Pyramid Attention Network for Medical Image Registration
This work addresses the challenge of capturing spatial relationships in medical image registration for applications like brain and abdominal MRI, representing an incremental improvement over existing deep-learning methods.
The paper tackles the problem of large-deformation medical image registration by proposing a pyramid attention network (PAN) that combines a dual-stream pyramid encoder with channel-wise attention and a multi-head local attention Transformer decoder, achieving favorable performance and outperforming CNN-based and Transformer-based networks on brain and abdominal MRI datasets.
The advent of deep-learning-based registration networks has addressed the time-consuming challenge in traditional iterative methods.However, the potential of current registration networks for comprehensively capturing spatial relationships has not been fully explored, leading to inadequate performance in large-deformation image registration.The pure convolutional neural networks (CNNs) neglect feature enhancement, while current Transformer-based networks are susceptible to information redundancy.To alleviate these issues, we propose a pyramid attention network (PAN) for deformable medical image registration.Specifically, the proposed PAN incorporates a dual-stream pyramid encoder with channel-wise attention to boost the feature representation.Moreover, a multi-head local attention Transformer is introduced as decoder to analyze motion patterns and generate deformation fields.Extensive experiments on two public brain magnetic resonance imaging (MRI) datasets and one abdominal MRI dataset demonstrate that our method achieves favorable registration performance, while outperforming several CNN-based and Transformer-based registration networks.Our code is publicly available at https://github.com/JuliusWang-7/PAN.