This short course will provide an essential introduction to theory and practice for information processing methods in medical imaging and computing. The focus of the module is on the registration and segmentation of medical images, alongside an overview of how biomarkers derived from image processing can be used to test scientific hypotheses or applied in clinical contexts. The lectures will present the theoretical basis of medical image registration, including the essential building blocks of all image registration algorithms. They will also give real-world examples of the practical application of medical image registration, and how best to validate the results. The workshops will give hands-on experience with using and implementing medical image registration algorithms.
Next, we will introduce medical image segmentation. The lectures will cover the motivation behind image segmentation in a biomedical context and discuss several different techniques for image segmentation. The course will also outline how image segmentation can generate imaging biomarkers. The segmentation workshops will provide walk-throughs of different image segmentation techniques.
Objectives
By the end of this course, you should:
- Understand the motivation for and basic components of image registration
- Understand some of the different approaches to segmentation of medical images
- See how these techniques when combined can create measures of key biomarkers from images
Prerequisites
Attendees should have access to a computer with a Mac, Linux, or Windows operating system (not a tablet, Chromebook, etc.). We plan most of the hands on activities to be built on cloud based infrastructure, so there should be minimal computational requirements for your computer. This module assumes some familiarity with medical imaging data and some mathematical concepts (basic linear algebra, calculus, and probability theory). Users must have some initial experience with Python and/or Matlab, such as the Software carpentry course.
Format of course
This will be a 2-3 day course. We do not yet have a date for this course.
