The following is a short list of fastMRI publications. Clicking on the title will take you further down in this page where other links to the paper manuscript, preprints, code, etc. will be present.
- Zbontar, J.*, Knoll, F.*, Sriram, A.*, Murrell, T., Huang, Z., Muckley, M. J., ... & Lui, Y. W. (2018). fastMRI: An Open Dataset and Benchmarks for Accelerated MRI. arXiv preprint arXiv:1811.08839.
- Zhang, Z., Romero, A., Muckley, M. J., Vincent, P., Yang, L., & Drozdzal, M. (2019). Reducing uncertainty in undersampled MRI reconstruction with active acquisition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2049-2058.
- Defazio, A. (2019). Offset Sampling Improves Deep Learning based Accelerated MRI Reconstructions by Exploiting Symmetry. arXiv preprint, arXiv:1912.01101.
- Knoll, F.*, Zbontar, J.*, Sriram, A., Muckley, M. J., Bruno, M., Defazio, A., ... & Lui, Y. W. (2020). fastMRI: A Publicly Available Raw k-Space and DICOM Dataset of Knee Images for Accelerated MR Image Reconstruction Using Machine Learning. Radiology: Artificial Intelligence, 2(1), e190007.
- Knoll, F.*, Murrell, T.*, Sriram, A.*, Yakubova, N., Zbontar, J., Rabbat, M., ... & Recht, M. P. (2020). Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge. Magnetic Resonance in Medicine, 84(6), pages 3054-3070.
- Sriram, A., Zbontar, J., Murrell, T., Zitnick, C. L., Defazio, A., & Sodickson, D. K. (2020). GrappaNet: Combining parallel imaging with deep learning for multi-coil MRI reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14315-14322.
- Recht, M. P., Zbontar, J., Sodickson, D. K., Knoll, F., Yakubova, N., Sriram, A., ... & Zitnick, C. L. (2020). Using Deep Learning to Accelerate Knee MRI at 3T: Results of an Interchangeability Study. American Journal of Roentgenology, 215(6), pages 1421-1429.
- Pineda, L., Basu, S., Romero, A., Calandra, R., & Drozdzal, M. (2020). Active MR k-space Sampling with Reinforcement Learning. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 23-33.
- Sriram, A.*, Zbontar, J.*, Murrell, T., Defazio, A., Zitnick, C. L., Yakubova, N., ... & Johnson, P. (2020). End-to-End Variational Networks for Accelerated MRI Reconstruction. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 64-73.
- Defazio, A., Murrell, T., & Recht, M. P. (2020). MRI Banding Removal via Adversarial Training. In Advances in Neural Information Processing Systems, 33, pages 7660-7670.
- Muckley, M. J.*, Riemenschneider, B.*, Radmanesh, A., Kim, S., Jeong, G., Ko, J., ... & Knoll, F. (2021). Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction. IEEE Transactions on Medical Imaging, 40(9), pages 2306-2317.
- Johnson, P. M., Jeong, G., Hammernik, K., Schlemper, J., Qin, C., Duan, J., ..., & Knoll, F. (2021). Evaluation of the Robustness of Learned MR Image Reconstruction to Systematic Deviations Between Training and Test Data for the Models from the fastMRI Challenge. In MICCAI Machine Learning for Medical Image Reconstruction Workshop, pages 25–34.
- Bakker, T., Muckley, M.J., Romero-Soriano, A., Drozdzal, M. & Pineda, L. (2022). On learning adaptive acquisition policies for undersampled multi-coil MRI reconstruction. In * International Conference on Medical Imaging with Deep Learning, pages 63-85.
- Radmanesh, A.*, Muckley, M. J.*, Murrell, T., Lindsey, E., Sriram, A., Knoll, F., ... & Lui, Y. W. (2022). Exploring the Acceleration Limits of Deep Learning VarNet-based Two-dimensional Brain MRI. Radiology: Artificial Intelligence, 4(6), page e210313.
