pith. sign in

arxiv: 1811.08839 · v2 · pith:XHYXCWQMnew · submitted 2018-11-21 · 💻 cs.CV · cs.LG· eess.SP· physics.med-ph· stat.ML

fastMRI: An Open Dataset and Benchmarks for Accelerated MRI

Jure Zbontar , Florian Knoll , Anuroop Sriram , Tullie Murrell , Zhengnan Huang , Matthew J. Muckley , Aaron Defazio , Ruben Stern
show 19 more authors
Patricia Johnson Mary Bruno Marc Parente Krzysztof J. Geras Joe Katsnelson Hersh Chandarana Zizhao Zhang Michal Drozdzal Adriana Romero Michael Rabbat Pascal Vincent Nafissa Yakubova James Pinkerton Duo Wang Erich Owens C. Lawrence Zitnick Michael P. Recht Daniel K. Sodickson Yvonne W. Lui
This is my paper

Pith reviewed 2026-05-23 22:03 UTC · model grok-4.3

classification 💻 cs.CV cs.LGeess.SPphysics.med-phstat.ML
keywords fastMRIMRI reconstructionmachine learningaccelerated MRIopen datasetbenchmarksraw measurementsmedical imaging
0
0 comments X

The pith

The fastMRI dataset supplies raw MRI measurements and clinical images to train and benchmark machine learning models for accelerated reconstruction.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents the fastMRI dataset, a large collection of raw MR measurements paired with clinical images, designed specifically for developing and testing machine learning methods that reconstruct full images from fewer measurements. Accelerating MRI this way could cut scan times, lower costs, and reduce patient discomfort while expanding use in time-sensitive settings. The authors pair the open dataset with fixed evaluation criteria so different algorithms can be compared directly, and they include a basic MRI tutorial for machine learning practitioners. The central aim is to give the research community shared resources that speed progress on reconstruction techniques.

Core claim

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.

What carries the argument

The fastMRI dataset: an open collection of raw MR measurements and corresponding clinical images together with standardized benchmarks for evaluating reconstruction quality.

If this is right

  • Researchers gain a common raw-data resource to train end-to-end reconstruction networks that operate directly on measurements.
  • Standardized metrics make it possible to rank competing algorithms on the same test cases without hidden differences in data or scoring.
  • Faster reconstruction pipelines become feasible for clinical workflows that previously could not tolerate long scan times.
  • Machine-learning groups without prior MRI experience can enter the field using the included tutorial and data.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same release model could be repeated for CT or ultrasound to create parallel open benchmarks in those modalities.
  • Models trained here may require domain-adaptation steps when scanner hardware or patient populations differ from the training distribution.
  • Widespread use of the data could eventually inform scanner design choices that favor data-efficient acquisition patterns.

Load-bearing premise

The dataset is large enough, diverse enough, and high enough in quality that models trained on it will produce useful reconstructions and allow fair method comparisons.

What would settle it

Multiple independent groups train models on the fastMRI data yet obtain no measurable improvement in reconstruction metrics over conventional methods when tested on new clinical scans from different scanners.

read the original 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.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 2 minor

Summary. The paper introduces the fastMRI dataset, a large-scale collection of raw k-space MR measurements and corresponding clinical MR images from knee and brain scans, together with baseline reconstruction methods, standardized evaluation metrics (including SSIM and PSNR), and a self-contained MRI primer for machine-learning researchers. The central claim is that releasing this openly accessible resource with fixed benchmarks will enable rapid community progress on accelerated MRI reconstruction.

Significance. If the dataset meets its stated scale and quality standards, the release constitutes a substantial contribution by removing a key barrier to reproducible ML research in MRI: the absence of large public raw-data collections. The provision of both raw measurements and images, plus fixed train/validation/test splits and evaluation protocols, directly supports fair benchmarking and is likely to be widely adopted.

