Efficient Large-Deformation Medical Image Registration via Recurrent Dynamic Correlation

2025-10-25

AI Summary

Medical image registration faces challenges in modeling large deformations and capturing long-range voxel correspondences. To address these issues, this paper proposes a recursive dynamic correlation registration framework. Methodologically, it introduces local correlation feature computation coupled with a recurrent dynamic search mechanism, incorporates a memory-augmented lightweight recurrent update module, and decouples motion and texture features to achieve efficient, low-redundancy voxel-level matching. Its key innovation lies in recursively adjusting the matching receptive field to jointly optimize global deformation modeling and local alignment accuracy. Evaluated on OASIS (non-affine), brain MRI, and abdominal CT datasets, the method achieves state-of-the-art performance: it reduces FLOPs by 90.5% and inference time by 96% compared to RDP, while simultaneously improving registration accuracy.

Technology Category

• Computer Vision: Motion & Tracking
• Search and Optimization: Learning to Search
• Machine Learning: Multimodal Learning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Deformable image registration estimates voxel-wise correspondences between images through spatial transformations, and plays a key role in medical imaging. While deep learning methods have significantly reduced runtime, efficiently handling large deformations remains a challenging task. Convolutional networks aggregate local features but lack direct modeling of voxel correspondences, promoting recent works to explore explicit feature matching. Among them, voxel-to-region matching is more efficient for direct correspondence modeling by computing local correlation features whithin neighbourhoods, while region-to-region matching incurs higher redundancy due to excessive correlation pairs across large regions. However, the inherent locality of voxel-to-region matching hinders the capture of long-range correspondences required for large deformations. To address this, we propose a Recurrent Correlation-based framework that dynamically relocates the matching region toward more promising positions. At each step, local matching is performed with low cost, and the estimated offset guides the next search region, supporting efficient convergence toward large deformations. In addition, we uses a lightweight recurrent update module with memory capacity and decouples motion-related and texture features to suppress semantic redundancy. We conduct extensive experiments on brain MRI and abdominal CT datasets under two settings: with and without affine pre-registration. Results show that our method exibits a strong accuracy-computation trade-off, surpassing or matching the state-of-the-art performance. For example, it achieves comparable performance on the non-affine OASIS dataset, while using only 9.5% of the FLOPs and running 96% faster than RDP, a representative high-performing method.

Problem

• Addressing large deformation challenges in medical image registration
• Improving voxel correspondence modeling beyond local feature limitations
• Enhancing efficiency and accuracy trade-off in deformation estimation

Innovation

• Dynamic relocation of matching regions for large deformations
• Lightweight recurrent module with memory and feature decoupling
• Efficient convergence with low-cost local matching steps