis with Context-Aware Generative Adversarial Networks
• Low-dose CT denoising with convolutional neural network

Cited by in corpus (150)

• Generative Adversarial Network in Medical Imaging: A Review
• Artificial Intelligence in the Creative Industries: A Review
• Deep Learning in Medical Image Registration: A Survey
• CT Super-resolution GAN Constrained by the Identical, Residual, and Cycle Learning Ensemble(GAN-CIRCLE)
• Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?
• Sharpness-aware Low dose CT denoising using conditional generative adversarial network
• FISTA-Net: Learning A Fast Iterative Shrinkage Thresholding Network for Inverse Problems in Imaging
• Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning
• Structure-sensitive Multi-scale Deep Neural Network for Low-Dose CT Denoising
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Neural Image Compression for Gigapixel Histopathology Image Analysis
• CTformer: Convolution-free Token2Token Dilated Vision Transformer for Low-dose CT Denoising
• Cycle Consistent Adversarial Denoising Network for Multiphase Coronary CT Angiography
• A Review on Deep Learning in Medical Image Reconstruction
• Boundary-weighted Domain Adaptive Neural Network for Prostate MR Image Segmentation
• Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methods
• CoreDiff: Contextual Error-Modulated Generalized Diffusion Model for Low-Dose CT Denoising and Generalization
• TomoGAN: Low-Dose Synchrotron X-Ray Tomography with Generative Adversarial Networks
• Solving Inverse Problems With Deep Neural Networks -- Robustness Included?
• EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising
• MRI Super-Resolution with Ensemble Learning and Complementary Priors
• Recent Progress in Transformer-based Medical Image Analysis
• A Deep Learning Framework for Single-Sided Sound Speed Inversion in Medical Ultrasound
• The LoDoPaB-CT Dataset: A Benchmark Dataset for Low-Dose CT Reconstruction Methods
• Dense Recurrent Neural Networks for Accelerated MRI: History-Cognizant Unrolling of Optimization Algorithms
• Zero-shot Medical Image Translation via Frequency-Guided Diffusion Models
• Noise Conscious Training of Non Local Neural Network powered by Self Attentive Spectral Normalized Markovian Patch GAN for Low Dose CT Denoising
• Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
• Unpaired image denoising using a generative adversarial network in X-ray CT
• Computationally Efficient Deep Neural Network for Computed Tomography Image Reconstruction
• Visual Attention Network for Low Dose CT
• Improved Multiple-Image-Based Reflection Removal Algorithm Using Deep Neural Networks
• LIT-Former: Linking In-plane and Through-plane Transformers for Simultaneous CT Image Denoising and Deblurring
• Low-Dose CT with Deep Learning Regularization via Proximal Forward Backward Splitting
• Three-dimensional Generative Adversarial Nets for Unsupervised Metal Artifact Reduction
• WNet: A data-driven dual-domain denoising model for sparse-view computed tomography with a trainable reconstruction layer
• Deep Efficient End-to-end Reconstruction (DEER) Network for Few-view Breast CT Image Reconstruction
• Which Pixel to Annotate: a Label-Efficient Nuclei Segmentation Framework
• Physics-/Model-Based and Data-Driven Methods for Low-Dose Computed Tomography: A survey
• 3D Segmentation Guided Style-based Generative Adversarial Networks for PET Synthesis
• MelanoGANs: High Resolution Skin Lesion Synthesis with GANs
• Biomedical Image Reconstruction: From the Foundations to Deep Neural Networks
• Improving Electron Micrograph Signal-to-Noise with an Atrous Convolutional Encoder-Decoder
• Neural Networks-based Regularization for Large-Scale Medical Image Reconstruction
• Hypernetwork-based Personalized Federated Learning for Multi-Institutional CT Imaging
• Natural Image Noise Dataset
• MANAS: Multi-Scale and Multi-Level Neural Architecture Search for Low-Dose CT Denoising
• Probabilistic self-learning framework for Low-dose CT Denoising
• DUG-RECON: A Framework for Direct Image Reconstruction using Convolutional Generative Networks
