{"id":14958191,"url":"https://github.com/project-monai/monai-deploy-app-sdk","last_synced_at":"2025-05-16T08:05:36.599Z","repository":{"id":37727496,"uuid":"378290631","full_name":"Project-MONAI/monai-deploy-app-sdk","owner":"Project-MONAI","description":"MONAI Deploy App SDK offers a framework and associated tools to design, develop and verify AI-driven applications in the healthcare imaging domain.","archived":false,"fork":false,"pushed_at":"2025-04-23T04:00:44.000Z","size":35477,"stargazers_count":104,"open_issues_count":55,"forks_count":53,"subscribers_count":22,"default_branch":"main","last_synced_at":"2025-05-16T08:05:31.129Z","etag":null,"topics":["ai","deep-learning","deploy","dicom","healthcare","image-processing","machine-learning","medical-imaging","ml","ml-infrastructure","ml-platform","mlops","model-deployment","model-serving","monai","pipeline","python","pytorch","workflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Project-MONAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2021-06-19T00:16:45.000Z","updated_at":"2025-05-12T23:36:55.000Z","dependencies_parsed_at":"2024-12-08T15:02:07.339Z","dependency_job_id":"00c96a03-b4f8-446b-b5ee-10a1714cae6f","html_url":"https://github.com/Project-MONAI/monai-deploy-app-sdk","commit_stats":{"total_commits":410,"total_committers":29,"mean_commits":"14.137931034482758","dds":0.6024390243902439,"last_synced_commit":"9608cd77d00a71089526cc8f46f17826ef99463c"},"previous_names":["project-monai/monai-app-sdk"],"tags_count":19,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Project-MONAI%2Fmonai-deploy-app-sdk","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Project-MONAI%2Fmonai-deploy-app-sdk/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Project-MONAI%2Fmonai-deploy-app-sdk/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Project-MONAI%2Fmonai-deploy-app-sdk/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Project-MONAI","download_url":"https://codeload.github.com/Project-MONAI/monai-deploy-app-sdk/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254493378,"owners_count":22080126,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","deep-learning","deploy","dicom","healthcare","image-processing","machine-learning","medical-imaging","ml","ml-infrastructure","ml-platform","mlops","model-deployment","model-serving","monai","pipeline","python","pytorch","workflow"],"created_at":"2024-09-24T13:16:26.711Z","updated_at":"2025-05-16T08:05:31.527Z","avatar_url":"https://github.com/Project-MONAI.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n\u003cimg src=\"https://raw.githubusercontent.com/Project-MONAI/MONAI/dev/docs/images/MONAI-logo-color.png\" width=\"50%\" alt='project-monai'\u003e\n\u003c/p\u003e\n\n💡 If you want to know more about MONAI Deploy WG vision, overall structure, and guidelines, please read [MONAI Deploy](https://github.com/Project-MONAI/monai-deploy) main repo first.\n\n# MONAI Deploy App SDK\n[![License](https://img.shields.io/badge/license-Apache%202.0-green.svg)](LICENSE)\n\n\nMONAI Deploy App SDK offers a framework and associated tools to design, develop and verify AI-driven applications in the healthcare imaging domain.\n\n## Features\n\n- Build medical imaging inference applications using a flexible, extensible \u0026 usable Pythonic API\n- Easy management of inference applications via programmable Directed Acyclic Graphs (DAGs)\n- Built-in operators to load DICOM data to be ingested in an inference app\n- Out-of-the-box support for in-proc PyTorch based inference\n- Easy incorporation of MONAI based pre and post transformations in the inference application\n- Package inference application with a single command into a portable MONAI Application Package\n- Locally run and debug your inference application using App Runner\n\n## User Guide\n\nUser guide is available at [docs.monai.io](https://docs.monai.io/projects/monai-deploy-app-sdk/en/stable/).\n\n## Citation\n\nIf you have used MONAI in your research, please cite us! The citation can be exported from: [https://arxiv.org/abs/2212.14177](https://arxiv.org/abs/2212.14177).\n\n## Installation\n\nTo install [the current release](https://pypi.org/project/monai-deploy-app-sdk/), you can simply run:\n\n```bash\npip install monai-deploy-app-sdk  # '--pre' to install a pre-release version.\n```\n\n### Prerequisites\n\n- This SDK depends on [NVIDIA Holoscan SDK](https://pypi.org/project/holoscan/) for its core implementation as well as its CLI, hence inherits its prerequisites, e.g. Ubuntu 22.04 with glibc 2.35 on X86-64 and NVIDIA dGPU drivers version 535 or above.\n- [CUDA 12.2](https://developer.nvidia.com/cuda-12-2-0-download-archive) or above is required along with a supported NVIDIA GPU with at least 8GB of video RAM.\n- If inference is not used in an example application and a GPU is not installed, at least [CUDA 12 runtime](https://pypi.org/project/nvidia-cuda-runtime-cu12/) 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 3.10 env, ```export LD_LIBRARY_PATH=`pwd`/.venv/lib/python3.10/site-packages/nvidia/cuda_runtime/lib:$LD_LIBRARY_PATH```\n- Python: 3.9 to 3.12\n\n## Getting Started\n\nGetting started guide is available at [here](https://docs.monai.io/projects/monai-deploy-app-sdk/en/stable/getting_started/index.html).