2019
DOI: 10.1038/s41597-019-0322-0
|View full text |Cite
|
Sign up to set email alerts
|

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

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 Emer… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
513
1
1

Year Published

2019
2019
2024
2024

Publication Types

Select...
8
1

Relationship

0
9

Authors

Journals

citations
Cited by 884 publications
(516 citation statements)
references
References 31 publications
1
513
1
1
Order By: Relevance
“…The large dataset of chest X-rays CheXpert provides another comprehensive source for pre-training the models [ 16 ], and 2.44% of the CheXpert images are from the pneumonia patients. The third dataset MIMIC-CXR covers 297 class labels for its chest X-ray images, and 6.9% of its images are from pneumonia patients [ 17 ].This study serves as the proof-of-principle experiment for the two-stage transfer learning strategy. So these existing datasets are not evaluated in this study.…”
Section: Methodsmentioning
confidence: 99%
“…The large dataset of chest X-rays CheXpert provides another comprehensive source for pre-training the models [ 16 ], and 2.44% of the CheXpert images are from the pneumonia patients. The third dataset MIMIC-CXR covers 297 class labels for its chest X-ray images, and 6.9% of its images are from pneumonia patients [ 17 ].This study serves as the proof-of-principle experiment for the two-stage transfer learning strategy. So these existing datasets are not evaluated in this study.…”
Section: Methodsmentioning
confidence: 99%
“…The data set for model training (hereafter, the modeling data set) was assembled from 2 hospital sources: MIMIC-4, 19 data set were used owing to available reports, the NIH data set was randomly sampled for report generation, from which only a subset of 11 692 images could be manually reread.…”
Section: Assembling the Data Sets For Model Trainingmentioning
confidence: 99%
“…Recently, thanks to the increased availability of large scale, high-quality labeled datasets [15,14,16] and high-performing deep network architectures [17,18,19,20], deep learning-based approaches have been able to reach, even outperform expert-level performance for many medical image interpretation tasks [21,22,23,24]. Most successful applications of deep neural networks in medical imaging rely on CNNs, which were introduced in 1998 by LeCun et al [25] and revolutionized in 2012 by Krizhevsky et al [26].…”
Section: Deep Learning In Medical Imagingmentioning
confidence: 99%