@article{60fe3d26df114068ba3ef29448611735,
title = "Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge",
abstract = "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.",
keywords = "challenge, compressed sensing, fast imaging, image reconstruction, machine learning, optimization, parallel imaging, public dataset",
author = "Florian Knoll and Tullie Murrell and Anuroop Sriram and Nafissa Yakubova and Jure Zbontar and Michael Rabbat and Aaron Defazio and Muckley, {Matthew J.} and Sodickson, {Daniel K.} and Zitnick, {C. Lawrence} and Recht, {Michael P.}",
note = "Funding Information: We first would like to thank all participants of the challenge. We thank the radiologists who provided the scoring for the second evaluation phase: Drs. Christine Chung and Mini Pathria of UCSD, Dr. Michael Tuite of University of Wisconsin, Dr. Christopher Beaulieu of Stanford, Drs. Naveen Subhas and Hakan Ilaslan of the Cleveland Clinic, and Dr. David Rubin of NYU Langone Health. We thank our external advisors for the organization of the challenge: Dr. Daniel Rueckert of Imperial College London, Dr. Jonathan Tamir of University of Texas at Austin, Dr. Joseph Cheng of Apple AI research and Dr. Frank Ong of Stanford. We also thank our colleagues Mark Tygert, Michal Drozdzal, Adriana Romero, Pascal Vincent, Erich Owens, Krzysztof Geras, Patricia Johnson, Mary Bruno, Jakob Asslaender, Yvonne Lui, Zhengnan Huang and Ruben Stern for their insights and feedback. We acknowledge grant support from the National Institutes of Health under grants NIH R01EB024532 and NIH P41EB017183. Florian Knoll, Tullie Murrell and Anuroop Sriram contributed equally to this work. Funding Information: We first would like to thank all participants of the challenge. We thank the radiologists who provided the scoring for the second evaluation phase: Drs. Christine Chung and Mini Pathria of UCSD, Dr. Michael Tuite of University of Wisconsin, Dr. Christopher Beaulieu of Stanford, Drs. Naveen Subhas and Hakan Ilaslan of the Cleveland Clinic, and Dr. David Rubin of NYU Langone Health. We thank our external advisors for the organization of the challenge: Dr. Daniel Rueckert of Imperial College London, Dr. Jonathan Tamir of University of Texas at Austin, Dr. Joseph Cheng of Apple AI research and Dr. Frank Ong of Stanford. We also thank our colleagues Mark Tygert, Michal Drozdzal, Adriana Romero, Pascal Vincent, Erich Owens, Krzysztof Geras, Patricia Johnson, Mary Bruno, Jakob Asslaender, Yvonne Lui, Zhengnan Huang and Ruben Stern for their insights and feedback. We acknowledge grant support from the National Institutes of Health under grants NIH R01EB024532 and NIH P41EB017183. Florian Knoll, Tullie Murrell and Anuroop Sriram contributed equally to this work. Publisher Copyright: {\textcopyright} 2020 International Society for Magnetic Resonance in Medicine",
year = "2020",
month = dec,
day = "1",
doi = "10.1002/mrm.28338",
language = "English (US)",
volume = "84",
pages = "3054--3070",
journal = "Magnetic resonance in medicine",
issn = "0740-3194",
publisher = "John Wiley and Sons Inc.",
number = "6",
}