Get Started

Are you looking to get started with Project MONAI? You can find installation and tutorial links below to help you quickly get started. If you're a more visual learner, you can find videos from our MONAI Bootcamp

For MONAI, you'll find Jupyter Notebooks available to help you through fundamental components and workflows, including 2D and 3D Classification and Segmentation, Image Registration, Digital Pathology, and Accelerated Training.

For MONAI Label, you'll find sample apps that utilize three different segmentation paradigms. Use the existing app as-is or create your own using these as a starting point.

For MONAI Deploy, you'll find example deployment apps starting with a simple app to a MedNIST segmentation tutorial. These tutorials will walk you through the process of creating your first deployment application through deploying it using MONAI Inference Server.

Installation

MONAI Core

A PyTorch-based, open-source framework for deep learning in healthcare imaging used to create state-of-the-art, end-to-end training workflows.

To install the current release run the following command:

pip install monai

MONAI Label

An intelligent open-source medical image labeling and learning tool that enables you to create annotated datasets and build AI annotation models quickly.

To install the current release run the following command:

pip install monailabel

MONAI Deploy

A framework and associated tools to design, verify and analyze the performance of AI-driven applications in the healthcare domain.

To install MONAI Deploy App SDK run the following command:

pip install monai-deploy-app-sdk

To install MONAI Deploy Inference Server (MIS) check out the installation guide.

MONAI Core Tutorials

2D Classification Examples

Image classification with MedNIST dataset

2D Segmentation Examples

Training and evaluation code examples for 2D medical image segmentation

3D Classification Examples

Training and evaluation code examples for 3D medical image classification

Training and evaluation code examples for 3D medical image classification (with PyTorch Ignite)

3D Segmentation Examples

Brain tumor 3D segmentation

Training and evaluation code examples for 3D medical image segmentation

Build a segmentation workflow (with PyTorch Ignite)

Performance Acceleration

Fast training under MONAI features

Data-parallel training with multiple-GPUs

GPU-based preprocessing in native PyTorch

MONAI Label Sample Applications

Left Atrium Semantic Segmentation

DeepEdit Model Trained for Left Atrium in the heart

DeepGrow Model Trained for Left Atrium in the heart

Spleen Semantic Segmentation

DeepEdit Model Trained for Spleen Segmentation

DeepGrow Model Trained for Spleen Segmentation

MONAI Deploy Tutorials

MONAI Deploy Application Workflow Tutorials

Creating a simple image processing App

Creating a MedNIST Classifier App

Creating a Spleen Segmentation App

Deploying an App with MONAI Inference Service (MIS)