FDGANet: Frequency dynamic graph attention network for undersampled MRI reconstruction

首页 > 成果 > 详情

认领

导出

Link by DOI

反馈

作者信息关键词期刊信息基础信息归属信息摘要

成果类型：

期刊论文

作者：

Xie, Yushan;Xiong, Dongping;Zhao, Heng;Zhou, Hong;Ling, Bingo Wing-Kuen;...

通讯作者：

Zhang, XZ

作者机构：

[Zhang, XZ; Zhang, Xiaozhi; Xie, Yushan] Univ South China, Sch Elect Engn, Hengyang 421001, Peoples R China.

[Xiong, Dongping] Univ South China, Sch Comp Software, Hengyang 421001, Peoples R China.

[Zhao, Heng; Zhou, Hong] Univ South China, Dept Radiol, Affiliated Hosp 1, Hengyang 421001, Peoples R China.

[Ling, Bingo Wing-Kuen] Guangdong Univ Technol, Sch Informat Engn, Guangzhou 510006, Peoples R China.

[Zhang, XZ; Zhang, Xiaozhi] Univ South China, Hunan Prov Key Lab Multiom & Artificial Intelligen, Key Lab Hunan Prov Major Brain Dis, Hengyang 421001, Peoples R China.

通讯机构：

[Zhang, XZ ] U

Univ South China, Sch Elect Engn, Hengyang 421001, Peoples R China.

Univ South China, Hunan Prov Key Lab Multiom & Artificial Intelligen, Key Lab Hunan Prov Major Brain Dis, Hengyang 421001, Peoples R China.

语种：

英文

关键词：

Undersampled MRI reconstruction;Wavelet transform;Dynamic graph attention;Non-local self-similarity

期刊：

Biomedical Signal Processing and Control

ISSN：

1746-8094

年：

2025

卷：

108

页码：

107933

DOI：

10.1016/j.bspc.2025.107933

基金类别：

National Natural Science Foundation of China [62071213]; Open Project Program of Hunan Provincial Key Laboratory of Multi-omics And Artificial Intelligence of Cardiovascular Diseases [2023TP1047]; Key Research and Development Projects of Hunan Province [2020SK51826]; Clinical Research 4310 Program of the First Affiliated Hospital of University of South China [20224310NHYCG03]

机构署名：

本校为第一且通讯机构

院系归属：

电气工程学院

摘要：

Undersampled magnetic resonance imaging (MRI) aims at reconstructing high-quanlity MR images from undersampled measurements, which plays a crucial role for accelerated MRI. Deep learning methods have shown great superiority in undersampled MRI. However, most of these approaches reconstruct MR images in the image domain, ignoring frequency characteristics. This leads to conflicting information between different frequencies, making it difficult to reconstruct a clearly structured image. In this work, we present a novel wavelet domain based dynamic graph attention network, called FDGANet, for und...

反馈

产权有误：本人成果被他人认领

数据有误：数据基本信息有误

归属有误：成果的院系归属、机构署名归属有误

其他原因：

验证码：

看不清楚，换一个

确定

取消

成果认领

标题：

用户	作者	通讯作者	--
	请选择	请选择	--

确定

取消

FDGANet: Frequency dynamic graph attention network for undersampled MRI reconstruction

反馈

成果认领

提示

该栏目需要登录且有访问权限才可以访问