无需训练，用新损失函数实现多模态医学图像精准配准。
Search-MIND: Training-Free Multi-Modal Medical Image Registration
- 通过分层粗到精策略与迭代优化实现无训练配准。
- 在CARE Liver和CHAOS数据集上优于传统方法与基线模型。
- 适合需要快速适配新模态的临床医学图像分析场景。
多模态图像配准在精准医疗中至关重要，但面临非线性强度关系和局部最优等挑战。深度学习模型虽可快速推理，却常因未见模态导致泛化能力下降。为此，我们提出Search-MIND，一种无需训练、面向实例的迭代优化配准框架。该方法采用粗到精策略：先进行分层粗配准，再通过可变形精调。引入两种新损失函数：方差加权互信息（VWMI），优先关注有信息量的组织区域，避免背景噪声和均匀区域干扰全局对齐；Search-MIND（S-MIND），通过扩大局部搜索范围，拓宽结构描述符的收敛区域。在CARE Liver 2025与CHAOS Challenge数据集上的评估表明，Search-MIND持续优于经典方法（如ANTs）及基于基础模型的方法（如DINO-reg），在多种模态下表现更稳定。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。