major comments (1)
  1. [§3] §3 (Dataset): the description of acquisition protocols, patient demographics, inclusion/exclusion criteria, and quality-control procedures is insufficiently detailed to allow independent assessment of dataset representativeness and potential biases; these elements are load-bearing for the claim that the resource will support clinically relevant advances.
minor comments (2)
  1. [Abstract, §1] The abstract and §1 state the goal of standardized evaluation but do not explicitly list the exact metrics and reconstruction baselines that will be used in the public leaderboard; adding a concise table would improve clarity.
  2. [§4] Figure captions and axis labels in the benchmark results section use inconsistent notation for acceleration factors (e.g., R=4 vs. 4×); harmonizing this would aid readability.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the positive evaluation of the fastMRI dataset release and for the recommendation of minor revision. We address the single major comment below.

read point-by-point responses

  1. Referee: [§3] §3 (Dataset): the description of acquisition protocols, patient demographics, inclusion/exclusion criteria, and quality-control procedures is insufficiently detailed to allow independent assessment of dataset representativeness and potential biases; these elements are load-bearing for the claim that the resource will support clinically relevant advances.

    Authors: We agree that Section 3 would benefit from greater detail on these points to support assessment of representativeness. In the revised manuscript we will expand the dataset description to include additional information on acquisition protocols (field strengths, sequence parameters, and sampling patterns), patient demographics (age and sex distributions where available), inclusion/exclusion criteria used by the contributing sites, and the quality-control steps applied prior to release. These additions will be drawn from the existing dataset documentation and acquisition metadata without altering the core claims of the paper. revision: yes

Circularity Check

0 steps flagged

No significant circularity: dataset release with no derivations

full rationale

The paper's central contribution is the release of the fastMRI dataset (raw k-space and images) together with acquisition protocols, patient cohorts, and baseline reconstruction benchmarks. No equations, fitted parameters, predictions, or uniqueness theorems are claimed or derived. The abstract and manuscript describe data collection and provide an introductory MRI section for ML readers; these steps are descriptive and externally verifiable against the released data itself. No self-citation chains, ansatzes, or renamings appear. The work is self-contained as a data resource paper.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a dataset introduction paper with no mathematical derivations, fitted parameters, or postulated entities; the contribution rests on data collection and release rather than axioms or free parameters.

pith-pipeline@v0.9.0 · 5760 in / 1071 out tokens · 42080 ms · 2026-05-23T22:03:02.564487+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 23 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MosaicMRI: A Diverse Dataset and Benchmark for Raw Musculoskeletal MRI

    cs.CV 2026-04 accept novelty 8.0

    MosaicMRI provides a diverse raw MSK MRI dataset that enables deep learning models to exploit cross-anatomical correlations, outperforming anatomy-specific training in low-sample regimes for accelerated reconstruction.

  2. On Hallucinations in Inverse Problems: Fundamental Limits and Provable Assessment Methods

    stat.ML 2026-05 unverdicted novelty 7.0

    Hallucinations in inverse problem reconstructions are fundamental to ill-posedness, with necessary and sufficient conditions plus computable bounds depending only on the forward model.

  3. Towards a Unified Theoretical Framework for Splitting-based Self-Supervised MRI Reconstruction

    eess.IV 2026-01 unverdicted novelty 7.0

    UNITS framework proves self-supervised splitting risk in MRI reconstruction is a weighted supervised risk, yielding identical Bayes-optimal predictors and relating training residuals to prediction bias.

  4. Patient-Adaptive Echocardiography using Cognitive Ultrasound

    eess.SP 2025-08 unverdicted novelty 7.0

    A temporal diffusion model enables adaptive selection of focused ultrasound transmits, outperforming random subsampling and diverging waves on EchoNet-Dynamic and in-house echocardiogram datasets while supporting real...

  5. A Plug-and-Play Method for Guided Multi-contrast MRI Reconstruction based on Content/Style Modeling

    eess.IV 2024-09 unverdicted novelty 7.0

    PnP-CoSMo is a modular plug-and-play iterative reconstruction technique that disentangles content and style in multi-contrast MR images to guide reconstruction from reference scans without k-space training data.

  6. SO-Mamba: State-Ownership Mamba for Unrolled MRI Reconstruction

    cs.CV 2026-05 unverdicted novelty 6.0

    SO-Mamba introduces state-ownership routing in Mamba regularizers for unrolled MRI reconstruction to separate resident carrier content from non-resident evidence across stages.