- Johnson, Patricia M., Lin, D. J., Zbontar, J., Zitnick, C. L., Sriram, A., Mucklye, M., ..., & Knoll, F. (2023). Deep learning reconstruction enables prospectively accelerated clinical knee MRI Radiology, page 220425.
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.
@inproceedings{zbontar2018fastMRI,
title={{fastMRI}: An Open Dataset and Benchmarks for Accelerated {MRI}},
author={Jure Zbontar and Florian Knoll and Anuroop Sriram and Tullie Murrell and Zhengnan Huang and Matthew J. Muckley and Aaron Defazio and Ruben Stern and Patricia Johnson and Mary Bruno and Marc Parente and Krzysztof J. Geras and Joe Katsnelson and Hersh Chandarana and Zizhao Zhang and Michal Drozdzal and Adriana Romero and Michael Rabbat and Pascal Vincent and Nafissa Yakubova and James Pinkerton and Duo Wang and Erich Owens and C. Lawrence Zitnick and Michael P. Recht and Daniel K. Sodickson and Yvonne W. Lui},
journal = {ArXiv e-prints},
archivePrefix = "arXiv",
eprint = {1811.08839},
year={2018}
}CVPR 2019
The goal of MRI reconstruction is to restore a high fidelity image from partially observed measurements. This partial view naturally induces reconstruction uncertainty that can only be reduced by acquiring additional measurements. In this paper, we present a novel method for MRI reconstruction that, at inference time, dynamically selects the measurements to take and iteratively refines the prediction in order to best reduce the reconstruction error and, thus, its uncertainty. We validate our method on a large scale knee MRI dataset, as well as on ImageNet. Results show that (1) our system successfully outperforms active acquisition baselines; (2) our uncertainty estimates correlate with error maps; and (3) our ResNet-based architecture surpasses standard pixel-to-pixel models in the task of MRI reconstruction. The proposed method not only shows high-quality reconstructions but also paves the road towards more applicable solutions for accelerating MRI.
@InProceedings{doi:10.1109/CVPR.2019.00215,
author = {Zhang, Zizhao and Romero, Adriana and Muckley, Matthew J. and Vincent, Pascal and Yang, Lin and Drozdzal, Michal},
title = {Reducing Uncertainty in Undersampled MRI Reconstruction With Active Acquisition},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019},
pages={2049--2053},
}Deep learning approaches to accelerated MRI take a matrix of sampled Fourier-space lines as input and produce a spatial image as output. In this work we show that by careful choice of the offset used in the sampling procedure, the symmetries in k-space can be better exploited, producing higher quality reconstructions than given by standard equally-spaced samples or randomized samples motivated by compressed sensing.
@misc{defazio2019offset,
title={Offset Sampling Improves Deep Learning based Accelerated MRI Reconstructions by Exploiting Symmetry},
author={Aaron Defazio},
year={2019},
eprint={1912.01101},
archivePrefix={arXiv},
primaryClass={eess.IV}
}fastMRI: A Publicly Available Raw k-Space and DICOM Dataset of Knee Images for Accelerated MR Image Reconstruction Using Machine Learning
Radiology: Artificial Intelligence
A publicly available dataset containing k-space data as well as Digital Imaging and Communications in Medicine image data of knee images for accelerated MR image reconstruction using machine learning is presented.
@article{doi:10.1148/ryai.2020190007,
Author = {Knoll, Florian and Zbontar, Jure and Sriram, Anuroop and Muckley, Matthew J. and Bruno, Mary and Defazio, Aaron and Parente, Marc and Geras, Krzysztof J. and Katsnelson, Joe and Chandarana, Hersh and Zhang, Zizhao and Drozdzal, Michal and Romero, Adriana and Rabbat, Michael and Vincent, Pascal and Pinkerton, James and Wang, Duo and Yakubova, Nafissa and Owens, Erich and Zitnick, C. Lawrence and Recht, Michael P. and Sodickson, Daniel K. and Lui, Yvonne W.},
Journal = {Radiology: Artificial Intelligence},
Title = {fastMRI: A Publicly Available Raw k-Space and DICOM Dataset of Knee Images for Accelerated MR Image Reconstruction Using Machine Learning},
Year = {2020},
volume={2},
number={1},
pages={e190007},
year={2020},
}Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge
Magnetic Resonance in Medicine
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.
