局部特征增强的磁共振图像Transformer重构  

MRI reconstruction based on Transformer with local feature enhancement

作　　者：熊承义[1,2] 陈文旗 高志荣[3] 马帅 李帆 XIONG Chengyi;CHEN Wenqi;GAO Zhirong;MA Shuai;LI Fan(South-Central Minzu University,College of Electronic and Information Engineering,Wuhan 430074,China;South-Central Minzu University,Hubei Key Lab of Intelligent Wireless Communication,Wuhan 430074,China;South-Central Minzu University,College of Computer Science,Wuhan 430074,China)

机构地区：[1]中南民族大学电子信息工程学院,武汉430074 [2]中南民族大学智能无线通信湖北省重点实验室,武汉430074 [3]中南民族大学计算机科学学院,武汉430074

出　　处：《中南民族大学学报（自然科学版）》2025年第1期50-57,共8页Journal of South-Central Minzu University(Natural Science Edition)

基　　金：多谱信息处理技术国家重点实验室基金资助项目(6142113210303);中央高校基本科研业务专项资金资助项目(CZY21013);中南民族大学研究生课程示范课程资助项目(YJS22039)。

摘　　要：研究了一种基于多头自注意力与卷积特征融合的磁共振图像Transformer重构方法.采用U型网络结构,通过学习图像的多尺度特征以提升重构性能.采用深度分离卷积与多头自注意力融合的Swin Transformer结构,改善网络的特征学习能力.在CC359-Brain数据集下基于多种采样模式进行仿真实验,结果证明了该方法在提升磁共振图像重构质量与降低系统复杂度方面的有效性.A Transformer reconstruction method of Magnetic Resonance Image(MRI)based on multi-head self-attention and convolution feature fusion is studied.The U-shaped network structure is adopted to improve the reconstruction performance by learning the multi-scale features of the image.The Swin Transformer structure of deep separation convolution and multi-head self-attention fusion is adopted to improve the feature learning ability of the network.Simulation experiments based on multiple sampling modes are carried out under CC359 Brain dataset,and the results show that the proposed method is effective in improving the quality of MRI reconstruction and reducing the system complexity.

关 键 词：磁共振成像 卷积神经网络 变换器 深度学习 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]