WO2022193379A1 - 图像重建模型生成及装置、图像重建方法及装置、设备、介质 - Google Patents

图像重建模型生成及装置、图像重建方法及装置、设备、介质 Download PDF

Info

Publication number
WO2022193379A1
WO2022193379A1 PCT/CN2021/085552 CN2021085552W WO2022193379A1 WO 2022193379 A1 WO2022193379 A1 WO 2022193379A1 CN 2021085552 W CN2021085552 W CN 2021085552W WO 2022193379 A1 WO2022193379 A1 WO 2022193379A1
Authority
WO
WIPO (PCT)
Prior art keywords
image reconstruction
space data
model
sampled
reconstruction model
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2021/085552
Other languages
English (en)
French (fr)
Inventor
梁栋
朱燕杰
黄文麒
柯子文
崔卓须
刘新
郑海荣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Institute of Advanced Technology of CAS
Original Assignee
Shenzhen Institute of Advanced Technology of CAS
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 Shenzhen Institute of Advanced Technology of CAS filed Critical Shenzhen Institute of Advanced Technology of CAS
Publication of WO2022193379A1 publication Critical patent/WO2022193379A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T12/00—Tomographic reconstruction from projections
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—Two-dimensional [2D] image generation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2211/00—Image generation
    • G06T2211/40—Computed tomography
    • G06T2211/412—Dynamic
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2211/00—Image generation
    • G06T2211/40—Computed tomography
    • G06T2211/424—Iterative

Definitions

  • the embodiments of the present application relate to the technical field of medical image processing, for example, to a method and apparatus for generating an image reconstruction model, an image reconstruction method and apparatus, a device, and a 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 rich information for clinical diagnosis of the heart.
  • the hardware for realizing magnetic resonance and the limitation of the duration of the cardiac motion cycle the temporal and spatial resolution of magnetic resonance cardiac cine imaging is often limited, and it is impossible to accurately assess some cardiac diseases, such as arrhythmia, etc. Cardiac function. Therefore, it is necessary to use fast imaging methods to improve the temporal and spatial resolution of magnetic resonance cardiac cine imaging under the premise of ensuring imaging quality.
  • Commonly used methods to accelerate magnetic resonance cardiac cine imaging include Parallel Imaging (PI), Compressed Sensing (CS) technology, low-rank matrix factorization and deep learning methods.
  • PI Parallel Imaging
  • CS Compressed Sensing
  • the embodiments of the present application provide an image reconstruction model generation and device, an image reconstruction method, device, equipment, and medium, so as to realize the speed of image reconstruction while making full use of the low-rank and sparse characteristics of sampled data to create an image Rebuild the model to improve the quality of the reconstructed image.
  • An image reconstruction model generation method including:
  • an image reconstruction model is established according to a sub-problem obtained by solving the magnetic resonance image reconstruction problem under the constraints of low-rank characteristics and sparse characteristics for the fully sampled K-space data, including:
  • the fully sampled K-space data is modeled to represent the magnetic resonance image reconstruction problem under the constraints of low-rank characteristics and sparse characteristics; setting the magnetic resonance image reconstruction problem Auxiliary variables representing the model, and determining a penalty function representing the model based on the auxiliary variables; determining three sub-problems representing the model according to the penalty function; solving the three sub-problems respectively, and analyzing the solution results Networking obtains the image reconstruction model.
  • the three sub-problems are solved separately, and the solution results are networked to obtain the image reconstruction model, including:
  • the rewriting the three sub-problems respectively includes:
  • the three sub-problems are respectively rewritten according to the result of the expansion of the penalty function at the preset value of the data fidelity item.
  • the image reconstruction model includes a low-rank network module, a sparse network module, and a data consistency module.
  • An image reconstruction method including:
  • an image reconstruction model generation device comprising:
  • the data preprocessing module is configured to obtain the full-sampled K-space data of the dynamic magnetic resonance image sequence, and obtain the under-sampled K-space data corresponding to the full-sampled K-space data based on the preset under-sampling model;
  • the data input module is configured to The under-sampled K-space data is input to the sub-problem obtained by solving the magnetic resonance image reconstruction problem under the constraints of low-rank characteristics and sparse characteristics based on the fully-sampled K-space data, and the established image reconstruction model is used for all the sub-problems.
