Filters








5 Hits in 3.9 sec

Nonlinear Dipole Inversion (NDI) enables Quantitative Susceptibility Mapping (QSM) without parameter tuning [article]

Daniel Polak, Itthi Chatnuntawech, Jaeyeon Yoon, Siddharth Srinivasan Iyer, Jongho Lee, Peter Bachert, Elfar Adalsteinsson, Kawin Setsompop, Berkin Bilgic
2019 arXiv   pre-print
We propose Nonlinear Dipole Inversion (NDI) for high-quality Quantitative Susceptibility Mapping (QSM) without regularization tuning, while matching the image quality of state-of-the-art reconstruction  ...  This technique adopts the simple gradient descent rule from NDI and learns the network parameters during training, hence requires no additional parameter tuning.  ...  Introduction Quantitative Susceptibility Mapping (QSM) provides exquisite gray/white matter contrast [1] and enables accurate quantification of iron in the brain [2] .  ... 
arXiv:1909.13692v1 fatcat:vmkz4xwmizc3naessutrpid7ua

MoDL-QSM: Model-based Deep Learning for Quantitative Susceptibility Mapping [article]

Ruimin Feng, Jiayi Zhao, He Wang, Baofeng Yang, Jie Feng, Yuting Shi, Ming Zhang, Chunlei Liu, Yuyao Zhang, Jie Zhuang, Hongjiang Wei
2021 arXiv   pre-print
Quantitative susceptibility mapping (QSM) has demonstrated great potential in quantifying tissue susceptibility in various brain diseases.  ...  However, the intrinsic ill-posed inverse problem relating the tissue phase to the underlying susceptibility distribution affects the accuracy for quantifying tissue susceptibility.  ...  Among them, the dipole inversion for estimating the susceptibility map from a local tissue field map is more complicated.  ... 
arXiv:2101.08413v2 fatcat:2pq6zm4l2bfuhisnganstjylii

Learned Proximal Networks for Quantitative Susceptibility Mapping [article]

Kuo-Wei Lai, Manisha Aggarwal, Peter van Zijl, Xu Li, Jeremias Sulam
2020 arXiv   pre-print
Quantitative Susceptibility Mapping (QSM) estimates tissue magnetic susceptibility distributions from Magnetic Resonance (MR) phase measurements by solving an ill-posed dipole inversion problem.  ...  Here, we present a Learned Proximal Convolutional Neural Network (LP-CNN) for solving the ill-posed QSM dipole inversion problem in an iterative proximal gradient descent fashion.  ...  Introduction Quantitative Susceptibility Mapping (QSM) is a Magnetic Resonance Imaging (MRI) technique that aims at mapping tissue magnetic susceptibility from gra-arXiv:2008.05024v1 [eess.IV] 11 Aug 2020  ... 
arXiv:2008.05024v1 fatcat:4yqlab2bk5bdxhd4fnddpllmky

SEPIA - SuscEptibility mapping PIpeline tool for phAse images [article]

Kwok-Shing Chan, José P Marques
2020 bioRxiv   pre-print
Quantitative susceptibility mapping (QSM) is a physics-driven computational technique that has a high sensitivity in quantifying iron deposition based on MRI phase images.  ...  In this paper, we present an open-source processing pipeline tool called SuscEptibility mapping PIpeline tool for phAse images (SEPIA) dedicated to the post-processing of MRI phase images and QSM.  ...  inversion (NDI) method (Polak et al., 2020) .  ... 
doi:10.1101/2020.07.23.217042 fatcat:zckw5dtkbfdg5atuxes3xr5nd4

BUDA-SAGE with self-supervised denoising enables fast, distortion-free, high-resolution T2, T2*, para- and dia-magnetic susceptibility mapping [article]

Zijing Zhang, Long Wang, Jaejin Cho, Congyu Liao, Hyeong-Geol Shin, Xiaozhi Cao, Jongho Lee, Jinmin Xu, Tao Zhang, Huihui Ye, Kawin Setsompop, Huafeng Liu (+1 others)
2021 arXiv   pre-print
Quantitative T2 and T2* maps were obtained using Bloch dictionary matching on the reconstructed echoes. QSM was estimated using nonlinear dipole inversion (NDI) on the gradient echoes.  ...  To rapidly obtain high resolution T2, T2* and quantitative susceptibility mapping (QSM) source separation maps with whole-brain coverage and high geometric fidelity.  ...  Susceptibility maps are estimated using the gradient echoes from the acquisition with nonlinear dipole inversion (NDI) (41) which is based on the nonlinear-MEDI (NMEDI) (42) approach, but magnitude weighting  ... 
arXiv:2108.12587v2 fatcat:rxo3ocng3neabkxj4563rlfcae