Conclusions
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.
@article{doi:10.1002/mrm.28338,
Author = {Knoll, Florian and Murrell, Tullie and Sriram, Anuroop and Yakubova, Nafissa and Zbontar, Jure and Rabbat, Michael and Defazio, Aaron and Muckley, Matthew J. and Sodickson, Daniel K. and Zitnick, C. Lawrence and Recht, Michael P.},
journal={Magnetic Resonance in Medicine},
volume={84},
issue={6},
pages={3054--3070},
year={2020},
}CVPR 2020
Magnetic Resonance Image (MRI) acquisition is an inherently slow process which has spurred the development of two different acceleration methods: acquiring multiple correlated samples simultaneously (parallel imaging) and acquiring fewer samples than necessary for traditional signal processing methods (compressed sensing). Both methods provide complementary approaches to accelerating MRI acquisition. In this paper, we present a novel method to integrate traditional parallel imaging methods into deep neural networks that is able to generate high quality reconstructions even for high acceleration factors. The proposed method, called GrappaNet, performs progressive reconstruction by first mapping the reconstruction problem to a simpler one that can be solved by a traditional parallel imaging methods using a neural network, followed by an application of a parallel imaging method, and finally fine-tuning the output with another neural network. The entire network can be trained end-to-end. We present experimental results on the recently released fastMRI dataset and show that GrappaNet can generate higher quality reconstructions than competing methods for both 4x and 8x acceleration.
@InProceedings{Sriram_2020_CVPR,
author = {Sriram, Anuroop and Zbontar, Jure and Murrell, Tullie and Zitnick, C. Lawrence and Defazio, Aaron and Sodickson, Daniel K.},
title = {GrappaNet: Combining Parallel Imaging With Deep Learning for Multi-Coil MRI Reconstruction},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
month = {June},
pages={14303--14310},
year = {2020}
}American Journal of Roentgenology
Objective
Deep Learning (DL) image reconstruction has the potential to disrupt the current state of MR imaging by significantly decreasing the time required for MR exams. Our goal was to use DL to accelerate MR imaging in order to allow a 5-minute comprehensive examination of the knee, without compromising image quality or diagnostic accuracy.
Methods
A DL model for image reconstruction using a variational network was optimized. The model was trained using dedicated multi-sequence training, in which a single reconstruction model was trained with data from multiple sequences with different contrast and orientations. Following training, data from 108 patients were retrospectively undersampled in a manner that would correspond with a net 3.49-fold acceleration of fully-sampled data acquisition and 1.88-fold acceleration compared to our standard two-fold accelerated parallel acquisition. An interchangeability study was performed, in which the ability of 6 readers to detect internal derangement of the knee was compared for the clinical and DL-accelerated images.
Results
The study demonstrated a high degree of interchangeability between standard and DL-accelerated images. In particular, results showed that interchanging the sequences would result in discordant clinical opinions no more than 4% of the time for any feature evaluated. Moreover, the accelerated sequence was judged by all six readers to have better quality than the clinical sequence.
Conclusions
An optimized DL model allowed for acceleration of knee images which performed interchangeably with standard images for the detection of internal derangement of the knee. Importantly, readers preferred the quality of accelerated images to that of standard clinical images.
