an invention by jordimassaguerpla
Project Description
MONAI is a set of open-source, freely available collaborative frameworks built for accelerating research and clinical collaboration in Medical Imaging. The goal is to accelerate the pace of innovation and clinical translation by building a robust software framework that benefits nearly every level of medical imaging, deep learning research, and deployment.
Open Source Design
MONAI is an open-source project. It is built on top of PyTorch and is released under the Apache 2.0 license.
Standardized
Aiming to capture best practices of AI development for healthcare researchers, with an immediate focus on medical imaging.
User Friendly
Providing user-comprehensible error messages and easy to program API interfaces.
Reproducible
Provides reproducibility of research experiments for comparisons against state-of-the-art implementations.
Easy Integration
Designed to be compatible with existing efforts and ease of 3rd party integration for various components.
High Quality
Delivering high-quality software with enterprise-grade development, tutorials for getting started and robust validation & documentation.
Goal for this Hackweek
The goal is to learn MONAI and understand the different deploy alternatives.
Resources
Anyone with interest on Medical applications based on Artificial Intelligence and MLOps in general is welcome to join. No previous knowledge is required.
Looking for hackers with the skills:
mlops ml mlflow pytorch artificial-intelligence kubernetes helm containers k3s
This project is part of:
Hack Week 22
Activity
Comments
-
over 1 year ago by jordimassaguerpla | Reply
I was able to deploy "Monai deploy" on a SUSE Rancher k3s cluster successfully!
It took fixing some helm charts plus writing some new ones.
As a result, I created this Pull Request upstream:
https://github.com/Project-MONAI/monai-deploy-workflow-manager/pull/666 .
There you can see there is a README file explaining how to reproduce the setup using k3s, plus the fixed and hew helm charts.
This project is in the early stages and it is very specialized, which has been a great opportunity to learn a lot!
The helm charts that have been contributed will let you deploy orthanc, which you can use to visualize x-rays, mri scans, patient data, .... Then you can "push" this to the monai deploy components that, ultimately, will start a container inside your cluster that will create the prediction. This will usually be a segmentation to help you visualize anomalies, and then this will get back to orthanc for your visualization.
Similar Projects
This project is one of its kind!