  • the image reconstruction model is trained; the model generation module is configured to complete the process when the mean square error between the reconstructed images generated by the image reconstruction model and the reconstructed images corresponding to the fully sampled K-space data satisfies a preset condition.
  • the trained image reconstruction model is used as the target image reconstruction model.
  • an image reconstruction device comprising:
  • the data acquisition module is configured to acquire the under-sampled K-space data of the dynamic magnetic resonance image sequence obtained based on the preset under-sampling model; the image reconstruction module is configured to input the under-sampled K-space data into the data generated by the above-mentioned image reconstruction model.
  • the target image reconstruction model obtained by the method the reconstructed image corresponding to the undersampled K-space data is obtained.
  • Also provided is a computer device comprising:
  • one or more processors a memory arranged to store one or more programs; when said one or more programs are executed by said one or more processors, causing said one or more processors to implement the above-mentioned images Reconstruction model generation method or image reconstruction method.
  • a computer-readable storage medium which stores a computer program, and when the program is executed by a processor, realizes the above-mentioned image reconstruction model generation method or image reconstruction method.
  • FIG. 1 is a flowchart of a method for generating an image reconstruction model provided in Embodiment 1 of the present application;
  • FIG. 2 is a schematic diagram of a network structure of an image reconstruction network provided in Embodiment 1 of the present application;
  • Embodiment 3 is a flowchart of an image reconstruction method provided in Embodiment 2 of the present application.
  • FIG. 4 is a schematic structural diagram of an apparatus for generating an image reconstruction model according to Embodiment 3 of the present application.
  • FIG. 5 is a schematic structural diagram of an image reconstruction apparatus according to Embodiment 4 of the present application.
  • FIG. 6 is a schematic structural diagram of a computer device according to Embodiment 5 of the present application.
  • FIG. 1 is a flowchart of a method for generating an image reconstruction model according to Embodiment 1 of the present application. This embodiment can be applied to a situation where a fully sampled image of a magnetic resonance dynamic image is used as a sample to train an image reconstruction model.
  • the method may be executed by an image reconstruction model generating apparatus, which may be implemented in software and/or hardware, and integrated into an electronic device with an application development function.
  • the image reconstruction model generation method includes the following steps:
  • the full-sampled K-space data of the dynamic magnetic resonance image sequence is pre-collected sample data, and a high-resolution magnetic resonance dynamic image can be reconstructed according to the full-sampled K-space data of the dynamic magnetic resonance image sequence.
  • the dynamic magnetic resonance image sequence may be each frame of the magnetic resonance cardiac cine imaging.
  • the preset undersampling model can be determined by the preset undersampling operator, the Fourier transform operator and the coil sensitivity parameter according to the requirement of the sampling acceleration multiple.
  • M is the undersampling operator
  • F is the Fourier transform operator
  • C is the coil sensitivity map
  • X is the fully sampled
  • step S110 first, in the fully sampled K-space data of the dynamic magnetic resonance image sequence, the multi-column data of the fully-sampled K-space data corresponding to each frame of image is spliced into a data with only one column in the order of the columns; then , splicing the column data corresponding to all image frames in the order of the image frames to obtain X.
  • C can be estimated by algorithms such as ESPIRiT or Walsh
  • F is the operator of the Fourier transform
  • M is a vector composed of 0 and 1, which determines which points are collected and which points are not collected, and the value of the points not collected is 0.
  • the image reconstruction model is an image reconstruction model that is modeled and trained according to the sparse prior and low-rank prior characteristics of dynamic magnetic resonance data.
  • the construction process of the image reconstruction model is as follows:
  • a low-rank matrix is constructed for the matrix X, and the matrix X can be decomposed into a background component L and a dynamic component S. Because there is a lot of related information between multiple frames in the background component L, the L matrix has a low rank. Meanwhile, in cardiac cine imaging, the beating area of the heart is small, and after the background component L is removed, the remaining S component itself has sparsity.
  • the dynamic component S may also be sparsely transformed to improve its sparsity. The stronger the S sparsity, the better the reconstructed image.
  • the coefficient transformation can be realized by methods such as Fourier transform, wavelet transform or discrete cosine transform. For example, a one-dimensional Fourier transform is performed on S in the time direction, and the transformed matrix is more sparse than S.
