VinDr-CXR
Adult chest radiographs with radiologist bounding boxes and image-level diagnoses, including no-finding exams
Open the source page ↗ See it in the directory
At a glance
- What it is
- Adult chest radiographs with radiologist bounding boxes and image-level diagnoses, including no-finding exams
- Area
- Chest
- Modality
- DX, CR
- Format
- DICOM
- Size
- 18,000 PA radiographs (15,000 train, 3,000 test)
- Normals included
- Yes
- License
- PhysioNet Credentialed Health Data License 1.5.0
- Commercial use
- Not allowed under the free terms
- Access
- Credentialed access under a data-use agreement
- Status
- Verified: source page reviewed by Hounsfield Lab
- Added
- 2026-10-18
- Last checked
- 2026-11-11
- Source
- physionet.org/content/vindr-cxr/
How to access
Create a PhysioNet account, complete CITI “Data or Specimens Only Research” training, and sign the Credentialed Health Data Use Agreement 1.5.0. Then download version 1.0.0 from the Files section.
Limitations
Credentialed research use. You may not share the files or re-identify anyone. Labels are boxes and global findings from 17 radiologists, not full narrative reports. Training labels are three independent readers; the test set is a five-reader consensus.
Citation required?
Yes. Cite the PhysioNet record and the VinDr-CXR paper named on that page. PhysioNet also asks you to contribute code with publications that use the data.
Related open-source tools
- TorchXRayVision: Library of chest X-ray dataset loaders and pretrained classification, segmentation and autoencoder models
- CXAS: Chest X-ray anatomy segmentation (Mask2Former models: 187 frontal and 177 lateral classes) plus 132 named landmarks and landmark-based measurements such as cardiothoracic ratio, costophrenic angle, Cobb angle and the Haller index, in mm for DICOM input; cxas_idc writes one multi-segment DICOM SEG and a TID 1500 SR per radiograph; trained on PAXRay++ CT-projected radiographs
- CheXagent: Foundation model for chest X-ray interpretation
- MedRAX: Reasoning agent for chest X-rays that orchestrates multiple CXR models (ICML 2025)
- pydicom: Read, modify and write DICOM files in Python
- highdicom: High-level Python API on pydicom for reading images and writing AI results as DICOM Segmentation, Structured Report, parametric map and annotation objects
- OHIF Viewer: Zero-footprint web DICOM viewer
More chest datasets
- CheXpert Plus: DX, CR · Stanford AIMI research use agreement (non-commercial; commercial license sold separately)
- COCA: CT · Stanford AIMI research use agreement (non-commercial; commercial license sold separately)
- INSPECT: CT · Stanford AIMI research use agreement (non-commercial; commercial license sold separately)
- LDCT-and-Projection-data: CT · Chest, liver, and phantom images CC BY 4.0; head images under the NIH Controlled Data Access Policy
- LIDC-IDRI: CT, CR, DX · CC BY 3.0
- Medical Segmentation Decathlon: CT, MR · CC BY-SA 4.0
Hounsfield Lab links to the source and does not host images. The license and access summary reflects the source page on the last-checked date; terms can change, so read the source before you download. Not legal advice.