Skip to content

MONAI Deploy App SDK offers a framework and associated tools to design, develop and verify AI-driven applications in the healthcare imaging domain.

License

Notifications You must be signed in to change notification settings

Project-MONAI/monai-deploy-app-sdk

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

project-monai

💡 If you want to know more about MONAI Deploy WG vision, overall structure, and guidelines, please read MONAI Deploy main repo first.

MONAI Deploy App SDK

License

MONAI Deploy App SDK offers a framework and associated tools to design, develop and verify AI-driven applications in the healthcare imaging domain.

Features

  • Build medical imaging inference applications using a flexible, extensible & usable Pythonic API
  • Easy management of inference applications via programmable Directed Acyclic Graphs (DAGs)
  • Built-in operators to load DICOM data to be ingested in an inference app
  • Out-of-the-box support for in-proc PyTorch based inference
  • Easy incorporation of MONAI based pre and post transformations in the inference application
  • Package inference application with a single command into a portable MONAI Application Package
  • Locally run and debug your inference application using App Runner

User Guide

User guide is available at docs.monai.io.

Installation

To install the current release, you can simply run:

pip install monai-deploy-app-sdk  # '--pre' to install a pre-release version.

Please also note the following system requirements:

  • Ubuntu 22.04 on X86-64 is required, as this is the only X86 platform that the underlying Holoscan SDK has been tested to support as of now.
  • CUDA 12 is required along with a supported NVIDIA GPU with at least 8GB of video RAM. If AI inference is not used in the example application and a GPU is not installed, at least CUDA 12 runtime is required, as this is one of the requirements of Holoscan SDK, in addition, the LIB_LIBRARY_PATH must be set to include the installed shared library, e.g. in a Python 3.8 env, export LD_LIBRARY_PATH=`pwd`/.venv/lib/python3.8/site-packages/nvidia/cuda_runtime/lib:$LD_LIBRARY_PATH

Getting Started

Getting started guide is available at here.

pip install monai-deploy-app-sdk  # '--pre' to install a pre-release version.

# Clone monai-deploy-app-sdk repository for accessing examples.
git clone https://github.com/Project-MONAI/monai-deploy-app-sdk.git
cd monai-deploy-app-sdk

# Install necessary dependencies for simple_imaging_app
pip install matplotlib Pillow scikit-image

# Execute the app locally
python examples/apps/simple_imaging_app/app.py -i examples/apps/simple_imaging_app/brain_mr_input.jpg -o output

# Package app (creating MAP Docker image), using `-l DEBUG` option to see progress.
monai-deploy package examples/apps/simple_imaging_app -c simple_imaging_app/app.yaml -t simple_app:latest --platform x64-workstation -l DEBUG

# Run the app with docker image and an input file locally
## Copy a test input file to 'input' folder
mkdir -p input && rm -rf input/*
cp examples/apps/simple_imaging_app/brain_mr_input.jpg input/
## Launch the app
monai-deploy run simple_app-x64-workstation-dgpu-linux-amd64:latest -i input -o output

Tutorials are provided to help getting started with the App SDK, to name but a few below.

YouTube Video (to be updated with the new version):

YouTube Video (to be updated with the new version):

https://github.com/Project-MONAI/monai-deploy-app-sdk/tree/main/examples/apps has example apps that you can see.

  • ai_livertumor_seg_app
  • ai_spleen_seg_app
  • ai_unetr_seg_app
  • dicom_series_to_image_app
  • mednist_classifier_monaideploy
  • simple_imaging_app

Contributing

For guidance on making a contribution to MONAI Deploy App SDK, see the contributing guidelines.

Community

To participate, please join the MONAI Deploy App SDK weekly meetings on the calendar and review the meeting notes.

Join the conversation on Twitter @ProjectMONAI or join our Slack channel.

Ask and answer questions over on MONAI Deploy App SDK's GitHub Discussions tab.

Links