WO2021253671A1 - 磁共振电影成像方法、装置、成像设备及存储介质 - Google Patents

磁共振电影成像方法、装置、成像设备及存储介质 Download PDF

Info

Publication number
WO2021253671A1
WO2021253671A1 PCT/CN2020/117462 CN2020117462W WO2021253671A1 WO 2021253671 A1 WO2021253671 A1 WO 2021253671A1 CN 2020117462 W CN2020117462 W CN 2020117462W WO 2021253671 A1 WO2021253671 A1 WO 2021253671A1
Authority
WO
WIPO (PCT)
Prior art keywords
magnetic resonance
sub
sparse
rank
low
Prior art date
Application number
PCT/CN2020/117462
Other languages
English (en)
French (fr)
Inventor
梁栋
朱燕杰
柯子文
刘新
郑海荣
Original Assignee
中国科学院深圳先进技术研究院
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中国科学院深圳先进技术研究院 filed Critical 中国科学院深圳先进技术研究院
Publication of WO2021253671A1 publication Critical patent/WO2021253671A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves 
    • A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves  involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
    • A61B5/004—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part
    • A61B5/0044—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part for the heart
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/30—Assessment of water resources

Definitions

  • This application relates to the field of magnetic resonance imaging, for example, to a magnetic resonance film imaging method, device, imaging equipment, and storage medium.
  • Magnetic resonance cardiac cine imaging is a non-invasive imaging technique that can be used to assess cardiac function, abnormal ventricular wall motion, etc., and provide a wealth of information for clinical diagnosis of the heart.
  • magnetic resonance cardiac cine imaging is often limited in terms of time and space resolution, and cannot accurately assess some heart diseases, such as arrhythmia. Therefore, under the premise of ensuring the imaging quality, it is particularly important to improve the speed and spatial resolution of MRI cardiac cine imaging.
  • the deep learning methods of related technologies cannot simultaneously take into account the image reconstruction time and image quality in the field of magnetic resonance film imaging.
  • the embodiments of the present application provide a magnetic resonance film imaging method, device, imaging device, and storage medium, which solve the problem that deep learning of related technologies cannot simultaneously take into account the image reconstruction time and image quality in the field of magnetic resonance film imaging.
  • an embodiment of the present application provides a magnetic resonance cine imaging method, including:
  • the magnetic resonance data is input into a trained imaging model to obtain a magnetic resonance movie image, wherein the imaging model is a sparse low-rank network model constructed based on the alternating direction multiplier algorithm, and the imaging model is used to control the alternating
  • the direction multiplier algorithm is iteratively solved according to the iterative parameters output by the neural network model to obtain the magnetic resonance movie image.
  • an embodiment of the present application also provides a magnetic resonance film imaging device, including:
  • the obtaining module is configured to obtain magnetic resonance data
  • the reconstruction module is configured to control the neural network model to determine the iteration parameters required for the current iteration solution according to the previous iteration solution result of the alternate direction multiplier algorithm, and to control the alternate direction multiplier algorithm to complete the current iteration solution process according to the iteration parameters, Until the current iterative solution result meets the preset convergence condition.
  • an embodiment of the present application also provides an imaging device, the imaging device including:
  • Storage device for storing programs
  • the processor realizes the magnetic resonance cine imaging method according to any embodiment.
  • an embodiment of the present application also provides a storage medium containing computer-executable instructions, which are used to execute the magnetic resonance cine imaging method as described in any of the embodiments when the computer-executable instructions are executed by a computer processor .
  • FIG. 1 is a flowchart of a magnetic resonance cine imaging method provided in Embodiment 1 of the present application;
  • Embodiment 2 is a schematic diagram of iterative ADMM algorithm provided by Embodiment 1 of the present application;
  • FIG. 3A is a structural block diagram of a magnetic resonance cine imaging apparatus provided by Embodiment 2 of the present application.
  • 3B is a structural block diagram of another magnetic resonance cine imaging apparatus provided by the second embodiment of the present application.
  • FIG. 4 is a structural block diagram of an imaging device provided in Embodiment 3 of the present application.
  • FIG. 1 is a flowchart of a magnetic resonance cine imaging method provided in Embodiment 1 of the present application.
  • the technical solution of this embodiment is applicable to the case where a sparse low-rank network model constructed based on the ADMM (Alternating Direction Method of Multipliers) algorithm is used to quickly reconstruct a high-quality magnetic resonance movie image.
  • the method may be executed by the magnetic resonance cine imaging apparatus provided in the embodiment of the present application, and the apparatus may be implemented in a software and/or hardware manner, and configured to be applied in a processor of an imaging device.
  • the method may include the following steps:
  • the magnetic resonance data in this embodiment is a magnetic resonance signal containing time information.
  • a magnetic resonance signal containing time information For example, cardiac magnetic resonance signals.
  • the magnetic resonance data is obtained, it is input into a trained imaging model, and the trained imaging model analyzes it to obtain a magnetic resonance movie image.
  • the imaging model is a sparse low-rank network model constructed based on the ADMM algorithm, and may be a model that combines the iterative solution process of the ADMM algorithm and the neural network model.
  • the neural network model is set to determine the iterative parameters required for the current iterative solution of the ADMM algorithm according to the previous iterative solution result of the ADMM algorithm, until the current iterative solution result meets the preset convergence condition. If the current iterative solution result meets the preset convergence condition, the neural network model ends the calculation of the iterative parameters, and the iterative solution result is the magnetic resonance film image to be output by the imaging model.
  • the method for constructing the imaging model includes: converting the under-collected reconstruction task of the magnetic resonance signal to iteratively solving the data consistency sub-problem, the low-rank sub-problem, the sparse sub-problem, and the auxiliary variable sub-problem based on the ADMM algorithm; and the control neural network
  • the model determines the iterative parameters required for the current iterative solution according to the previous iterative solution results of the data consistency sub-problem, low-rank sub-problem, sparse sub-problem, and auxiliary variable sub-problem, and controls the ADMM algorithm to complete the current iterative solution process according to the iterative parameters , Until the current iterative solution result meets the preset convergence condition.
  • the under-collection reconstruction task of the magnetic resonance signal is converted into the step of solving the data consistency sub-problem, the low-rank sub-problem, the sparse sub-problem and the auxiliary variable sub-problem, including: the under-collection of the magnetic resonance signal
  • the reconstruction task is modeled as the data consistency constraint problem, the transform domain sparse constraint problem and the low rank constraint problem; then the data consistency problem, the transform domain sparse problem and the low rank constraint problem are solved based on the ADMM algorithm to reconstruct the under-collection of the magnetic resonance signal. It is transformed into solving data consistency sub-problems, low-rank sub-problems, sparse sub-problems and auxiliary variable sub-problems.
  • the process can be as follows:
  • the under-taken reconstruction problem of the cardiac movie image can be modeled as the following optimization problem:
  • P is the sampling matrix
  • F is the Fourier transform
  • D is the sparse transform
  • g( ⁇ ) is the sparse constraint
  • * ⁇ i ( ⁇ i ,i) is The kernel function
  • ⁇ is a vector of singular values
  • the kernel norm is the sum of the first i largest singular values of the signal, reflecting the low-rank characteristics of the signal; ⁇ 1 and ⁇ 2 are both regularization coefficients.
  • ⁇ 1 is the Lagrangian multiplier in the sparse transformation
  • ⁇ 2 is the Lagrangian multiplier in the sparse transformation
  • ⁇ 1 is the penalty coefficient in the sparse transformation
  • ⁇ 2 is the penalty coefficient in the low-rank transformation.
  • IST means that the signal is decomposed by SVD (Singular Value Decomposition), that is, singular value decomposition, to obtain the eigenvalue vector, threshold the eigenvalue vector, and then restore to the original signal;
  • S is a non-linear threshold function, used to The sparse matrix performs threshold filtering; ⁇ 1 is the regularization coefficient for sparse transformation, ⁇ 2 is the regularization coefficient for low-rank transformation, ⁇ 1 is the update step in sparse transformation, and ⁇ 2 is the update step in low-rank transformation.
  • I is the unit matrix of all 1
  • m and n are the size of x
  • ⁇ is the singular value of x
  • u is the left singular value vector of x
  • v is the right singular value vector of x
  • p is for The constant that controls the scale.
  • T represents the transposed matrix
  • P T represents the transposed matrix of "P”
  • * " represents the adjoint matrix
  • v i * represents the adjoint matrix of "v i” .
  • the neural network model can use the previous iterative solution result of the ADMM algorithm to determine the iterative parameters required for its current iterative solution until the current iterative solution result meets the preset convergence conditions. It is understandable that the combination of the ADMM algorithm and the neural network model enables the neural network model to quickly and accurately determine the current iterative solution based on the prior knowledge of the learned magnetic resonance data in terms of sparseness and low rank Iteration parameters.
  • the iteration parameters include regularization coefficients ⁇ 1, ⁇ 2 and sparse transformation D.
  • the imaging model After the imaging model is constructed, it cannot be used directly for image reconstruction, and a certain number of samples need to be trained to generate a trained imaging model. After the trained imaging model is obtained, the trained imaging model can be used to reconstruct the magnetic resonance data to generate a magnetic resonance movie image.
  • the technical solutions of the magnetic resonance cine imaging method provided by the embodiments of the present application are compared with related technologies.
  • Combining the ADMM algorithm with the neural network model allows the neural network model to learn the prior knowledge of sparse and low-rank magnetic resonance data, and use the learned prior knowledge to quickly and accurately determine the solution of the ADMM algorithm in each iteration The required iterative parameters until the iterative solution result of the ADMM algorithm meets the preset convergence conditions. Because the iterative parameter is determined more quickly and accurately, the time required for the image reconstruction process is greatly reduced, and the quality of the reconstructed magnetic resonance film image is greatly improved.
  • Fig. 3A is a structural block diagram of a magnetic resonance cine imaging apparatus provided by an embodiment of the present application.
  • the device is used to execute the magnetic resonance cine imaging method provided in any of the foregoing embodiments, and the device can be implemented in software or hardware.
  • the device includes:
  • the obtaining module 11 is configured to obtain magnetic resonance data
  • the reconstruction module 12 is configured to input the magnetic resonance data into a trained imaging model to obtain a magnetic resonance movie image, wherein the imaging model is a sparse low-rank network model constructed based on the ADMM algorithm, and is used to control the ADMM
  • the algorithm performs an iterative solution based on the iterative parameters output by the neural network model to obtain a magnetic resonance movie image.
  • the device further includes a model building module 101 (see FIG. 3B), and the model building module includes:
  • the task conversion unit is configured to convert the under-collection reconstruction task of the magnetic resonance signal based on the ADMM algorithm to iteratively solve the data consistency sub-problem, the low-rank sub-problem, the sparse sub-problem and the auxiliary variable sub-problem;
  • the combination unit is configured to control the neural network model to determine the iteration parameters required for the current iteration solution according to the previous iteration solution result of the ADMM algorithm, and to control the ADMM algorithm to complete the current iteration solution process according to the iteration parameter until the current iteration solution result meets Preset convergence conditions.
  • the task conversion unit can optionally be configured to model the under-collection reconstruction task of the magnetic resonance signal as a data consistency constraint problem, a transform domain sparse constraint problem, and a low-rank constraint problem; solve the data consistency problem, transform domain sparseness problem based on ADMM Problem and low-rank constraint problem to transform the under-collection reconstruction task of magnetic resonance signals into solving data consistency sub-problems, low-rank sub-problems, sparse sub-problems and auxiliary variable sub-problems.
  • the device further includes a training module 102 (see FIG. 3B), which is configured to receive training sample data and complete the training of the imaging model according to the received training sample data to generate a trained imaging model.
  • a training module 102 (see FIG. 3B), which is configured to receive training sample data and complete the training of the imaging model according to the received training sample data to generate a trained imaging model.
  • the technical solutions of the magnetic resonance cine imaging apparatus provided by the embodiments of the present application are compared with related technologies.
  • Combining the ADMM algorithm with the neural network model allows the neural network model to learn the prior knowledge of sparse and low-rank magnetic resonance data, and use the learned prior knowledge to quickly and accurately determine the solution of the ADMM algorithm in each iteration The required iterative parameters until the iterative solution result of the ADMM algorithm meets the preset convergence conditions. Because the iterative parameter is determined more quickly and accurately, the time required for the image reconstruction process is greatly reduced, and the quality of the reconstructed magnetic resonance film image is greatly improved.
  • the magnetic resonance cine imaging apparatus provided by the embodiment of the present application can execute the magnetic resonance cine imaging method provided by any embodiment of the present application, and has the corresponding functional modules and beneficial effects for the execution method.
  • FIG. 4 is a schematic structural diagram of an imaging device provided in Embodiment 3 of the application.
  • the device includes a processor 201, a memory 202, an input device 203, and an output device 204; the number of processors 201 in the device may be one Or more, one processor 201 is taken as an example in FIG. 4; the processor 201, the memory 202, the input device 203, and the output device 204 in the device may be connected by a bus or other methods.
  • a bus connection is taken as an example.
  • the memory 202 can be used to store software programs, computer-executable programs, and modules, such as the magnetic resonance film imaging method, device, imaging device, and program instructions/modules corresponding to the storage medium in the embodiments of the present application (For example, acquisition module 11 and reconstruction module 12).
  • the processor 201 executes various functional applications and data processing of the device by running the software programs, instructions, and modules stored in the memory 202, that is, realizes the aforementioned magnetic resonance film imaging method, device, imaging device, and storage medium.
  • the memory 202 may mainly include a program storage area and a data storage area.
  • the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created according to the use of the terminal, and the like.
  • the memory 202 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.
  • the memory 202 may include a memory remotely provided with respect to the processor 201, and these remote memories may be connected to the device through a network. Examples of the aforementioned network may include the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
  • the input device 203 can be used to receive inputted digital or character information, and generate key signal input related to user settings and function control of the device.
  • the output device 204 may include a display device such as a display screen, for example, a display screen of a user terminal.
  • the fourth embodiment of the present application also provides a storage medium containing computer-executable instructions, when the computer-executable instructions are executed by a computer processor, they are used to execute a magnetic resonance film imaging method, device, imaging device, and storage medium ,
  • the method includes:
  • the control neural network model determines the iterative parameters required for the current iterative solution according to the previous iterative solution result of the ADMM algorithm, and controls the ADMM algorithm to complete the current iterative solution process according to the iterative parameter until the current iterative solution result meets the preset convergence condition.
  • a storage medium provided by an embodiment of the present application contains computer-executable instructions.
  • the computer-executable instructions can execute the method operations described above, and can also execute the magnetic resonance cine imaging method provided by any embodiment of the present application. Related operations in.
  • the various units and modules included are only divided according to the functional logic, as long as the corresponding functions can be realized; in addition, the names of the functional units are only for It is easy to distinguish each other.
  • the technical solution of the magnetic resonance film imaging method includes: acquiring magnetic resonance data; inputting the magnetic resonance data into a trained imaging model to obtain a magnetic resonance film image, wherein the imaging model is constructed based on the ADMM algorithm
  • the sparse low-rank network model of the imaging model is used to control the ADMM algorithm to perform corresponding iterative solutions according to the iterative parameters output by the neural network model to obtain the magnetic resonance movie image.
  • Combining the ADMM algorithm with the neural network model allows the neural network model to learn the prior knowledge of sparse and low-rank magnetic resonance data, and use the learned prior knowledge to quickly and accurately determine the solution of the ADMM algorithm in each iteration The required iterative parameters until the iterative solution result of the ADMM algorithm meets the preset convergence conditions. Because the iterative parameter is determined more quickly and accurately, the time required for the image reconstruction process is greatly reduced, and the quality of the reconstructed magnetic resonance film image is greatly improved.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Physics & Mathematics (AREA)
  • Radiology & Medical Imaging (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Pathology (AREA)
  • Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Veterinary Medicine (AREA)
  • Medical Informatics (AREA)
  • Biophysics (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Cardiology (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)
  • Image Analysis (AREA)

Abstract

一种磁共振电影成像方法、装置、成像设备及存储介质，该方法包括：获取磁共振数据（S101）；磁共振数据输入至已训练的成像模型中以得到磁共振电影图像，其中，成像模型是基于交替方向乘子算法构建的稀疏低秩网络模型，用于控制交替方向乘子算法根据神经网络模型输出的迭代参数进行迭代求解以得到磁共振电影图像（S102）。

Description

磁共振电影成像方法、装置、成像设备及存储介质
本公开要求在2020年06月18日提交中国专利局、申请号为202010560886.0的中国专利申请的优先权，以上申请的全部内容通过引用结合在本公开中。
技术领域
本申请涉及磁共振成像领域，例如涉及一种磁共振电影成像方法、装置、成像设备及存储介质。
背景技术
磁共振心脏电影成像是一种非侵入式的成像技术，能够用于评估心功能，室壁运动异常等，为心脏临床诊断提供丰富的信息。然而，由于磁共振物理、硬件和心脏运动周期时长的制约，磁共振心脏电影成像往往在时间和空间分辨率方面受限，无法准确评估部分心脏疾病，如心率不齐等。因此，在保证成像质量的前提下，提高磁共振心脏电影成像的速度和空间分辨率尤为重要。
近年来，很多人都在探索深度学习方法在磁共振电影成像领域的使用。比如，基于级联卷积网络(DC-CNN)、卷积递归神经网络(CRNN)以及多监督交叉域网络DIMENSION的磁共振电影成像，均取得了良好的重建效果。但由于这三种神经网络均是直接学习从欠采图像到全采图像的映射关系，使得它们在图像重建过程需要较长的重建时间，或者重建出的磁共振心脏电影图像的质量较低。
综上，相关技术的深度学习方法无法在磁共振电影成像领域同时兼顾图像重建时间和图像质量。
发明内容
本申请实施例提供了一种磁共振电影成像方法、装置、成像设备及存储介质，解决了相关技术的深度学习无法在磁共振电影成像领域同时兼顾图像重建时间和图像质量的问题。
第一方面，本申请实施例提供了一种磁共振电影成像方法，包括：
获取磁共振数据；
将所述磁共振数据输入至已训练的成像模型中以得到磁共振电影图像，其中，所述成像模型是基于交替方向乘子算法构建的稀疏低秩网络模型，所述成像模型用于控制交替方向乘子算法根据神经网络模型输出的迭代参数进行迭代求解以得到磁共振电影图像。
第二方面，本申请实施例还提供了一种磁共振电影成像装置，包括：
获取模块，被配置为获取磁共振数据；
重建模块，被配置为控制神经网络模型根据交替方向乘子算法的前一次的迭代求解结果确定当前迭代求解所需的迭代参数，以及控制交替方向乘子算法根据该迭代参数完成当前迭代求解过程，直至当前迭代求解结果符合预设收敛条件。
第三方面，本申请实施例还提供了一种成像设备，所述成像设备包括：
处理器；
存储装置，用于存储程序；
当所述程序被所述处理器执行，使得所述处理器实现如任意实施例所述的磁共振电影成像方法。
第四方面，本申请实施例还提供了一种存储介质，包含计算机可执行指令，所述计算机可执行指令在由计算机处理器执行时用于执行如任意实施例所述的磁共振电影成像方法。
附图说明
下面将对实施例描述中所需要使用的附图做一简单地介绍。下面描述中的附图是本申请的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本申请实施例一提供的磁共振电影成像方法的流程图；
图2是本申请实施例一提供的ADMM算法的迭代示意图；
图3A是本申请实施例二提供的磁共振电影成像装置的结构框图；
图3B是本申请实施例二提供的又一磁共振电影成像装置的结构框图；
图4是本申请实施例三提供的成像设备的结构框图。
具体实施方式
以下将参照本申请实施例中的附图，通过实施方式清楚、完整地描述本申请的技术方案，显然，所描述的实施例是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
实施例一
图1是本申请实施例一提供的磁共振电影成像方法的流程图。本实施例的技术方案适用于使用基于ADMM(Alternating Direction Method of Multipliers，交替方向乘子)算法构建的稀疏低秩网络模型快速重建出高质量的磁共振电影图像的情况。该方法可以由本申请实施例提供的磁共振电影成像装置来执行，该装置可以采用软件和/或硬件的方式实现，并配置在成像设备的处理器中应用。 该方法可以包括如下步骤：
S101、获取磁共振数据。
本实施例的磁共振数据为包含时间信息的磁共振信号。比如，心脏磁共振信号。
S102、将磁共振数据输入至已训练的成像模型中以得到磁共振电影图像，其中，成像模型是基于ADMM算法构建的稀疏低秩网络模型，用于控制ADMM算法根据神经网络模型输出的迭代参数进行相应的迭代求解以得到磁共振电影图像。
磁共振数据得到之后，将其输入已训练的成像模型中，由该已训练的成像模型对其分析，以得到磁共振电影图像。
在一是实施例中，成像模型是基于ADMM算法构建的稀疏低秩网络模型，可以为将ADMM算法的迭代求解过程与神经网络模型相结合而成的模型。在该成像模型中，神经网络模型被设置为，根据ADMM算法前一次的迭代求解结果确定ADMM算法当前迭代求解所需的迭代参数，直至当前的迭代求解结果符合预设收敛条件。如果当前的迭代求解结果符合预设收敛条件，则神经网络模型结束迭代参数的计算，该迭代求解结果即为成像模型要输出的磁共振电影图像。