  • L, S, and X are data matrices of the same dimension.
  • the MRI reconstruction problem can be written as:
  • ⁇ L and ⁇ S are the regularization factors for low-quality constraints and sparse constraints, respectively, A is the encoding matrix, y is the undermined k-space data, and D is the sparse transformation matrix.
  • * represents the matrix kernel norm, that is, the sum of the non-zero singular values of the matrix is calculated. In mathematics, the sum norm is often used to approximate the matrix rank.
  • auxiliary variable X can enable L and S to perform inexact search in the initial iterative step after the model is successfully constructed, so that the algorithm can converge to the optimal L and S more quickly. Fast convergence is very important for iterative algorithm networking, because during networking, a small number of iterative network modules need to be used to replace the original more iterative steps.
  • the penalty function can be solved by an alternate minimization algorithm, and the following three sub-problems are obtained.
  • the target image reconstruction model can be obtained by networking the following three sub-problems.
  • the angle brackets indicate the inner product of the two matrices within the angle brackets. It is equivalent to the 0th-order term in the Taylor expansion of the function, but here is a matrix, so it must be written in the form of an inner product.
  • L has a low rank
  • Equation 9 the form of the iterative solution can be as shown in Equation 9, there are still three problems to be solved: first, the iteration takes a long time to converge, and the reconstruction speed is slow, especially after the calculation of singular value decomposition is added to the iterative process; third Second, the regularization parameter is difficult to adjust, and it takes a lot of time to try. Especially, L+S has two components. If ⁇ L is too large compared to ⁇ S , the S part of the reconstructed image will not be sparse enough and contain a large number of static components.
  • L+S-Net contains multiple network blocks, and each network block contains the Three network modules, namely the low-rank module L k , the sparse module S k , and the data consistency module X k :
  • the low-rank module L k+1 performs a learnable singular value soft threshold operation (Learned Singular Value Threshold, LSVT) on X k -S k , which is the same as that shown in formula (10), but the threshold is replaced by a learnable value Variables:
  • the threshold value of the soft threshold operator is:
  • ⁇ 1 is the largest singular value and ⁇ is a learnable threshold factor.
  • ⁇ is a learnable threshold factor.
  • a learnable convolutional neural network C is used to replace the approximation operator
  • the threshold factor ⁇ , the convolutional neural network C, and the update step size ⁇ are all independently learnable.
  • X 0 and L 0 are initialized to zero-padded corresponding to the under-mined K-space data y
  • S 0 is initialized with all 0s, and these learnable parameters are continuously optimized, and finally high-quality reconstruction results are obtained to generate an image reconstruction model.
  • the reconstructed image corresponding to the fully sampled K-space data is a standard image with high reconstruction quality.
  • the process of image reconstruction model training is the process of learning and updating the parameters in the model.
  • the optimization of parameters makes the image output by the model closer and closer to the standard image. .
  • the under-sampled K-space data corresponding to the full-sampled K-space data is obtained; then, the The undersampled K-space data is input to, and the image reconstruction model is established according to the sub-problem obtained by solving the magnetic resonance image reconstruction problem under the constraints of low-rank and sparse characteristics on the full-sampled K-space data, and the model is trained; when When the mean square error between the reconstructed image generated by the image reconstruction model and the reconstructed image corresponding to the fully sampled K-space data satisfies the preset condition, the model training is completed, and the target image reconstruction model is obtained.
  • the image reconstruction model can be established by making full use of the low-rank and sparse characteristics of the sampled data while speeding up the image reconstruction speed. to improve the reconstructed image quality.
  • FIG. 3 is a flowchart of an image reconstruction method according to Embodiment 2 of the present application, and this embodiment is applicable to the case of medical image reconstruction.
  • the method may be performed by an image reconstruction apparatus, and the apparatus may be implemented in software and/or hardware, and integrated into a computer device with an application development function.
  • the image reconstruction method includes the following steps:
  • the sampling model can be set according to the requirement of the sampling speed, and the preset undersampling model is determined by the preset undersampling operator, the Fourier transform operator and the coil sensitivity parameter.
  • the preset undersampling operator determines how fast the samples are doubled.