@article{doi:10.2214/AJR.20.23313,
author={Recht, Michael P. and Zbontar, Jure and Sodickson, Daniel K. and Knoll, Florian and Yakubova, Nafissa and Sriram, Anuroop and Murrell, Tullie and Defazio, Aaron and Rabbat, Michael and Rybak, Leon and Kline, Mitchell and Ciavarra, Gina and Alaia, Erin F. and Samim, Mohammad and Walter, William R. and Lin, Dana and Lui, Yvonne W. and Muckley, Matthew and Huang, Zhengnan and Johnson, Patricia and Stern, Ruben and Zitnick, C. Lawrence},
title={Using Deep Learning to Accelerate Knee MRI at 3T: Results of an Interchangeability Study},
journal={American Journal of Roentgenology},
volume={215},
number={6},
pages={1421--1429},
Year = {2020}
}MICCAI 2020
Deep learning approaches have recently shown great promise in accelerating magnetic resonance image (MRI) acquisition. The majority of existing work have focused on designing better reconstruction models given a pre-determined acquisition trajectory, ignoring the question of trajectory optimization. In this paper, we focus on learning acquisition trajectories given a fixed image reconstruction model. We formulate the problem as a sequential decision process and propose the use of reinforcement learning to solve it. Experiments on a large scale public MRI dataset of knees show that our proposed models significantly outperform the state-of-the-art in active MRI acquisition, over a large range of acceleration factors.
@inproceedings{doi:10.1007/978-3-030-59713-9_3,
title={Active MR k-space sampling with reinforcement learning},
author={Pineda, Luis and Basu, Sumana and Romero, Adriana and Calandra, Roberto and Drozdzal, Michal},
booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
pages={23--33},
year={2020},
}MICCAI 2020
The slow acquisition speed of magnetic resonance imaging (MRI) has led to the development of two complementary methods: acquiring multiple views of the anatomy simultaneously (parallel imaging) and acquiring fewer samples than necessary for traditional signal processing methods (compressed sensing). While the combination of these methods has the potential to allow much faster scan times, reconstruction from such undersampled multi-coil data has remained an open problem. In this paper, we present a new approach to this problem that extends previously proposed variational methods by learning fully end-to-end. Our method obtains new state-of-the-art results on the fastMRI dataset for both brain and knee MRIs.
@inproceedings{doi:10.1007/978-3-030-59713-9_7,
title={End-to-End Variational Networks for Accelerated {MRI} Reconstruction},
author={Anuroop Sriram and Jure Zbontar and Tullie Murrell and Aaron Defazio and C. Lawrence Zitnick and Nafissa Yakubova and Florian Knoll and Patricia Johnson},
booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
pages={64--73},
year={2020},
}NeurIPS 2020
MRI images reconstructed from sub-sampled Cartesian data using deep learning techniques often show a characteristic banding (sometimes described as streaking), which is particularly strong in low signal-to-noise regions of the reconstructed image. In this work, we propose the use of an adversarial loss that penalizes banding structures without requiring any human annotation. Our technique greatly reduces the appearance of banding, without requiring any additional computation or post-processing at reconstruction time. We report the results of a blind comparison against a strong baseline by a group of expert evaluators (board-certified radiologists), where our approach is ranked superior at banding removal with no statistically significant loss of detail.
@inproceedings{defazio2020mri,
title={MRI Banding Removal via Adversarial Training},
author={Aaron Defazio and Tullie Murrell and Michael P. Recht},
year={2020},
booktitle={Advances in Neural Information Processing Systems},
volume={33},
pages={7660--7670},
}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.
