Practical MONAI

Integrating AI Into Research, Processes, and Products Involving Medical Imaging

This is an intensive course intended to give clinicians, biomedical researchers, and medical industry professionals practical knowledge to help them determine how to incorporate medical image AI into their practice, research, processes, and products.   Special emphasis is placed on MONAI, the freely available, open-source platform for medical image AI research and product development.   Software coding skills are not required, but we will be reviewing the software structure of AI training systems as well as exploring no-code solutions.

Target Audience

 Including but not limited to:

• Medical and public health professionals, faculty, and students
• Biomedical engineering and biological science professionals, faculty, and students
• Entrepreneurs, established business leaders, and project managers wanting to incorporate medical images into their products and processes

Objectives

• Strengths and weaknesses of the state of the art in medical image AI
• The role of MONAI, public data collections, and cloud computing in medical image AI R&D
• Open-source tools for annotating medical images and training AI systems, without coding
• Methods for understanding the basis of AI decisions, i.e., explainable AI
• Options for deploying medical image AI systems into clinical workflows

Prerequisites

• Experience with medical images and their role in clinical decisions.
• Familiarity with image processing software. For example, experience using clinical workstations or related software such as Osirix or 3D Slicer, or experience using photo editing applications such as Adobe Photoshop or related applications.
• Python script writing experience is a bonus. It is not required, with the majority of the course focusing on existing tools rather than coding.

Agenda

This course is approximately 8 hours, which can be divided into 2 sessions.