  7. NexOP: Joint Optimization of NEX-Aware k-space Sampling and Image Reconstruction for Low-Field MRI

    eess.IV 2026-05 unverdicted novelty 6.0

    NexOP jointly optimizes NEX-aware k-space sampling probabilities and multi-measurement reconstruction to raise effective SNR in low-field MRI under a fixed total sampling budget.

  8. Phase-map synthesis from magnitude-only MR images using conditional score-based diffusion models with application in training of accelerated MRI reconstruction models

    cs.CV 2026-05 unverdicted novelty 6.0

    Conditional score-based diffusion models synthesize phase maps from magnitude-only MR images to generate k-space datasets that train superior deep learning models for accelerated MRI reconstruction compared to smooth-...

  9. BrainDINO: A Brain MRI Foundation Model for Generalizable Clinical Representation Learning

    cs.LG 2026-04 unverdicted novelty 6.0

    BrainDINO delivers a single self-supervised brain MRI representation that generalizes to tumor segmentation, disease classification, brain age estimation, and other tasks without volumetric pretraining or full fine-tuning.

  10. Are Natural-Domain Foundation Models Effective for Accelerated Cardiac MRI Reconstruction?

    eess.IV 2026-04 unverdicted novelty 6.0

    Natural-domain foundation models provide competitive and more robust priors than task-specific models for accelerated cardiac MRI reconstruction in cross-domain settings.

  11. Generative Modeling of Complex-Valued Brain MRI Data

    eess.IV 2026-04 unverdicted novelty 6.0

    A cVAE plus flow-matching model generates realistic complex-valued brain MRI that preserves phase coherence above 0.997 and yields synthetic data that trains abnormality classifiers to 0.880 AUROC, beating the 0.842 r...

  12. Information-Theoretic Optimization for Task-Adapted Compressed Sensing Magnetic Resonance Imaging

    cs.LG 2026-04 unverdicted novelty 6.0

    An information-theoretic optimization framework for task-adapted CS-MRI enables adaptive sampling at arbitrary ratios and probabilistic inference for uncertainty while supporting joint reconstruction-task or privacy-f...

  13. Vision-Language Model-Guided Deep Unrolling Enables Personalized, Fast MRI

    cs.CV 2026-04 unverdicted novelty 6.0

    PASS combines a vision-language model with physics-based deep unrolling to create personalized, anomaly-aware fast MRI that improves image quality and downstream diagnostic tasks.

  14. Stochastic Generative Plug-and-Play Priors

    cs.CV 2026-04 conditional novelty 6.0

    Noise injection into plug-and-play algorithms using pretrained score-based diffusion denoisers optimizes a Gaussian-smoothed objective and yields better reconstructions for severely ill-posed imaging tasks.

  15. Beyond Accuracy: Evaluating Posterior Fidelity of Diffusion Inverse Solvers

    cs.LG 2026-02 unverdicted novelty 6.0

    Diffusion inverse solvers are assessed for posterior fidelity using a new score-based Kernel Stein Discrepancy metric that requires no ground-truth posterior, revealing that reconstruction accuracy alone is insufficient.

  16. Interlaced R2D2 DNN Series for Scalable Non-Cartesian MRI with Sensitivity Self-calibration

    eess.IV 2025-03 unverdicted novelty 6.0

    iR2D2 extends the R2D2 DNN series paradigm with an interlaced dual-series architecture and error-controlled updates to jointly reconstruct MR images and self-calibrate sensitivity maps from undersampled radial k-space data.

  17. Bilevel Optimized Implicit Neural Representation for Scan-Specific Accelerated MRI Reconstruction

    eess.IV 2025-02 unverdicted novelty 6.0

    Bilevel-optimized implicit neural representation with Gaussian process hyperparameter tuning enables scan-specific accelerated MRI reconstruction without training data.

  18. Scan-Adaptive MRI Undersampling Using Neighbor-based Optimization (SUNO)

    eess.IV 2025-01 unverdicted novelty 6.0

    SUNO learns per-scan adaptive k-space undersampling patterns via ICD optimization and NN lookup from low-frequency data, showing better reconstruction quality than standard patterns at 4x and 8x acceleration on fastMR...

