fastMRI: An Open Dataset and Benchmarks for Accelerated MRI (2018-11-21T00:00:00.000000Z)

TL;DR

The fastMRI dataset is introduced, 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.

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.

Authors

F. Knoll

6 papers

Jure Zbontar

6 papers

Anuroop Sriram

11 papers

TL;DR

Abstract

Authors

References75 items

Simulating single-coil MRI from the responses of multiple coils

DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning

Recurrent inference machines for accelerated MRI reconstruction.

Magnetic resonance angiography with compressed sensing: An evaluation of moyamoya disease

Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer

InverseNet: Solving Inverse Problems with Splitting Networks

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

Deep Image Prior

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

Accelerated Magnetic Resonance Imaging by Adversarial Neural Network

Deep learning for undersampled MRI reconstruction

Framing U-Net via Deep Convolutional Framelets: Application to Sparse-View CT

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

ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases

Image reconstruction by domain-transform manifold learning

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

Learning a variational network for reconstruction of accelerated MRI data

One Network to Solve Them All — Solving Linear Inverse Problems Using Deep Projection Models

Loss Functions for Image Restoration With Neural Networks

A Deep Cascade of Convolutional Neural Networks for MR Image Reconstruction

ISMRM Raw data format: A proposed standard for MRI raw datasets

Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge

Deep ADMM-Net for Compressive Sensing MRI

Compressed Sensing Dynamic MRI Reconstruction Using GPU-accelerated 3D Convolutional Sparse Coding

Instance Normalization: The Missing Ingredient for Fast Stylization

Improved Techniques for Training GANs

Accelerating magnetic resonance imaging via deep learning

Perceptual Losses for Real-Time Style Transfer and Super-Resolution

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

U-Net: Convolutional Networks for Biomedical Image Segmentation

ImageNet Large Scale Visual Recognition Challenge

ESPIRiT—an eigenvalue approach to autocalibrating parallel MRI: Where SENSE meets GRAPPA

A new perceptual difference model for diagnostically relevant quantitative image quality evaluation: a preliminary study.

MR Image Reconstruction from Undersampled k-Space with Bayesian Dictionary Learning

Seven Challenges in Image Quality Assessment: Past, Present, and Future Research

FSIM: A Feature Similarity Index for Image Quality Assessment

Mean squared error: Love it or leave it? A new look at Signal Fidelity Measures

Comparison and Evaluation of Methods for Liver Segmentation From CT Datasets

Sparse MRI: The application of compressed sensing for rapid MR imaging

Application of perceptual difference model on regularization techniques of parallel MR imaging.

Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information

Image quality assessment: from error visibility to structural similarity

Multiscale structural similarity for image quality assessment

SNR-optimality of sum-of-squares reconstruction for phased-array magnetic resonance imaging.

Generalized autocalibrating partially parallel acquisitions (GRAPPA)

SENSE: Sensitivity encoding for fast MRI

Perceptual quality metrics applied to still image compression

Simultaneous acquisition of spatial harmonics (SMASH): Fast imaging with radiofrequency coil arrays

Perceptual image distortion

Nonlinear total variation based noise removal algorithms

The NMR phased array

Deep convolutional neural networks for accelerated dynamic magnetic resonance imaging

“ Simultaneous Acquisition of Spatial Harmonics ( SMASH ) : Fast Imaging with Radiofrequency Coil Arrays

Bram van Ginneken, and Colin Jacobs. Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules

Learning a Variational Model for Compressed Sensing MRI Reconstruction

Deep Learning

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016

Software toolbox and programming library for compressed sensing and parallel imaging

Creation of fully sampled MR data repository for compressed sensing of the knee

Lecture 6.5 -rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural networks for machine learning

Computer Vision - Algorithms and Applications

3D Segmentation in the Clinic: A Grand Challenge

Current Status of the Digital Database for Screening Mammography

reconstruction rss root-sum-of-squares reconstruction of the multi-coil k-space that was used to derive the emulated single-coil k-space cropped to the center 320 × 320 region

ismrmrd header The XML header copied verbatim from the ISMRMRD ﬁle that was used to generate the HDF5 ﬁle

DICOM images: spatially-resolved images for which the raw data was discarded during the acquisition process

acquisition Acquisition protocol (either CORPD or CORPDFS, indicating coronal proton density with or without fat saturation, respectively

mask Deﬁnes the undersampled Cartesian k-space trajectory. The number of elements in the mask tensor is the same as the width of k-space

Ground-truth images: real-valued images reconstructed from fully-sampled multi-coil acquisitions using the simple root-sum-of-squares method

acceleration Acceleration factor of the undersampled k-space trajectory (either 4 or 8)

patient id A unique string identifying the examination, and substituting anonymously for the patient identiﬁcation

The inverse Fourier transform of the single-coil k-space data cropped to the center 320 × 320 region

The Euclidean norm and the largest entry of the target volume

tar.gz Validation dataset for the single-coil track. The HDF5 ﬁles have the same structure as the HDF5 ﬁles in singlecoil train

multicoil test.tar.gz Test dataset for the multi-coil track. The HDF5 ﬁles contain the following tensors

Field of Study