• Benchmarking Deep Learning-Based Low-Dose CT Image Denoising Algorithms
• Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CT
• Adversarial Sparse-View CBCT Artifact Reduction
• IQAGPT: Image Quality Assessment with Vision-language and ChatGPT Models
• Systematic Review on Learning-based Spectral CT
• Ultra Low-Parameter Denoising: Trainable Bilateral Filter Layers in Computed Tomography
• Noise2Context: Context-assisted Learning 3D Thin-layer Low Dose CT Without Clean Data
• Improved Trainable Calibration Method for Neural Networks on Medical Imaging Classification
• Sketch-Guided Scenery Image Outpainting
• An Unsupervised Reconstruction Method For Low-Dose CT Using Deep Generative Regularization Prior
• ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising
• CT-Mamba: A Hybrid Convolutional State Space Model for Low-Dose CT Denoising
• Deep neural networks-based denoising models for CT imaging and their efficacy
• Generative Models Improve Radiomics Reproducibility in Low Dose CTs: A Simulation Study
• DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising
• DuDoTrans: Dual-Domain Transformer Provides More Attention for Sinogram Restoration in Sparse-View CT Reconstruction
• Generative adversarial networks and adversarial methods in biomedical image analysis
• Physical Accuracy of Deep Neural Networks for 2D and 3D Multi-Mineral Segmentation of Rock micro-CT Images
• JBFnet -- Low Dose CT Denoising by Trainable Joint Bilateral Filtering
• Inflating 2D Convolution Weights for Efficient Generation of 3D Medical Images
• Limited Parameter Denoising for Low-dose X-ray Computed Tomography Using Deep Reinforcement Learning
• Physics-assisted Generative Adversarial Network for X-Ray Tomography
• Bayesian Inference with Generative Adversarial Network Priors
• Medical Imaging Synthesis using Deep Learning and its Clinical Applications: A Review
• ML-LBM: Machine Learning Aided Flow Simulation in Porous Media
• Using Uncertainty in Deep Learning Reconstruction for Cone-Beam CT of the Brain
• A game-theoretic approach for Generative Adversarial Networks
• Impact of loss functions on the performance of a deep neural network designed to restore low-dose digital mammography
• Dual Network Architecture for Few-view CT -- Trained on ImageNet Data and Transferred for Medical Imaging
• X-ray Photon-Counting Data Correction through Deep Learning
• Low-Dose CT Image Denoising Using Parallel-Clone Networks
• Super-resolution MRI through Deep Learning
• Eformer: Edge Enhancement based Transformer for Medical Image Denoising
• Contextual colorization and denoising for low-light ultra high resolution sequences
• Total-Body Low-Dose CT Image Denoising using Prior Knowledge Transfer Technique with Contrastive Regularization Mechanism
• Two Birds with One Stone: Transforming and Generating Facial Images with Iterative GAN
• Overview of image-to-image translation by use of deep neural networks: denoising, super-resolution, modality conversion, and reconstruction in medical imaging
• Generative Adversarial U-Net for Domain-free Medical Image Augmentation
• LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT
• Low-Dose CT via Deep CNN with Skip Connection and Network in Network
• Deep Learning Based Computed Tomography Whys and Wherefores
• An unsupervised deep learning framework for medical image denoising
• A Dataset-free Deep learning Method for Low-Dose CT Image Reconstruction
• AdaIN-Switchable CycleGAN for Efficient Unsupervised Low-Dose CT Denoising
• DiffusionCT: Latent Diffusion Model for CT Image Standardization
• Data Consistent Artifact Reduction for Limited Angle Tomography with Deep Learning Prior
• MRI to PET Cross-Modality Translation using Globally and Locally Aware GAN (GLA-GAN) for Multi-Modal Diagnosis of Alzheimer's Disease
• Limited View Tomographic Reconstruction Using a Deep Recurrent Framework with Residual Dense Spatial-Channel Attention Network and Sinogram Consistency
• Deep learning in bioinformatics: introduction, application, and perspective in big data era
• Unsupervised Enhancement of Real-World Depth Images Using Tri-Cycle GAN