@article{muckley2021results,
author={Muckley, Matthew J. and Riemenschneider, Bruno and Radmanesh, Alireza and Kim, Sunwoo and Jeong, Geunu and Ko, Jingyu and Jun, Yohan and Shin, Hyungseob and Hwang, Dosik and Mostapha, Mahmoud and Arberet, Simon and Nickel, Dominik and Ramzi, Zaccharie and Ciuciu, Philippe and Starck, Jean-Luc and Teuwen, Jonas and Karkalousos, Dimitrios and Zhang, Chaoping and Sriram, Anuroop and Huang, Zhengnan and Yakubova, Nafissa and Lui, Yvonne W. and Knoll, Florian},
journal={IEEE Transactions on Medical Imaging},
title={Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction},
year={2021},
volume={40},
number={9},
pages={2306--2317},
doi={10.1109/TMI.2021.3075856}
}Evaluation of the Robustness of Learned MR Image Reconstruction to Systematic Deviations Between Training and Test Data for the Models from the fastMRI Challenge
The 2019 fastMRI challenge was an open challenge designed to advance research in the field of machine learning for MR image reconstruction. The goal for the participants was to reconstruct undersampled MRI k-space data. The original challenge left an open question as to how well the reconstruction methods will perform in the setting where there is a systematic difference between training and test data. In this work we tested the generalization performance of the submissions with respect to various perturbations, and despite differences in model architecture and training, all of the methods perform very similarly.
@inproceedings{johnson2021evaluation,
author={Patricia M. Johnson and Geunu Jeong and Kerstin Hammernik and Jo Schlemper and Chen Qin and Jinming Duan and Daniel Rueckert and Jingu Lee and Nicola Pezzotti and Elwin De Weerdt and Sahar Yousefi and Mohamed S. Elmahdy and Jeroen Hendrikus Franciscus Van Gemert and Christophe Schülke and Mariya Doneva and Tim Nielsen and Sergey Kastryulin and Boudewijn P. F. Lelieveldt and Matthias J. P. Van Osch and Marius Staring and Eric Z. Chen and Puyang Wang and Xiao Chen and Terrence Chen and Vishal M. Patel and Shanhui Sun and Hyungseob Shin and Yohan Jun and Taejoon Eo and Sewon Kim and Taeseong Kim and Dosik Hwang and Patrick Putzky and Dimitrios Karkalousos and Jonas Teuwen and Nikita Miriakov and Bart Bakker and Matthan Caan and Max Welling and Matthew J. Muckley and Florian Knoll},
title={Evaluation of the Robustness of Learned {MR} Image Reconstruction to Systematic Deviations Between Training and Test Data for the Models from the {fastMRI} Challenge},
booktitle={International Workshop on Machine Learning for Medical Image Reconstruction},
year={2021},
pages={25--34},
}Most current approaches to undersampled multi-coil MRI reconstruction focus on learning the reconstruction model for a fixed, equidistant acquisition trajectory. In this paper, we study the problem of joint learning of the reconstruction model together with acquisition policies. To this end, we extend the End-to-End Variational Network with learnable acquisition policies that can adapt to different data points. We validate our model on a coil-compressed version of the large scale undersampled multi-coil fastMRI dataset using two undersampling factors: 4× and 8×. Our experiments show on-par performance with the learnable non-adaptive and handcrafted equidistant strategies at 4×, and an observed improvement of more than 2% in SSIM at 8× acceleration, suggesting that potentially-adaptive k-space acquisition trajectories can improve reconstructed image quality for larger acceleration factors. However, and perhaps surprisingly, our best performing policies learn to be explicitly non-adaptive.
@inproceedings{bakker2022adaptive,
title={On learning adaptive acquisition policies for undersampled multi-coil {MRI} reconstruction},
author={Tim Bakker and Matthew Muckley and Adriana Romero-Soriano and Michal Drozdzal and Luis Pineda},
booktitle={Proceedings of Machine Learning Research (MIDL)},
year={2022},
}Purpose
To explore the limits of deep learning-based brain MRI reconstruction and identify useful acceleration ranges for general-purpose imaging and potential screening.
Materials and Methods
In this retrospective study conducted from 2019 through 2021, a model was trained for reconstruction on 5,847 brain MRIs. Performance was evaluated across a wide range of accelerations (up to 100-fold along a single phase-encoded direction for two-dimensional [2D] slices) on the fastMRI test set collected by New York University, consisting of 558 image volumes. In a sample of 69 volumes, reconstructions were classified by radiologists for identifying two clinical thresholds: 1) general-purpose diagnostic imaging and 2) potential use in a screening protocol. A Monte Carlo procedure was developed for estimating reconstruction error with only undersampled data. The model was evaluated on both in-domain and out-of-domain data. Confidence intervals were calculated using the percentile bootstrap method.
