• Corpus ID: 53759905

fastMRI: An Open Dataset and Benchmarks for Accelerated MRI

  title={fastMRI: An Open Dataset and Benchmarks for Accelerated MRI},
  author={Jure Zbontar and Florian Knoll and Anuroop Sriram and Matthew Muckley and Mary Bruno and Aaron Defazio and Marc Parente and Krzysztof J. Geras and Joe Katsnelson and Hersh Chandarana and Zizhao Zhang and Michal Drozdzal and Adriana Romero and Michael G. Rabbat and Pascal Vincent and James Pinkerton and Duo Wang and Nafissa Yakubova and Erich Owens and C. Lawrence Zitnick and Michael P. Recht and Daniel K. Sodickson and Yvonne W. Lui},
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… 

Improving the Speed of MRI with Artificial Intelligence

Preliminary studies show the promise of the variational network, a state-of-the-art technique, to generalize to many different anatomical regions and achieve comparable diagnostic accuracy as conventional methods.

Benchmarking MRI Reconstruction Neural Networks on Large Public Datasets

The main finding of this benchmark is that it is beneficial to perform more iterations between the image and the measurement spaces compared to having a deeper per-space network.

Multi-Coil MRI Reconstruction Challenge—Assessing Brain MRI Reconstruction Models and Their Generalizability to Varying Coil Configurations

The challenge experimental design is described, the results of a set of baseline and state-of-the-art brain MRI reconstruction models are summarized, and the challenges of obtaining generalizable models that are required prior to broader clinical adoption are highlighted.

Improving Fast MRI Reconstructions with Pretext Learning in Low-Data Regime

This paper exploits the self supervision based learning by introducing a pretext method to boost feature learning using the more commonly available under-sampled MR data and demonstrates that self-supervision ensures stable training and improves MR image reconstruction.

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

This paper hosts the second fastMRI competition targeted towards reconstructing MR images with subsampled k-space data and identifies common failure modes across the submissions, highlighting areas of need for future research in the MRI reconstruction community.

Iterative Data Refinement for Self-Supervised MR Image Reconstruction

Experimental results show that without utilizing any fully sampled MRI data, the proposed self-supervised framework possesses strong capabilities in capturing image details and structures at high acceleration factors.

Calibrationless MRI Reconstruction With A Plug-In Denoiser

This work pairs the High-dimensional Fast Convolutional Framework (HICU) with a plug-in denoiser and demonstrates its feasibility using 2D brain data, to leverage non-linear machine learning priors for MR image reconstruction from highly under-sampled k-space data.

k-Space and DICOM Dataset of Knee Images for Accelerated MR Image Reconstruction Using Machine Learning

The purpose of the fastMRI dataset is to provide the first large-scale dataset tailored to the problem of image reconstruction using machine learning techniques, and to enable accelerated MRI acquisitions of two-dimensional (2D) fastspin-echo sequences that are commonly used in musculoskeletal examinations.

Deep attention super-resolution of brain magnetic resonance images acquired under clinical protocols

The automatic raw segmentation of tissues and lesions using the super-resolved images has fewer false positives and higher accuracy than those obtained from interpolated images in protocols represented with more than three sets in the training sample, making the approach a strong candidate for practical application in clinical and collaborative research.

Learned Compression of High Dimensional MRI Datasets

This work proposes a novel neural network-based coil compression method in pursuit of higher reconstruction accuracy and faster coil compression, which achieves up to 1.5x lower NRMSE and up to 10 times runtime speed compared to traditional methods on a benchmark test dataset.

Accelerated Magnetic Resonance Imaging by Adversarial Neural Network

A main challenge in Magnetic Resonance Imaging for clinical applications is speeding up scan time, and short scan time can enhance temporal resolution in dynamic scans, such as functional MRI or dynamic contrast enhanced MRI.

Accelerating magnetic resonance imaging via deep learning

This paper proposes a deep learning approach for accelerating magnetic resonance imaging (MRI) using a large number of existing high quality MR images as the training datasets. An off-line

Deep convolutional neural networks for accelerated dynamic magnetic resonance imaging

Compared to state-of-the-art CS reconstruction techniques, this CNN achieves reconstruction speeds that are 150x faster without significant loss of image quality, and preliminary results suggest that CNNs may allow scan times that are 2x faster than those allowed by CS.

A Deep Cascade of Convolutional Neural Networks for MR Image Reconstruction

This work proposes a framework for reconstructing MR images from undersampled data using a deep cascade of convolutional neural networks to accelerate the data acquisition process and shows that for Cartesian undersampling of 2D cardiac MR images, the proposed method outperforms the state-of-the-art compressed sensing approaches.

Recurrent inference machines for accelerated MRI reconstruction.

Recurrent Inference Machines is proposed to use as a framework for accelerated MRI reconstruction and it is shown in experiments that the model can generalize well across different setups, while at the same time it outperforms another deep learning method and a compressed sensing approach.

Deep learning for undersampled MRI reconstruction

A deep learning method for faster magnetic resonance imaging (MRI) by reducing k-space data with sub-Nyquist sampling strategies and a rationale for why the proposed approach works well is provided.

A Transfer‐Learning Approach for Accelerated MRI Using Deep Neural Networks

The goal of this study is to introduce a transfer‐learning approach to address the problem of data scarcity in training deep networks for accelerated MRI.

ADMM-Net: A Deep Learning Approach for Compressive Sensing MRI

Due to the combination of the advantages in model-based approach and deep learning approach, the ADMM-Nets achieve state-of-the-art reconstruction accuracies with fast computational speed.

Deep ADMM-Net for Compressive Sensing MRI

Experiments on MRI image reconstruction under different sampling ratios in k-space demonstrate that the proposed novel ADMM-Net algorithm significantly improves the baseline ADMM algorithm and achieves high reconstruction accuracies with fast computational speed.

A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction

A framework for reconstructing dynamic sequences of 2-D cardiac magnetic resonance images from undersampled data using a deep cascade of convolutional neural networks (CNNs) to accelerate the data acquisition process is proposed and it is demonstrated that CNNs can learn spatio-temporal correlations efficiently by combining convolution and data sharing approaches.