Welcome to AI for 3D medical imaging!

Course map

This course is going to introduce you to building AI algorithms for problems that involve 3D medical images, predominantly those produced by Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) scanners.

In this lesson, we will provide some context, motivation for the content which we decided to include, and discuss the structure for this course.

Course Learning Objectives

These are the learning objective for this course:

• Understand what 3D medical images are, who uses them, and for what purposes
• Perform exploratory data analysis on 3D image datasets in common formats such as DICOM and NIFTI
• Apply popular machine learning algorithms for both classification and segmentation tasks using real-world medical imaging datasets
• Learn to integrate trained models into a clinical imaging environment and troubleshoot your deployments
• Provide input into the algorithm validation process as required for field deployments

We believe that mastering those will help you get oriented in the field, and give you a great boost on the path of developing great AI systems.

Course Concepts

We will be touching upon many concepts throughout this course, that span multiple fields. Here is a diagram that may help you build a mental picture as we dive deeper into these concepts and how they play together.

The dark blue color is used for those concepts which we spend more time on, while gray ones are mentioned and are relevant, but are not discussed in detail.

Some of these may be familiar to you, and some may be new. We will try to provide links at the end of each lesson to help you explore these in further detail.