Mamba? Catch The Hype Or Rethink What Really Helps for Image Registration
This work addresses the issue of overhyped methods in image registration for medical imaging researchers, highlighting incremental improvements and the need for better evaluation.
The paper tackles the problem of image registration by showing that using advanced computational elements does not significantly improve accuracy, while registration-specific designs yield only a marginal 1.5% improvement over the baseline.
Our findings indicate that adopting "advanced" computational elements fails to significantly improve registration accuracy. Instead, well-established registration-specific designs offer fair improvements, enhancing results by a marginal 1.5\% over the baseline. Our findings emphasize the importance of rigorous, unbiased evaluation and contribution disentanglement of all low- and high-level registration components, rather than simply following the computer vision trends with "more advanced" computational blocks. We advocate for simpler yet effective solutions and novel evaluation metrics that go beyond conventional registration accuracy, warranting further research across diverse organs and modalities. The code is available at \url{https://github.com/BailiangJ/rethink-reg}.