Search-MIND: Training-Free Multi-Modal Medical Image Registration

TL;DR

Search-MIND is a training-free, iterative framework for multi-modal medical image registration that improves accuracy and robustness by using novel loss functions and a hierarchical optimization strategy.

Contribution

It introduces a training-free, instance-specific registration method with new loss functions, enhancing stability and performance over classical and foundation model approaches.

Findings

Outperforms classical baselines like ANTs in accuracy.

Achieves superior stability across diverse modalities.

Demonstrates effectiveness on CARE Liver 2025 and CHAOS datasets.

Abstract

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.