在一实施例中，成像模型的构建方法包括：基于ADMM算法将磁共振信号的欠采重建任务转换为迭代求解数据一致子问题、低秩子问题、稀疏子问题和辅助变量子问题；控制神经网络模型根据数据一致子问题、低秩子问题、稀疏子问题和辅助变量子问题的前一次的迭代求解结果，确定当前迭代求解所需的迭代参数，以及控制ADMM算法根据该迭代参数完成当前迭代求解过程，直至当前迭代求解结果符合预设收敛条件。
在一些实施例中，基于ADMM算法将磁共振信号的欠采重建任务转换为求 解数据一致子问题、低秩子问题、稀疏子问题和辅助变量子问题的步骤，包括：将磁共振信号的欠采重建任务建模为数据一致约束问题、变换域稀疏约束问题和低秩约束问题；然后基于ADMM算法求解数据一致问题、变换域稀疏问题和低秩约束问题，以将磁共振信号的欠采重建任务转换为求解数据一致子问题、低秩子问题、稀疏子问题和辅助变量子问题。该过程可以为如下：
对于磁共振数据，即K空间数据
Figure PCTCN2020117462-appb-000001
其对应的欠采心脏电影图像为
Figure PCTCN2020117462-appb-000002
该心脏电影图像的欠采重建问题可被建模为以下优化问题：
Figure PCTCN2020117462-appb-000003
其中，A＝PF为测量矩阵，P为采样矩阵，F为傅里叶变换，D为稀疏变换，g(·)为稀疏约束，||·|| *＝∑ i(Σ i,i)是核函数，Σ是·的奇异值向量，核范数是对信号的前i个最大奇异值进行求和，反映了信号的低秩特性；λ 1和λ 2均是正则化系数。
引入辅助变量z＝Dx，t＝x，则上述优化问题变为：
Figure PCTCN2020117462-appb-000004
公式(2)的增广拉格朗日形式如下：
Figure PCTCN2020117462-appb-000005
其中，α 1为稀疏变换中的拉格朗日乘子，α 2为稀疏变换中的拉格朗日乘子，ρ 1为稀疏变换中的惩罚系数，ρ 2为低秩变换中的惩罚系数。
利用ADMM算法对公式(3)进行求解，可以得到：
Figure PCTCN2020117462-appb-000006
利用变换
Figure PCTCN2020117462-appb-000007
A＝FP，t (n+1)使用奇异值阈值表示，则得到如下四个子问题。
Figure PCTCN2020117462-appb-000008
其中，IST表示对信号进行SVD(Singular Value Decomposition)分解，即奇异值分解，得到特征值向量，并对特征值向量进行阈值操作，然后恢复到原信号；S为非线性阈值函数，用于对稀疏矩阵进行阈值过滤；λ1是用于稀疏变换的正则化系数，λ2是用于低秩变换的正则化系数，η 1是稀疏变换中的更新步长，η 2是低秩变换中的更新步长，I是全1的单位矩阵，m和n是x的尺寸(size)，σ是x的奇异值，u是x的左奇异值向量，v是x的右奇异值向量，p是用于控制尺度的常数。
可理解的是，“ T”表示转置矩阵，例如，“P T”表示“P”的转置矩阵；“ *”表示伴随矩阵，例如，“v i *”表示“v i”的伴随矩阵。
将公式(5)的迭代求解步骤参见图2，将其与神经网络模型相结合。结合之后，神经网络模型可以利用ADMM算法的前一次迭代求解结果确定其当前迭 代求解所需的迭代参数，直至当前迭代求解结果符合预设收敛条件。可以理解的是，将ADMM算法与神经网络模型相结合，使得神经网络模型可以根据所学习的磁共振数据在稀疏和低秩两方面的先验知识，快速准确地确定出当前迭代求解所需的迭代参数。其中，迭代参数包括正则化系数λ1、λ2和稀疏变换D。
可以理解的是，成像模型构建完成之后，并不能直接使用其进行图像重建，还需要使用一定数量的样本对其进行训练，以生成已训练的成像模型。得到已训练的成像模型之后，即可使用该已训练的成像模型对磁共振数据进行图像重建，以生成磁共振电影图像。
本申请实施例提供的磁共振电影成像方法的技术方案，相较于相关技术。将ADMM算法与神经网络模型结合，使得神经网络模型可以学习磁共振数据在稀疏和低秩两方面的先验知识，并利用所学的这些先验知识快速准确地确定ADMM算法每次迭代求解所需的迭代参数，直至ADMM算法的迭代求解结果符合预设收敛条件，由于迭代参数的确定更加快速准确，因此图像重建过程所需时间大幅减少，重建出的磁共振电影图像的质量大幅提高。
实施例二
图3A是本申请实施例提供的磁共振电影成像装置的结构框图。该装置用于执行上述任意实施例所提供的磁共振电影成像方法，该装置可选为软件或硬件实现。该装置包括：
获取模块11，被配置为获取磁共振数据；
重建模块12，被配置为将所述磁共振数据输入至已训练的成像模型中以得到磁共振电影图像，其中，所述成像模型是基于ADMM算法构建的稀疏低秩网络模型，用于控制ADMM算法根据神经网络模型输出的迭代参数进行迭代求解 以得到磁共振电影图像。
可选地，该装置还包括模型构建模块101(参见图3B)，该模型构建模块包括：
任务转换单元，被配置为基于ADMM算法将磁共振信号的欠采重建任务转换为迭代求解数据一致子问题、低秩子问题、稀疏子问题和辅助变量子问题；