Results
Radiologists rated 100% of 69 volumes as having sufficient image quality for general-purpose imaging at up to 4× acceleration and 65 of 69 (94%) of volumes as having sufficient image quality for screening at up to 14× acceleration. The Monte Carlo procedure estimated ground truth peak signal-to-noise ratio and mean squared error with coefficients of determination greater than 0.5 at all accelerations. Out-of-distribution experiments demonstrated the model’s ability to produce images substantially distinct from the training set, even at 100× acceleration.
Conclusion
For 2D brain images using deep learning-based reconstruction, maximum acceleration for potential screening was 3–4 times higher than that for diagnostic general-purpose imaging.
@article{radmanesh2022exploring,
title={Exploring the Acceleration Limits of Deep Learning {VarNet}-based Two-dimensional Brain {MRI}},
author={Radmanesh, Alireza and Muckley, Matthew J and Murrell, Tullie and Lindsey, Emma and Sriram, Anuroop and Knoll, Florian and Sodickson, Daniel K and Lui, Yvonne W},
journal={Radiology: Artificial Intelligence},
volume={4},
number={6},
pages={e210313},
year={2022},
publisher={Radiological Society of North America}
}Abstract
Compared with conventional reconstruction, deep learning reconstruction of prospectively accelerated knee MRI enabled an almost twofold scan time reduction, improved image quality, and had equivalent diagnostic utility.
Background
MRI is a powerful diagnostic tool with a long acquisition time. Recently, deep learning (DL) methods have provided accelerated high-quality image reconstructions from undersampled data, but it is unclear if DL image reconstruction can be reliably translated to everyday clinical practice.
Purpose
To determine the diagnostic equivalence of prospectively accelerated DL-reconstructed knee MRI compared with conventional accelerated MRI for evaluating internal derangement of the knee in a clinical setting.
Materials and Methods
A DL reconstruction model was trained with images from 298 clinical 3-T knee examinations. In a prospective analysis, patients clinically referred for knee MRI underwent a conventional accelerated knee MRI protocol at 3 T followed by an accelerated DL protocol between January 2020 and February 2021. The equivalence of the DL reconstruction of the images relative to the conventional images for the detection of an abnormality was assessed in terms of interchangeability. Each examination was reviewed by six musculoskeletal radiologists. Analyses pertaining to the detection of meniscal or ligament tears and bone marrow or cartilage abnormalities were based on four-point ordinal scores for the likelihood of an abnormality. Additionally, the protocols were compared with use of four-point ordinal scores for each aspect of image quality: overall image quality, presence of artifacts, sharpness, and signal-to-noise ratio.
Results
A total of 170 participants (mean age ± SD, 45 years ± 16; 76 men) were evaluated. The DL-reconstructed images were determined to be of diagnostic equivalence with the conventional images for detection of abnormalities. The overall image quality score, averaged over six readers, was significantly better (P < .001) for the DL than for the conventional images.
Conclusion
In a clinical setting, deep learning reconstruction enabled a nearly twofold reduction in scan time for a knee MRI and was diagnostically equivalent with the conventional protocol.
@article{johnson2023deep,
title={Deep Learning Reconstruction Enables Prospectively Accelerated Clinical Knee MRI},
author={Johnson, Patricia M. and Lin, Dana J. and Zbontar, Jure and Zitnick, C. Lawrence and Sriram, Anuroop and Muckley, Matthew and Babb, James S. and Kline, Mitchell and Ciavarra, Gina and Alaia, Erin and Samim, Mohammad and Walter, William R. and Calderon, Liz and Pock, Thomas and Sodickson, Daniel K. and Recht, Michael P. and Knoll, Florian},
journal = {Radiology},
pages = {220425},
year = {2023},
doi = {10.1148/radiol.220425},
}