• Dual-energy CT imaging from single-energy CT data with material decomposition convolutional neural network
• Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network
• Learning to Scan: A Deep Reinforcement Learning Approach for Personalized Scanning in CT Imaging
• Self-supervised Dynamic CT Perfusion Image Denoising with Deep Neural Networks
• Deep Learning Assisted Denoising of Experimental Micrographs
• Using a Generative Adversarial Network for CT Normalization and its Impact on Radiomic Features
• STAN-CT: Standardizing CT Image using Generative Adversarial Network
• Cross-domain Denoising for Low-dose Multi-frame Spiral Computed Tomography
• Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent
• Data Consistent CT Reconstruction from Insufficient Data with Learned Prior Images
• CT Reconstruction with PDF: Parameter-Dependent Framework for Multiple Scanning Geometries and Dose Levels
• Deep-learning-based Breast CT for Radiation Dose Reduction
• MetaInv-Net: Meta Inversion Network for Sparse View CT Image Reconstruction
• Equivariant Imaging: Learning Beyond the Range Space
• Deep High-Resolution Network for Low Dose X-ray CT Denoising
• Denoising of 3-D Magnetic Resonance Images Using a Residual Encoder-Decoder Wasserstein Generative Adversarial Network
• SHEAR-net: An End-to-End Deep Learning Approach for Single Push Ultrasound Shear Wave Elasticity Imaging
• A Deep learning Approach to Generate Contrast-Enhanced Computerised Tomography Angiography without the Use of Intravenous Contrast Agents
• Task-Oriented Low-Dose CT Image Denoising
• TED-net: Convolution-free T2T Vision Transformer-based Encoder-decoder Dilation network for Low-dose CT Denoising
• Learning image from projection: a full-automatic reconstruction (FAR) net for sparse-views computed tomography
• Quadratic Autoencoder (Q-AE) for Low-dose CT Denoising
• Noise2Inpaint: Learning Referenceless Denoising by Inpainting Unrolling
• Machine learning and serving of discrete field theories -- when artificial intelligence meets the discrete universe
• A robust multi-domain network for short-scanning amyloid PET reconstruction
• Multi-Scale Texture Loss for CT denoising with GANs
• Three-dimensional visualization of X-ray micro-CT with large-scale datasets: Efficiency and accuracy for real-time interaction
• Sensorless Freehand 3D Ultrasound Reconstruction via Deep Contextual Learning
• Improving Generalizability in Limited-Angle CT Reconstruction with Sinogram Extrapolation
• Provably Convergent Learned Inexact Descent Algorithm for Low-Dose CT Reconstruction
• Improved Material Decomposition with a Two-step Regularization for spectral CT
• A Model-based Deep Learning Reconstruction for X-ray CT
• Field of View Extension in Computed Tomography Using Deep Learning Prior
• Unsupervised Despeckling
• A hierarchical approach to deep learning and its application to tomographic reconstruction
• A Green Learning Approach to LDCT Image Restoration
• Stabilizing Deep Tomographic Reconstruction
• "One-Shot" Reduction of Additive Artifacts in Medical Images
• UVTomo-GAN: An adversarial learning based approach for unknown view X-ray tomographic reconstruction
• An Adversarial Learning Based Approach for Unknown View Tomographic Reconstruction
• Multi-Cycle-Consistent Adversarial Networks for CT Image Denoising
• Assessing the Impact of Deep Neural Network-based Image Denoising on Binary Signal Detection Tasks
• TextureWGAN: Texture Preserving WGAN with MLE Regularizer for Inverse Problems
• Comparative Evaluation of 3D and 2D Deep Learning Techniques for Semantic Segmentation in CT Scans
• Pathology-Aware Generative Adversarial Networks for Medical Image Augmentation
• W-Cell-Net: Multi-frame Interpolation of Cellular Microscopy Videos
• A Deep Optimization Approach for Image Deconvolution
• Low Dose Helical CBCT denoising by using domain filtering with deep reinforcement learning
• AHP-Net: adaptive-hyper-parameter deep learning based image reconstruction method for multilevel low-dose CT
• Deep Interactive Denoiser (DID) for X-Ray Computed Tomography
• Analysis of Macula on Color Fundus Images Using Heightmap Reconstruction Through Deep Learning