Master's Thesis in Medical Imaging: Keypoint Correspondence-Based Medical Image Registration

11.03.2025, Diplomarbeiten, Bachelor- und Masterarbeiten

A thesis at the Chair for Computational Imaging and AI in Medicine (Prof. Dr. Julia Schnabel)

Lesion tracking and image registration (finding the deformation between two images) are fundamental tasks in clinical practice for the diagnosis and monitoring of diseases. For this, establishing correct point correspondences between multiple images is essential.
Recent research in computer vision explores the use of advanced DL models for keypoint learning and matching in the context of various downstream tasks, including object detection, tracking, image editing, and classification, as well as the fusion of high-level semantic and low-level geometric features.

This thesis aims to explore the transfer of classical and DL-based keypoint detection and matching techniques from computer vision to medical image registration.
In particular, the student will
(i) perform literature research on the topic,
(ii) explore SOTA correspondence matching techniques in the context of medical images, and
(iii) develop new techniques for specific tasks on multimodal images, e.g., MR and CT.
The project can be adapted to the student’s interests and background.

Requirements
• Prior practical experience with and good understanding of machine learning/deep learning,
• Very good programming skills in Python (including PyTorch),
• Independent work style and excellent communication skills,
• Interest in medical imaging and the development of novel algorithmic methods.

The start date, ideally, is March/April 2025.
The thesis is offered by the Chair for Computational Imaging and AI in Medicine (Prof. Dr. Julia Schnabel) and supervised by Anna Reithmeir and Dr. Daniel Lang.

Contact: If interested, please send your transcripts and a short motivation to anna.reithmeir@tum.de and lang@helmholtz-munich.de.

Kontakt: anna.reithmeir@tum.de, lang@helmholtz-munich.de