PuSH - Publication Server of Helmholtz Zentrum München

Kogl, F. ; Reithmeir, A. ; Sideri-Lampretsa, V.* ; Machado, I.* ; Braren, R.* ; Rueckert, D.* ; Schnabel, J.A. ; Zimmer, V.A.*

General vision encoder features as guidance in medical image registration.

In: (Biomedical Image Registration). Berlin [u.a.]: Springer, 2024. 265-279 (Lect. Notes Comput. Sc. ; 15249 LNCS)
DOI
General vision encoders like DINOv2 and SAM have recently transformed computer vision. Even though they are trained on natural images, such encoder models have excelled in medical imaging, e.g., in classification, segmentation, and registration. However, no in-depth comparison of different state-of-the-art general vision encoders for medical registration is available. In this work, we investigate how well general vision encoder features can be used in the dissimilarity metrics for medical image registration. We explore two encoders that were trained on natural images as well as one that was fine-tuned on medical data. We apply the features within the well-established B-spline FFD registration framework. In extensive experiments on cardiac cine MRI data, we find that using features as additional guidance for conventional metrics improves the registration quality. The code is available at github.com/compai-lab/2024-miccai-koegl.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Conference contribution
Corresponding Author
Keywords Feature-based Distance Measures ; Foundation Models
ISSN (print) / ISBN 0302-9743
e-ISSN 1611-3349
Conference Title Biomedical Image Registration
Journal Lecture Notes in Computer Science
Quellenangaben Volume: 15249 LNCS, Issue: , Pages: 265-279 Article Number: , Supplement: ,
Publisher Springer
Publishing Place Berlin [u.a.]
Non-patent literature Publications
Institute(s) Institute for Machine Learning in Biomed Imaging (IML)