Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss

Abstract

Compressed Sensing MRI (CS-MRI) has provided theoretical foundations upon which the time-consuming MRI acquisition process can be accelerated. However, it primarily relies on iterative numerical solvers which still hinders their adaptation in time-critical applications. In addition, recent advances in deep neural networks have shown their potential in computer vision and image processing, but their adaptation to MRI reconstruction is still in an early stage. In this paper, we propose a novel deep learning-based generative adversarial model, RefineGAN, for fast and accurate CS-MRI reconstruction. The proposed model is a variant of fully-residual convolutional autoencoder and generative adversarial networks (GANs), specifically designed for CS-MRI formulation; it employs deeper generator and discriminator networks with cyclic data consistency loss for faithful interpolation in the given under-sampled k-space data. In addition, our solution leverages a chained network to further enhance the reconstruction quality. RefineGAN is fast and accurate -- the reconstruction process is extremely rapid, as low as tens of milliseconds for reconstruction of a 256x256 image, because it is one-way deployment on a feed-forward network, and the image quality is superior even for extremely low sampling rate (as low as 10%) due to the data-driven nature of the method. We demonstrate that RefineGAN outperforms the state-of-the-art CS-MRI methods by a large margin in terms of both running time and image quality via evaluation using several open-source MRI databases.

submitted to IEEE Transactions on Medical Imaging

References in corpus (1)

• Deep Generative Adversarial Networks for Compressed Sensing Automates MRI

Cited by in corpus (95)