结合单元，被配置为控制神经网络模型根据ADMM算法的前一次的迭代求解结果确定当前迭代求解所需的迭代参数，以及控制ADMM算法根据该迭代参数完成当前迭代求解过程，直至当前迭代求解结果符合预设收敛条件。
其中，任务转换单元可选被配置为将磁共振信号的欠采重建任务建模为数据一致约束问题、变换域稀疏约束问题和低秩约束问题；基于ADMM求解所述数据一致问题、变换域稀疏问题和低秩约束问题，以将磁共振信号的欠采重建任务转换为求解数据一致子问题、低秩子问题、稀疏子问题和辅助变量子问题。
可选地，该装置还包括训练模块102(参见图3B)，被配置为接收训练样本数据，并根据所接收的训练样本数据完成成像模型的训练，以生成已训练的成像模型。
本申请实施例提供的磁共振电影成像装置的技术方案，相较于相关技术。将ADMM算法与神经网络模型结合，使得神经网络模型可以学习磁共振数据在稀疏和低秩两方面的先验知识，并利用所学的这些先验知识快速准确地确定ADMM算法每次迭代求解所需的迭代参数，直至ADMM算法的迭代求解结果符合预设收敛条件，由于迭代参数的确定更加快速准确，因此图像重建过程所需时间大幅减少，重建出的磁共振电影图像的质量大幅提高。
本申请实施例所提供的磁共振电影成像装置可执行本申请任意实施例所提供的磁共振电影成像方法，具备执行方法相应的功能模块和有益效果。
实施例三
图4为本申请实施例三提供的成像设备的结构示意图，如图4所示，该设备包括处理器201、存储器202、输入装置203以及输出装置204；设备中处理器201的数量可以是一个或多个，图4中以一个处理器201为例；设备中的处理器201、存储器202、输入装置203以及输出装置204可以通过总线或其他方式连接，图4中以通过总线连接为例。
存储器202作为一种计算机可读存储介质，可用于存储软件程序、计算机可执行程序以及模块，如本申请实施例中的磁共振电影成像方法、装置、成像设备及存储介质对应的程序指令/模块(例如，获取模块11和重建模块12)。处理器201通过运行存储在存储器202中的软件程序、指令以及模块，从而执行设备的各种功能应用以及数据处理，即实现上述的磁共振电影成像方法、装置、成像设备及存储介质。
存储器202可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序；存储数据区可存储根据终端的使用所创建的数据等。此外，存储器202可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实例中，存储器202可包括相对于处理器201远程设置的存储器，这些远程存储器可以通过网络连接至设备。上述网络的实例可以包括互联网、企业内部网、局域网、移动通信网及其组合。
输入装置203可用于接收输入的数字或字符信息，以及产生与设备的用户设置以及功能控制有关的键信号输入。
输出装置204可包括显示屏等显示设备，例如，用户终端的显示屏。
实施例四
本申请实施例四还提供了一种包含计算机可执行指令的存储介质，所述计算机可执行指令在由计算机处理器执行时用于执行一种磁共振电影成像方法、装置、成像设备及存储介质，该方法包括：
获取磁共振数据；
控制神经网络模型根据ADMM算法的前一次的迭代求解结果确定当前迭代求解所需的迭代参数，以及控制ADMM算法根据该迭代参数完成当前迭代求解过程，直至当前迭代求解结果符合预设收敛条件。
当然，本申请实施例所提供的一种存储介质，包含计算机可执行指令，其计算机可执行指令可以执行如上所述的方法操作，还可以执行本申请任意实施例所提供的磁共振电影成像方法中的相关操作。
通过以上关于实施方式的描述，所属领域的技术人员可以清楚地了解到，本申请可借助软件及必需的通用硬件来实现，当然也可以通过硬件实现，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如计算机的软盘、只读存储器(Read-Only Memory，简称ROM)、随机存取存储器(Random Access Memory，简称RAM)、闪存(FLASH)、硬盘或光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述的磁共振电影成像方法。
值得注意的是，上述磁共振电影成像装置的实施例中，所包括的各个单元和模块只是按照功能逻辑进行划分的，只要能够实现相应的功能即可；另外， 各功能单元的名称也只是为了便于相互区分。
本申请实施例提供的磁共振电影成像方法的技术方案，包括：获取磁共振数据；将磁共振数据输入至已训练的成像模型中以得到磁共振电影图像，其中，成像模型是基于ADMM算法构建的稀疏低秩网络模型，成像模型用于控制ADMM算法根据神经网络模型输出的迭代参数进行相应的迭代求解以得到磁共振电影图像。相较于相关技术。将ADMM算法与神经网络模型结合，使得神经网络模型可以学习磁共振数据在稀疏和低秩两方面的先验知识，并利用所学的这些先验知识快速准确地确定ADMM算法每次迭代求解所需的迭代参数，直至ADMM算法的迭代求解结果符合预设收敛条件，由于迭代参数的确定更加快速准确，因此图像重建过程所需时间大幅减少，重建出的磁共振电影图像的质量大幅提高。