\n\n```bash\npip install monai-deploy-app-sdk  # '--pre' to install a pre-release version.\n\n# Clone monai-deploy-app-sdk repository for accessing examples.\ngit clone https://github.com/Project-MONAI/monai-deploy-app-sdk.git\ncd monai-deploy-app-sdk\n\n# Install necessary dependencies for simple_imaging_app\npip install matplotlib Pillow scikit-image\n\n# Execute the app locally\npython examples/apps/simple_imaging_app/app.py -i examples/apps/simple_imaging_app/input/brain_mr_input.jpg -o output\n\n# Package app (creating MAP Docker image), using `-l DEBUG` option to see progress.\n# Also please note that postfix will be added to user supplied tag for identifying CPU architecture and GPU type etc.\nmonai-deploy package examples/apps/simple_imaging_app -c examples/apps/simple_imaging_app/app.yaml -t simple_app:latest --platform x64-workstation -l DEBUG\n\n# Run the app with docker image and an input file locally\n## Copy a test input file to 'input' folder\nmkdir -p input \u0026\u0026 rm -rf input/*\ncp examples/apps/simple_imaging_app/input/brain_mr_input.jpg input/\n## Launch the app\nmonai-deploy run simple_app-x64-workstation-dgpu-linux-amd64:latest -i input -o output\n```\n\n### [Tutorials](https://docs.monai.io/projects/monai-deploy-app-sdk/en/stable/getting_started/tutorials/index.html)\n\nTutorials are provided to help getting started with the App SDK, to name but a few below.\n\n#### [1) Creating a simple image processing app](https://docs.monai.io/projects/monai-deploy-app-sdk/en/stable/getting_started/tutorials/simple_app.html)\n\n#### [2) Creating MedNIST Classifier app](https://docs.monai.io/projects/monai-deploy-app-sdk/en/stable/getting_started/tutorials/mednist_app.html)\n\nYouTube Video (to be updated with the new version):\n\n- [MedNIST Classification Example](https://www.youtube.com/watch?v=WwjilJFHuU4)\n\n### [3) Creating a Segmentation app](https://docs.monai.io/projects/monai-deploy-app-sdk/en/stable/getting_started/tutorials/segmentation_app.html)\n\nYouTube Video (to be updated with the new version):\n\n- [Spleen Organ Segmentation - Jupyter Notebook Tutorial](https://www.youtube.com/watch?v=cqDVxzYt9lY)\n- [Spleen Organ Segmentation - Deep Dive](https://www.youtube.com/watch?v=nivgfD4pwWE)\n\n### [4) Creating a Segmentation app including visualization with Clara Viz](https://docs.monai.io/projects/monai-deploy-app-sdk/en/stable/getting_started/tutorials/segmentation_clara-viz_app.html)\n\n### [5) Creating a Segmentation app consuming a MONAI Bundle](https://docs.monai.io/projects/monai-deploy-app-sdk/en/stable/getting_started/tutorials/monai_bundle_app.html)\n\n### [Examples](https://docs.monai.io/projects/monai-deploy-app-sdk/en/stable/getting_started/examples.html)\n\n\u003chttps://github.com/Project-MONAI/monai-deploy-app-sdk/tree/main/examples/apps\u003e has example apps that you can see.\n\n- ai_livertumor_seg_app\n- ai_spleen_seg_app\n- ai_unetr_seg_app\n- dicom_series_to_image_app\n- mednist_classifier_monaideploy\n- simple_imaging_app\n\n## Contributing\n\nFor guidance on making a contribution to MONAI Deploy App SDK, see the [contributing guidelines](https://github.com/Project-MONAI/monai-deploy/blob/main/CONTRIBUTING.md).\n\n## Community\n\nTo participate, please join the MONAI Deploy App SDK weekly meetings on the [calendar](https://calendar.google.com/calendar/u/0/embed?src=c_954820qfk2pdbge9ofnj5pnt0g@group.calendar.google.com\u0026ctz=America/New_York) and review the [meeting notes](https://docs.google.com/document/d/1viIh3vyP6_gZBKcnu7gb8fU0tm9aWBOcKCMGezIWNQw/edit#).\n\nJoin the conversation on Twitter [@ProjectMONAI](https://twitter.com/ProjectMONAI) or join our [Slack channel](https://forms.gle/QTxJq3hFictp31UM9).\n\nAsk and answer questions over on [MONAI Deploy App SDK's GitHub Discussions tab](https://github.com/Project-MONAI/monai-deploy-app-sdk/discussions).\n\n## Links\n\n- Website: \u003chttps://monai.io\u003e\n- API documentation: \u003chttps://docs.monai.io/projects/monai-deploy-app-sdk\u003e\n- Code: \u003chttps://github.com/Project-MONAI/monai-deploy-app-sdk\u003e\n- Project tracker: \u003chttps://github.com/Project-MONAI/monai-deploy-app-sdk/projects\u003e\n- Issue tracker: \u003chttps://github.com/Project-MONAI/monai-deploy-app-sdk/issues\u003e\n- Wiki: \u003chttps://github.com/Project-MONAI/monai-deploy-app-sdk/wiki\u003e\n- Test status: \u003chttps://github.com/Project-MONAI/monai-deploy-app-sdk/actions\u003e\n- PyPI package: \u003chttps://pypi.org/project/monai-deploy-app-sdk\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fproject-monai%2Fmonai-deploy-app-sdk","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fproject-monai%2Fmonai-deploy-app-sdk","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fproject-monai%2Fmonai-deploy-app-sdk/lists"}