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.
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.
Matthew Muckley
4 papers
M. Bruno
2 papers
Aaron Defazio
6 papers
Marc Parente
2 papers
Krzysztof J. Geras
8 papers
Joe Katsnelson
3 papers
H. Chandarana
2 papers
Adriana Romero
5 papers
Michael G. Rabbat
9 papers
James Pinkerton
3 papers
Duo Wang
2 papers
N. Yakubova
5 papers
Erich Owens
2 papers
C. L. Zitnick
19 papers
M. Recht
4 papers
D. Sodickson
4 papers
Y. Lui
3 papers
M. Drozdzal
6 papers
Pascal Vincent
5 papers
Zizhao Zhang
3 papers