The MONAI framework is the open-source foundation being created by Project MONAI. MONAI is a freely available, community-supported, PyTorch-based framework for deep learning in healthcare imaging. It provides domain-optimized foundational capabilities for developing healthcare imaging training workflows in a native PyTorch paradigm.
MONAI is an open-source project. It is built on top of PyTorch and is released under the Apache 2.0 license.
Aiming to capture best practices of AI development for healthcare researchers, with an immediate focus on medical imaging.
Providing user-comprehensible error messages and easy to program API interfaces.
Provides reproducibility of research experiments for comparisons against state-of-the-art implementations.
Designed to be compatible with existing efforts and ease of 3rd party integration for various components.
Delivering high-quality software with enterprise-grade development, tutorials for getting started and robust validation & documentation.
MedNIST image classification
Getting started with a GPU powered Colab tutorial
Abdominal CT segmentation with 3D UNet
Medical image segmentation tutorial
Histology image transformation demo
2D transformation demo
Volumetric image transformation demo
3D transformation tutorial
Accelerate model training by caching the preprocessors
Demo on the caching dataset
Data-parallel training with multiple-GPUs
Multi-GPU training demo
GPU-based preprocessing in native PyTorch
GPU-based pipeline demo
Build a segmentation workflow (with PyTorch Ignite)
Segmentation workflow demo
Build a segmentation workflow (with PyTorch Lightning)
Segmentation workflow demo
Developer's guide on MONAI transformations
Concepts of the MONAI transformations
Training and evaluation code examples for medical image classification.
Brain MRI classification examples
Training and evaluation code examples for medical image classification (with PyTorch Ignite).
Brain MRI classification examples with Ignite
Training and evaluation code examples for medical image segmentation.
Volumetric image segmentation examples
Training and evaluation code examples for medical image segmentation (with PyTorch Ignite).
Volumetric image segmentation examples with Ignite
Customizable design for varying user expertise to interact with the package.
Flexible pre-processing for multi-dimensional medical imaging data.
Medical Imaging optimized reference implementations for networks, losses, validation metrics, etc.
Compositional & portable enabling ease of integration in existing workflows.
Object-oriented Pythonic programming paradigm.
Multi-GPU and data parallel processing supported.
Provides ready-to-use deep learning models, walk-through tutorials and examples to get kick-started for AI development on a common foundation.
For advanced academic and translational researchers, MONAI provides modular domain optimized components that can be easily integrated into existing workflows and enables reproducibility of research experiments for comparison.
Project MONAI is an initiative originally started by NVIDIA & King’s College London to establish an inclusive community of AI researchers for the development and exchange of best practices for AI in healthcare imaging across academia and enterprise researchers.