Project-MONAI/MONAI

What is it?

Key features

• 01Flexible pre-processing for multi-dimensional medical imaging data
• 02Domain-specific networks, losses and evaluation metrics
• 03Compositional, portable APIs that integrate with existing PyTorch workflows
• 04Multi-GPU and multi-node data parallelism support
• 05MONAI Bundle format for packaging and sharing models

Use cases

• Training segmentation or classification models on CT or MRI volumes
• Adding medical-domain losses and metrics to an existing PyTorch training pipeline
• Scaling model training across multiple GPUs or nodes
• Reusing and sharing pretrained models through the bundle format

Topics

FAQ

What is MONAI?

A PyTorch-based open-source framework for deep learning on healthcare imaging data, covering preprocessing, networks, losses and metrics. MONAI is a deep learning framework built on PyTorch for healthcare imaging. It targets researchers and clinicians who need to build end-to-end training workflows for multi-dimensional medical image data, such as 2D and 3D scans, without assembling every component from scratch.

Is MONAI free to use? What license does it have?

MONAI is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.

Is MONAI still maintained?

Actively maintained. The last commit to MONAI was on Oct 17, 2026.

What can I use MONAI for?

Training segmentation or classification models on CT or MRI volumes Adding medical-domain losses and metrics to an existing PyTorch training pipeline Scaling model training across multiple GPUs or nodes Reusing and sharing pretrained models through the bundle format

Where can I get MONAI?

The source code and installation instructions are on GitHub: https://github.com/Project-MONAI/MONAI