Learning-based single-step quantitative susceptibility mapping reconstruction without brain extraction
Wei, Hongjiang1; Cao, Steven2; Zhang, Yuyao3; Guan, Xiaojun4; Yan, Fuhua5; Yeom, Kristen W.6; Liu, Chunlei2,7
2019-11-15
Source PublicationNEUROIMAGE
ISSN1053-8119
Volume202
DOI10.1016/j.neuroimage.2019.116064
AbstractQuantitative susceptibility mapping (QSM) estimates the underlying tissue magnetic susceptibility from MRI gradient-echo phase signal and typically requires several processing steps. These steps involve phase unwrapping, brain volume extraction, background phase removal and solving an ill-posed inverse problem relating the tissue phase to the underlying susceptibility distribution. The resulting susceptibility map is known to suffer from inaccuracy near the edges of the brain tissues, in part due to imperfect brain extraction, edge erosion of the brain tissue and the lack of phase measurement outside the brain. This inaccuracy has thus hindered the application of QSM for measuring susceptibility of tissues near the brain edges, e.g., quantifying cortical layers and generating superficial venography. To address these challenges, we propose a learning-based QSM reconstruction method that directly estimates the magnetic susceptibility from total phase images without the need for brain extraction and background phase removal, referred to as autoQSM. The neural network has a modified U-net structure and is trained using QSM maps computed by a two-step QSM method. 209 healthy subjects with ages ranging from 11 to 82 years were employed for patch-wise network training. The network was validated on data dissimilar to the training data, e.g., in vivo mouse brain data and brains with lesions, which suggests that the network generalized and learned the underlying mathematical relationship between magnetic field perturbation and magnetic susceptibility. Quantitative and qualitative comparisons were performed between autoQSM and other two-step QSM methods. AutoQSM was able to recover magnetic susceptibility of anatomical structures near the edges of the brain including the veins covering the cortical surface, spinal cord and nerve tracts near the mouse brain boundaries. The advantages of high-quality maps, no need for brain volume extraction, and high reconstruction speed demonstrate autoQSM's potential for future applications.
KeywordMRI Magnetic resonance imaging QSM Quantitative susceptibility mapping Deep learning Neural network
URL查看原文
Indexed BySCI
Language英语
Funding ProjectNational Institutes of Health[NIMH R01MH096979] ; National Institutes of Health[U01EB025162]
WOS Research AreaNeurosciences & Neurology ; Radiology, Nuclear Medicine & Medical Imaging
WOS SubjectNeurosciences ; Neuroimaging ; Radiology, Nuclear Medicine & Medical Imaging
WOS IDWOS:000491861000063
PublisherACADEMIC PRESS INC ELSEVIER SCIENCE
EISSN1095-9572
WOS KeywordENABLED DIPOLE INVERSION ; ZERO-ECHO-TIME ; WHITE-MATTER ; IN-VIVO ; NEURAL-NETWORKS ; MRI ; IMAGE ; MULTIPLE ; CONTRAST ; FIELD
Original Document TypeArticle
Citation statistics
Cited Times [WOS]:0   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://kms.shanghaitech.edu.cn/handle/2MSLDSTB/80512
Collection信息科学与技术学院_PI研究组_张玉瑶组
Corresponding AuthorWei, Hongjiang; Liu, Chunlei
Affiliation1.Shanghai Jiao Tong Univ, Sch Biomed Engn, Inst Med Imaging Technol, Shanghai, Peoples R China
2.Univ Calif Berkeley, Dept Elect Engn & Comp Sci, 505 Cory Hall, Berkeley, CA 94720 USA
3.ShanghaiTech Univ, Sch Informat & Sci & Technol, Shanghai, Peoples R China
4.Zhejiang Univ, Affiliated Hosp 2, Dept Radiol, Sch Med, Hangzhou, Zhejiang, Peoples R China
5.Shanghai Jiao Tong Univ, Rui Jin Hosp, Sch Med, Dept Radiol, Shanghai, Peoples R China
6.Stanford Univ, Lucile Packard Childrens Hosp, Dept Radiol, Palo Alto, CA USA
7.Univ Calif Berkeley, Helen Wills Neurosci Inst, 505 Cory Hall, Berkeley, CA 94720 USA
Recommended Citation
GB/T 7714
Wei, Hongjiang,Cao, Steven,Zhang, Yuyao,et al. Learning-based single-step quantitative susceptibility mapping reconstruction without brain extraction[J]. NEUROIMAGE,2019,202.
APA Wei, Hongjiang.,Cao, Steven.,Zhang, Yuyao.,Guan, Xiaojun.,Yan, Fuhua.,...&Liu, Chunlei.(2019).Learning-based single-step quantitative susceptibility mapping reconstruction without brain extraction.NEUROIMAGE,202.
MLA Wei, Hongjiang,et al."Learning-based single-step quantitative susceptibility mapping reconstruction without brain extraction".NEUROIMAGE 202(2019).
Files in This Item: Download All
File Name/Size DocType Version Access License
10.1016@j.neuroimage(19245KB)期刊论文未知开放获取UnknownView Download
Related Services
Usage statistics
Scholar Google
Similar articles in Scholar Google
[Wei, Hongjiang]'s Articles
[Cao, Steven]'s Articles
[Zhang, Yuyao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wei, Hongjiang]'s Articles
[Cao, Steven]'s Articles
[Zhang, Yuyao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wei, Hongjiang]'s Articles
[Cao, Steven]'s Articles
[Zhang, Yuyao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 10.1016@j.neuroimage.2019.116064.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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