SemiMAR: Semi-Supervised Learning for CT Metal Artifact Reduction

计算机科学 人工智能 深度学习 工件(错误) 发电机(电路理论) 监督学习 还原(数学) 模式识别(心理学) 半监督学习 特征(语言学) 领域(数学分析) 机器学习 计算机视觉 人工神经网络 功率(物理) 数学分析 语言学 物理 几何学 数学 哲学 量子力学
作者
Tao Wang,Hui Yu,Zhiwen Wang,Hu Chen,Yan Liu,Jingfeng Lu,Yi Zhang
出处
期刊:IEEE Journal of Biomedical and Health Informatics [Institute of Electrical and Electronics Engineers]
卷期号:27 (11): 5369-5380 被引量:3
标识
DOI:10.1109/jbhi.2023.3312292
摘要

Metal artifacts lead to CT imaging quality degradation. With the success of deep learning (DL) in medical imaging, a number of DL-based supervised methods have been developed for metal artifact reduction (MAR). Nonetheless, fully-supervised MAR methods based on simulated data do not perform well on clinical data due to the domain gap. Although this problem can be avoided in an unsupervised way to a certain degree, severe artifacts cannot be well suppressed in clinical practice. Recently, semi-supervised metal artifact reduction (MAR) methods have gained wide attention due to their ability in narrowing the domain gap and improving MAR performance in clinical data. However, these methods typically require large model sizes, posing challenges for optimization. To address this issue, we propose a novel semi-supervised MAR framework. In our framework, only the artifact-free parts are learned, and the artifacts are inferred by subtracting these clean parts from the metal-corrupted CT images. Our approach leverages a single generator to execute all complex transformations, thereby reducing the model's scale and preventing overlap between clean part and artifacts. To recover more tissue details, we distill the knowledge from the advanced dual-domain MAR network into our model in both image domain and latent feature space. The latent space constraint is achieved via contrastive learning. We also evaluate the impact of different generator architectures by investigating several mainstream deep learning-based MAR backbones. Our experiments demonstrate that the proposed method competes favorably with several state-of-the-art semi-supervised MAR techniques in both qualitative and quantitative aspects.
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
刚刚
科目三应助健忘惜萱采纳,获得10
1秒前
4秒前
无花果应助一颗苹果采纳,获得10
4秒前
4秒前
结实的青荷完成签到,获得积分10
5秒前
尊敬惜儿发布了新的文献求助10
7秒前
8秒前
现代的慕青完成签到,获得积分10
9秒前
Owen应助科研通管家采纳,获得20
9秒前
小二郎应助科研通管家采纳,获得10
10秒前
清爽电脑应助科研通管家采纳,获得10
10秒前
科研通AI2S应助科研通管家采纳,获得10
10秒前
10秒前
丘比特应助吃鱼的猫采纳,获得10
11秒前
11秒前
愉快太清完成签到,获得积分10
12秒前
丘比特应助无情的玉米采纳,获得10
13秒前
15秒前
16秒前
LIUJIAWEI完成签到,获得积分10
16秒前
每天都在找完成签到,获得积分10
17秒前
伶俐从筠发布了新的文献求助10
18秒前
大模型应助陶1122采纳,获得10
18秒前
20秒前
20秒前
21秒前
顾矜应助忆修采纳,获得10
21秒前
吃鱼的猫发布了新的文献求助10
22秒前
知行合一发布了新的文献求助150
23秒前
25秒前
Arizaq发布了新的文献求助10
26秒前
胡霖完成签到,获得积分10
28秒前
g3618发布了新的文献求助10
28秒前
奋斗忆南发布了新的文献求助10
29秒前
32秒前
愉快太清发布了新的文献求助10
32秒前
33秒前
Arizaq完成签到,获得积分10
33秒前
36秒前
高分求助中
The Mother of All Tableaux Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 2400
Ophthalmic Equipment Market by Devices(surgical: vitreorentinal,IOLs,OVDs,contact lens,RGP lens,backflush,diagnostic&monitoring:OCT,actorefractor,keratometer,tonometer,ophthalmoscpe,OVD), End User,Buying Criteria-Global Forecast to2029 2000
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Cognitive Neuroscience: The Biology of the Mind (Sixth Edition) 1000
Optimal Transport: A Comprehensive Introduction to Modeling, Analysis, Simulation, Applications 800
Official Methods of Analysis of AOAC INTERNATIONAL 600
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 3959210
求助须知:如何正确求助?哪些是违规求助? 3505538
关于积分的说明 11124306
捐赠科研通 3237248
什么是DOI,文献DOI怎么找? 1789010
邀请新用户注册赠送积分活动 871512
科研通“疑难数据库(出版商)”最低求助积分说明 802824