• Generative Adversarial Network in Medical Imaging: A Review
• Self-Supervised Learning of Physics-Guided Reconstruction Neural Networks without Fully-Sampled Reference Data
• Distribution Matching Losses Can Hallucinate Features in Medical Image Translation
• Image Reconstruction: From Sparsity to Data-adaptive Methods and Machine Learning
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• Adaptive Diffusion Priors for Accelerated MRI Reconstruction
• Improving GANs for Speech Enhancement
• Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN
• A Deep Information Sharing Network for Multi-contrast Compressed Sensing MRI Reconstruction
• A Deep Learning Framework for Single-Sided Sound Speed Inversion in Medical Ultrasound
• Unsupervised Medical Image Translation Using Cycle-MedGAN
• J-MoDL: Joint Model-Based Deep Learning for Optimized Sampling and Reconstruction
• PhaseGAN: A deep-learning phase-retrieval approach for unpaired datasets
• 2022 Review of Data-Driven Plasma Science
• Deep variational network for rapid 4D flow MRI reconstruction
• MoCoNet: Motion Correction in 3D MPRAGE images using a Convolutional Neural Network approach
• Wasserstein GANs for MR Imaging: from Paired to Unpaired Training
• PUERT: Probabilistic Under-sampling and Explicable Reconstruction Network for CS-MRI
• Deep Efficient End-to-end Reconstruction (DEER) Network for Few-view Breast CT Image Reconstruction
• Biomedical Image Reconstruction: From the Foundations to Deep Neural Networks
• Deep MRI Reconstruction: Unrolled Optimization Algorithms Meet Neural Networks
• Deep Learning Methods for Parallel Magnetic Resonance Image Reconstruction
• Deep Learning for Neuroimaging-based Diagnosis and Rehabilitation of Autism Spectrum Disorder: A Review
• Ghost imaging based on Y-net: a dynamic coding and conjugate-decoding approach
• An Unsupervised Deep Learning Method for Multi-coil Cine MRI
• Highly Scalable Image Reconstruction using Deep Neural Networks with Bandpass Filtering
• Neural Architecture Search for Compressed Sensing Magnetic Resonance Image Reconstruction
• Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space with Softplus Loss
• Joint Frequency and Image Space Learning for MRI Reconstruction and Analysis
• Generative adversarial networks and adversarial methods in biomedical image analysis
• Geometric Approaches to Increase the Expressivity of Deep Neural Networks for MR Reconstruction
• Training End-to-End Unrolled Iterative Neural Networks for SPECT Image Reconstruction
• $\Sigma$-net: Systematic Evaluation of Iterative Deep Neural Networks for Fast Parallel MR Image Reconstruction
• Inflating 2D Convolution Weights for Efficient Generation of 3D Medical Images
• An Interpretable MRI Reconstruction Network with Two-grid-cycle Correction and Geometric Prior Distillation
• A Single Video Super-Resolution GAN for Multiple Downsampling Operators based on Pseudo-Inverse Image Formation Models
• DeepcomplexMRI: Exploiting deep residual network for fast parallel MR imaging with complex convolution
• k-Space Deep Learning for Accelerated MRI
• Momentum-Net: Fast and convergent iterative neural network for inverse problems
• DuDoRNet: Learning a Dual-Domain Recurrent Network for Fast MRI Reconstruction with Deep T1 Prior
• Assessment of Data Consistency through Cascades of Independently Recurrent Inference Machines for fast and robust accelerated MRI reconstruction
• Medical Imaging Synthesis using Deep Learning and its Clinical Applications: A Review
• A deep cascade of ensemble of dual domain networks with gradient-based T1 assistance and perceptual refinement for fast MRI reconstruction
• Medical Image Generation using Generative Adversarial Networks
• AutoSamp: Autoencoding k-space Sampling via Variational Information Maximization for 3D MRI
• Dual Network Architecture for Few-view CT -- Trained on ImageNet Data and Transferred for Medical Imaging
• Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition
• Learning Task-Specific Strategies for Accelerated MRI
• A Tutorial on MRI Reconstruction: From Modern Methods to Clinical Implications
• Deep Learning Techniques for Inverse Problems in Imaging
• DIMENSION: Dynamic MR Imaging with Both K-space and Spatial Prior Knowledge Obtained via Multi-Supervised Network Training
• A Multi-attribute Controllable Generative Model for Histopathology Image Synthesis
• Compressed Sensing MRI Reconstruction Regularized by VAEs with Structured Image Covariance
• NPB-REC: A Non-parametric Bayesian Deep-learning Approach for Undersampled MRI Reconstruction with Uncertainty Estimation
• Co-VeGAN: Complex-Valued Generative Adversarial Network for Compressive Sensing MR Image Reconstruction
• Model-based Deep Medical Imaging: the roadmap of generalizing iterative reconstruction model using deep learning
• SANTIS: Sampling-Augmented Neural neTwork with Incoherent Structure for MR image reconstruction
• MRI Reconstruction with Regularized 3D Diffusion Model (R3DM)
• Towards multi-sequence MR image recovery from undersampled k-space data
• Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectives
• Model Learning: Primal Dual Networks for Fast MR imaging
• Artificial Intelligence-Based Image Reconstruction in Cardiac Magnetic Resonance
• AliasNet: Alias Artefact Suppression Network for Accelerated Phase-Encode MRI
• LANTERN: learn analysis transform network for dynamic magnetic resonance imaging with small dataset
• Transfer Learning Enhanced Generative Adversarial Networks for Multi-Channel MRI Reconstruction
• Deep learning for fast MR imaging: a review for learning reconstruction from incomplete k-space data
• Fast MRI Reconstruction Using Deep Learning-based Compressed Sensing: A Systematic Review
• Learning Apparent Diffusion Coefficient Maps from Accelerated Radial k-Space Diffusion-Weighted MRI in Mice using a Deep CNN-Transformer Model
• Adaptive convolutional neural networks for k-space data interpolation in fast magnetic resonance imaging
• Advancing MRI Reconstruction: A Systematic Review of Deep Learning and Compressed Sensing Integration
• Deep Decomposition Learning for Inverse Imaging Problems
• Homotopic Gradients of Generative Density Priors for MR Image Reconstruction
• Efficient Structurally-Strengthened Generative Adversarial Network for MRI Reconstruction
• CRDN: Cascaded Residual Dense Networks for Dynamic MR Imaging with Edge-enhanced Loss Constraint
• Converged Deep Framework Assembling Principled Modules for CS-MRI
• Deep Parallel MRI Reconstruction Network Without Coil Sensitivities
• Deep Attentive Wasserstein Generative Adversarial Networks for MRI Reconstruction with Recurrent Context-Awareness
• DONet: Dual-Octave Network for Fast MR Image Reconstruction
• Model Adaptation for Image Reconstruction using Generalized Stein's Unbiased Risk Estimator
• Accelerating MR Imaging via Deep Chambolle-Pock Network
• MANTIS: Model-Augmented Neural neTwork with Incoherent k-space Sampling for efficient MR T2 mapping
• MED-TEX: Transferring and Explaining Knowledge with Less Data from Pretrained Medical Imaging Models
• An Adversarial Learning Based Approach for Unknown View Tomographic Reconstruction
• Generative Model Adversarial Training for Deep Compressed Sensing
• Structurally Adaptive Multi-Derivative Regularization for Image Recovery from Sparse Fourier Samples
• High-Resolution Pelvic MRI Reconstruction Using a Generative Adversarial Network with Attention and Cyclic Loss
• FA-GAN: Fused Attentive Generative Adversarial Networks for MRI Image Super-Resolution
• Selective Sampling and Mixture Models in Generative Adversarial Networks
• Reconstructing unseen modalities and pathology with an efficient Recurrent Inference Machine
• UVTomo-GAN: An adversarial learning based approach for unknown view X-ray tomographic reconstruction
• Fine-grained MRI Reconstruction using Attentive Selection Generative Adversarial Networks
• Unpaired Deep Learning for Accelerated MRI using Optimal Transport Driven CycleGAN
• Compressed Sensing with Probability-based Prior Information
• SEGAN: Structure-Enhanced Generative Adversarial Network for Compressed Sensing MRI Reconstruction
• MD-Recon-Net: A Parallel Dual-Domain Convolutional Neural Network for Compressed Sensing MRI