  19. MK-ResRecon: Multi-Kernel Residual Framework for Texture-Aware 3D MRI Refinement from Sparse 2D Slices

    cs.CV 2026-05 unverdicted novelty 5.0

    MK-ResRecon predicts missing slices with a multi-kernel texture-aware loss while IdentityRefineNet3D refines the combined 3D volume to enable accurate reconstruction from highly sparse 2D inputs.

  20. Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism

    cs.LG 2025-10 unverdicted novelty 5.0

    Nirvana adds a task-aware memory trigger and updater to specialized generalist models, achieving strong general benchmark results, lowest perplexity in biomedicine/finance/law, and improved MRI reconstruction fidelity.

  21. HiFi-Mamba: Dual-Stream W-Laplacian Enhanced Mamba for High-Fidelity MRI Reconstruction

    eess.IV 2025-08 unverdicted novelty 5.0

    HiFi-Mamba uses stacked W-Laplacian spectral decoupling and unidirectional HiFi-Mamba blocks to improve high-frequency detail preservation and efficiency over prior Mamba, CNN, and Transformer models for MRI reconstruction.

  22. A Survey on Diffusion Models for Inverse Problems

    cs.LG 2024-09 unverdicted novelty 5.0

    A survey that introduces taxonomies for categorizing pre-trained diffusion model methods applied to inverse problems and analyzes their connections and challenges.

  23. Flemme: A Flexible and Modular Learning Platform for Medical Images

    eess.IV 2024-08 unverdicted novelty 4.0

    Flemme is a modular platform separating encoders (conv/transformer/SSM) from encoder-decoder architectures for medical images, with a hierarchical pyramid loss yielding reported average gains of 5.6% Dice and 5.57% PSNR.

Reference graph

Works this paper leans on

60 extracted references · 60 canonical work pages · cited by 23 Pith papers

  1. [1]

    Diagnostic assessment of deep learning algorithms for detection of lymph node metas- tases in women with breast cancer

    Babak Ehteshami Bejnordi, Mitko Veta, Paul Johannes Van Diest, Bram Van Ginneken, Nico Karsse- meijer, Geert Litjens, Jeroen AWM Van Der Laak, Meyke Hermsen, Quirine F Manson, Maschenka Balkenhol, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metas- tases in women with breast cancer. Journal of the American Medical A...

    work page 2017

  2. [2]

    Robust uncertainty principles: Exact sig- nal reconstruction from highly incomplete frequency information

    Emmanuel J Cand` es, Justin Romberg, and Terence Tao. Robust uncertainty principles: Exact sig- nal reconstruction from highly incomplete frequency information. IEEE Transactions on Information Theory, 52(2), 2006

    work page 2006

  3. [3]

    Seven challenges in image quality assessment: past, present, and future research

    Damon M Chandler. Seven challenges in image quality assessment: past, present, and future research. ISRN Signal Processing , 2013

    work page 2013

  4. [4]

    Jen-Hao Rick Chang, Chun-Liang Li, Barnab´ as P´ oczos, B. V. K. Vijaya Kumar, and Aswin C. Sankara- narayanan. One network to solve them all - solving linear inverse problems using deep projection models. IEEE International Conference on Computer Vision (ICCV) , 2017

    work page 2017

  5. [5]

    A transfer-learning approach for accelerated MRI using deep neural networks

    Salman Ul Hassan Dar and Tolga C ¸ ukur. A transfer-learning approach for accelerated MRI using deep neural networks. arXiv preprint, 2017

    work page 2017

  6. [6]

    Perceptual quality metrics applied to still image compression

    Michael P Eckert and Andrew P Bradley. Perceptual quality metrics applied to still image compression. Signal Processing, 70(3), 1998

    work page 1998

  7. [7]

    Kai Fan, Qi Wei, Wenlin Wang, Amit Chakraborty, and Katherine A. Heller. InverseNet: Solving inverse problems with splitting networks. arXiv preprint, 2017

    work page 2017

  8. [8]

    3d segmentation in the clinic: A grand challenge

    Bram Van Ginneken, Tobias Heimann, and Martin Styner. 3d segmentation in the clinic: A grand challenge. In MICCAI Workshop on 3D Segmentation in the Clinic: A Grand Challenge , 2007

    work page 2007

  9. [9]

