IMJENSE: Scan-specific Implicit Representation for Joint Coil Sensitivity and Image Estimation in Parallel MRI

doi:10.1109/TMI.2023.3342156

	IMJENSE: Scan-specific Implicit Representation for Joint Coil Sensitivity and Image Estimation in Parallel MRI
	Feng, Ruimin 1; Wu, Qing2 ; Feng, Jie 1; She, Huajun 1; Liu, Chunlei 3; Zhang, Yuyao2 ; Wei, Hongjiang 1
	2023
发表期刊	IEEE TRANSACTIONS ON MEDICAL IMAGING
ISSN	1558-254X
EISSN	1558-254X
卷号	PP 期号:99 页码:1539-1553
发表状态	已发表
DOI	10.1109/TMI.2023.3342156
摘要	Parallel imaging is a commonly used technique to accelerate magnetic resonance imaging (MRI) data acquisition. Mathematically, parallel MRI reconstruction can be formulated as an inverse problem relating the sparsely sampled k-space measurements to the desired MRI image. Despite the success of many existing reconstruction algorithms, it remains a challenge to reliably reconstruct a high-quality image from highly reduced k-space measurements. Recently, implicit neural representation has emerged as a powerful paradigm to exploit the internal information and the physics of partially acquired data to generate the desired object. In this study, we introduced IMJENSE, a scan-specific implicit neural representation-based method for improving parallel MRI reconstruction. Specifically, the underlying MRI image and coil sensitivities were modeled as continuous functions of spatial coordinates, parameterized by neural networks and polynomials, respectively. The weights in the networks and coefficients in the polynomials were simultaneously learned directly from sparsely acquired k-space measurements, without fully sampled ground truth data for training. Benefiting from the powerful continuous representation and joint estimation of the MRI image and coil sensitivities, IMJENSE outperforms conventional image or k-space domain reconstruction algorithms. With extremely limited calibration data, IMJENSE is more stable than supervised calibrationless and calibration-based deep-learning methods. Results show that IMJENSE robustly reconstructs the images acquired at 5× and 6× accelerations with only 4 or 8 calibration lines in 2D Cartesian acquisitions, corresponding to 22.0% and 19.5% undersampling rates. The high-quality results and scanning specificity make the proposed method hold the potential for further accelerating the data acquisition of parallel MRI. © 1982-2012 IEEE.
关键词	implicit neural representation MRI acceleration neural networks parallel imaging scan-specific
URL	查看原文
收录类别	EI
语种	英语
出版者	Institute of Electrical and Electronics Engineers Inc.
EI入藏号	20235115239587
EI主题词	Magnetic resonance imaging
EI分类号	461.4 Ergonomics and Human Factors Engineering ; 701.2 Magnetism: Basic Concepts and Phenomena ; 716.1 Information Theory and Signal Processing ; 723.2 Data Processing and Image Processing ; 746 Imaging Techniques
原始文献类型	Journal article (JA)
来源库	IEEE
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/347967
专题	信息科学与技术学院信息科学与技术学院_本科生信息科学与技术学院_博士生信息科学与技术学院_PI研究组_张玉瑶组
通讯作者	Wei, Hongjiang
作者单位	1.School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China; 2.School of Information Science and Technology, ShanghaiTech University, Shanghai, China; 3.Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA
推荐引用方式 GB/T 7714	Feng, Ruimin,Wu, Qing,Feng, Jie,et al. IMJENSE: Scan-specific Implicit Representation for Joint Coil Sensitivity and Image Estimation in Parallel MRI[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING,2023,PP(99):1539-1553.
APA	Feng, Ruimin.,Wu, Qing.,Feng, Jie.,She, Huajun.,Liu, Chunlei.,...&Wei, Hongjiang.(2023).IMJENSE: Scan-specific Implicit Representation for Joint Coil Sensitivity and Image Estimation in Parallel MRI.IEEE TRANSACTIONS ON MEDICAL IMAGING,PP(99),1539-1553.
MLA	Feng, Ruimin,et al."IMJENSE: Scan-specific Implicit Representation for Joint Coil Sensitivity and Image Estimation in Parallel MRI".IEEE TRANSACTIONS ON MEDICAL IMAGING PP.99(2023):1539-1553.