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

By Alistair E. W. Johnson, Tom J. Pollard, Seth J. Berkowitz, N. Greenbaum, Matthew P. Lungren, Chih-Ying Deng, R. Mark, Steven Horng. 2019

2,082 citations recorded by the source corpus.

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. Measurement(s) Radiograph • investigation results report Technology Type(s) Chest Radiography • digital curation • Radiologist Sample Characteristic - Organism Homo sapiens Measurement(s) Radiograph • investigation results report Technology Type(s) Chest Radiography • digital curation • Radiologist Sample Characteristic - Organism Homo sapiens Machine-accessible metadata file describing the reported data: https://doi.org/10.6084/m9.figshare.10303823

Subfields: Artificial Intelligence, Pulmonary and Respiratory Medicine, Radiology, Nuclear Medicine and Imaging, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Pulmonary and Respiratory Medicine

In Radiology, Nuclear Medicine and Imaging

In Evaluation & Benchmarks

Citations in the corpus

Contrastive Learning of Medical Visual Representations from Paired Images and Text (2020, methodology): “• Chest image encoder: We use version 2 of the public MIMIC-CXR database (Johnson et al., 2019), which is a collection of chest radiograph images paired with their textual reports, and since its release has become a standard resource for studying multi-modal”
Multimodal Representation Learning via Maximization of Local Mutual Information (2021, background): “1 shows an example image-text pair, where the image is a chest radiograph and the document is the associated radiology report [13].”
Large language models are few-shot clinical information extractors (2022, background): “To overcome these issues, practitioners often incorporate task-specific domain knowledge and regular expressions, even in modern deep learning pipelines, but these solutions can be brittle (Luo et al., 2020; Skreta et al., 2021; Chapman et al., 2001; Irvin et al., 2019; Johnson et al., 2019; Chauhan”
RadGraph: Extracting Clinical Entities and Relations from Radiology Reports (2021, methodology): “Large-scale datasets, such as MIMIC-CXR [1] and CheXpert [2], use automated radiology report labelers [2–6] to extract common medical conditions from reports.”
BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs (2023, background): “Second, existing parallel image-text datasets in the biomedical domain are relatively small, ranging from 7k to 377k pairs (e.g., 377,110 pairs for MIMIC-CXR [10], 224,316 pairs for CheXpert [11], 7,562 pairs for ARCH [12], and 87,952 pairs for ROCO [13]).”
Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation (2020, methodology): “For the training data, the training set of MIMIC-CXR (Johnson et al. 2019) is used as the source of sentence pairs.”
PubMedCLIP: How Much Does CLIP Benefit Visual Question Answering in the Medical Domain? (2023, methodology): “Previous work (Rajpurkar et al., 2017; Wang et al., 2017; Irvin et al., 2019; Johnson et al., 2019a) also proposes large-scale multi-modal datasets in the medical domain.”
Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis (2020, background): “, the recent MIMIC-CXR (24) x-ray dataset or the Retinal Fundus Glaucoma Challenge (REFUGE) database of ophtalmological images (25), just to name a few].”