Unsupervised Domain Adaptation for EM Image Denoising with Invertible Networks

人工智能 图像去噪 计算机科学 可逆矩阵 图像(数学) 降噪 模式识别(心理学) 适应(眼睛) 计算机视觉 领域(数学分析) 域适应 数学 数学分析 物理 分类器(UML) 纯数学 光学
作者
Shiyu Deng,Yinda Chen,Wei Huang,Ruobing Zhang,Zhiwei Xiong
出处
期刊:IEEE Transactions on Medical Imaging [Institute of Electrical and Electronics Engineers]
卷期号:: 1-1
标识
DOI:10.1109/tmi.2024.3431192
摘要

Electron microscopy (EM) image denoising is critical for visualization and subsequent analysis. Despite the remarkable achievements of deep learning-based non-blind denoising methods, their performance drops significantly when domain shifts exist between the training and testing data. To address this issue, unpaired blind denoising methods have been proposed. However, these methods heavily rely on image-to-image translation and neglect the inherent characteristics of EM images, limiting their overall denoising performance. In this paper, we propose the first unsupervised domain adaptive EM image denoising method, which is grounded in the observation that EM images from similar samples share common content characteristics. Specifically, we first disentangle the content representations and the noise components from noisy images and establish a shared domain-agnostic content space via domain alignment to bridge the synthetic images (source domain) and the real images (target domain). To ensure precise domain alignment, we further incorporate domain regularization by enforcing that: the pseudo-noisy images, reconstructed using both content representations and noise components, accurately capture the characteristics of the noisy images from which the noise components originate, all while maintaining semantic consistency with the noisy images from which the content representations originate. To guarantee lossless representation decomposition and image reconstruction, we introduce disentanglement-reconstruction invertible networks. Finally, the reconstructed pseudo-noisy images, paired with their corresponding clean counterparts, serve as valuable training data for the denoising network. Extensive experiments on synthetic and real EM datasets demonstrate the superiority of our method in terms of image restoration quality and downstream neuron segmentation accuracy. Our code is publicly available at https://github.com/sydeng99/DADn.
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
qiqi完成签到,获得积分10
刚刚
肖肖发布了新的文献求助10
刚刚
JUdy发布了新的文献求助10
刚刚
自己完成签到,获得积分10
1秒前
常芹完成签到,获得积分10
1秒前
kkmedici关注了科研通微信公众号
1秒前
爱听歌的树叶完成签到,获得积分10
2秒前
3秒前
不宁不令完成签到,获得积分10
4秒前
圆滚滚完成签到,获得积分10
5秒前
6秒前
唐_完成签到,获得积分10
7秒前
桐桐应助彳亍而行采纳,获得10
7秒前
8秒前
qiqi发布了新的文献求助10
8秒前
9秒前
JUdy完成签到,获得积分10
10秒前
lll完成签到,获得积分10
11秒前
11秒前
11秒前
小艾完成签到,获得积分10
12秒前
英姑应助含糊采纳,获得10
12秒前
柒月小鱼完成签到 ,获得积分10
12秒前
奋斗雁山发布了新的文献求助10
12秒前
12秒前
13秒前
这样很OK发布了新的文献求助10
13秒前
tay完成签到,获得积分20
16秒前
韦谷兰发布了新的文献求助10
17秒前
QQQ发布了新的文献求助10
17秒前
Bio应助哈哈采纳,获得30
17秒前
18秒前
18秒前
kkmedici发布了新的文献求助30
18秒前
叮咚完成签到,获得积分10
19秒前
不想完成签到,获得积分10
19秒前
这样很OK完成签到,获得积分10
20秒前
GXWFDC完成签到,获得积分10
20秒前
西瓜汁完成签到,获得积分10
20秒前
Lisa完成签到,获得积分20
21秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3988838
求助须知:如何正确求助?哪些是违规求助? 3531250
关于积分的说明 11252914
捐赠科研通 3269838
什么是DOI,文献DOI怎么找? 1804820
邀请新用户注册赠送积分活动 881943
科研通“疑难数据库(出版商)”最低求助积分说明 809028