Subspace Model-Assisted Deep Learning for Improved Image Reconstruction

人工智能 先验概率 迭代重建 计算机科学 深度学习 子空间拓扑 修补 图像复原 模式识别(心理学) 先验与后验 计算机视觉 图像(数学) 图像处理 贝叶斯概率 哲学 认识论
作者
Yue Guan,Yudu Li,Ruihao Liu,Ziyu Meng,Yao Li,Leslie Ying,Yiping P. Du,Zhi‐Pei Liang
出处
期刊:IEEE Transactions on Medical Imaging [Institute of Electrical and Electronics Engineers]
卷期号:42 (12): 3833-3846 被引量:3
标识
DOI:10.1109/tmi.2023.3313421
摘要

Image reconstruction from limited and/or sparse data is known to be an ill-posed problem and a priori information/constraints have played an important role in solving the problem. Early constrained image reconstruction methods utilize image priors based on general image properties such as sparsity, low-rank structures, spatial support bound, etc. Recent deep learning-based reconstruction methods promise to produce even higher quality reconstructions by utilizing more specific image priors learned from training data. However, learning high-dimensional image priors requires huge amounts of training data that are currently not available in medical imaging applications. As a result, deep learning-based reconstructions often suffer from two known practical issues: a) sensitivity to data perturbations (e.g., changes in data sampling scheme), and b) limited generalization capability (e.g., biased reconstruction of lesions). This paper proposes a new method to address these issues. The proposed method synergistically integrates model-based and data-driven learning in three key components. The first component uses the linear vector space framework to capture global dependence of image features; the second exploits a deep network to learn the mapping from a linear vector space to a nonlinear manifold; the third is an unrolling-based deep network that captures local residual features with the aid of a sparsity model. The proposed method has been evaluated with magnetic resonance imaging data, demonstrating improved reconstruction in the presence of data perturbation and/or novel image features. The method may enhance the practical utility of deep learning-based image reconstruction.
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
aa完成签到 ,获得积分10
1秒前
乌云乌云快走开完成签到,获得积分10
1秒前
Unbelievable完成签到,获得积分10
1秒前
5秒前
张教授完成签到 ,获得积分10
6秒前
bob完成签到,获得积分10
9秒前
辛勤谷雪完成签到,获得积分10
13秒前
00完成签到 ,获得积分10
16秒前
嬗变的天秤完成签到,获得积分10
17秒前
lm番茄完成签到,获得积分10
18秒前
Miianlli完成签到 ,获得积分10
18秒前
19秒前
TUTU完成签到,获得积分10
21秒前
swy完成签到,获得积分10
21秒前
夜雨诗意完成签到,获得积分10
21秒前
活力的妙芙完成签到,获得积分10
23秒前
Zlj完成签到 ,获得积分10
23秒前
lm番茄发布了新的文献求助10
24秒前
懒大王完成签到 ,获得积分10
24秒前
自信的高山完成签到,获得积分10
24秒前
吴旭东完成签到,获得积分10
24秒前
hujun完成签到 ,获得积分10
25秒前
糊涂的皮卡丘完成签到 ,获得积分10
26秒前
CometF完成签到 ,获得积分10
26秒前
Mu丶tou完成签到,获得积分10
28秒前
火山暴涨球技完成签到,获得积分10
28秒前
无私诗云完成签到,获得积分10
29秒前
程程完成签到,获得积分10
30秒前
怕孤独的如凡完成签到 ,获得积分10
34秒前
孤独的涵柳完成签到 ,获得积分10
35秒前
36秒前
嘻嘻哈哈啊完成签到 ,获得积分10
36秒前
好好完成签到,获得积分10
36秒前
SOL完成签到,获得积分10
38秒前
cbq完成签到 ,获得积分10
40秒前
千瓦时醒醒完成签到,获得积分10
40秒前
风趣霆完成签到,获得积分10
41秒前
Zhuzhu完成签到 ,获得积分10
41秒前
落叶捎来讯息完成签到 ,获得积分10
42秒前
44秒前
高分求助中
Les Mantodea de Guyane Insecta, Polyneoptera 2500
Technologies supporting mass customization of apparel: A pilot project 450
A Field Guide to the Amphibians and Reptiles of Madagascar - Frank Glaw and Miguel Vences - 3rd Edition 400
Brain and Heart The Triumphs and Struggles of a Pediatric Neurosurgeon 400
Cybersecurity Blueprint – Transitioning to Tech 400
Mixing the elements of mass customisation 400
Периодизация спортивной тренировки. Общая теория и её практическое применение 310
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 3784858
求助须知:如何正确求助?哪些是违规求助? 3330123
关于积分的说明 10244413
捐赠科研通 3045505
什么是DOI,文献DOI怎么找? 1671716
邀请新用户注册赠送积分活动 800627
科研通“疑难数据库(出版商)”最低求助积分说明 759557