MONAI Core
MONAI Core 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.
Research & Development Tools
MONAI Core provides a comprehensive toolkit that bridges research innovation and clinical application. Our tools are designed for both researchers pushing the boundaries of medical AI and clinicians seeking practical solutions.
Medical-Specific Transforms
Optimized for 2D, 3D, and 4D medical imaging data
Smart caching for 10x faster data loading
Reproducible pipelines with deterministic training
DICOM, NIFTI, and PNG/JPEG support built-in
State-of-the-Art Models
VISTA-3D: Leading 3D segmentation model
31+ pre-trained models ready for fine-tuning
Easy model customization and extension
Automated model selection with Auto3DSeg
Research Workflows
Experiment tracking and version control
Real-time visualization with TensorBoard
Multi-GPU training support built-in
Automated hyperparameter tuning
Modular Components
Built on PyTorch, MONAI Core provides composable transforms, standardized interfaces, and validated implementations. Import only what you need or use our end-to-end workflows.
Core Components
Metrics
Specialized metrics for medical image analysis (Dice, Hausdorff, etc.)
Losses
Medical-specific loss functions for segmentation, registration, and reconstruction
Networks
State-of-the-art medical imaging architectures
Applications
End-to-end applications
Datasets
Efficient medical imaging data loading and processing
Quick Install
Example Usage
from monai.transforms import (
Compose,
LoadImage,
ScaleIntensity,
AddChannel
)
# Define transforms for image preprocessing
transforms = Compose([
LoadImage(image_only=True),
AddChannel(),
ScaleIntensity()
])
# Apply transforms to your image
image = transforms(image_path)
Auto3DSeg: State-of-the-Art Medical Segmentation
Achieve hassle-free, state-of-the-art performance in 3D medical image segmentation with MONAI's automated solution for both novice and expert users.
Key Features
Dataset Analysis
Automatic analysis of dataset intensity, size, and spacing for optimal preprocessing.
Algorithm Generation
Automatic configuration of algorithm folders based on data assessment.
GPU Optimization
Built-in GPU support for accelerated training, validation, and inference.
Model Ensemble
Integration of multiple models for enhanced accuracy and reliability.
Competition Achievements
MICCAI 2023 Challenges
- Multiple 1st Place wins in BraTS 2023
- 1st Place in KiTS 2023 (Kidney Segmentation)
- 1st Place in SEG.A. 2023 (Aorta Segmentation)
- 1st Place in MVSEG 2023 (Mitral Valve)
Research Impact
MONAI Core is trusted by researchers worldwide, powering breakthrough discoveries in medical AI.
Research Publications
Over 1500 peer-reviewed papers have been published using MONAI, advancing the field of medical AI.
Competition Success
MONAI-powered solutions have won numerous medical imaging challenges and competitions.
Pre-trained Models
Access a growing collection of pre-trained models for various medical imaging tasks.
How to Cite MONAI Core
If you use MONAI in your research, please cite our paper:
@article{cardoso2022monai,
title={MONAI: An open-source framework for deep learning in healthcare},
author={M Jorge Cardoso, Wenqi Li, Richard Brown, Nic Ma, Eric Kerfoot, Yiheng Wang, Benjamin Murrey, Andriy Myronenko, Can Zhao, Dong Yang, Vishwesh Nath, Yufan He, Ziyue Xu, Ali Hatamizadeh, Andriy Myronenko, Wentao Zhu, Yun Liu, Mingxin Zheng, Yucheng Tang, Isaac Yang, Michael Zephyr, Behrooz Hashemian, Sachidanand Alle, Mohammad Zalbagi Darestani, Charlie Budd, Marc Modat, Tom Vercauteren, Guotai Wang, Yiwen Li, Yipeng Hu, Yunguan Fu, Benjamin Gorman, Hans Johnson, Brad Genereaux, Barbaros S Erdal, Vikash Gupta, Andres Diaz-Pinto, Andre Dourson, Lena Maier-Hein, Paul F Jaeger, Michael Baumgartner, Jayashree Kalpathy-Cramer, Mona Flores, Justin Kirby, Lee A D Cooper, Holger R Roth, Daguang Xu, David Bericat, Ralf Floca, S Kevin Zhou, Haris Shuaib, Keyvan Farahani, Klaus H Maier-Hein, Stephen Aylward, Prerna Dogra, Sebastien Ourselin, Andrew Feng},
journal={arXiv:2211.02701},
year={2022}
}
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.
Documentation
Access comprehensive documentation covering everything from basic concepts to advanced implementations.
GitHub Repository
Explore the source code, contribute to development, and stay up to date with the latest features.
Join the Discussion
Connect with the MONAI community on Slack. Get help, share ideas, and collaborate with others.
Tutorials
Learn from hands-on tutorials and examples covering a wide range of medical imaging tasks.