RWKVMatch: Vision RWKV-based Multi-scale Feature Matching Network for Unsupervised Deformable Medical Image Registration

Abstract

Medical image registration is essential for integrating information from diverse imaging modalities for clinical diagnosis and treatment planning. Despite significant advancements, achieving efficient and precise deformable image registration remains a formidable challenge. In this study, we propose a novel medical image registration model, RWKVMatch, which employs global attention and cross-fusion mechanism based on the Vision-RWKV module to address complex deformations in medical images effectively. Additionally, the elastic transformation from data augmentation techniques is integrated into the model architecture to enhance its capability to handle multi-scale features and improve robustness to geometric variations in image registration. Experimental evaluations on two medical image registration datasets indicate the effectiveness of our approach, surpassing existing state-of-the-art methods in terms of registration accuracy and computational efficiency. These findings underscore the potential of RWKVMatch as a highly effective tool for medical image registration.