CASIA OpenIR  > 中国科学院分子影像重点实验室
DERnet: a deep neural network for end-to-end reconstruction in magnetic particle imaging
Peng, Zhengyao1,2,3; Yin, Lin1,2,3; Sun, Zewen1,2,3; Liang, Qian1,2,3; Ma, Xiaopeng4; An, Yu1,3,5,6; Tian, Jie1,3,5,6; Du, Yang1,2,3
Source PublicationPHYSICS IN MEDICINE AND BIOLOGY
ISSN0031-9155
2024-01-07
Volume69Issue:1Pages:15
Abstract

Objective. Magnetic particle imaging (MPI) shows potential for contributing to biomedical research and clinical practice. However, MPI images are effectively affected by noise in the signal as its reconstruction is an ill-posed inverse problem. Thus, effective reconstruction method is required to reduce the impact of the noise while mapping signals to MPI images. Traditional methods rely on the hand-crafted data-consistency (DC) term and regularization term based on spatial priors to achieve noise-reducing and reconstruction. While these methods alleviate the ill-posedness and reduce noise effects, they may be difficult to fully capture spatial features. Approach. In this study, we propose a deep neural network for end-to-end reconstruction (DERnet) in MPI that emulates the DC term and regularization term using the feature mapping subnetwork and post-processing subnetwork, respectively, but in a data-driven manner. By doing so, DERnet can better capture signal and spatial features without relying on hand-crafted priors and strategies, thereby effectively reducing noise interference and achieving superior reconstruction quality. Main results. Our data-driven method outperforms the state-of-the-art algorithms with an improvement of 0.9-8.8 dB in terms of peak signal-to-noise ratio under various noise levels. The result demonstrates the advantages of our approach in suppressing noise interference. Furthermore, DERnet can be employed for measured data reconstruction with improved fidelity and reduced noise. In conclusion, our proposed method offers performance benefits in reducing noise interference and enhancing reconstruction quality by effectively capturing signal and spatial features. Significance. DERnet is a promising candidate method to improve MPI reconstruction performance and facilitate its more in-depth biomedical application.

Keywordmagnetic particle imaging end-to-end reconstruction deep learning image reconstruction
DOI10.1088/1361-6560/ad13cf
WOS KeywordTRACER ; NANOPARTICLE
Indexed BySCI
Language英语
Funding ProjectBeijing Municipal Natural Science Foundation https://doi.org/10.13039/501100005089[62027901] ; Beijing Municipal Natural Science Foundation https://doi.org/10.13039/501100005089[82272111] ; Beijing Municipal Natural Science Foundation https://doi.org/10.13039/501100005089[92159303] ; Beijing Municipal Natural Science Foundation https://doi.org/10.13039/501100005089[81871514] ; Beijing Municipal Natural Science Foundation https://doi.org/10.13039/501100005089[61901472,62201570] ; Beijing Municipal Natural Science Foundation https://doi.org/10.13039/501100005089[82230067] ; National Natural Science Foundation of China[7212207] ; National Natural Science Foundation of China[4332058] ; Beijing Natural Science Foundation
Funding OrganizationBeijing Municipal Natural Science Foundation https://doi.org/10.13039/501100005089 ; National Natural Science Foundation of China ; Beijing Natural Science Foundation
WOS Research AreaEngineering ; Radiology, Nuclear Medicine & Medical Imaging
WOS SubjectEngineering, Biomedical ; Radiology, Nuclear Medicine & Medical Imaging
WOS IDWOS:001128968900001
PublisherIOP Publishing Ltd
Sub direction classification医学影像处理与分析
planning direction of the national heavy laboratoryAI For Science
Paper associated data
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/54992
Collection中国科学院分子影像重点实验室
Corresponding AuthorAn, Yu; Tian, Jie; Du, Yang
Affiliation1.Inst Automat, CAS Key Lab Mol Imaging, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
3.Beijing Key Lab Mol Imaging, Beijing, Peoples R China
4.Shandong Univ, Sch Control Sci & Engn, Jinan, Shandon, Peoples R China
5.Beihang Univ, Key Lab Big Data Based Precis Med, Minist Ind & Informat Technol, Beijing, Peoples R China
6.Beihang Univ, Sch Engn Med, Beijing, Peoples R China
Recommended Citation
GB/T 7714
Peng, Zhengyao,Yin, Lin,Sun, Zewen,et al. DERnet: a deep neural network for end-to-end reconstruction in magnetic particle imaging[J]. PHYSICS IN MEDICINE AND BIOLOGY,2024,69(1):15.
APA Peng, Zhengyao.,Yin, Lin.,Sun, Zewen.,Liang, Qian.,Ma, Xiaopeng.,...&Du, Yang.(2024).DERnet: a deep neural network for end-to-end reconstruction in magnetic particle imaging.PHYSICS IN MEDICINE AND BIOLOGY,69(1),15.
MLA Peng, Zhengyao,et al."DERnet: a deep neural network for end-to-end reconstruction in magnetic particle imaging".PHYSICS IN MEDICINE AND BIOLOGY 69.1(2024):15.
Files in This Item: Download All
File Name/Size DocType Version Access License
DERnet A Deep Neural(1035KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Peng, Zhengyao]'s Articles
[Yin, Lin]'s Articles
[Sun, Zewen]'s Articles
Baidu academic
Similar articles in Baidu academic
[Peng, Zhengyao]'s Articles
[Yin, Lin]'s Articles
[Sun, Zewen]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Peng, Zhengyao]'s Articles
[Yin, Lin]'s Articles
[Sun, Zewen]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: DERnet A Deep Neural Network for End-to-end Reconstruction in Magnetic Particle Imaging.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.