fastMRI+, Clinical pathology annotations for knee and brain fully sampled magnetic resonance imaging data

Ruiyang Zhao; Burhaneddin Yaman; Yuxin Zhang; Russell Stewart; Austin Dixon; Florian Knoll; Zhengnan Huang; Yvonne W Lui; Michael S Hansen; Matthew P Lungren

doi:10.1038/s41597-022-01255-z

fastMRI+, Clinical pathology annotations for knee and brain fully sampled magnetic resonance imaging data

Sci Data. 2022 Apr 5;9(1):152. doi: 10.1038/s41597-022-01255-z.

Authors

Ruiyang Zhao^{1

2

3}, Burhaneddin Yaman^{1

4}, Yuxin Zhang^{1

2

3}, Russell Stewart^{1

5}, Austin Dixon^{1

6}, Florian Knoll⁷, Zhengnan Huang⁷, Yvonne W Lui⁷, Michael S Hansen⁸, Matthew P Lungren^{1

5}

Affiliations

¹ Microsoft Research, Redmond, USA.
² University of Wisconsin-Madison, Department of Radiology, Madison, USA.
³ University of Wisconsin-Madison, Department of Medical Physics, Madison, USA.
⁴ University of Minnesota, Department of Electrical and Computer Engineering, Minneapolis, USA.
⁵ Stanford University, School of Medicine, Stanford, USA.
⁶ Duke University, School of Medicine, Durham, USA.
⁷ New York University, School of Medicine, New York, USA.
⁸ Microsoft Research, Redmond, USA. Michael.Hansen@microsoft.com.

Abstract

Improving speed and image quality of Magnetic Resonance Imaging (MRI) using deep learning reconstruction is an active area of research. The fastMRI dataset contains large volumes of raw MRI data, which has enabled significant advances in this field. While the impact of the fastMRI dataset is unquestioned, the dataset currently lacks clinical expert pathology annotations, critical to addressing clinically relevant reconstruction frameworks and exploring important questions regarding rendering of specific pathology using such novel approaches. This work introduces fastMRI+, which consists of 16154 subspecialist expert bounding box annotations and 13 study-level labels for 22 different pathology categories on the fastMRI knee dataset, and 7570 subspecialist expert bounding box annotations and 643 study-level labels for 30 different pathology categories for the fastMRI brain dataset. The fastMRI+ dataset is open access and aims to support further research and advancement of medical imaging in MRI reconstruction and beyond.

Publication types

Dataset

MeSH terms

Brain* / diagnostic imaging
Brain* / pathology
Humans
Image Processing, Computer-Assisted*
Knee Joint* / diagnostic imaging
Knee Joint* / pathology
Magnetic Resonance Imaging

Grants and funding

P41 EB017183/EB/NIBIB NIH HHS/United States