VinDr Lab

VinDr Lab: Open-source Data Platform
for Medical AI

Building high-quality datasets and algorithms with lean process

Why choose VinDr Lab?


Open Source

Open labeling platform with essential functions.


Qualified Contributors

Experienced medical experts from different domains in our network.


Bootstrap AI Loop

Accelerating data labeling with ML.
Consulting AI project management.

Our features

Project Management

Manage full medical data cycle at study level

Control workflow with blind and/or open annotating

Track project progress and status of each task

Label Management

Customize preset label groups or create a new one

Allow hierarchical labels

Arrange the order of labels appearing to labelers

Annotation Tools

View DICOM images with full-fledged toolboxes

Annotate with Bounding Box, Polygon, Brush

Elaborate annotations with notes and comments

Task Management

Re-assign tasks if unsatisfactory

Monitor the distribution of labels in a project

Control versions of exported labels

Medical Experts

100+ experienced radiologists who have collaborated with us in creating high-quality datasets of multiple imaging modalities.

Open Source software

VinDr Lab is available under an open-source, commercially-permissive software license (MIT). The license does not impose restriction on the use of the software.

Open Source application

VinDr Lab provides a high-level web-interface equibbed with advanced annotation tools and project management features.

VinDr Lab documentation

Documentation includes Our Design, User and Developer Guide.

Our public demo

This demo site give you an interactive demo with view only permission
(demo account is provided on Github page)

Our full demo

Full demo give you access to project as a manager: assign, labeling and more

Our use cases

VinDr-CXR

This is a large-scale dataset of chest X-ray images that was created via the VinDr Lab platform. It contains more than 18,000 CXR scans collected from two major hospitals in Vietnam. The images were labeled for the presence of 28 different radiographic findings and diagnoses in collaboration with a total of 17 experienced radiologists. VinDr-CXR is currently the largest dataset with radiologist-generated annotations. The dataset is explored to organize a competition hosted by the Kaggle platform.