AWS and NVIDIA build applications and solutions to make healthcare more accessible, affordable and efficient by accelerating cloud connectivity of enterprise imaging. MONAI (Medical Open Network for Artificial Intelligence) is a framework for building and deploying medical AI that is offered as either open-source or as a part of the NVIDIA AI Enterprise software suite. It has three key modules to support medical AI development: MONAI Label, MONAI Core, and MONAI Deploy. AWS HealthImaging (AHI) is a HIPAA-eligible, highly scalable, performant, and cost effective medical imagery store. We have developed an AWS HealthImaging python client as MONAI Deploy connector to integrate medical imaging AI applications with sub-second image retrieval latencies at scale powered by cloud-native APIs. The MONAI AI models and applications can be hosted on Amazon SageMaker, which is a fully managed service to deploy Machine Learning (ML) models at scale. Amazon SageMaker takes care of setting up and managing instances for model training and inference and provides built-in metrics and logs for endpoints that you can use to monitor and receive alerts. It also offers a variety of NVIDIA GPU instances for ML training and inference, as well as multiple model deployment options with automatic scaling, including real-time inference, serverless inference, asynchronous inference and batch transform.
Here is the architecture diagram, showing how MONAI Application Package (MAP) can be deployed on Amazon SageMaker managed inference endpoints and make inference predictions on the medical images from AHI:
Here is the architecture diagram, showing how to retreive medical images from AHI and use MONAI Core to train model on Amazon SageMaker:
Where the DICOM headers can be indexed and searched through Amazon Glue and Amazon Athena
-
Use AWS Account with one of the following AWS regions, where AWS HealthImaging is available: North Virginia (us-east-1), Oregon (us-west-2), Ireland (eu-west-1), and Sydney (ap-southeast-2)
-
Download the CloudFormation tempalte and deploy the template to create Amazon SageMaker Domain and necessary Amazon IAM roles
- Launch SageMaker Studio application.
- Enable JupyterLab v3 extension and install ‘Imjoy-jupyter-extension' if you want to visualize medical images on SageMaker notebook interactively using itkwidgets:
This library is licensed under the MIT-0 License. See the LICENSE file.