  • M is the undersampling operator
  • F is the Fourier transform operator
  • C is the coil sensitivity maps
  • X is the dynamic magnetic resonance that will be fully sampled
  • step S210 first, in the full-sampled K-space data of the dynamic magnetic resonance image sequence, the multi-column data of the full-sampled K-space data corresponding to each frame of image is spliced into a data with only one column according to the sequence of columns; then, The column data corresponding to all image frames are spliced in the order of the image frames to obtain X.
  • C can be estimated by algorithms such as ESPIRiT or Walsh
  • F is the operator of the Fourier transform
  • M is a vector composed of 0 and 1, which determines which points are collected and which points are not collected, and the value of the points not collected is 0.
  • under-sampled K-space data can be obtained through the above sampling model. For example, acquiring magnetic resonance sampling data of cardiac dynamics.
  • the target image reconstruction model is a model for image reconstruction under the constraints of low-rank characteristics and sparse characteristics, which can reconstruct high-quality images.
  • a reconstructed image is obtained by sampling according to a preset sampling model and inputting the sampling data into the trained image reconstruction model; it solves the problem that the image reconstruction time in the related art is long or the sampling data cannot be fully utilized.
  • the problem of image reconstruction based on the characteristics of the image realizes that while speeding up the image reconstruction speed, it can make full use of the low-rank and sparse characteristics of the sampled data to establish an image reconstruction model to improve the quality of the reconstructed image.
  • FIG. 4 is a schematic structural diagram of an image reconstruction model generating apparatus according to Embodiment 3 of the present application. This embodiment can be applied to a situation where an image reconstruction model is trained using a fully sampled image of a magnetic resonance dynamic image as a sample.
  • the image reconstruction model generation apparatus includes a data preprocessing module 310 , a data input module 320 and a model generation module 330 .
  • the data preprocessing module 310 is configured to obtain full-sampled K-space data of the dynamic magnetic resonance image sequence, and obtain under-sampled K-space data corresponding to the full-sampled K-space data based on a preset under-sampling model;
  • the data input module 320 is configured to set In order to input the under-sampled K-space data to the sub-problem obtained by solving the magnetic resonance image reconstruction problem under the constraints of the low-rank characteristic and sparse characteristic for the fully-sampled K-space data, the established image reconstruction model,
  • the model is trained;
  • the model generation module 330 is configured to complete the model training when the mean square error between the reconstructed images generated by the image reconstruction model and the reconstructed images corresponding to the fully sampled K-space data satisfies a preset condition, Get the target image reconstruction model.
  • the under-sampled K-space data corresponding to the full-sampled K-space data is obtained; then, the The undersampled K-space data is input to, and the image reconstruction model is established according to the sub-problem obtained by solving the magnetic resonance image reconstruction problem under the constraints of low-rank and sparse characteristics on the full-sampled K-space data, and the model is trained; when When the mean square error between the reconstructed image generated by the image reconstruction model and the reconstructed image corresponding to the fully sampled K-space data satisfies the preset condition, the model training is completed, and the target image reconstruction model is obtained.
  • the image reconstruction model can be established by making full use of the low-rank and sparse characteristics of the sampled data while speeding up the image reconstruction speed. to improve the reconstructed image quality.
  • the image reconstruction model generation device further includes a model construction module, which is configured as a sub-problem obtained by solving the magnetic resonance image reconstruction problem under the constraints of low-rank characteristics and sparse characteristics based on the fully sampled K-space data, Build an image reconstruction model.
  • a model construction module which is configured as a sub-problem obtained by solving the magnetic resonance image reconstruction problem under the constraints of low-rank characteristics and sparse characteristics based on the fully sampled K-space data, Build an image reconstruction model.
  • model construction module is set to:
  • the fully sampled K-space data is modeled to represent the magnetic resonance image reconstruction problem under the constraints of low-rank characteristics and sparse characteristics; setting the magnetic resonance image reconstruction problem Auxiliary variables representing the model, and determining a penalty function representing the model based on the auxiliary variables; determining three sub-problems representing the model according to the penalty function; solving the three sub-problems respectively, and obtaining a networked the image reconstruction model.
  • model construction module can also be set to:
  • the three sub-problems are optimized and rewritten respectively; the optimized and rewritten three sub-problems are solved respectively by the approaching gradient method, and an iterative representation of the solution of each sub-problem is obtained; the process of the iterative representation is networked to obtain the Image reconstruction model.