    Generalized autocalibrating partially parallel acquisitions (GRAPPA)

    Mark A Griswold, Peter M Jakob, Robin M Heidemann, Mathias Nittka, Vladimir Jellus, Jianmin Wang, Berthold Kiefer, and Axel Haase. Generalized autocalibrating partially parallel acquisitions (GRAPPA). Magnetic Resonance in Medicine , 47(6), 2002

    work page 2002

  10. [10]

    Learning a Variational Model for Compressed Sensing MRI Reconstruction

    Kerstin Hammernik, Florian Knoll, Daniel K Sodickson, and Thomas Pock. Learning a Variational Model for Compressed Sensing MRI Reconstruction. In Magnetic Resonance in Medicine (ISMRM) , 2016

    work page 2016

  11. [11]

    Recht, Daniel K

    Kerstin Hammernik, Teresa Klatzer, Erich Kobler, Michael P. Recht, Daniel K. Sodickson, Thomas Pock, and Florian Knoll. Learning a variational network for reconstruction of accelerated MRI data. Magnetic Resonance in Medicine , 2018

    work page 2018

  12. [12]

    Framing U-Net via deep convolutional framelets: Application to sparse- view CT

    Yoseob Han and Jong Chul Ye. Framing U-Net via deep convolutional framelets: Application to sparse- view CT. IEEE Transactions on Medical Imaging , 37(6), 2018

    work page 2018

  13. [13]

    Current status of the digital database for screening mammography

    Michael Heath, Kevin Bowyer, Daniel Kopans, P Kegelmeyer, Richard Moore, Kyong Chang, and S Munishkumaran. Current status of the digital database for screening mammography. In Digital Mammography, 1998

    work page 1998

  14. [14]

    Comparison and evaluation of methods for liver segmentation from CT datasets

    Tobias Heimann, Bram Van Ginneken, Martin A Styner, Yulia Arzhaeva, Volker Aurich, Christian Bauer, Andreas Beck, Christoph Becker, Reinhard Beichel, Gy¨ orgy Bekes, et al. Comparison and evaluation of methods for liver segmentation from CT datasets. IEEE Transactions on Medical Imaging , 28(8), 2009

    work page 2009

  15. [15]

    MR image reconstruction from undersampled k-space with bayesian dictionary learning

    Yue Huang, John Paisley, Xianbo Chen, Xinghao Ding, Feng Huang, and Xiao-Ping Zhang. MR image reconstruction from undersampled k-space with bayesian dictionary learning. arXiv preprint, 2013

    work page 2013

  16. [16]

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

    Donglai Huo, Dan Xu, Zhi-Pei Liang, and David Wilson. Application of perceptual difference model on regularization techniques of parallel MR imaging. Magnetic Resonance Imaging , 24(2), 2006. 29

    work page 2006

  17. [17]

    Deep learning for undersampled MRI reconstruction

    Chang Min Hyun, Hwa Pyung Kim, Sung Min Lee, Sungchul Lee, and Jin Keun Seo. Deep learning for undersampled MRI reconstruction. Physics in medicine and biology , 63(13), 2018

    work page 2018

  18. [18]

    ISMRM raw data format: a proposed standard for MRI raw datasets

    Souheil J Inati, Joseph D Naegele, Nicholas R Zwart, Vinai Roopchansingh, Martin J Lizak, David C Hansen, Chia-Ying Liu, David Atkinson, Peter Kellman, Sebastian Kozerke, et al. ISMRM raw data format: a proposed standard for MRI raw datasets. Magnetic resonance in medicine , 77(1), 2017

    work page 2017

  19. [19]

    Perceptual losses for real-time style transfer and super-resolution

    Justin Johnson, Alexandre Alahi, and Li Fei-Fei. Perceptual losses for real-time style transfer and super-resolution. In European Conference on Computer Vision , 2016

    work page 2016

  20. [20]

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

    Erik G Larsson, Deniz Erdogmus, Rui Yan, Jose C Principe, and Jeffrey R Fitzsimmons. SNR-optimality of sum-of-squares reconstruction for phased-array magnetic resonance imaging. Journal of Magnetic Resonance, 163(1), 2003

    work page 2003

  21. [21]

