Synopsis:
Artificial Intelligence (AI) has been proven to support radiologist clinical decision-making, and help reduce doctor burnout. To apply AI in medical imaging diagnosis, we need vast amount of annotated medical images to develop a supervised AI model. Annotating medical images accurately is an important procedure. However, it is tedious, time consuming, and demands costly, specialty-oriented skills which are not easily accessible. AI Assisted Annotation (AIAA) has been developed to largely reduce the manual process.
In this workshop, we will present an AWS solution by running MONAI label on Amazon Elastic Compute Cloud (Amazon EC2) with autoscaling - which has been mounted to the same Amazon Elastic File System (Amazon EFS) volume shared with Amazon Sagemaker notebook instances. Through the common file sharing, clinicians and data scientists can collaborate on the same data sets through different tools, and use Amazon AppStream to stream a desktop platform, and name 3D slider for interactive medical image annotation.
Key Learning Objectives:
- Deploy AWS infrastructure for AIAA of medical image using MONAI Label
- Conduct AIAA on medical images in an interactive manner with 3D slider
- Build deep learning model in Amazon SageMaker, and deploy the model to enhance annotation performance
- AI developers with varying levels of development experience.
- Service developers can use ExeML to quickly build AI application without coding.
- Beginners can directly use built-in algorithms to build AI applications.
- AI engineers can use multiple development environments to quickly compile code for modeling and application development.
