Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge

Abstract

Purpose: To advance research in the field of machine learning for MR image reconstruction with an open challenge. Methods: We provided participants with a dataset of raw k-space data from 1,594 consecutive clinical exams of the knee. The goal of the challenge was to reconstruct images from these data. In order to strike a balance between realistic data and a shallow learning curve for those not already familiar with MR image reconstruction, we ran multiple tracks for multi-coil and single-coil data. We performed a two-stage evaluation based on quantitative image metrics followed by evaluation by a panel of radiologists. The challenge ran from June to December of 2019. Results: We received a total of 33 challenge submissions. All participants chose to submit results from supervised machine learning approaches. Conclusion: The challenge led to new developments in machine learning for image reconstruction, provided insight into the current state of the art in the field, and highlighted remaining hurdles for clinical adoption.

References in corpus (12)

• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)
• Image reconstruction by domain transform manifold learning
• MoDL: Model Based Deep Learning Architecture for Inverse Problems
• On instabilities of deep learning in image reconstruction - Does AI come at a cost?
• Learned Primal-dual Reconstruction
• A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction
• Deep BCD-Net Using Identical Encoding-Decoding CNN Structures for Iterative Image Recovery
• ADMM-Net: A Deep Learning Approach for Compressive Sensing MRI
• Convolutional Recurrent Neural Networks for Dynamic MR Image Reconstruction
• i-RIM applied to the fastMRI challenge
• LEARN: Learned Experts' Assessment-based Reconstruction Network for Sparse-data CT

Cited by in corpus (30)

• Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction
• Solving Inverse Problems With Deep Neural Networks -- Robustness Included?
• Can stable and accurate neural networks be computed? -- On the barriers of deep learning and Smale's 18th problem
• Multi-Modal MRI Reconstruction Assisted with Spatial Alignment Network
• Measuring Robustness in Deep Learning Based Compressive Sensing
• Multi-Mask Self-Supervised Learning for Physics-Guided Neural Networks in Highly Accelerated MRI
• A multispeaker dataset of raw and reconstructed speech production real-time MRI video and 3D volumetric images
• Zero-Shot Self-Supervised Learning for MRI Reconstruction
• A study of why we need to reassess full reference image quality assessment with medical images
• Deep, Deep Learning with BART
• Assessment of Data Consistency through Cascades of Independently Recurrent Inference Machines for fast and robust accelerated MRI reconstruction
• HyperSLICE: HyperBand optimized Spiral for Low-latency Interactive Cardiac Examination
• A Densely Interconnected Network for Deep Learning Accelerated MRI
• A Tutorial on MRI Reconstruction: From Modern Methods to Clinical Implications
• MRI Banding Removal via Adversarial Training
• Agreement of Image Quality Metrics with Radiological Evaluation in the Presence of Motion Artifacts
• FReSCO: Flow Reconstruction and Segmentation for low latency Cardiac Output monitoring using deep artifact suppression and segmentation
• High-Fidelity Accelerated MRI Reconstruction by Scan-Specific Fine-Tuning of Physics-Based Neural Networks
• Experimental design for MRI by greedy policy search
• Optimal MRI Undersampling Patterns for Ultimate Benefit of Medical Vision Tasks
• On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations
• NoSENSE: Learned unrolled cardiac MRI reconstruction without explicit sensitivity maps
• JotlasNet: Joint Tensor Low-Rank and Attention-based Sparse Unrolling Network for Accelerating Dynamic MRI
• End-to-End AI-based MRI Reconstruction and Lesion Detection Pipeline for Evaluation of Deep Learning Image Reconstruction
• Gradient-Based Learning of Discrete Structured Measurement Operators for Signal Recovery
• Bayesian Optimization of Sampling Densities in MRI
• Towards Ultrafast MRI via Extreme k-Space Undersampling and Superresolution
• Estimating MRI Image Quality via Image Reconstruction Uncertainty
• Universal Undersampled MRI Reconstruction
• AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry