Multi-modal deep learning based 3D image registration for osseous anatomies

Multi-modal deep learning based 3D image registration for osseous anatomies

van Ulsen, Hidde (TU Delft Electrical Engineering, Mathematics and Computer Science)

Staring, M. (mentor)
van Stralen, Marijn (mentor)
Reinders, M.J.T. (graduation committee)
Hildebrandt, K.A. (graduation committee)

Delft University of Technology

2022-06-14

Image registration is a fundamental requirement for many medical applications. In recent years, deep learning approaches for registration have shown to be a promising alternative to conventional methods. However, most learning based methods do not consider the different physical properties of various tissues, which can result in unrealistic deformation in anatomical regions where both deformable tissue and rigid bone is present. In this work, we develop and evaluate deep learning methods for intrapatient CT-MR registration while maintaining rigidity of the bones. Unconstrained and locally constrained registration methods are compared in an unsupervised and weakly-supervised setting. The results show that qualitatively and quantitatively accurate registrations can be obtained.

Deep learning
Image registration
Medical imaging

http://resolver.tudelft.nl/uuid:558b77ff-af85-4e6d-8c22-3e15842dcfd0

Student theses

master thesis

© 2022 Hidde van Ulsen