Claims (10)

  1. 一种磁共振电影成像方法，包括：
    获取磁共振数据；
    将所述磁共振数据输入至已训练的成像模型中以得到磁共振电影图像，其中，所述成像模型是基于交替方向乘子算法构建的稀疏低秩网络模型，所述成像模型用于控制交替方向乘子算法根据神经网络模型输出的迭代参数进行迭代求解以得到磁共振电影图像。
  2. 根据权利要求1所述的磁共振电影成像方法，其中，所述神经网络模型用于根据交替方向乘子算法前一次的迭代求解结果确定交替方向乘子算法当前迭代求解所需的迭代参数。
  3. 根据权利要求1所述的磁共振电影成像方法，其中，所述成像模型的构建方法包括：
    基于交替方向乘子算法将磁共振信号的欠采重建任务转换为迭代求解数据一致子问题、低秩子问题、稀疏子问题和辅助变量子问题；
    控制神经网络模型根据数据一致子问题、低秩子问题、稀疏子问题和辅助变量子问题的前一次的迭代求解结果，确定当前迭代求解所需的迭代参数，以及控制交替方向乘子算法根据该迭代参数完成当前迭代求解过程，直至当前迭代求解结果符合预设收敛条件。
  4. 根据权利要求3所述的磁共振电影成像方法，其中，所述基于交替方向乘子算法将磁共振信号的欠采重建任务转换为求解数据一致子问题、低秩子问题、稀疏子问题和辅助变量子问题，包括：
    将磁共振信号的欠采重建任务建模为数据一致约束问题、变换域稀疏约束问题和低秩约束问题；
    基于交替方向乘子求解所述数据一致问题、变换域稀疏问题和低秩约束问 题，以将磁共振信号的欠采重建任务转换为求解数据一致子问题、低秩子问题、稀疏子问题和辅助变量子问题。
  5. 根据权利要求3所述的磁共振电影成像方法，其中，
    所述数据一致子问题为：
    Figure PCTCN2020117462-appb-100001
    所述低秩子问题为：
    Figure PCTCN2020117462-appb-100002
    所述稀疏子问题为：
    Figure PCTCN2020117462-appb-100003
    所述辅助变量更新子问题为：
    Figure PCTCN2020117462-appb-100004
    其中，y为磁共振信号，x是图像数据，P是采样矩阵，F是傅里叶变换；z、t是辅助变量，z＝Dx，t＝x，D是稀疏变换；
    Figure PCTCN2020117462-appb-100005
    α 1为稀疏变换中的拉格朗日乘子，α 2为低秩变换中的拉格朗日乘子；ρ 1为稀疏变换中的惩罚系数，ρ 2为低秩变换中的惩罚系数；IST表示对信号进行奇异值分解得到特征值向量，并对特征值向量进行阈值操作，然后恢复到原信号；S为非线性阈值函数；λ1是用于稀疏变换的正则化系数、λ2是用于低秩变换的正则化系数，η 1是稀疏变换中的更新步长，η 2是低秩变换中的更新步长，I是全1的单位矩阵，m和n是x的尺寸，σ是x的奇异值，u是x的左奇异值向量，v是x的右奇异值向量，p是用于控制尺度的常数。
  6. 根据权利要求5所述的磁共振电影成像方法，其中，所述迭代参数包括 D、λ 1和λ 2。
  7. 根据权利要求1-6任一所述的磁共振电影成像方法，其中，所述磁共振数据为心脏磁共振数据。
  8. 一种磁共振电影成像装置，包括：
    获取模块，被配置为获取磁共振数据；
    重建模块，被配置为控制神经网络模型根据交替方向乘子算法的前一次的迭代求解结果确定当前迭代求解所需的迭代参数，以及控制交替方向乘子算法根据该迭代参数完成当前迭代求解过程，直至当前迭代求解结果符合预设收敛条件。
  9. 一种成像设备，所述成像设备包括：
    处理器；
    存储装置，用于存储程序；
    当所述程序被所述处理器执行，使得所述处理器实现如权利要求1-7中任一所述的磁共振电影成像方法。
  10. 一种存储介质，包含计算机可执行指令，所述计算机可执行指令在由计算机处理器执行时用于执行如权利要求1-7中任一所述的磁共振电影成像方法。
PCT/CN2020/117462 2020-06-18 2020-09-24 磁共振电影成像方法、装置、成像设备及存储介质 WO2021253671A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010560886.0A CN111714124B (zh) 2020-06-18 2020-06-18 磁共振电影成像方法、装置、成像设备及存储介质
CN202010560886.0 2020-06-18

Publications (1)

Publication Number Publication Date
WO2021253671A1 true WO2021253671A1 (zh) 2021-12-23

Family

ID=72567537

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/117462 WO2021253671A1 (zh) 2020-06-18 2020-09-24 磁共振电影成像方法、装置、成像设备及存储介质

Country Status (2)

Country Link
CN (1) CN111714124B (zh)
WO (1) WO2021253671A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113933773A (zh) * 2021-09-30 2022-01-14 深圳先进技术研究院 基于深度学习的磁共振成像方法、系统、终端及存储介质
CN116919380A (zh) * 2023-09-15 2023-10-24 浙江大华技术股份有限公司 压缩感知磁共振成像方法、模型训练方法及其成像装置
CN118141356B (zh) * 2024-04-30 2024-07-02 天津工业大学 基于模型驱动的深度admm展开eit成像方法

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5226066A (en) * 1991-08-29 1993-07-06 Adac Laboratories Apparatus and methods for cardiac biplane acquisition
CN103093430A (zh) * 2013-01-25 2013-05-08 西安电子科技大学 基于稀疏低秩与字典学习的心脏mri图像去模糊方法
CN104240256A (zh) * 2014-09-25 2014-12-24 西安电子科技大学 一种基于层次化稀疏建模的图像显著性检测方法
CN105389833A (zh) * 2015-12-24 2016-03-09 南京信息工程大学 一种基于在线迭代子空间学习的目标跟踪方法
US9655522B2 (en) * 2014-10-10 2017-05-23 Cedars-Sinai Medical Center Method and system for “push-button” comprehensive cardiac MR examination using continuous self-gated 3D radial imaging
CN109157210A (zh) * 2018-07-11 2019-01-08 厦门大学 一种基于admm和神经网络的心外膜电位重建方法
CN109284820A (zh) * 2018-10-26 2019-01-29 北京图森未来科技有限公司 一种深度神经网络的结构搜索方法及装置
US20190050372A1 (en) * 2017-08-14 2019-02-14 City University Of Hong Kong Systems and methods for robust low-rank matrix approximation
US20200011951A1 (en) * 2018-07-06 2020-01-09 The Board Of Trustees Of The Leland Stanford Junior University Deep Learning based Methods to Accelerate Multi-Spectral Imaging
CN110766768A (zh) * 2019-10-23 2020-02-07 深圳先进技术研究院 一种磁共振图像重建方法、装置、设备和介质
CN110766769A (zh) * 2019-10-23 2020-02-07 深圳先进技术研究院 一种磁共振图像重建方法、装置、设备和介质
JP2020030691A (ja) * 2018-08-23 2020-02-27 株式会社日立製作所 最適化システム及び最適化方法
CN111192663A (zh) * 2018-11-14 2020-05-22 深圳先进技术研究院 磁共振电影成像方法、装置、设备和存储介质
CN111292240A (zh) * 2020-01-23 2020-06-16 上海交通大学 一种基于成像模型与机器学习的磁共振超分辨率成像方法