    Deep Learning

    Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. Deep Learning. Nature, 521(7553), 2015

    work page 2015

  22. [22]

    Kai Lonning, Patrick Putzky, Matthan W. A. Caan, and Max Welling. Recurrent inference machines for accelerated MRI reconstruction, 2018

    work page 2018

  23. [23]

    Sparse MRI: The Application of Compressed Sensing for Rapid MR Imaging

    Michael Lustig, David Donoho, and John M Pauly. Sparse MRI: The Application of Compressed Sensing for Rapid MR Imaging. Magnetic Resonance in Medicine , 58(6), 2007

    work page 2007

  24. [24]

    Menze, Andrs Jakab, Stefan Bauer, Jayashree Kalpathy-Cramer, Keyvan Farahani, Justin Kirby, Yuliya Burren, Nicole Porz, Johannes Slotboom, Roland Wiest, Levente Lanczi, Elizabeth R

    Bjoern H. Menze, Andrs Jakab, Stefan Bauer, Jayashree Kalpathy-Cramer, Keyvan Farahani, Justin Kirby, Yuliya Burren, Nicole Porz, Johannes Slotboom, Roland Wiest, Levente Lanczi, Elizabeth R. Gerstner, Marc-Andr Weber, Tal Arbel, Brian B. Avants, Nicholas Ayache, Patricia Buendia, D. Louis Collins, Nicolas Cordier, Jason J. Corso, Antonio Criminisi, Tilak...

    work page 2015

  25. [25]

    Jun Miao, Feng Huang, Sreenath Narayan, and David L. Wilson. A new perceptual difference model for diagnostically relevant quantitative image quality evaluation: A preliminary study. Magnetic Resonance Imaging, 31(4), 2013

    work page 2013

  26. [26]

    SENSE: sensitivity encoding for fast MRI

    Klaas P Pruessmann, Markus Weiger, Markus B Scheidegger, and Peter Boesiger. SENSE: sensitivity encoding for fast MRI. Magnetic resonance in medicine , 42(5), 1999

    work page 1999

  27. [27]

    Compressed sensing dynamic MRI reconstruction using GPU- accelerated 3d convolutional sparse coding

    Tran Minh Quan and Won-Ki Jeong. Compressed sensing dynamic MRI reconstruction using GPU- accelerated 3d convolutional sparse coding. In Medical Image Computing and Computer-Assisted Inter- vention (MICCAI) , 2016

    work page 2016

  28. [28]

    The NMR phased array

    Peter B Roemer, William A Edelstein, Cecil E Hayes, Steven P Souza, and Otward M Mueller. The NMR phased array. Magnetic resonance in medicine , 16(2), 1990

    work page 1990

  29. [29]

    U-Net: Convolutional networks for biomedical image segmentation

    Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention , 2015

    work page 2015

  30. [30]

    Nonlinear total variation based noise removal algorithms

    Leonid I Rudin, Stanley Osher, and Emad Fatemi. Nonlinear total variation based noise removal algorithms. Physica D: nonlinear phenomena , 60(1-4), 1992

    work page 1992

  31. [31]

    Berg, and Li Fei-Fei

    Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, and Li Fei-Fei. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision , 2015. 30

    work page 2015

  32. [32]

    Improved techniques for training GANs

    Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. Improved techniques for training GANs. In Advances in Neural Information Processing Systems , 2016

    work page 2016

  33. [33]

    Sandino, Neerav Dixit, Joseph Y

    Christopher M. Sandino, Neerav Dixit, Joseph Y. Cheng, and Shreyas S Vasanawala. Deep convolu- tional neural networks for accelerated dynamic magnetic resonance imaging. Technical report, Stanford University, 2017

    work page 2017

  34. [34]

    Creation of fully sampled MR data repository for compressed sensing of the knee, 2013

    Anne Marie Sawyer, Michael Lustig, Marcus Alley, Phdmartin Uecker, Patrick Virtue, Peng Lai, Shreyas Vasanawala, and Ge Healthcare. Creation of fully sampled MR data repository for compressed sensing of the knee, 2013

    work page 2013

  35. [35]

