Search-MIND: Training-Free Multi-Modal Medical Image Registration
For medical image registration tasks, Search-MIND provides a training-free solution that avoids generalization collapse on unseen modalities, addressing a key limitation of deep learning methods.
Search-MIND is a training-free, iterative optimization framework for multi-modal medical image registration that uses a coarse-to-fine strategy with two novel loss functions (VWMI and S-MIND). It outperforms classical baselines like ANTs and foundation model-based approaches like DINO-reg on CARE Liver 2025 and CHAOS Challenge datasets, offering superior stability across diverse modalities.
Multi-modal image registration plays a critical role in precision medicine but faces challenges from non-linear intensity relationships and local optima. While deep learning models enable rapid inference, they often suffer from generalization collapse on unseen modalities. To address this, we propose Search-MIND, a training-free, iterative optimization framework for instance-specific registration. Our pipeline utilizes a coarse-to-fine strategy: a hierarchical coarse alignment stage followed by deformable refinement. We introduce two novel loss functions: Variance-Weighted Mutual Information (VWMI), which prioritizes informative tissue regions to shield global alignment from background noise and uniform regions, and Search-MIND (S-MIND), which broadens the convergence basin of structural descriptors by considering larger local search range. Evaluations on CARE Liver 2025 and CHAOS Challenge datasets show that Search-MIND consistently outperforms classical baselines like ANTs and foundation model-based approaches like DINO-reg, offering superior stability across diverse modalities.