Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020134826 - PARALLEL MAGNETIC RESONANCE IMAGING METHOD AND RELATED EQUIPMENT

Publication Number WO/2020/134826
Publication Date 02.07.2020
International Application No. PCT/CN2019/121508
International Filing Date 28.11.2019
IPC
G01R 33/56 2006.01
GPHYSICS
01MEASURING; TESTING
RMEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
33Arrangements or instruments for measuring magnetic variables
20involving magnetic resonance
44using nuclear magnetic resonance
48NMR imaging systems
54Signal processing systems, e.g. using pulse sequences
56Image enhancement or correction, e.g. subtraction or averaging techniques
CPC
G01R 33/56
GPHYSICS
01MEASURING; TESTING
RMEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
33Arrangements or instruments for measuring magnetic variables
20involving magnetic resonance
44using nuclear magnetic resonance [NMR]
48NMR imaging systems
54Signal processing systems, e.g. using pulse sequences ; , Generation or control of pulse sequences
56Image enhancement or correction, e.g. subtraction or averaging techniques ; , e.g. improvement of signal-to-noise ratio and resolution
G01R 33/5608
GPHYSICS
01MEASURING; TESTING
RMEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
33Arrangements or instruments for measuring magnetic variables
20involving magnetic resonance
44using nuclear magnetic resonance [NMR]
48NMR imaging systems
54Signal processing systems, e.g. using pulse sequences ; , Generation or control of pulse sequences
56Image enhancement or correction, e.g. subtraction or averaging techniques ; , e.g. improvement of signal-to-noise ratio and resolution
5608Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels
G06N 3/04
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G06N 3/084
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
084Back-propagation
Applicants
  • 深圳先进技术研究院 SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY [CN]/[CN]
Inventors
  • 梁栋 LIANG, Dong
  • 王珊珊 WANG, Shanshan
  • 程慧涛 CHENG, Huitao
  • 刘新 LIU, Xin
  • 郑海荣 ZHENG, Hairong
Agents
  • 北京市诚辉律师事务所 BEIJING CHENGHUI LAW FIRM
Priority Data
201811581817.724.12.2018CN
Publication Language Chinese (ZH)
Filing Language Chinese (ZH)
Designated States
Title
(EN) PARALLEL MAGNETIC RESONANCE IMAGING METHOD AND RELATED EQUIPMENT
(FR) PROCÉDÉ D'IMAGERIE PAR RÉSONANCE MAGNÉTIQUE PARALLÈLE ET ÉQUIPEMENT ASSOCIÉ
(ZH) 磁共振并行成像方法及相关设备
Abstract
(EN)
A parallel magnetic resonance imaging method, comprising: obtaining undersampled image data acquired by magnetic resonance coils of multiple parallel channels in K-space (S101); obtaining a pre-built comprehensive neural network model, wherein the comprehensive neural network model comprises interconnected neural networks and a K-space-consistent layer (S102); inputting the undersampled image data of each channel into the comprehensive neural network model, so that the neural networks may initially reconstruct the undersampled image data and the space-consistent layer performs back substitution processing on an initial reconstruction result, so as to obtain target reconstruction image data (S103); and merging the target reconstruction image data of all channels to obtain image data of a single channel (S104). Hence, the present method adds the K-space-consistent layer to the neural network models, and said layer uses the undersampled image data before reconstruction to perform back substitution processing on the reconstructed image data, thereby retaining more image details and improving an image reconstruction effect. Also provided is related equipment for parallel magnetic resonance imaging.
(FR)
L'invention concerne un procédé d'imagerie par résonance magnétique parallèle, comprenant les étapes suivantes : obtention de données d'image sous-échantillonnées acquises par des bobines de résonance magnétique de multiples canaux parallèles dans un espace K (S101); obtention d'un modèle de réseau neuronal complet pré-construit, le modèle de réseau neuronal complet comprenant des réseaux neuronaux interconnectés et une couche cohérente avec l'espace K (S102); entrée des données d'image sous-échantillonnées de chaque canal dans le modèle de réseau neuronal complet, de sorte que les réseaux neuronaux peuvent initialement reconstruire les données d'image sous-échantillonnées et la couche cohérente avec l'espace effectue un traitement de rétro-substitution sur un résultat de reconstruction initial, de façon à obtenir des données d'image de reconstruction cible (S103); et fusion des données d'image de reconstruction cible de tous les canaux afin d'obtenir des données d'image d'un seul canal (S104). Par conséquent, le procédé selon la présente invention ajoute la couche cohérente avec l'espace K aux modèles de réseau neuronal, et ladite couche utilise les données d'image sous-échantillonnées avant la reconstruction pour effectuer un traitement de rétro-substitution sur les données d'image reconstruites, ce qui permet de conserver plus de détails d'image et d'améliorer un effet de reconstruction d'image. L'invention concerne également un équipement associé pour l'imagerie par résonance magnétique parallèle.
(ZH)
一种磁共振并行成像方法,该方法获得并行的多个通道的磁共振线圈在K空间上采集的欠采样图像数据(S101),获得预先构建的神经网络综合模型;其中神经网络综合模型包括相互连接的神经网络以及K空间一致层(S102),将各个通道的欠采样图像数据输入至神经网络综合模型中,以使神经网络对欠采样图像数据初步重建以及空间一致层对初步重建结果进行回代处理,得到目标重建图像数据(S103),合并所有通道的目标重建图像数据,以得到单通道的图像数据(S104)。可见,该方法在神经网络模型中添加了K空间一致层,该层使用重建前的欠采样图像数据对重建后的图像数据进行回代处理,从而保留了更多的图像细节,提高了图像重建效果。另外还提供了磁共振并行成像相关设备。
Also published as
Latest bibliographic data on file with the International Bureau