    Hajnal, Anthony N

    Jo Schlemper, Jose Caballero, Joseph V. Hajnal, Anthony N. Price, and Daniel Rueckert. A deep cascade of convolutional neural networks for MR image reconstruction. Information Processing in Medical Imaging, 2017

    work page 2017

  36. [36]

    Hajnal, Anthony N

    Jo Schlemper, Jose Caballero, Joseph V. Hajnal, Anthony N. Price, and Daniel Rueckert. A deep cascade of convolutional neural networks for dynamic MR image reconstruction. IEEE Transactions on medical imaging, 37(2), 2018

    work page 2018

  37. [37]

    Arnaud Arindra Adiyoso Setio, Alberto Traverso, Thomas de Bel, Moira S. N. Berens, Cas van den Bo- gaard, Piergiorgio Cerello, Hao Chen, Qi Dou, Maria Evelina Fantacci, Bram Geurts, Robbert van der Gugten, Pheng-Ann Heng, Bart Jansen, Michael M. J. de Kaste, Valentin Kotov, Jack Yu-Hung Lin, Jeroen T. M. C. Manders, Alexander S´ onora-Mengana, Juan Carlos...

    work page 2017

  38. [38]

    Accelerated magnetic resonance imaging by adversarial neu- ral network

    Ohad Shitrit and Tammy Riklin Raviv. Accelerated magnetic resonance imaging by adversarial neu- ral network. In M. Jorge Cardoso, Tal Arbel, Gustavo Carneiro, Tanveer F. Syeda-Mahmood, Jo˜ ao Manuel R. S. Tavares, Mehdi Moradi, Andrew P. Bradley, Hayit Greenspan, Jo˜ ao Paulo Papa, Anant Madabhushi, Jacinto C. Nascimento, Jaime S. Cardoso, Vasileios Belag...

    work page 2017

  39. [39]

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

    Daniel K Sodickson and Warren J Manning. Simultaneous acquisition of spatial harmonics (SMASH): fast imaging with radiofrequency coil arrays. Magnetic resonance in medicine , 38(4), 1997

    work page 1997

  40. [40]

    Computer vision algorithms and applications

    Richard Szeliski. Computer vision algorithms and applications . Springer, 2011

    work page 2011

  41. [41]

    Perceptual image distortion

    Patrick C Teo and David J Heeger. Perceptual image distortion. In IEEE International Conference on Image Processing (ICIP) , volume 2, 1994

    work page 1994

  42. [42]

    Lecture 6.5 - rmsprop: Divide the gradient by a running average of its recent magnitude

    Tijmen Tieleman and Geoffrey Hinton. Lecture 6.5 - rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural networks for machine learning, 2012

    work page 2012

  43. [43]

    Simulating single-coil MRI from the responses of multiple coils

    Mark Tygert and Jure Zbontar. Simulating single-coil MRI from the responses of multiple coils. arXiv preprint, 2018

    work page 2018

  44. [44]

    Murphy, Marcus T

    Martin Uecker, Patrick Virtue, Frank Ong, Mark J. Murphy, Marcus T. Alley, Shreyas S. Vasanawala, and Michael Lustig. Software toolbox and programming library for compressed sensing and parallel imaging. In ISMRM Workshop on Data Sampling and Image Reconstruction , 2013

    work page 2013

  45. [45]

    ESPIRiT -an eigenvalue approach to autocalibrating parallel MRI: where SENSE meets GRAPPA

    Martin Uecker, Peng Lai, Mark J Murphy, Patrick Virtue, Michael Elad, John M Pauly, Shreyas S Vasanawala, and Michael Lustig. ESPIRiT -an eigenvalue approach to autocalibrating parallel MRI: where SENSE meets GRAPPA. Magnetic resonance in medicine , 71(3), 2014. 31

    work page 2014

  46. [46]

    Lempitsky

    Dmitry Ulyanov, Andrea Vedaldi, and Victor S. Lempitsky. Instance normalization: The missing ingredient for fast stylization. arXiv preprint, 2016

    work page 2016

  47. [47]

    Lempitsky

    Dmitry Ulyanov, Andrea Vedaldi, and Victor S. Lempitsky. Deep image prior. arXiv preprint, 2017

    work page 2017

  48. [48]

