Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Dec 12;6(1):317.
doi: 10.1038/s41597-019-0322-0.

MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports

Alistair E W Johnson  1 , Tom J Pollard  2 , Seth J Berkowitz  3 , Nathaniel R Greenbaum  4 , Matthew P Lungren  5 , Chih-Ying Deng  6 , Roger G Mark  2 , Steven Horng  4
Affiliations

MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports

Alistair E W Johnson et al. Sci Data. .

Abstract

Chest radiography is an extremely powerful imaging modality, allowing for a detailed inspection of a patient's chest, but requires specialized training for proper interpretation. With the advent of high performance general purpose computer vision algorithms, the accurate automated analysis of chest radiographs is becoming increasingly of interest to researchers. Here we describe MIMIC-CXR, a large dataset of 227,835 imaging studies for 65,379 patients presenting to the Beth Israel Deaconess Medical Center Emergency Department between 2011-2016. Each imaging study can contain one or more images, usually a frontal view and a lateral view. A total of 377,110 images are available in the dataset. Studies are made available with a semi-structured free-text radiology report that describes the radiological findings of the images, written by a practicing radiologist contemporaneously during routine clinical care. All images and reports have been de-identified to protect patient privacy. The dataset is made freely available to facilitate and encourage a wide range of research in computer vision, natural language processing, and clinical data mining.

PubMed Disclaimer

Conflict of interest statement

The M.I.T. Laboratory for Computational Physiology received funding from Philips Healthcare to create the database described in this paper.

Figures

Fig. 1
Fig. 1
Example study contained in MIMIC-CXR. Above (a), the radiology report provides the interpretation of the image. PHI has been removed and replaced with three underscores (_ _ _). Below, the two chest radiographs for this study are shown: (b) the frontal view (left image) and (c) the lateral view (right image).
Fig. 2
Fig. 2
Images which highlight the amount of variation present in MIMIC-CXR. From left to right: (a) poor patient positioning, (b) black box obscuring potential PHI, (c) secondary collimation to improve image quality, and (d) incorrect image orientation information in the meta-data.
See this image and copyright information in PMC

References

    1. Rosenkrantz AB, Hughes DR, Duszak R., Jr. The US radiologist workforce: an analysis of temporal and geographic variation by using large national datasets. Radiology. 2015;279:175–184. doi: 10.1148/radiol.2015150921. - DOI - PubMed
    1. Rosenkrantz AB, Wang W, Hughes DR, Duszak R., Jr. A county-level analysis of the us radiologist workforce: physician supply and subspecialty characteristics. J Am Coll Radiol. 2018;15:601–606. doi: 10.1016/j.jacr.2017.11.007. - DOI - PubMed
    1. Rimmer, A. Radiologist shortage leaves patient care at risk, warns royal college. BMJ359, j4683 (2017). - PubMed
    1. Bastawrous S, Carney B. Improving patient safety: Avoiding unread imaging exams in the national VA enterprise electronic health record. J Digit Imaging. 2017;30:309–313. doi: 10.1007/s10278-016-9937-2. - DOI - PMC - PubMed
    1. Rosman DA, et al. Imaging in the land of 1000 hills: Rwanda radiology country report. J Glob Radiol. 2015;1:5.

Publication types