MIMIC-CXR, a De-identified Publicly Available Database of Chest Radiographs with Free-text Reports

Overview

Journal Sci Data

Specialty Science

Date 2019 Dec 14

PMID 31831740

Citations 275

Authors

Alistair E W Johnson

Tom J Pollard

Seth J Berkowitz

Nathaniel R Greenbaum

Matthew P Lungren

Chih-Ying Deng

Roger G Mark

Steven Horng

Affiliations

Soon will be listed here.

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.

Citing Articles

Towards a holistic framework for multimodal LLM in 3D brain CT radiology report generation.

Li C, Chang K, Yang C, Wu H, Chen W, Bansal H Nat Commun. 2025; 16(1):2258.

PMID: 40050277 PMC: 11885477. DOI: 10.1038/s41467-025-57426-0.

Medical foundation large language models for comprehensive text analysis and beyond.

Xie Q, Chen Q, Chen A, Peng C, Hu Y, Lin F NPJ Digit Med. 2025; 8(1):141.

PMID: 40044845 PMC: 11882967. DOI: 10.1038/s41746-025-01533-1.

Multi-Branch CNN-LSTM Fusion Network-Driven System With BERT Semantic Evaluator for Radiology Reporting in Emergency Head CTs.

Tomassini S, Duranti D, Zeggada A, Cosimo Quattrocchi C, Melgani F, Giorgini P IEEE J Transl Eng Health Med. 2025; 13:61-74.

PMID: 40035027 PMC: 11875635. DOI: 10.1109/JTEHM.2025.3535676.

Cross-Modal Augmented Transformer for Automated Medical Report Generation.

Tang Y, Yuan Y, Tao F, Tang M IEEE J Transl Eng Health Med. 2025; 13:33-48.

PMID: 40035024 PMC: 11875640. DOI: 10.1109/JTEHM.2025.3536441.

Interpretability of AI race detection model in medical imaging with saliency methods.

Konate S, Lebrat L, Cruz R, Wawira Gichoya J, Price B, Seyyed-Kalantari L Comput Struct Biotechnol J. 2025; 28:63-70.

PMID: 40026803 PMC: 11871413. DOI: 10.1016/j.csbj.2025.01.007.

References

Candemir S, Jaeger S, Palaniappan K, Musco J, Singh R, Xue Z . Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration. IEEE Trans Med Imaging. 2013; 33(2):577-90. DOI: 10.1109/TMI.2013.2290491. View

Braunschweiger P, Goodman K . The CITI program: an international online resource for education in human subjects protection and the responsible conduct of research. Acad Med. 2007; 82(9):861-4. DOI: 10.1097/ACM.0b013e31812f7770. View

Rosenkrantz A, Wang W, Hughes D, Duszak Jr R . A County-Level Analysis of the US Radiologist Workforce: Physician Supply and Subspecialty Characteristics. J Am Coll Radiol. 2018; 15(4):601-606. DOI: 10.1016/j.jacr.2017.11.007. View

Pollard T, Johnson A, Raffa J, Celi L, Mark R, Badawi O . The eICU Collaborative Research Database, a freely available multi-center database for critical care research. Sci Data. 2018; 5:180178. PMC: 6132188. DOI: 10.1038/sdata.2018.178. View

Shiraishi J, Katsuragawa S, Ikezoe J, Matsumoto T, Kobayashi T, Komatsu K . Development of a digital image database for chest radiographs with and without a lung nodule: receiver operating characteristic analysis of radiologists' detection of pulmonary nodules. AJR Am J Roentgenol. 2000; 174(1):71-4. DOI: 10.2214/ajr.174.1.1740071. View

Rosenkrantz A, Hughes D, Duszak Jr R . The U.S. Radiologist Workforce: An Analysis of Temporal and Geographic Variation by Using Large National Datasets. Radiology. 2015; 279(1):175-84. DOI: 10.1148/radiol.2015150921. View

LEEMING B, Simon M, Jackson J, Horowitz G, Bleich H . Advances in radiologic reporting with Computerized Language Information Processing (CLIP). Radiology. 1979; 133(2):349-53. DOI: 10.1148/133.2.349. View

Simon M, LEEMING B, Bleich H, Reiffen B, Byrd J, Blair D . Computerized radiology reporting using coded language. Radiology. 1974; 113(2):343-9. DOI: 10.1148/113.2.343. View

Bustos A, Pertusa A, Salinas J, Iglesia-Vaya M . PadChest: A large chest x-ray image dataset with multi-label annotated reports. Med Image Anal. 2020; 66:101797. DOI: 10.1016/j.media.2020.101797. View

10.

Simon M . AN IMPROVED RADIOLOGICAL CALSSIFICATION OF DISEASES. Br J Radiol. 1965; 38:116-21. DOI: 10.1259/0007-1285-38-446-116. View

11.

Johnson A, Stone D, Celi L, Pollard T . The MIMIC Code Repository: enabling reproducibility in critical care research. J Am Med Inform Assoc. 2017; 25(1):32-39. PMC: 6381763. DOI: 10.1093/jamia/ocx084. View

12.

Jaeger S, Candemir S, Antani S, Wang Y, Lu P, Thoma G . Two public chest X-ray datasets for computer-aided screening of pulmonary diseases. Quant Imaging Med Surg. 2014; 4(6):475-7. PMC: 4256233. DOI: 10.3978/j.issn.2223-4292.2014.11.20. View

13.

Bastawrous S, Carney B . Improving Patient Safety: Avoiding Unread Imaging Exams in the National VA Enterprise Electronic Health Record. J Digit Imaging. 2017; 30(3):309-313. PMC: 5422229. DOI: 10.1007/s10278-016-9937-2. View

14.

Goldberger A, Amaral L, Glass L, Hausdorff J, Ivanov P, Mark R . PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation. 2000; 101(23):E215-20. DOI: 10.1161/01.cir.101.23.e215. View

15.

Demner-Fushman D, Kohli M, Rosenman M, Shooshan S, Rodriguez L, Antani S . Preparing a collection of radiology examinations for distribution and retrieval. J Am Med Inform Assoc. 2015; 23(2):304-10. PMC: 5009925. DOI: 10.1093/jamia/ocv080. View

16.

Johnson A, Pollard T, Berkowitz S, Greenbaum N, Lungren M, Deng C . MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports. Sci Data. 2019; 6(1):317. PMC: 6908718. DOI: 10.1038/s41597-019-0322-0. View

17.

Rimmer A . Radiologist shortage leaves patient care at risk, warns royal college. BMJ. 2017; 359:j4683. DOI: 10.1136/bmj.j4683. View

18.

Neamatullah I, Douglass M, Lehman L, Reisner A, Villarroel M, Long W . Automated de-identification of free-text medical records. BMC Med Inform Decis Mak. 2008; 8:32. PMC: 2526997. DOI: 10.1186/1472-6947-8-32. View

19.

Johnson A, Pollard T, Shen L, Lehman L, Feng M, Ghassemi M . MIMIC-III, a freely accessible critical care database. Sci Data. 2016; 3:160035. PMC: 4878278. DOI: 10.1038/sdata.2016.35. View

20.

Wilson G, Aruliah D, Brown C, Chue Hong N, Davis M, Guy R . Best practices for scientific computing. PLoS Biol. 2014; 12(1):e1001745. PMC: 3886731. DOI: 10.1371/journal.pbio.1001745. View