Resources

The Chest ImaGenome dataset is a scene graph dataset with additional chronological comparison relations for chest X-rays. It is automatically derived from the MIMIC-CXR dataset. A manually annotated gold standard is also available for 500 patients.

This dataset was a collected using an eye tracking system while a radiologist interpreted and read 1,083 public CXR images. The dataset contains the following aligned modalities: image, transcribed report text, dictation audio and eye gaze data.

CXLSeg dataset: Chest X-ray with Lung Segmentation, a comparatively large dataset of segmented Chest X-ray radiographs based on the MIMIC-CXR dataset. This contains segmentation results of 243,324 frontal view images and corresponding masks.

BRAX contains 24,959 chest radiography exams and 40,967 images acquired in a large general Brazilian hospital. All images have been read by trained radiologists and 14 labels were derived from Brazilian Portuguese reports using NLP.

VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations

Chest x-rays in JPG format with structured labels derived from the associated radiology report.

Chest radiographs in DICOM format with associated free-text reports.

A chest x-rays segmentation dataset derived from MIMIC-CXR based on deep learning algorithm and human examination.

Smartphone-captured CXR images including photographs taken from MIMIC-CXR and CheXpert, photographs taken by resident doctors, and photographs taken with different devices.

Benchmark dataset for report generation based on fundus fluorescein angiography images and reports.