MONAI Label

MONAI Label is an intelligent image labeling and learning tool that enables you to create training datasets and build AI annotation models to accelerate the development of AI applications in medical imaging.

Get Started Documentation Get Involved

Annotation Tools for Clinical Workflows

MONAI Label combines AI assistance with clinical expertise to deliver fast, accurate, and consistent annotations. Our tools adapt to your workflow while continuously learning from your expertise.

AI-Assisted Annotation

Interactive AI models for faster annotation

Active learning for model improvement

Real-time AI assistance

Clinical Integration

3D Slicer, MITK, OHIF viewer integration

DICOM and PACS integration

Multi-user collaboration support

Extensible Platform

Customizable annotation strategies

Plugin architecture for flexibility

Easy integration with existing tools

Domain-Specific Solutions

MONAI Label delivers specialized solutions optimized for each medical imaging domain. Our tools adapt to your specific needs, whether you're working with 3D volumes, microscopy slides, or video sequences.

Radiology Use Case

Radiology

Perfect for organ segmentation, tumor detection, and anatomical measurements in CT and MRI scans. Seamlessly integrated with OHIF, MITK, and 3D Slicer, our tools accelerate volumetric analysis while maintaining high accuracy.

Sample Applications
Pathology Use Case

Pathology

Specialized in cell detection and tissue classification for whole slide imaging. Integrated with QuPath, DSA, and CellProfiler for rapid analysis of microscopy data.

Sample Applications
Endoscopy Use Case

Endoscopy

Optimized for polyp detection and tool tracking in video sequences. Integrated with CVAT for efficient frame-by-frame annotation with automated tracking.

Sample Applications

Getting Started with MONAI Label

Get started with MONAI Label in minutes. Our step-by-step guide will help you set up your environment and launch your first AI-assisted annotation server. After setup, you'll be ready to connect to your preferred viewer and start annotating with AI assistance.

1

Install MONAI Label

Install via pip package manager

pip install monailabel
2

Download Sample App

Get a pre-configured radiology application

monailabel apps --download \ --name radiology \ --output apps
3

Download Sample Dataset

Get example medical imaging data

monailabel datasets --download \ --name Task09_Spleen \ --output datasets
4

Launch Server

Start MONAI Label server with your configuration

monailabel start_server \ --app apps/radiology \ --studies datasets/Task09_Spleen/imagesTr \ --conf models deepedit

Additional Resources

Sample Applications

Explore example annotation apps for radiology, pathology, and endoscopy

Documentation

Comprehensive guides and API documentation for MONAI Label

Community Support

Get help and share experiences with the MONAI Label community

Intelligent Active Learning

MONAI Label's intelligent active learning system dramatically reduces annotation time while maintaining high accuracy. Our advanced algorithms identify the most informative samples and continuously improve model performance.

Active Learning Framework Diagram
50-80%

Faster annotation time

2x

Faster model convergence

90%

Accuracy with fewer labels

Smart Sample Selection

  • Uncertainty sampling identifies challenging cases
  • Diversity metrics ensure varied training data
  • Model ensemble disagreement detection

Continuous Model Improvement

  • Real-time model updates during annotation
  • Transfer learning from pre-trained models
  • Support for UNet, UNETR, and SwinUNETR

Quality Assurance

  • Real-time validation metrics
  • Uncertainty estimation for predictions
  • Automated annotation quality checks

Resources & Training

Get started with MONAI Label through our comprehensive learning resources and training materials.

Video Tutorials

MONAI Label Deep Dive Series

Comprehensive tutorials covering all aspects of MONAI Label

MONAI Bootcamp

Overview and hands-on training from our latest bootcamp

Documentation & Guides

Quickstart Guide

Get up and running with MONAI Label in minutes

API Documentation

Detailed technical documentation and API references

Sample Applications

Example applications and best practices

How to Cite MONAI Label

If you use MONAI Label in your research, please cite our paper: 

@article{monailabel2024,
    title={MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical Images},
    author={Diaz-Pinto, Andres and Alle, Sachidanand and Nath, Vishwesh and Tang, Yucheng and Ihsani, Alvin and Asad, Muhammad and P{\'e}rez-Garc{\'i}a, Fernando and Mehta, Pritesh and Li, Wenqi and Flores, Mona and Roth, Holger R. and Vercauteren, Tom and Xu, Daguang and Dogra, Prerna and Ourselin, Sebastien and Feng, Andrew and Cardoso, M. Jorge},
    journal={Medical Image Analysis},
    year={2024},
    doi={10.1016/j.media.2024.103207}
}
DOI

Get Involved in the Community

Join our growing community of researchers, developers, and healthcare professionals. Get help, share your work, and contribute to advancing medical image annotation. Consider joining our Human-AI Interaction Working Group to help standardize and improve AI-assisted annotation workflows.

Documentation

Access comprehensive documentation covering everything from basic concepts to advanced annotation strategies.

Deep Dive

Human-AI Interaction Working Group

Join our working group focused on standardizing and supporting Human-AI interaction cycles through well-defined interfaces for AI-assisted annotation.

Join the Group

GitHub Repository

Explore the source code, contribute to development, and access sample applications for radiology, pathology, and endoscopy to learn from real-world annotation scenarios.

View Code

Join the Discussion

Connect with the MONAI community on Slack. Get help, share ideas, and collaborate with other developers.

Join Slack