  • model construction module may also be configured to optimize and rewrite the three sub-problems in the following ways, including:
  • the three sub-problems are optimized and rewritten respectively according to the result of the expansion of the penalty function at the preset value of the data fidelity item.
  • the image reconstruction model includes a low-rank network module, a sparse network module and a data consistency network module.
  • the image reconstruction model generation apparatus provided by the embodiment of the present application can execute the image reconstruction model generation method provided by any embodiment of the present application, and has functional modules and effects corresponding to the execution method.
  • FIG. 5 is a schematic structural diagram of an image reconstruction apparatus according to Embodiment 4 of the present application, and this embodiment is applicable to situations where this embodiment is applicable.
  • the image reconstruction apparatus includes a data acquisition module 410 and an image reconstruction module 420 .
  • the data acquisition module 410 is configured to acquire the under-sampled k-space data of the dynamic magnetic resonance image sequence obtained based on the preset under-sampling model; the image reconstruction module 420 is configured to input the under-sampled K-space data into the data obtained by any of the embodiments.
  • the target image reconstruction model obtained by the image reconstruction model generation method a reconstructed image corresponding to the undersampled K-space data is obtained.
  • a reconstructed image is obtained by sampling according to a preset sampling model and inputting the sampling data into the trained image reconstruction model; it solves the problem that the image reconstruction time in the related art is long or the sampling data cannot be fully utilized.
  • the problem of image reconstruction based on the characteristics of the image realizes that while speeding up the image reconstruction speed, it can make full use of the low-rank and sparse characteristics of the sampled data to establish an image reconstruction model to improve the quality of the reconstructed image.
  • the image reconstruction apparatus provided by the embodiment of the present application can execute the image reconstruction method provided by any embodiment of the present application, and has functional modules and effects corresponding to the execution method.
  • FIG. 6 is a schematic structural diagram of a computer device according to Embodiment 5 of the present application.
  • Figure 6 shows a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present application.
  • the computer device 12 shown in FIG. 6 is only an example, and should not impose any limitations on the functions and scope of use of the embodiments of the present application.
  • the computer device 12 may be any terminal device with computing capability, such as an intelligent controller, a server, a mobile phone and other terminal devices.
  • computer device 12 takes the form of a general-purpose computing device.
  • Components of computer device 12 may include, but are not limited to, one or more processors or processing units 16 , system memory 28 , and a bus 18 connecting various system components including system memory 28 and processing unit 16 .
  • Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of a variety of bus structures.
  • these architectures include, but are not limited to, Industrial Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (Video Electronics Standards) Association, VESA) local bus and Peripheral Component Interconnect (PCI) bus.
  • Computer device 12 includes, for example, various computer system readable media. These media can be any available media that can be accessed by computer device 12, including both volatile and nonvolatile media, removable and non-removable media.
  • System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and/or cache memory 32 .
  • Computer device 12 may include other removable/non-removable, volatile/non-volatile computer system storage media.
  • storage system 34 may be configured to read and write to non-removable, non-volatile magnetic media (not shown in FIG. 6, commonly referred to as a "hard drive").
  • a magnetic disk drive configured to read and write to removable non-volatile magnetic disks (eg "floppy disks") and removable non-volatile optical disks (eg Compact Disc Read-Only Memory) may be provided Read-Only Memory, CD-ROM), digital versatile disc read-only memory (Digital Versatile Disc Read-Only Memory, DVD-ROM) or other optical media) optical disk drive for reading and writing.
  • each drive may be connected to bus 18 through one or more data media interfaces.
  • System memory 28 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of embodiments of the present application.
  • a program/utility 40 having a set (at least one) of program modules 42, which may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and programs Data, each or a combination of these examples may include an implementation of a network environment.
  • Program modules 42 generally perform the functions and/or methods of the embodiments described herein.
  • Computer device 12 may also communicate with one or more external devices 14 (eg, keyboard, pointing device, display 24, etc.), may also communicate with one or more devices that enable a user to interact with computer device 12, and/or communicate with Any device (eg, network card, modem, etc.) that enables the computer device 12 to communicate with one or more other computing devices. Such communication may take place through an input/output (I/O) interface 22 . Also, computer device 12 may communicate with one or more networks (eg, Local Area Network (LAN), Wide Area Network (WAN), and/or public networks such as the Internet) through network adapter 20. As shown, network adapter 20 communicates with other modules of computer device 12 via bus 18 . It should be understood that, although not shown in FIG.
