Cui Xinxin, Zhou Yuee, Wei Caihong, Suo Guodong, Jin Fengqing, Yang Jianlan
School of Medical Information Engineering, Gansu University of Traditional Chinese Medicine, Lanzhou, Gansu, 730000, China.
Quanzhou Orthopedic Traumatological Hospital of Fujian University of Traditional Chinese Medicine, Quanzhou, 362000, Fujian, China.
Sci Rep. 2025 May 5;15(1):15707. doi: 10.1038/s41598-025-00403-w.
In recent years, the pyramid-based encoder-decoder network architecture has become a popular solution to the problem of large deformation image registration due to its excellent multi-scale deformation field prediction ability. However, there are two main limitations in existing research: one is that it over-focuses on the fusion of multi-layer deformation sub-fields on the decoding path, while ignoring the impact of feature encoders on network performance; the other is the lack of specialized design for the characteristics of feature maps at different scales. To this end, we propose an innovative hybrid Transformer and convolution iteratively optimized pyramid network for large deformation brain image registration. Specifically, four encoder variants are designed to study the impact of different structures on the performance of the pyramid registration network. Secondly, the Swin-Transformer module is combined with the convolution iterative strategy, and each layer of the decoder is carefully designed according to the semantic information characteristics of different decoding layers. Extensive experimental results on three public brain magnetic resonance imaging datasets show that our method has the highest registration accuracy compared with 9 cutting-edge registration methods, which fully verifies the effectiveness and application potential of our model design.
近年来，基于金字塔的编码器-解码器网络架构因其出色的多尺度变形场预测能力，已成为解决大变形图像配准问题的一种流行方案。然而，现有研究存在两个主要局限性：一是过度关注解码路径上多层变形子场的融合，而忽略了特征编码器对网络性能的影响；另一个是缺乏针对不同尺度特征图特性的专门设计。为此，我们提出了一种创新的混合Transformer与卷积迭代优化金字塔网络，用于大变形脑图像配准。具体而言，设计了四种编码器变体来研究不同结构对金字塔配准网络性能的影响。其次，将Swin-Transformer模块与卷积迭代策略相结合，并根据不同解码层的语义信息特征对解码器的每一层进行精心设计。在三个公开的脑磁共振成像数据集上的大量实验结果表明，与9种前沿配准方法相比，我们的方法具有最高的配准精度，充分验证了我们模型设计的有效性和应用潜力。
