基于Transformer的多尺度可变形三维医学图像配准  

Multi-scale Deformable 3D Medical Image Registration Based on Transformer

作　　者：陈璐莹 喻国荣 鲍海洲 边小勇[1,2] 陈聪鹏 CHEN Lu-Ying;YU Guo-Rong;BAO Hai-Zhou;BIAN Xiao-Yong;CHEN Cong-Peng(School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430081,China;Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System,Wuhan University of Science and Technology,Wuhan 430081,China)

机构地区：[1]武汉科技大学计算机科学与技术学院,武汉430081 [2]武汉科技大学智能信息处理与实时工业系统湖北省重点实验室,武汉430081

出　　处：《计算机系统应用》2025年第1期47-57,共11页Computer Systems & Applications

基　　金：湖北省教育厅青年人才项目(Q20221108)。

摘　　要：由于人体器官的不规则形变,可变形三维医学图像配准仍然是医学图像处理中的难题.针对该问题,本文提出了一种基于Transformer的多尺度可变形三维医学图像配准方法.该方法首先采用多尺度策略来实现多层次的连接,以捕捉不同层次的信息.通过自注意力机制提取全局特征,并利用膨胀卷积捕获更广泛的上下文信息和更细节的局部特征,从而增强配准网络对全局和局部特征的融合能力.其次,本文根据图像梯度的稀疏性先验,引入了归一化总梯度作为损失函数,有效减少了噪声和伪影对配准过程的干扰,更好地适应不同模态的医学图像.在公开的脑MRI数据集(OASIS和LPBA)上评估本文所提方法的性能.综合结果表明,该方法不仅能保持基于学习的方法在运行时间上的优势,还在均方误差和结构相似性等指标上表现出较高的性能.此外,消融实验的结果进一步证明了本文所提方法和归一化总梯度损失函数设计的有效性.Deformable 3D medical image registration remains challenging due to irregular deformations of human organs.This study proposes a multi-scale deformable 3D medical image registration method based on Transformer.Firstly,the method adopts a multi-scale strategy to realize multi-level connections to capture different levels of information.Selfattention mechanism is employed to extract global features,and dilated convolution is used to capture broader context information and more detailed local features,so as to enhance the registration network’s fusion capacity for global and local features.Secondly,according to the sparse prior of the image gradient,the normalized total gradient is introduced as a loss function,effectively reducing the interference of noise and artifacts on the registration process,and better adapting to different modes of medical images.The performance of the proposed method is evaluated on publicly available brain MRI datasets(OASIS and LPBA).The results show that the proposed method can not only maintain the advantages of the learning-based method in run-time but also well performs in mean square error and structural similarity.In addition,ablation experiment results further prove the validity of the method and normalized total gradient loss function design proposed in this study.

关 键 词：医学图像 图像配准 TRANSFORMER 多尺度 可变形 

分 类 号：R318[医药卫生—生物医学工程] TP391.41[医药卫生—基础医学]