Meeting Banner
Abstract #0657

fastMRI: a publicly available raw k-space dataset for accelerated MRI reconstruction using machine learning

Florian Knoll1, Matthew Muckley1, Jure Zbontar2, Anuroop Sriram2, Aaron Defazio2, Michal Drozdzal 2, Krzysztof Geras1, Mary Bruno1, Marc Parente1, Nafissa Yakubova2, Mike Rabbat2, Adriana Romero Soriano2, Pascal Vincent2, Erich Owens2, Joe Katsnelson3, Hersh Chandarana1, Yvonne W Lui1, Daniel K Sodickson1, Larry Zitnick2, and Michael P Recht1

1Center for Advanced Imaging Innovation and Research, Department of Radiology, New York University School of Medicine, New York, NY, United States, 2Facebook Artificial Intelligence Research, Menlo Park, CA, United States, 3Medical Center IT, New York University School of Medicine, New York, NY, United States

Despite the substantial increase in research activity in machine learning for MR image reconstruction, no large scale raw k-space data set is publicly available. This makes it challenging to reproduce and validate comparisons of different approaches, and it restricts access to work on this problem to researchers associated with large academic medical centers. This abstract introduces the first large-scale database of MRI data for reconstruction. The database currently includes about 7500 raw MRI k-space data sets from a range of MRI systems and clinical patient populations, with corresponding images derived from the rawdata using reference image reconstruction algorithms. Approximately 30000 additional clinical image datasets not directly associated with the rawdata are also included, and we plan to add to the database over time.

This abstract and the presentation materials are available to members only; a login is required.

Join Here