{"ID":2834628,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.01913","arxiv_id":"2512.01913","title":"Disentangling Progress in Medical Image Registration: Beyond Trend-Driven Architectures towards Domain-Specific Strategies","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 $\\sim3\\%$. All models and experiments are released within a transparent, modular benchmark that enables plug-and-play comparison for new architectures and registration tasks (https://github.com/BailiangJ/rethink-reg). 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.","short_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-specifi...","url_abs":"https://arxiv.org/abs/2512.01913","url_pdf":"https://arxiv.org/pdf/2512.01913v1","authors":"[\"Bailiang Jian\",\"Jiazhen Pan\",\"Rohit Jena\",\"Morteza Ghahremani\",\"Hongwei Bran Li\",\"Daniel Rueckert\",\"Christian Wachinger\",\"Benedikt Wiestler\"]","published":"2025-12-01T17:30:43Z","proceeding":"eess.IV","tasks":"[\"eess.IV\",\"cs.CV\"]","methods":"[\"Transformer\",\"Generative Adversarial Network\",\"Convolutional Neural Network\"]","has_code":false,"code_links":[{"ID":606429,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2834628,"paper_url":"https://arxiv.org/abs/2512.01913","paper_title":"Disentangling Progress in Medical Image Registration: Beyond Trend-Driven Architectures towards Domain-Specific Strategies","repo_url":"https://github.com/BailiangJ/rethink-reg","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}