---
title: "MONAI Core"
description: "MONAI Core is the flagship library of Project MONAI for medical AI development. It includes medical-specific image transforms, state-of-the-art models like UNETR for 3D segmentation, and Auto3DSeg for automated model selection."
canonical: https://project-monai.github.io/core.html
audience: [researcher, engineer]
last_updated: 2026-06-11
source: core.html
---
MONAI Core · Train

# The training library  
built for medical imaging

DICOM and NIfTI transforms, validated 3D architectures (UNETR, SwinUNETR, VISTA-3D, MAISI), and losses calibrated for class-imbalanced anatomy, all on plain PyTorch, so your `nn.Module` and `DataLoader` habits carry over.

[Get Started](#quick-start) [Documentation](https://monai.readthedocs.io/en/stable/) [GitHub](https://github.com/Project-MONAI/MONAI)

train a 3D segmenter

$ pip install monai

```
from monai.networks.nets import UNETR
from monai.losses import DiceCELoss
from monai.transforms import LoadImaged

model = UNETR(in_channels=1,
              out_channels=14,
              img_size=(96, 96, 96))
loss = DiceCELoss(to_onehot_y=True)
```

Capabilities

## Everything between raw scans and a trained model

Not a general ML framework retrofitted for healthcare: every layer, from data loading to evaluation, is designed around 3D medical volumes.

### Medical-Specific Transforms

`LoadImaged`, `Spacingd`, `RandCropByPosNegLabeld`: dictionary transforms that keep image and label in sync

`CacheDataset` and smart caching for up to 10x faster data loading

Deterministic pipelines for reproducible training runs

DICOM, NIfTI, and PNG/JPEG I/O built in (2D, 3D, and 4D)

### State-of-the-Art Architectures

MAISI: latent-diffusion generation of synthetic 3D CT with controllable anatomy

VISTA-3D: universal 3D segmentation, promptable across 100+ anatomical classes

UNETR and SwinUNETR transformer backbones, plus classic UNet variants

40+ pre-trained Model Zoo bundles ready for fine-tuning

### Research Workflows

`sliding_window_inference` for whole-volume prediction on limited GPU memory

Dice, Hausdorff, and Surface Distance metrics with batched GPU evaluation

Multi-GPU (DDP) and mixed-precision training out of the box

TensorBoard visualization and experiment tracking hooks

Quick Start

## One install, ten composable modules

Import only what you need (transforms, networks, losses) or use the end-to-end workflows. Every module links to its API reference.

preprocess a CT volume

$ pip install monai

```
from monai.transforms import (
    Compose, LoadImage,
    EnsureChannelFirst, ScaleIntensity,
)

transforms = Compose([
    LoadImage(image_only=True),
    EnsureChannelFirst(),
    ScaleIntensity(),
])

image = transforms("ct_chest.nii.gz")
```

Want the full walkthrough? [Browse the tutorials repository](https://github.com/Project-MONAI/tutorials)

### Core Modules

[

#### Transforms

Spatial, intensity, and dictionary-based medical transforms



](https://monai.readthedocs.io/en/stable/transforms.html)[

#### Networks

UNETR, SwinUNETR, SegResNet, and more reference nets



](https://monai.readthedocs.io/en/stable/networks.html)[

#### Losses

DiceLoss, DiceCELoss, FocalLoss for imbalanced anatomy



](https://monai.readthedocs.io/en/stable/losses.html)[

#### Metrics

Dice, Hausdorff, Surface Distance, and more



](https://monai.readthedocs.io/en/stable/metrics.html)[

#### Data

CacheDataset, PersistentDataset, efficient loaders



](https://monai.readthedocs.io/en/stable/data.html)[

#### Inferers

Sliding-window and patch-based inference



](https://monai.readthedocs.io/en/stable/inferers.html)[

#### Optimizers

Optimizers and LR schedules for medical tasks



](https://monai.readthedocs.io/en/stable/optimizers.html)[

#### Applications

End-to-end apps: Auto3DSeg, MAISI, VISTA



](https://monai.readthedocs.io/en/stable/apps.html)[

#### Visualization

2D/3D plotting and TensorBoard utilities



](https://monai.readthedocs.io/en/stable/visualize.html)[

#### Utils

Determinism, type conversion, helper functions



](https://monai.readthedocs.io/en/stable/utils.html)

Automation

## Auto3DSeg: segmentation that tunes itself

Point Auto3DSeg at a labeled dataset and it analyzes intensity, size, and spacing, configures candidate algorithms, trains them on your GPUs, and ensembles the winners. The same pipeline is behind multiple MICCAI challenge wins.

### How it works

#### Dataset Analysis

Automatic profiling of intensity ranges, volume sizes, and voxel spacing to pick the right preprocessing.

#### Algorithm Generation

Generates ready-to-train algorithm folders (SegResNet, SwinUNETR, DiNTS) configured from the data assessment.

#### GPU-Accelerated Training

Multi-GPU training, validation, and inference without extra configuration.

#### Model Ensemble

Combines the best-performing candidates into a single, more accurate ensemble.

### Proven in competition

#### MICCAI 2023 Challenges

-   Multiple 1st place wins in BraTS 2023 (brain tumors)
-   1st place in KiTS 2023 (kidney segmentation)
-   1st place in SEG.A. 2023 (aorta segmentation)
-   1st place in MVSEG 2023 (mitral valve)

[Explore Auto3DSeg tutorials](https://github.com/Project-MONAI/tutorials/tree/main/auto3dseg)

Impact

## The default research stack for medical-imaging AI

The numbers are verifiable: each links to its source where one exists.

5K+

### Peer-reviewed papers

Published research that builds on MONAI, across radiology, pathology, and beyond.

20+

### Challenge wins

MONAI-powered entries have topped medical-imaging competitions including BraTS and KiTS.

40+

### Model Zoo bundles

Pre-trained, reproducible bundles: weights, configs, and inference code packaged together.

Reference

## How to cite MONAI Core

If MONAI supports your research, please cite the framework 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}
}

[View on DOI](https://doi.org/10.48550/arXiv.2211.02701)

Connect

## Build with the community

Questions, contributions, and roadmap discussions all happen in the open: on GitHub, Slack, and the working-group calls.

### Documentation

API reference and concept guides, from your first transform to distributed training.

[Read the Docs](https://monai.readthedocs.io/en/latest/index.html)

### GitHub Repository

Source code, issues, and pull requests, with contributions reviewed and merged in the open.

[View Code](https://github.com/Project-MONAI/MONAI)

### Slack Community

Real-time help and collaboration with maintainers, researchers, and clinicians.

[Join Slack](https://join.slack.com/t/projectmonai/shared_invite/zt-3hucgm02q-i8Bn9XofDZs2UGOH4jUl4w)

### Tutorials

Hands-on notebooks covering segmentation, classification, registration, and generative models.

[View Tutorials](https://github.com/Project-MONAI/tutorials)

[Or join the Developers Working Group](wg_developers.html)