fastMRI: An Open Dataset and Benchmarks for Accelerated MRI

Abstract

Accelerating Magnetic Resonance Imaging (MRI) by taking fewer measurements has the potential to reduce medical costs, minimize stress to patients and make MRI possible in applications where it is currently prohibitively slow or expensive. We introduce the fastMRI dataset, a large-scale collection of both raw MR measurements and clinical MR images, that can be used for training and evaluation of machine-learning approaches to MR image reconstruction. By introducing standardized evaluation criteria and a freely-accessible dataset, our goal is to help the community make rapid advances in the state of the art for MR image reconstruction. We also provide a self-contained introduction to MRI for machine learning researchers with no medical imaging background.

35 pages, 10 figures

References in corpus (6)

• Instance Normalization: The Missing Ingredient for Fast Stylization
• Image reconstruction by domain transform manifold learning
• Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge
• ADMM-Net: A Deep Learning Approach for Compressive Sensing MRI
• One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models
• InverseNet: Solving Inverse Problems with Splitting Networks

Cited by in corpus (113)

• Self-Supervised Learning of Physics-Guided Reconstruction Neural Networks without Fully-Sampled Reference Data
• Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction
• Plug and play methods for magnetic resonance imaging (long version)
• Solving Inverse Problems With Deep Neural Networks -- Robustness Included?
• Solving 3D Inverse Problems using Pre-trained 2D Diffusion Models
• The Modern Mathematics of Deep Learning
• MRI Super-Resolution with Ensemble Learning and Complementary Priors
• Reinventing 2D Convolutions for 3D Images
• J-MoDL: Joint Model-Based Deep Learning for Optimized Sampling and Reconstruction
• Dense Recurrent Neural Networks for Accelerated MRI: History-Cognizant Unrolling of Optimization Algorithms
• High-Frequency Space Diffusion Models for Accelerated MRI
• Deep Learning for Retrospective Motion Correction in MRI: A Comprehensive Review
• B-spline Parameterized Joint Optimization of Reconstruction and K-space Trajectories (BJORK) for Accelerated 2D MRI
• Artificial Intelligence in Glioma Imaging: Challenges and Advances
• Multi-Modal MRI Reconstruction Assisted with Spatial Alignment Network
• Measuring Robustness in Deep Learning Based Compressive Sensing
• PUERT: Probabilistic Under-sampling and Explicable Reconstruction Network for CS-MRI
• Dual-Domain Reconstruction Networks with V-Net and K-Net for fast MRI
• EvalAI: Towards Better Evaluation Systems for AI Agents
• pymia: A Python package for data handling and evaluation in deep learning-based medical image analysis
• Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization
• Deep Learning Methods for Parallel Magnetic Resonance Image Reconstruction
• Learning Sampling and Model-Based Signal Recovery for Compressed Sensing MRI
• Introduction to Latent Variable Energy-Based Models: A Path Towards Autonomous Machine Intelligence
• The risk of bias in denoising methods
• Spatially Regularized Parametric Map Reconstruction for Fast Magnetic Resonance Fingerprinting
• Complex Network for Complex Problems: A comparative study of CNN and Complex-valued CNN
• Stable Deep MRI Reconstruction using Generative Priors
• Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximation
• Joint Frequency and Image Space Learning for MRI Reconstruction and Analysis
• Geometric Approaches to Increase the Expressivity of Deep Neural Networks for MR Reconstruction
• ENSURE: A General Approach for Unsupervised Training of Deep Image Reconstruction Algorithms
• $\Sigma$-net: Systematic Evaluation of Iterative Deep Neural Networks for Fast Parallel MR Image Reconstruction
• Two-and-a-half Order Score-based Model for Solving 3D Ill-posed Inverse Problems
• Adaptive-CS-Net: FastMRI with Adaptive Intelligence
• Efficient approximation of Jacobian matrices involving a non-uniform fast Fourier transform (NUFFT)
• Optimal Transport driven CycleGAN for Unsupervised Learning in Inverse Problems
• Rethinking Re-Sampling in Imbalanced Semi-Supervised Learning
• Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networks
• Self-Supervised Learning for Medical Image Data with Anatomy-Oriented Imaging Planes
• Assessment of Data Consistency through Cascades of Independently Recurrent Inference Machines for fast and robust accelerated MRI reconstruction
• Exploring Separable Attention for Multi-Contrast MR Image Super-Resolution
• Single-pass Object-adaptive Data Undersampling and Reconstruction for MRI
• i-RIM applied to the fastMRI challenge
• Deep Learning for Biomedical Image Reconstruction: A Survey
• A deep cascade of ensemble of dual domain networks with gradient-based T1 assistance and perceptual refinement for fast MRI reconstruction
• Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Data
• 3D Brain and Heart Volume Generative Models: A Survey
• Fast MRI Reconstruction via Edge Attention
