Ferienakademie 2022:
Computational Medical Imaging

Summer school course

• Date: September 18 to 30, 2022
• Location: Sarntal Valley, South Tyrol, Italy

• Instructors:
• PD Dr. Christian Riess (Friedrich-Alexander Universität Erlangen-Nürnberg)
• PD Dr. Tobias Lasser (Technische Universität München)
• Guest lecturer: Melia Fleischmann (LMU Klinikum)

Course description

In this course we will explore computational imaging techniques in the context of medical imaging. This covers the various image processing tasks such as segmentation, registration, detection and classification, as well as tomographic reconstruction. As in many other fields, deep learning techniques have had a tremendous impact in medical imaging, next to, and in combination with, the more classical variational methods.

The course is organized in two parts. In the first part, each participant will give a 30 minute presentation on a selected topic of computational medical imaging. In the second part, the participants will work together to develop a small-scale application of computational imaging in the context of X-ray imaging. We will be building upon existing open source frameworks, using a Python interface.

Link to last year's course.

Course preparation

There will be a joint meeting for preparation on Friday, July 15, 2022, at 15:00 via BBB

Topic selection: list of available presentation topics

• select your three preferred topics (sorted by preference)
• send them by email to Tobias Lasser until July 25, 2022

Course materials

Presentations: (for PDFs see GitLab instance)

1. Iterative Reconstruction
2. Including Prior Information
3. Optical Tomography
4. Optoacoustic Tomography
5. Light Field and Fourier Light Field Microscopy
6. X-ray Phase Contrast Imaging
7. X-ray Dark-field Imaging
8. X-ray Tensor Tomography
9. Spectral X-ray Computed Tomography
10. Generative Adversarial Networks
11. Transformers in Medical Imaging
12. Embedding of Operators
13. Tomographic Image Reconstruction
14. Invertible Neural Networks
15. Saliency Maps
16. Out-of-distribution Detections
17. Adversarial Examples
18. Few Shot Learning