Disentangling Progress in Medical Image Registration: Beyond Trend-Driven Architectures Towards Domain-Specific Strategies

MCML Authors

Bailiang Jian

→ Group Christian Wachinger
 Artificial Intelligence in Medical Imaging

Morteza Ghahremani

Dr.

→ Group Christian Wachinger
 Artificial Intelligence in Medical Imaging

Daniel Rückert

Prof. Dr.

Director

Artificial Intelligence in Healthcare and Medicine

Christian Wachinger

Prof. Dr.

Principal Investigator

Artificial Intelligence in Medical Imaging

Benedikt Wiestler

Prof. Dr.

Principal Investigator

AI for Image-Guided Diagnosis and Therapy

Abstract

Medical image registration drives quantitative analysis across organs, modalities, and patient populations. Recent deep learning methods often combine low-level 'trend-driven' computational blocks from computer vision, such as large-kernel CNNs, Transformers, and state-space models, with high-level registration-specific designs like motion pyramids, correlation layers, and iterative refinement. Yet, their relative contributions remain unclear and entangled. This raises a central question: should future advances in registration focus on importing generic architectural trends or on refining domain-specific design principles? Through a modular framework spanning brain, lung, cardiac, and abdominal registration, we systematically disentangle the influence of these two paradigms. Our evaluation reveals that low-level 'trend-driven' computational blocks offer only marginal or inconsistent gains, while high-level registration-specific designs consistently deliver more accurate, smoother, and more robust deformations. These domain priors significantly elevate the performance of a standard U-Net baseline, far more than variants incorporating 'trend-driven' blocks, achieving an average relative improvement of ∼3%. All models and experiments are released within a transparent, modular benchmark that enables plug-and-play comparison for new architectures and registration tasks (this https URL). This dynamic and extensible platform establishes a common ground for reproducible and fair evaluation, inviting the community to isolate genuine methodological contributions from domain priors. Our findings advocate a shift in research emphasis: from following architectural trends to embracing domain-specific design principles as the true drivers of progress in learning-based medical image registration.

misc JPJ+25

Preprint

Authors

Links

Research Area

 C1 | Medicine