VinDr Lab

VinDr Lab: Labeling solution
for Medical AI

Building high-quality datasets and algorithms
with lean process and experienced experts

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.

VinDr Laboratory - Our public demo

This demo site give you an interactive demo with view only permission.
It's also a Datahub where we hosted all our public datasets.

VinDr Labelling - Our full demo

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

Our use cases


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.


Vingroup Big Data Institute (VinBigdata) has created and made freely available the VinDr-SpineXR: A large-scale X-ray dataset for spinal lesions detection and classification. The VinDr-SpineXR contains 10,469 images from 5,000 studies that are manually annotated with 13 types of abnormalities, each scan was annotated by an expert radiologist.

To the best of our knowledge, the VinDr-SpineXR is currently the largest dataset to date that provides radiologist’s bounding-box annotations for developing supervised-learning object detection algorithms. 


VinDr-RibCXR is a dataset for automatic segmentation and labeling of individual ribs from chest X-ray (CXR) scans. The VinDr-RibCXR contains 245 CXRs with corresponding ground truth annotations provided by human experts. Each image was assigned to an expert, who manually segmented and annotated each of 20 ribs, denoted as L1→L10 (left ribs) and R1→R10 (right ribs). The masks of ribs (see Figure 1) were then stored in a JSON file that can later be used for training instance segmentation models.