  • computer device 12 may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, disk arrays (Redundant Arrays of Independent Disks, RAID) systems, tape drives, and data backup storage systems, etc.
  • the processing unit 16 executes a variety of functional applications and data processing by running the program stored in the system memory 28, for example, implementing the steps of an image reconstruction model generation method provided by the embodiment of the present invention, and the method includes:
  • the steps of an image reconstruction method provided by the embodiment of the present invention can also be implemented, and the method includes:
  • the sixth embodiment provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the image reconstruction model generation method provided by any embodiment of the present application, including:
  • the steps of an image reconstruction method provided by the embodiment of the present invention can also be implemented, and the method includes:
  • the computer storage medium of the embodiments of the present application may adopt any combination of one or more computer-readable media.
  • the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination of the above. Examples (non-exhaustive list) of computer readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, RAM, ROM, Erasable Programmable Read-Only Memory (Erasable Programmable Read-Only Memory) Memory, EPROM or flash memory), optical fiber, CD-ROM, optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.
  • a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a propagated data signal in baseband or as part of a carrier wave, with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • a computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .
  • the program code embodied on the computer readable medium may be transmitted by any suitable medium, including but not limited to: wireless, wire, optical fiber cable, radio frequency (RF), etc., or any suitable combination of the above.
  • suitable medium including but not limited to: wireless, wire, optical fiber cable, radio frequency (RF), etc., or any suitable combination of the above.
  • Computer program code for carrying out the operations of the present application may be written in one or more programming languages, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional A procedural programming language, such as the "C" language or similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any kind of network, including a LAN or WAN, or may be connected to an external computer (eg, using an Internet service provider to connect through the Internet).
  • the above-mentioned multiple modules or multiple steps of the present application can be implemented by a general-purpose computing device, and they can be centralized on a single computing device, or distributed on a network composed of multiple computing devices. implemented by program code executable by a computer device so that they can be stored in a storage device and executed by a computing device, or they can be separately made into a plurality of integrated circuit modules, or a plurality of modules or steps in them can be made into a single integrated circuit modules.
  • the present application is not limited to any particular combination of hardware and software.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)

Abstract

一种图像重建模型生成及装置、图像重建方法及装置、设备、介质。图像重建模型生成方法包括：获取动态磁共振图像序列的全采样K空间数据，并基于预设欠采样模型得到全采样K空间数据对应的欠采样K空间数据（S110）；将欠采样K空间数据输入至，根据对全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题进行求解得到的子问题，建立的图像重建模型，对图像重建模型进行训练（S120）；当所述图像重建模型生成的重建图像，与所述全采样K空间数据对应的重建图像间的均方误差满足预设条件时，完成模型训练，得到目标图像重建模型（S130）。

Description

图像重建模型生成及装置、图像重建方法及装置、设备、介质
本申请要求在2021年03月17日提交中国专利局、申请号为202110287100.7的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及医学图像处理技术领域，例如涉及一种图像重建模型生成方法及装置、图像重建方法及装置、设备、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，由于磁共振的物理特性、实现磁共振的硬件和心脏运动周期时长的制约，磁共振心脏电影成像的时间和空间分辨率往往受限，无法准确评估部分心脏疾病，如心率不齐等的心功能情况。因此，需要在保证成像质量的前提下，利用快速成像方法提高磁共振心脏电影成像的时间和空间分辨率。
常用的加速磁共振心脏电影成像的方法，包括并行成像(Parallel Imaging，PI)、压缩感知(Compressed Sensing，CS)技术、基于低秩矩阵分解以及深度学习方法。
但是，传统的并行成像或者压缩感知技术，没有利用大数据先验，并且这种迭代优化方法的参数较难选择且耗时。而基于深度学习的神经网络方法虽然能够避免迭代求解步骤，加速了重建时间，但是由于深度学习的神经网络方法仅仅依赖于大数据的稀疏先验，限制了图像重建效果的提升。
发明内容
本申请实施例提供了一种图像重建模型生成及装置、图像重建方法及装置、设备、介质，以实现在加快图像重建速度的同时，能够充分利用采样数据的低秩特性与稀疏特性，建立图像重建模型，以提升重建图像质量。
提供了一种图像重建模型生成方法，包括：
获取动态磁共振图像序列的全采样K空间数据，并基于预设欠采样模型得到所述全采样K空间数据对应的欠采样K空间数据；将所述欠采样K空间数据输入至，根据对所述全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题进行求解得到的子问题，建立的图像重建模型，对所述图像 重建模型进行训练；在所述图像重建模型生成的重建图像，与所述全采样K空间数据对应的重建图像间的均方误差满足预设条件的情况下，完成对所述图像重建模型的训练，将训练后的图像重建模型作为目标图像重建模型。
一实现方式中，根据对所述全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题求解得到的子问题，建立图像重建模型，包括：
根据磁共振扫描对象运动在时间上的周期性，将所述全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题模型化表示；设置所述磁共振图像重建问题的表示模型的辅助变量，并基于所述辅助变量确定所述表示模型的罚函数；根据所述罚函数确定所述表示模型的三个子问题；对所述三个子问题分别进行求解，并对求解结果网络化得到所述图像重建模型。
一实现方式中，所述对所述三个子问题分别进行求解，并对求解结果网络化得到所述图像重建模型，包括：
分别对所述三个子问题进行改写；采用迫近梯度法分别对改写后的三个子问题进行求解，得到每个子问题的解的迭代表示；将每个子问题的解的迭代表示的过程网络化，得到所述图像重建模型。
一实现方式中，所述分别对所述三个子问题进行改写，包括：
根据所述罚函数在数据保真项的预设数值展开表示的结果，分别对所述三个子问题进行改写。
一实现方式中，所述图像重建模型包括低秩网络模块、稀疏网络模块和数据一致性模块。
还提供了一种图像重建方法，包括：
获取基于预设欠采样模型得到的动态磁共振图像序列的欠采样K空间数据；将所述欠采样K空间数据输入至上述的图像重建模型生成方法得到的目标图像重建模型中，得到所述欠采样K空间数据对应的重建图像。
还提供了一种图像重建模型生成装置，包括：
