High-Throughput Deep Unfolding Network for Compressive Sensing MRI

计算机科学 可解释性 压缩传感 水准点(测量) 瓶颈 信息瓶颈法 吞吐量 算法 频道(广播) 人工智能 数学优化 数学 相互信息 计算机网络 大地测量学 嵌入式系统 地理 电信 无线
作者
Jian Zhang,Zhenyu Zhang,Jingfen Xie,Yongbing Zhang
出处
期刊:IEEE Journal of Selected Topics in Signal Processing [Institute of Electrical and Electronics Engineers]
卷期号:16 (4): 750-761 被引量:16
标识
DOI:10.1109/jstsp.2022.3170227
摘要

Deep unfolding network (DUN) has become the mainstream for compressive sensing MRI (CS-MRI) due to its good interpretability and high performance. Different optimization algorithms are usually unfolded into deep networks with different architectures, in which one iteration corresponds to one stage of DUN. However, there are few works discussing the following two questions: Which optimization algorithm is better after being unfolded into a DUN? What are the bottlenecks in existing DUNs? This paper attempts to answer these questions and give a feasible solution. For the first question, our mathematical and empirical analysis verifies the similarity of DUNs unfolded by alternating minimization (AM), alternating iterative shrinkage-thresholding algorithm (ISTA) and alternating direction method of multipliers (ADMM). For the second question, we point out that one major bottleneck of existing DUNs is that the input and output of each stage are just images of one channel, which greatly limits the transmission of network information. To break the information bottleneck, this paper proposes a novel, simple yet powerful high-throughput deep unfolding network (HiTDUN), which is not constrained by any optimization algorithm and can transmit multi-channel information between adjacent network stages. The developed multi-channel fusion strategy can also be easily incorporated into existing DUNs to further boost their performance. Extensive CS-MRI experiments on three benchmark datasets demonstrate that the proposed HiTDUN outperforms existing state-of-the-art DUNs by large margins while maintaining fast computational speed. 1 For reproducible research, the source codes and training models of our HiTDUN. [Online]. Available: https://github.com/jianzhangcs/HiTDUN.
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
哈哈哈啊完成签到,获得积分10
刚刚
JuliaWang完成签到 ,获得积分10
1秒前
xin完成签到,获得积分10
1秒前
无花果应助ttttt采纳,获得10
2秒前
科研通AI5应助Ma采纳,获得10
2秒前
苏烟完成签到 ,获得积分10
4秒前
huche完成签到,获得积分10
4秒前
HonS完成签到,获得积分10
5秒前
5秒前
幽默白晴完成签到,获得积分10
6秒前
冷酷丹翠完成签到 ,获得积分10
6秒前
格格巫完成签到 ,获得积分10
7秒前
7秒前
毅力鸟完成签到,获得积分10
8秒前
爱吃巧克力的克里克完成签到,获得积分10
8秒前
发酒疯很方便吃完成签到,获得积分10
8秒前
郭mm发布了新的文献求助10
8秒前
AteeqBaloch完成签到,获得积分10
8秒前
ttttt完成签到,获得积分20
9秒前
科研达人完成签到,获得积分10
9秒前
亲情之友完成签到,获得积分10
9秒前
xubcay完成签到,获得积分10
9秒前
10秒前
Dsivan完成签到,获得积分10
10秒前
junzilan完成签到,获得积分10
10秒前
想把太阳揣兜里完成签到,获得积分10
11秒前
成就映秋完成签到,获得积分10
11秒前
伍六七完成签到,获得积分10
11秒前
mayi完成签到,获得积分10
12秒前
CipherSage应助zzzkyt采纳,获得10
12秒前
某某某完成签到,获得积分10
12秒前
DD完成签到,获得积分10
12秒前
chinbaor完成签到,获得积分10
12秒前
Dsivan发布了新的文献求助10
12秒前
pragmatic完成签到,获得积分10
12秒前
chen完成签到 ,获得积分10
12秒前
隐形的乐枫完成签到,获得积分10
13秒前
甜美白昼完成签到,获得积分10
13秒前
山野村夫完成签到,获得积分10
13秒前
叶宇豪完成签到,获得积分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
Immigrant Incorporation in East Asian Democracies 600
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 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 3968603
求助须知:如何正确求助?哪些是违规求助? 3513420
关于积分的说明 11168029
捐赠科研通 3248900
什么是DOI,文献DOI怎么找? 1794540
邀请新用户注册赠送积分活动 875187
科研通“疑难数据库(出版商)”最低求助积分说明 804676