Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction

Abstract

Accelerating MRI scans is one of the principal outstanding problems in the MRI research community. Towards this goal, we hosted the second fastMRI competition targeted towards reconstructing MR images with subsampled k-space data. We provided participants with data from 7,299 clinical brain scans (de-identified via a HIPAA-compliant procedure by NYU Langone Health), holding back the fully-sampled data from 894 of these scans for challenge evaluation purposes. In contrast to the 2019 challenge, we focused our radiologist evaluations on pathological assessment in brain images. We also debuted a new Transfer track that required participants to submit models evaluated on MRI scanners from outside the training set. We received 19 submissions from eight different groups. Results showed one team scoring best in both SSIM scores and qualitative radiologist evaluations. We also performed analysis on alternative metrics to mitigate the effects of background noise and collected feedback from the participants to inform future challenges. Lastly, we identify common failure modes across the submissions, highlighting areas of need for future research in the MRI reconstruction community.

M. J. Muckley and B. Riemenschneider contributed equally to this work. This updates to version accepted in IEEE Transactions on Medical Imaging. It includes a rewrite of Section II.E as well as minor changes and corrections

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• scikit-image: Image processing in Python
• cuDNN: Efficient Primitives for Deep Learning
• Recurrent Inference Machines for Solving Inverse Problems
• CG-SENSE revisited: Results from the first ISMRM reproducibility challenge
• XPDNet for MRI Reconstruction: an application to the 2020 fastMRI challenge
• $\Sigma$-net: Systematic Evaluation of Iterative Deep Neural Networks for Fast Parallel MR Image Reconstruction
• i-RIM applied to the fastMRI challenge
• Multi-Coil MRI Reconstruction Challenge -- Assessing Brain MRI Reconstruction Models and their Generalizability to Varying Coil Configurations

Cited by in corpus (34)

• Can stable and accurate neural networks be computed? -- On the barriers of deep learning and Smale's 18th problem
• Bayesian MRI Reconstruction with Joint Uncertainty Estimation using Diffusion Models
• Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement
• B-spline Parameterized Joint Optimization of Reconstruction and K-space Trajectories (BJORK) for Accelerated 2D MRI
• Multi-Modal MRI Reconstruction Assisted with Spatial Alignment Network
• Measuring Robustness in Deep Learning Based Compressive Sensing
• Image reconstruction algorithms in radio interferometry: from handcrafted to learned regularization denoisers
• Robust Compressed Sensing MRI with Deep Generative Priors
• A multispeaker dataset of raw and reconstructed speech production real-time MRI video and 3D volumetric images
• Connections between Deep Equilibrium and Sparse Representation Models with Application to Hyperspectral Image Denoising
• A study of why we need to reassess full reference image quality assessment with medical images
• Physics-informed compressed sensing for PC-MRI: an inverse Navier-Stokes problem
• Assessment of Data Consistency through Cascades of Independently Recurrent Inference Machines for fast and robust accelerated MRI reconstruction
• T2LR-Net: An unrolling network learning transformed tensor low-rank prior for dynamic MR image reconstruction
• Self-Supervised Learning for Improved Calibrationless Radial MRI with NLINV-Net
• A Densely Interconnected Network for Deep Learning Accelerated MRI
• NESTANets: Stable, accurate and efficient neural networks for analysis-sparse inverse problems
• Bayesian inverse Navier-Stokes problems: joint flow field reconstruction and parameter learning
• End-to-end Memory-Efficient Reconstruction for Cone Beam CT
• A Flow-based Truncated Denoising Diffusion Model for Super-resolution Magnetic Resonance Spectroscopic Imaging
• Agreement of Image Quality Metrics with Radiological Evaluation in the Presence of Motion Artifacts
• MRI Reconstruction with Regularized 3D Diffusion Model (R3DM)
• Validation and Generalizability of Self-Supervised Image Reconstruction Methods for Undersampled MRI
• Complex-valued Federated Learning with Differential Privacy and MRI Applications
• Deep network series for large-scale high-dynamic range imaging
• Optimal MRI Undersampling Patterns for Ultimate Benefit of Medical Vision Tasks
• NoSENSE: Learned unrolled cardiac MRI reconstruction without explicit sensitivity maps
• End-to-End AI-based MRI Reconstruction and Lesion Detection Pipeline for Evaluation of Deep Learning Image Reconstruction
• JotlasNet: Joint Tensor Low-Rank and Attention-based Sparse Unrolling Network for Accelerating Dynamic MRI
• DeDA: Deep Directed Accumulator
• UNISELF: A Unified Network with Instance Normalization and Self-Ensembled Lesion Fusion for Multiple Sclerosis Lesion Segmentation
• Bayesian Optimization of Sampling Densities in MRI
• Simultaneous Image Quality Improvement and Artefacts Correction in Accelerated MRI
• AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry