BSS-TFNet: Attention-Enhanced Background Signal Suppression Network for Time-Frequency Spectrum in Magnetic Particle Imaging | |
Wei, Zechen1,2; Liu, Yanjun3,4,5; Zhu, Tao1,2; Yang, Xin1,2; Tian, Jie4,5,6; Hui, Hui1,2 | |
刊名 | IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE |
2023-12-12 | |
页码 | 15 |
关键词 | Magnetic particle imaging deep learning self-attention mechanism time-frequency spectrum background signal |
ISSN号 | 2471-285X |
DOI | 10.1109/TETCI.2023.3337342 |
通讯作者 | Yang, Xin(xin.yang@ia.ac.cn) ; Hui, Hui(hui.hui@ia.ac.cn) |
英文摘要 | Magnetic particle imaging (MPI) is a rapidly developing medical imaging modality, which uses the nonlinear response of superparamagnetic iron oxide nanoparticles to the applied magnetic field to image their spatial distribution. Background signal is the main source of artifacts in MPI, which mainly includes harmonic interference and Gaussian noise. For different sources of noise, the existing methods directly process the time domain signal to achieve signal enhancement or construct system function by frequency domain signal to obtain high-quality reconstructed images. However, due to the randomness and variety of the background signal, the existing methods fail to eliminate all kinds of noise at the same time, especially when the noise is nonlinear. In this work, we proposed a deep learning method adopting self-attention mechanism, which can effectively suppress different levels of harmonic interference and Gaussian noise simultaneously. Our method deals with the two-dimensional time-frequency spectrum acquired by short-time Fourier transform from the temporal signal, learning global features and local features between time and frequency domain through the network, to achieve the purpose of reducing background noise. The performance of our method is analyzed via simulation experiments and imaging experiments performed with an in-house MPI scanner, which shows that our method can effectively suppress background signals and obtain high-quality MPI images. |
资助项目 | National Key Research and Development Program of China |
WOS关键词 | RECONSTRUCTION ; SENSITIVITY ; RESOLUTION ; TRACER |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:001134429900001 |
资助机构 | National Key Research and Development Program of China |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/54868] |
专题 | 自动化研究所_中国科学院分子影像重点实验室 |
通讯作者 | Yang, Xin; Hui, Hui |
作者单位 | 1.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing Key Lab Mol Imaging, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 3.Beihang Univ, Key Lab Big Data Based Precis Med, Minist Ind & Informat Technol Peoples Republ China, Beijing 100190, Peoples R China 4.Beihang Univ, Sch Engn Med, Beijing 100190, Peoples R China 5.Beihang Univ, Sch Biol Sci & Med Engn, Beijing 100190, Peoples R China 6.Beihang Univ, Inst Automat, Minist Ind & Informat Technol Peoples Republ China, Key Lab Big Data Based Precis Med,CAS Key Lab Mol, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Wei, Zechen,Liu, Yanjun,Zhu, Tao,et al. BSS-TFNet: Attention-Enhanced Background Signal Suppression Network for Time-Frequency Spectrum in Magnetic Particle Imaging[J]. IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE,2023:15. |
APA | Wei, Zechen,Liu, Yanjun,Zhu, Tao,Yang, Xin,Tian, Jie,&Hui, Hui.(2023).BSS-TFNet: Attention-Enhanced Background Signal Suppression Network for Time-Frequency Spectrum in Magnetic Particle Imaging.IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE,15. |
MLA | Wei, Zechen,et al."BSS-TFNet: Attention-Enhanced Background Signal Suppression Network for Time-Frequency Spectrum in Magnetic Particle Imaging".IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE (2023):15. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论