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

Source: [Search-MIND: Training-Free Multi-Modal Medical Image Registration](<https://www.sota2.com/research/paper/69ddca077d0172140ec79969>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-15T05:00:04.591Z

Authors: Boya Wang, Ruizhe Li, Chao Chen, Xin Chen

Published: 2026-04-10T00:42:24.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Registration on CHAOS Same-Patient](<https://www.sota2.com/research/sota/image-registration-on-chaos-same-patient.md>): Image Registration; CHAOS Same-Patient; DSC: 71.8.

- [Image Registration on CHAOS Cross-Patient](<https://www.sota2.com/research/sota/image-registration-on-chaos-cross-patient.md>): Image Registration; CHAOS Cross-Patient; DSC: 65.6.

- [Image Registration on CARE T1](<https://www.sota2.com/research/sota/image-registration-on-care-t1.md>): Image Registration; CARE T1; DSC: 92.

- [Image Registration on CARE T2](<https://www.sota2.com/research/sota/image-registration-on-care-t2.md>): Image Registration; CARE T2; DSC: 76.1.

- [Image Registration on CARE DWI](<https://www.sota2.com/research/sota/image-registration-on-care-dwi.md>): Image Registration; CARE DWI; DSC: 79.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.09743>)

[PDF](<https://arxiv.org/pdf/2604.09743.pdf>)
