Deformable Medical Image Registration (DMIR) aims to establish precise anatomical alignment of multiple medical images. However, the existing U-shape networks encounter difficulties in efficiently transferring multi-scale feature information from the encoder to the decoder. To address this issue, we propose a novel backbone network called MFCTrans, which constructs effective feature connection in DMIR. Drawing inspiration from the attention mechanism observed in the human cognitive system, our proposed method employs a Feature Fusion and Assignment Transformer (FFAT) module and a Spatial Cross Attention Fusion (SCAF) module. The former facilitates the fusion of multi-channel features, while the latter guides the integration of multi-scale information. A Multiple Residual (MR) branch is also deployed between the encoder and FFAT to improve the network’s generalization. We conduct extensive qualitative and quantitative evaluations on the OASIS and LPBA40 datasets. The proposed method achieves higher Dice scores than Transmorph by 1.3% and 2.0% on the respective datasets while maintaining a comparable voxel folding percentage. Ablation studies analyze the impacts and efficiency of each component in the proposed method. In summary, our proposed network offers a promising framework for achieving high-quality medical image registration and holds significant potential for applications in computer vision and cognitive computation.

可变形医学图像配准（DMIR）旨在建立多个医学图像的精确解剖对齐。然而，现有的 U 形网络在有效地将多尺度特征信息从编码器传输到解码器方面遇到困难。为了解决这个问题，我们提出了一种称为 MFCTrans 的新型骨干网络，它在 DMIR 中构建有效的特征连接。受人类认知系统中观察到的注意力机制的启发，我们提出的方法采用了特征融合和分配转换器（FFAT）模块和空间交叉注意力融合（SCAF）模块。前者有利于多通道特征的融合，后者引导多尺度信息的融合。编码器和 FFAT 之间还部署了多重残差 (MR) 分支，以提高网络的泛化能力。我们对 OASIS 和 LPBA40 数据集进行了广泛的定性和定量评估。所提出的方法在各自的数据集上实现了比 Transmorph 高 1.3% 和 2.0% 的 Dice 分数，同时保持了可比的体素折叠百分比。消融研究分析了所提出方法中每个组成部分的影响和效率。总之，我们提出的网络为实现高质量医学图像配准提供了一个有前景的框架，并在计算机视觉和认知计算方面具有巨大的应用潜力。