MONAI Deploy

MONAI Deploy provides a standardized framework that simplifies deployment while ensuring reliability, performance, and seamless integration with existing healthcare infrastructure.

Get Started Documentation Get Involved

Why MONAI Deploy?

Accelerate your journey from research to clinical deployment with a framework designed specifically for healthcare AI, offering unique advantages over traditional deployment approaches.

Standardized Packaging

Single MAP format for all environments

Reproducible multi-site deployments

Built-in dependency management

Healthcare-Native

DICOM and PACS integration

Clinical workflow optimization

Healthcare compliance ready

Scalable Architecture

Horizontal scaling capabilities

Real-time performance monitoring

Load balancing & failover

Enterprise Deployment Features

MONAI Deploy provides a comprehensive platform for deploying AI models in clinical environments. Discover the key features that make enterprise deployment seamless and secure.

Development Pipeline

1

Trained Model

Models trained using MONAI Core or MONAI Label

2

MONAI Deploy App SDK

Build and package AI applications

3

MONAI App Package

Standardized deployment container

Hospital Operations

4

Inference Engine

Execute AI models efficiently

5

Workflow Manager

Orchestrate data flow and tasks

6

Informatics Gateway

Handle DICOM and FHIR data exchange

7

PACS

Connect with hospital imaging systems

MONAI Artifacts
MONAI Subsystems
Third-Party System

Technical Components

App Development

MONAI Application Package

A Pythonic SDK to build deploy-ready AI Apps in Healthcare. Create standardized, portable applications ready for deployment.

Learn More

Workflow Manager

Orchestration Hub

Central orchestration system for the MONAI Deploy Platform. Manage complex workflows and coordinate between different components seamlessly.

Learn More

Informatics Gateway

Data Integration

Facilitates seamless I/O for DICOM and FHIR data. Connect AI Applications to Healthcare Information Systems with standardized protocols.

Learn More

Getting Started with MONAI Deploy App SDK

Follow these steps to begin deploying your AI models using MONAI Deploy.

1

Environment Setup

Install MONAI Deploy SDK and set up your development environment using our comprehensive setup guide.

pip install monai-deploy-app-sdk   # Clone the MONAI Deploy App SDK repository for example applications git clone https://github.com/Project-MONAI/monai-deploy-app-sdk.git cd monai-deploy-app-sdk   # Install additional dependencies required for the simple imaging application pip install matplotlib Pillow scikit-image
View Setup Guide
2

Application Development

Run your first MONAI Deploy application using our simple imaging example.

# Run the MONAI Deploy application locally python examples/apps/simple_imaging_app/app.py \ -i examples/apps/simple_imaging_app/brain_mr_input.jpg \ -o output
View Tutorial
3

Package Creation

Create a MONAI Application Package (MAP) to ensure consistent deployment across different environments.

# Package the application to create a MAP Docker image monai-deploy package examples/apps/simple_imaging_app \ -c simple_imaging_app/app.yaml \ -t simple_app:latest \ --platform x64-workstation \ -l DEBUG
Packaging Guide
4

Deployment

Deploy your packaged application to your clinical environment with our deployment guide.

# Create the input directory and remove any existing files mkdir -p input rm -rf input/*   # Copy the test file to the input directory cp examples/apps/simple_imaging_app/brain_mr_input.jpg input/   # Launch the MONAI application monai-deploy run simple_app-x64-workstation-dgpu-linux-amd64:latest \ -i input -o output
Deployment Guide

Additional Resources

Example Applications

Learn from real-world examples and sample applications

API Reference

Detailed documentation of all MONAI Deploy components

Community Support

Join discussions and get help from the community

Real-World Applications

Discover how leading healthcare organizations are leveraging MONAI Deploy to transform patient care through AI-powered medical imaging.

Siemens Healthineers - Enterprise AI Integration Partner

Siemens Healthineers

Enterprise Integration

Siemens Healthineers has integrated MONAI Deploy into their AI-Rad Companion platform, enabling seamless deployment of AI models across their extensive healthcare network. This integration has significantly reduced deployment time and improved model performance monitoring.

Learn More
Mayo Clinic - Healthcare Innovation Partner

Mayo Clinic

Healthcare Innovation

The Center for Augmented Intelligence in Imaging at Mayo Clinic Florida has developed infrastructure for seamless integration of imaging AI models using MONAI.

Learn More
AI Centre for Value Based Healthcare - Research Platform Partner

AI Centre for Value Based Healthcare

Research Platform

AIDE, the AI Deployment Engine, enables safe and efficient deployment of AI models by seamlessly integrating them into research workflows.

Learn More
mercure - Open Source DICOM Orchestrator

mercure

Open Source

An open-source DICOM orchestrator that seamlessly integrates MONAI Application Packages (MAPs), streamlining the deployment of AI models for research.

Learn More

How to Cite MONAI Deploy

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

@article{gupta2024monai,
    title={Current State of Community-Driven Radiological AI Deployment in Medical Imaging},
    author={Gupta, Vikash and Erdal, Barbaros and Ramirez, Carolina and Floca, Ralf and Genereaux, Bradley and Bryson, Sidney and Bridge, Christopher and Kleesiek, Jens and Nensa, Felix and Braren, Rickmer and Younis, Khaled and Penzkofer, Tobias and Bucher, Andreas Michael and Qin, Ming Melvin and Bae, Gigon and Lee, Hyeonhoon and Cardoso, M Jorge and Ourselin, Sebastien and Kerfoot, Eric and Choudhury, Rahul and White, Richard D and Cook, Tessa and Bericat, David and Lungren, Matthew and Haukioja, Risto and Shuaib, Haris},
    journal={JMIR AI},
    volume={3},
    pages={e55833},
    year={2024},
    doi={10.2196/55833}
}
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 AI deployment.

Documentation

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

Deep Dive

GitHub Repository

Explore the source code, contribute to development, and stay up to date with the latest features and improvements.

View Code

Join the Discussion

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

Join Slack

Sample Applications

Explore example applications and learn from real-world deployment scenarios.

View Examples