Iterative Temporal-spatial Transformer-based Cardiac T1 Mapping MRI Reconstruction

计算机科学 变压器 人工智能 计算机视觉 物理 电压 量子力学
作者
Jun Lyu,Guangming Wang,M. Shamim Hossain
出处
期刊:ACM Transactions on Multimedia Computing, Communications, and Applications [Association for Computing Machinery]
卷期号:20 (6): 1-18 被引量:3
标识
DOI:10.1145/3643640
摘要

The precise reconstruction of accelerated magnetic resonance imaging (MRI) brings about notable advantages, such as enhanced diagnostic precision and decreased examination costs. In contrast, traditional cardiac MRI necessitates repetitive acquisitions across multiple heartbeats, resulting in prolonged acquisition times. Significant strides have been made in accelerating MRI through deep learning-based reconstruction methods. However, these existing methods encounter certain limitations: (1) The intricate nature of heart reconstruction involving multiple complex time-series data poses a challenge in exploring nonlinear dependencies between temporal contexts. (2) Existing research often overlooks weight sharing in iterative frameworks, impeding the effective capturing of non-local information and, consequently, limiting improvements in model performance. In order to improve cardiac MRI reconstruction, we propose a novel temporal-spatial transformer with a strategy in this study. Based on the multi-level encoder and decoder transformer architecture, we conduct multi-level spatiotemporal information feature aggregation over several adjacent views, that create nonlinear dependencies among features and efficiently learn important information among adjacent cardiac temporal frames. Additionally, in order to improve contextual awareness between neighboring views, we add cross-view attention for temporal information fusion. Furthermore, we introduce an iterative strategy for training weights during the reconstruction process, which improves feature fusion in critical locations and reduces the number of computations required to calculate global feature dependencies. Extensive experiments have demonstrated the substantial superiority of this procedure over the most advanced techniques, suggesting that it has broad potential for clinical use.
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
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
丘比特应助公瑾采纳,获得10
1秒前
小女完成签到,获得积分10
2秒前
Owen应助亲亲亲采纳,获得10
3秒前
友好紊发布了新的文献求助10
3秒前
Lucas应助沉静的大侠采纳,获得10
4秒前
Ava应助王359采纳,获得10
5秒前
日出发布了新的文献求助10
7秒前
8秒前
乐乐应助日出采纳,获得10
10秒前
研友_n0QYAZ完成签到 ,获得积分10
10秒前
英俊的铭应助友好紊采纳,获得10
13秒前
哈哈学习学习噢完成签到,获得积分10
14秒前
14秒前
弯弯完成签到 ,获得积分10
15秒前
缪尔岚完成签到,获得积分10
16秒前
共享精神应助何YI采纳,获得10
17秒前
亲亲亲完成签到,获得积分10
18秒前
张玉关注了科研通微信公众号
19秒前
科研通AI5应助zhangliangliang采纳,获得10
25秒前
27秒前
27秒前
28秒前
31秒前
搜集达人应助辰小七采纳,获得10
33秒前
33秒前
277777发布了新的文献求助10
34秒前
bkagyin应助LL采纳,获得10
34秒前
何YI发布了新的文献求助10
34秒前
35秒前
36秒前
刘琪发布了新的文献求助10
36秒前
Guanpgt发布了新的文献求助10
38秒前
38秒前
火火火木完成签到 ,获得积分10
39秒前
亲亲亲发布了新的文献求助10
40秒前
40秒前
40秒前
所所应助ChenY采纳,获得30
41秒前
41秒前
ZHI发布了新的文献求助10
42秒前
高分求助中
【此为提示信息,请勿应助】请按要求发布求助,避免被关 20000
Production Logging: Theoretical and Interpretive Elements 3000
CRC Handbook of Chemistry and Physics 104th edition 1000
Density Functional Theory: A Practical Introduction, 2nd Edition 840
J'AI COMBATTU POUR MAO // ANNA WANG 660
Izeltabart tapatansine - AdisInsight 600
Gay and Lesbian Asia 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 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3757592
求助须知:如何正确求助?哪些是违规求助? 3300765
关于积分的说明 10115053
捐赠科研通 3015238
什么是DOI,文献DOI怎么找? 1655911
邀请新用户注册赠送积分活动 790145
科研通“疑难数据库(出版商)”最低求助积分说明 753611