Analysis of deep complex‐valued convolutional neural networks for MRI reconstruction and phase‐focused applications

卷积神经网络 计算机科学 卷积(计算机科学) 人工智能 深度学习 模式识别(心理学) 相似性(几何) 相(物质) 复杂网络 建筑 算法 网络体系结构 人工神经网络 图像(数学) 物理 量子力学 万维网 艺术 计算机安全 视觉艺术
作者
Elizabeth K. Cole,Joseph Y. Cheng,John M. Pauly,Shreyas Vasanawala
出处
期刊:Magnetic Resonance in Medicine [Wiley]
卷期号:86 (2): 1093-1109 被引量:100
标识
DOI:10.1002/mrm.28733
摘要

Purpose Deep learning has had success with MRI reconstruction, but previously published works use real‐valued networks. The few works which have tried complex‐valued networks have not fully assessed their impact on phase. Therefore, the purpose of this work is to fully investigate end‐to‐end complex‐valued convolutional neural networks (CNNs) for accelerated MRI reconstruction and in several phase‐based applications in comparison to 2‐channel real‐valued networks. Methods Several complex‐valued activation functions for MRI reconstruction were implemented, and their performance was compared. Complex‐valued convolution was implemented and tested on an unrolled network architecture and a U‐Net–based architecture over a wide range of network widths and depths with knee, body, and phase‐contrast datasets. Results Quantitative and qualitative results demonstrated that complex‐valued CNNs with complex‐valued convolutions provided superior reconstructions compared to real‐valued convolutions with the same number of trainable parameters for both an unrolled network architecture and a U‐Net–based architecture, and for 3 different datasets. Complex‐valued CNNs consistently had superior normalized RMS error, structural similarity index, and peak SNR compared to real‐valued CNNs. Conclusion Complex‐valued CNNs can enable superior accelerated MRI reconstruction and phase‐based applications such as fat–water separation, and flow quantification compared to real‐valued convolutional neural networks.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
风登楼发布了新的文献求助10
刚刚
左丘曼冬完成签到,获得积分10
1秒前
小罗黑的发布了新的文献求助10
2秒前
2秒前
香蕉觅云应助asbefore采纳,获得10
2秒前
Danboard发布了新的文献求助10
2秒前
2秒前
zzjjyy完成签到,获得积分10
3秒前
3秒前
鸢梓尔发布了新的文献求助10
3秒前
4秒前
4秒前
4秒前
Unfair完成签到,获得积分10
4秒前
Savannah发布了新的文献求助10
5秒前
高大梦琪发布了新的文献求助10
5秒前
在水一方应助王倩采纳,获得10
6秒前
hala安胖胖完成签到,获得积分10
6秒前
6秒前
天天快乐应助多情的飞绿采纳,获得10
6秒前
顾矜应助非凡梦采纳,获得10
6秒前
7秒前
i羽翼深蓝i完成签到,获得积分10
7秒前
Yolo发布了新的文献求助10
8秒前
赘婿应助专一的映容采纳,获得10
8秒前
123发布了新的文献求助10
9秒前
ting发布了新的文献求助10
9秒前
听南发布了新的文献求助10
9秒前
9秒前
Allen224完成签到,获得积分10
10秒前
咲韶完成签到,获得积分10
10秒前
舒适香露发布了新的文献求助10
10秒前
鸡蛋灌饼完成签到,获得积分10
10秒前
11秒前
11秒前
辣比小欣完成签到,获得积分10
11秒前
乔er一完成签到,获得积分10
11秒前
memo完成签到,获得积分10
12秒前
Danboard完成签到,获得积分20
13秒前
1111发布了新的文献求助10
13秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3970240
求助须知:如何正确求助?哪些是违规求助? 3514997
关于积分的说明 11176725
捐赠科研通 3250268
什么是DOI,文献DOI怎么找? 1795244
邀请新用户注册赠送积分活动 875725
科研通“疑难数据库(出版商)”最低求助积分说明 805004