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104933683B (zh) * 2015-06-09 2018-12-04 南昌大学 一种用于磁共振快速成像的非凸低秩重建方法
CN106780372B (zh) * 2016-11-30 2019-06-18 华南理工大学 一种基于广义树稀疏的权重核范数磁共振成像重建方法
CN106934778B (zh) * 2017-03-10 2019-11-29 北京工业大学 一种基于小波域结构和非局部分组稀疏的mr图像重建方法
CN107991636B (zh) * 2017-11-24 2020-05-12 哈尔滨工业大学 一种基于适应性结构低秩矩阵的快速磁共振图像重建方法
CN109191404B (zh) * 2018-09-07 2020-06-26 西安交通大学 一种基于e-3dtv正则的高光谱图像修复方法
AU2020100462A4 (en) * 2020-03-26 2020-04-30 Hu, Xiaoyan MISS Edge-preserving image super-resolution via low rank and total variation model

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5226066A (en) * 1991-08-29 1993-07-06 Adac Laboratories Apparatus and methods for cardiac biplane acquisition
CN103093430A (zh) * 2013-01-25 2013-05-08 西安电子科技大学 基于稀疏低秩与字典学习的心脏mri图像去模糊方法
CN104240256A (zh) * 2014-09-25 2014-12-24 西安电子科技大学 一种基于层次化稀疏建模的图像显著性检测方法
US9655522B2 (en) * 2014-10-10 2017-05-23 Cedars-Sinai Medical Center Method and system for “push-button” comprehensive cardiac MR examination using continuous self-gated 3D radial imaging
CN105389833A (zh) * 2015-12-24 2016-03-09 南京信息工程大学 一种基于在线迭代子空间学习的目标跟踪方法
US20190050372A1 (en) * 2017-08-14 2019-02-14 City University Of Hong Kong Systems and methods for robust low-rank matrix approximation
US20200011951A1 (en) * 2018-07-06 2020-01-09 The Board Of Trustees Of The Leland Stanford Junior University Deep Learning based Methods to Accelerate Multi-Spectral Imaging
CN109157210A (zh) * 2018-07-11 2019-01-08 厦门大学 一种基于admm和神经网络的心外膜电位重建方法
JP2020030691A (ja) * 2018-08-23 2020-02-27 株式会社日立製作所 最適化システム及び最適化方法
CN109284820A (zh) * 2018-10-26 2019-01-29 北京图森未来科技有限公司 一种深度神经网络的结构搜索方法及装置
CN111192663A (zh) * 2018-11-14 2020-05-22 深圳先进技术研究院 磁共振电影成像方法、装置、设备和存储介质
CN110766769A (zh) * 2019-10-23 2020-02-07 深圳先进技术研究院 一种磁共振图像重建方法、装置、设备和介质
CN110766768A (zh) * 2019-10-23 2020-02-07 深圳先进技术研究院 一种磁共振图像重建方法、装置、设备和介质
CN111292240A (zh) * 2020-01-23 2020-06-16 上海交通大学 一种基于成像模型与机器学习的磁共振超分辨率成像方法

Also Published As

Publication number Publication date
CN111714124A (zh) 2020-09-29
CN111714124B (zh) 2023-11-03

Similar Documents

Publication Publication Date Title
Zhang et al. A review on deep learning in medical image reconstruction
WO2021253671A1 (zh) 磁共振电影成像方法、装置、成像设备及存储介质
Sulam et al. On multi-layer basis pursuit, efficient algorithms and convolutional neural networks
Ng et al. Solving constrained total-variation image restoration and reconstruction problems via alternating direction methods
Sreehari et al. Plug-and-play priors for bright field electron tomography and sparse interpolation
Jiang et al. Single image super-resolution via locally regularized anchored neighborhood regression and nonlocal means
Liu et al. Learning converged propagations with deep prior ensemble for image enhancement
US20190354832A1 (en) Method and system for learning on geometric domains using local operators
Mukherjee et al. Learned reconstruction methods with convergence guarantees: A survey of concepts and applications
WO2022134971A1 (zh) 一种降噪模型的训练方法及相关装置
Sun et al. Learning non-locally regularized compressed sensing network with half-quadratic splitting
Wei et al. Tfpnp: Tuning-free plug-and-play proximal algorithms with applications to inverse imaging problems
Liu et al. Sgd-net: Efficient model-based deep learning with theoretical guarantees
Miao et al. A General-Thresholding Solution for l p (0<; p<; 1) Regularized CT Reconstruction
CN109658468B (zh) 磁共振参数成像方法、装置、设备及存储介质
WO2020114329A1 (zh) 磁共振快速参数成像方法及装置
CN111383741B (zh) 医学成像模型的建立方法、装置、设备及存储介质
CN113674172B (zh) 一种图像处理方法、系统、装置及存储介质
CN117011673B (zh) 基于噪声扩散学习的电阻抗层析成像图像重建方法和装置
Mdrafi et al. Joint learning of measurement matrix and signal reconstruction via deep learning
Kelkar et al. Prior image-constrained reconstruction using style-based generative models
CN111383742A (zh) 一种医学成像模型的建立方法、装置、设备及存储介质
Zhao et al. A deep variational Bayesian framework for blind image deblurring
WO2022193379A1 (zh) 图像重建模型生成及装置、图像重建方法及装置、设备、介质
Barbano et al. Unsupervised knowledge-transfer for learned image reconstruction

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20941216

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20941216

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 20941216

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 09.08.2023)

122 Ep: pct application non-entry in european phase

Ref document number: 20941216

Country of ref document: EP

Kind code of ref document: A1