Abstract
Transformer-based image registration methods have achieved notable success, but they still face challenges, such as difficulties in representing both global and local features, the inability of standard convolution operations to focus on key regions, and inefficiencies in restoring global context using the decoder. To address these issues, we extended the Swin-UNet architecture and incorporated dynamic snake convolution (DSConv) into the model, expanding it into three dimensions. This improvement enables the model to better capture spatial information at different scales, enhancing its adaptability to complex anatomical structures and their intricate components. Additionally, multi-scale dense skip connections were introduced to mitigate the spatial information loss caused by downsampling, enhancing the model's ability to capture both global and local features. We also introduced a novel optimization-based weakly supervised strategy, which iteratively refines the deformation field generated during registration, enabling the model to produce more accurate registered images. Building on these innovations, we proposed OSS DSC-STUNet+ (Swin-UNet+ with 3D dynamic snake convolution). Experimental results on the IXI, OASIS, and LPBA40 brain MRI datasets demonstrated up to a 16.3% improvement in Dice coefficient compared to five classical methods. The model exhibits outstanding performance in terms of registration accuracy, efficiency, and feature preservation.