Master Seminar - Medical Image Registration (IN2107, IN4462)

Time: Wednesday 10-12 a.m.

Location: Garching (in-person)

Image registration is the process of aligning two or more images, and crucial for many image analysis pipelines. This seminar will cover selected material of image registration for medical imaging. Basic problem formulations to recent advances in the field will be discussed. This includes, but is not limited to:

• Learning and non-learning based image registration
• Optimization techniques
• Image registration for multi-modal data
• Multi-resolution and regularization strategies
• Linear and non-linear deformations
• Supervised and unsupervised learning
• Clinical applications

Requirements:

• Background in image processing and machine learning
• Interest in medical image analysis

Goal and organization:

The participating students will learn the fundamental concepts of image registration. They will acquire the skills to analyze critically state-of-the-art research work and to define own research questions. Basic concepts will be introduced with an overview of different research topics. The participants will select a research paper (suggestions given by the lecturers) and independently work on it with a final oral presentation and a written report. Presentations of members of international research groups will provide the students with insights into state-of-the-art research in the field.

Please register via the TUM matching system: https://matching.in.tum.de or write an email to anna.reithmeir@tum.de.

The seminar will take place Wednesdays from 10 a.m. to 12.a.m. in Garching.