• Scan-specific Self-supervised Bayesian Deep Non-linear Inversion for Undersampled MRI Reconstruction
• A Complex Quasi-Newton Proximal Method for Image Reconstruction in Compressed Sensing MRI
• Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition
• Regularizing linear inverse problems with convolutional neural networks
• $\Sigma$-net: Ensembled Iterative Deep Neural Networks for Accelerated Parallel MR Image Reconstruction
• Organ-based Chronological Age Estimation based on 3D MRI Scans
• GRAPPA-GANs for Parallel MRI Reconstruction
• Learning Task-Specific Strategies for Accelerated MRI
• Compressed Sensing: From Research to Clinical Practice with Data-Driven Learning
• QSMGAN: Improved Quantitative Susceptibility Mapping using 3D Generative Adversarial Networks with Increased Receptive Field
• MRI Banding Removal via Adversarial Training
• Compressed Sensing MRI Reconstruction Regularized by VAEs with Structured Image Covariance
• Co-VeGAN: Complex-Valued Generative Adversarial Network for Compressive Sensing MR Image Reconstruction
• NPB-REC: A Non-parametric Bayesian Deep-learning Approach for Undersampled MRI Reconstruction with Uncertainty Estimation
• Accelerated Intravascular Ultrasound Imaging using Deep Reinforcement Learning
• A study on the adequacy of common IQA measures for medical images
• Experimental design for MRI by greedy policy search
• MRI Image Reconstruction via Learning Optimization Using Neural ODEs
• Complex-valued Federated Learning with Differential Privacy and MRI Applications
• Convex Regularization Behind Neural Reconstruction
• Deep MRI Reconstruction with Radial Subsampling
• Prior Image-Constrained Reconstruction using Style-Based Generative Models
• Multi-Contrast MRI Super-Resolution via a Multi-Stage Integration Network
• SHFormer: Dynamic Spectral Filtering Convolutional Neural Network and High-pass Kernel Generation Transformer for Adaptive MRI Reconstruction
• Contrastive Learning for Local and Global Learning MRI Reconstruction
• Back-Projection Diffusion: Solving the Wideband Inverse Scattering Problem with Diffusion Models
• Powers of layers for image-to-image translation
• Optimal MRI Undersampling Patterns for Ultimate Benefit of Medical Vision Tasks
• End-to-End AI-based MRI Reconstruction and Lesion Detection Pipeline for Evaluation of Deep Learning Image Reconstruction
• Conditional Normalizing Flows for Low-Dose Computed Tomography Image Reconstruction
• Optimizing full 3D SPARKLING trajectories for high-resolution T2*-weighted Magnetic Resonance Imaging
• JotlasNet: Joint Tensor Low-Rank and Attention-based Sparse Unrolling Network for Accelerating Dynamic MRI
• Explicit Abnormality Extraction for Unsupervised Motion Artifact Reduction in Magnetic Resonance Imaging
• Transformer Compressed Sensing via Global Image Tokens
• Deep learning for fast MR imaging: a review for learning reconstruction from incomplete k-space data
• Robust Equivariant Imaging: a fully unsupervised framework for learning to image from noisy and partial measurements
• Adaptive convolutional neural networks for k-space data interpolation in fast magnetic resonance imaging
• Bayesian Optimization of Sampling Densities in MRI
• Deep Image prior with StruCtUred Sparsity (DISCUS) for dynamic MRI reconstruction
• A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems
• IFR-Net: Iterative Feature Refinement Network for Compressed Sensing MRI
• Towards Ultrafast MRI via Extreme k-Space Undersampling and Superresolution
• Deep Network Interpolation for Accelerated Parallel MR Image Reconstruction
• Adaptive Local Neighborhood-based Neural Networks for MR Image Reconstruction from Undersampled Data
• A Few-Shot Learning Approach for Accelerated MRI via Fusion of Data-Driven and Subject-Driven Priors
• Dual Averaging is Surprisingly Effective for Deep Learning Optimization
• Universal Undersampled MRI Reconstruction
• Learned SIRT for Cone Beam Computed Tomography Reconstruction
• Improved low-count quantitative PET reconstruction with an iterative neural network
• Progressively-Growing AmbientGANs For Learning Stochastic Object Models From Imaging Measurements
• Simultaneous Image Quality Improvement and Artefacts Correction in Accelerated MRI
• DONet: Dual-Octave Network for Fast MR Image Reconstruction
• Parallel-beam X-ray CT datasets of apples with internal defects and label balancing for machine learning
• Boosting the Performance of Plug-and-Play Priors via Denoiser Scaling
• Is good old GRAPPA dead?
• Equivariant plug-and-play image reconstruction
• Compressed Sensing via Measurement-Conditional Generative Models
• Patient-Adaptive and Learned MRI Data Undersampling Using Neighborhood Clustering
• Learning to Predict Error for MRI Reconstruction
• Calibrationless MRI Reconstruction with a Plug-in Denoiser
• Fine-grained MRI Reconstruction using Attentive Selection Generative Adversarial Networks
• Model-Aware Regularization For Learning Approaches To Inverse Problems
• Unpaired Deep Learning for Accelerated MRI using Optimal Transport Driven CycleGAN
• Enhanced Magnetic Resonance Image Synthesis with Contrast-Aware Generative Adversarial Networks