    Accelerating magnetic resonance imaging via deep learning

    Shanshan Wang, Zhenghang Su, Leslie Ying, Xi Peng, Shun Zhu, Feng Liang, Dagan Feng, and Dong Liang. Accelerating magnetic resonance imaging via deep learning. In IEEE International Symposium on Biomedical Imaging (ISBI) , 2016

    work page 2016

  49. [49]

    High- resolution image synthesis and semantic manipulation with conditional GANs

    Ting-Chun Wang, Ming-Yu Liu, Jun-Yan Zhu, Andrew Tao, Jan Kautz, and Bryan Catanzaro. High- resolution image synthesis and semantic manipulation with conditional GANs. Conference on Computer Vision and Pattern Recognition (CVPR) , 2018

    work page 2018

  50. [50]

    ChestX-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases

    Xiaosong Wang, Yifan Peng, Le Lu, Zhiyong Lu, Mohammadhadi Bagheri, and Ronald Summers. ChestX-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2017

    work page 2017

  51. [51]

    Mean squared error: Love it or leave it? a new look at signal fidelity measures

    Zhou Wang and Alan C Bovik. Mean squared error: Love it or leave it? a new look at signal fidelity measures. IEEE signal processing magazine , 26(1), 2009

    work page 2009

  52. [52]

    Multiscale structural similarity for image quality assessment

    Zhou Wang, Eero P Simoncelli, and Alan C Bovik. Multiscale structural similarity for image quality assessment. In Asilomar Conference on Signals, Systems & Computers , 2003

    work page 2003

  53. [53]

    Image quality assessment: from error visibility to structural similarity

    Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing , 13(4):600–612, 2004

    work page 2004

  54. [54]

    Takahashi, Takeshi Funaki, Susumu Miyamoto, Aur´ elien F

    Takayuki Yamamoto, T Okada, Yasutaka Fushimi, Akira Yamamoto, Koji Fujimoto, Sachi Okuchi, Hikaru Fukutomi, Jun C. Takahashi, Takeshi Funaki, Susumu Miyamoto, Aur´ elien F. Stalder, Yutaka Natsuaki, Peter Speier, and Kaori Togashi. Magnetic resonance angiography with compressed sensing: An evaluation of moyamoya disease. In PloS one , 2018

    work page 2018

  55. [55]

    Deeplesion: Automated mining of large-scale lesion annotations and universal lesion detection with deep learning

    Ke Yan, Xiaosong Wang, Le Lu, and Ronald Summers. Deeplesion: Automated mining of large-scale lesion annotations and universal lesion detection with deep learning. Journal of Medical Imaging , 5, 2018

    work page 2018

  56. [56]

    Deep ADMM-Net for compressive sensing MRI

    Yan Yang, Jian Sun, Huibin Li, and Zongben Xu. Deep ADMM-Net for compressive sensing MRI. Advances in Neural Information Processing Systems 29 , 2016

    work page 2016

  57. [57]

    ADMM-Net: A deep learning approach for compressive sensing MRI

    Yan Yang, Jian Sun, Huibin Li, and Zongben Xu. ADMM-Net: A deep learning approach for compressive sensing MRI. arXiv preprint, 2017

    work page 2017

  58. [58]

    FSIM: a feature similarity index for image quality assessment

    Lin Zhang, Lei Zhang, Xuanqin Mou, David Zhang, et al. FSIM: a feature similarity index for image quality assessment. IEEE transactions on Image Processing , 20(8), 2011

    work page 2011

  59. [59]

    Loss functions for image restoration with neural networks

    Hang Zhao, Orazio Gallo, Iuri Frosio, and Jan Kautz. Loss functions for image restoration with neural networks. IEEE Transactions on Computational Imaging , 3(1), 2017

    work page 2017

  60. [60]

    Liu, Stephen F

    Bo Zhu, Jeremiah Z. Liu, Stephen F. Cauley, Bruce R. Rosen, and Matthew S. Rosen. Image recon- struction by domain-transform manifold learning. Nature, 555(7697), 2018. A Raw k-space File Descriptions ISMRMRD files were converted into simpler HDF5 files that store the entire k-space in a single tensor. One HDF5 file was created per volume. The HDF5 files shar...

    work page 2018