数据预处理模块，设置为获取动态磁共振图像序列的全采样K空间数据，并基于预设欠采样模型得到所述全采样K空间数据对应的欠采样K空间数据；数据输入模块，设置为将所述欠采样K空间数据输入至，根据对所述全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题进行求解得到的子问题，建立的图像重建模型，对所述图像重建模型进行训练；模型生成模块，设置为在所述图像重建模型生成的重建图像，与所述全采样K空间数据对应的重建图像间的均方误差满足预设条件的情况下，完成对所述图像重建模 型的训练，将训练后的图像重建模型作为目标图像重建模型。
还提供了一种图像重建装置，包括：
数据获取模块，设置为获取基于预设欠采样模型得到的动态磁共振图像序列的欠采样K空间数据；图像重建模块，设置为将所述欠采样K空间数据输入至由上述的图像重建模型生成方法得到的目标图像重建模型中，得到所述欠采样K空间数据对应的重建图像。
还提供了一种计算机设备，包括：
一个或多个处理器；存储器，设置为存储一个或多个程序；当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现上述的图像重建模型生成方法或图像重建方法。
还提供了一种计算机可读存储介质，存储有计算机程序，该程序被处理器执行时实现上述的图像重建模型生成方法或图像重建方法。
附图说明
图1是本申请实施例一提供的一种图像重建模型生成方法的流程图；
图2是本申请实施例一提供的一种图像重建网络的网络结构示意图；
图3是本申请实施例二提供的一种图像重建方法的流程图；
图4是本申请实施例三提供的一种图像重建模型生成装置的结构示意图；
图5是本申请实施例四提供的一种图像重建装置的结构示意图；
图6是本申请实施例五提供的一种计算机设备的结构示意图。
具体实施方式
下面结合附图和实施例对本申请进行说明。
实施例一
图1为本申请实施例一提供的一种图像重建模型生成方法的流程图，本实施例可适用于以磁共振动态图像的全采样图像为样本，训练图像重建模型的情况。该方法可以由图像重建模型生成装置执行，该装置可以由软件和/或硬件的方式来实现，集成于具有应用开发功能的电子设备中。
如图1所示，图像重建模型生成方法包括以下步骤：
S110、获取动态磁共振图像序列的全采样K空间数据，并基于预设欠采样模型得到所述全采样K空间数据对应的欠采样K空间数据。
动态磁共振图像序列的全采样K空间数据是预先采集的样本数据，可以根据动态磁共振图像序列的全采样K空间数据重建得到高分辨率的磁共振动态图像。例如，动态磁共振图像序列可以是磁共振心脏电影成像中的每一帧图像。预设欠采样模型可以根据采样加速倍数的需求由预设欠采样算子、傅里叶变换算子及线圈敏感度参数确定。
预设欠采样模型可以表示为y＝MFCX(1)；其中，M为欠采样算子，F是傅里叶变换算子，C是线圈敏感度矩阵(sensitivity maps)，X是将全采样的动态磁共振图像序列中的每一帧图像拉伸成一维向量，多个一维向量按图像帧顺序作为列顺序拼接在一起，形成的一个图像矩阵，y是欠采样K空间数据。在步骤S110的中，首先，将动态磁共振图像序列的全采样K空间数据中，每一帧图像对应的全采样K空间数据的多列数据按照列的顺序拼接成为一个只有一列的数据；然后，将所有图像帧对应的列数据按照图像帧的顺序进行拼接，得到X。C可以通过ESPIRiT或者Walsh等算法估计出来，F就是傅里叶变换的算子，M是由0和1构成的向量，决定哪些点采集，哪些点不采集，不采集的点数值为0。
S120、将所述欠采样K空间数据输入至，根据对所述全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题进行求解得到的子问题，建立的图像重建模型，对模型进行训练。
图像重建模型是根据动态磁共振数据的稀疏先验和低秩先验特性进行建模并训练得到的图像重建模型。该图像重建模型的构建过程如下：
首先，针对矩阵X先构造出低秩矩阵，可以将矩阵X分解成背景分量L和动态分量S，因为背景分量L中多帧之间存在大量相关信息，所以L矩阵具有低秩性。同时，在心脏电影成像中，心脏跳动的区域较小，去除了背景分量L后，剩余的S分量本身就具有稀疏性。在一种实施方式中，还可以对动态分量S进行稀疏变换，使其稀疏性提升。S稀疏性越强，重建图像的效果越好。系数变换可以通过傅里叶变换、小波变换或是离散余弦变换等方法实现。例如，对S在时间方向做一维傅里叶变换，变换后的矩阵比S更稀疏。L、S及X是维度相同的数据矩阵。
根据心脏跳动在时间方向的周期性，在低秩特性和稀疏特性的约束下MRI重建问题可以写作：
Figure PCTCN2021085552-appb-000001
其中，λ L和λ S分别是低质约束和稀疏约束的正则化因子，A是编码矩阵，y是欠采的K空间数据，D是稀疏变换矩阵。|| ||*表示矩阵核范数，即计算矩阵非零奇异值之和。数学上常用和范数来逼近矩阵秩。
为了解决该MRI重建问题，在本实施例中引入一个辅助变量X，用来代表L 和S的累加和。那么上述优化问题可以写作：
Figure PCTCN2021085552-appb-000002
辅助变量X的引入可以在模型构造成功后，最开始的迭代步骤中，使L和S可以进行非精确搜索，从而使算法更快收敛到最优的L和S。快速收敛对于迭代算法网络化十分重要，因为网络化时，需要用少量的迭代网络模块代替原先较多的迭代步骤。为了解公式(3)中的等式优化问题，确定公式(3)的罚函数：
Figure PCTCN2021085552-appb-000003
罚函数可以通过交替最小化算法求解，得到如下三个子问题，最终将如下三个子问题进行网络化便可以得到目标图像重建模型。
Figure PCTCN2021085552-appb-000004
在一种实施例中，由于在X子问题中求解(A *A+ρI) -1较为耗时，可以采用一种非精确方式求解X子问题。将罚函数J在数据保真项
Figure PCTCN2021085552-appb-000005
Figure PCTCN2021085552-appb-000006
的
Figure PCTCN2021085552-appb-000007
处线性展开来得到X子优化问题：
Figure PCTCN2021085552-appb-000008
其中，
Figure PCTCN2021085552-appb-000009
表示J线性化处理后的结果，
Figure PCTCN2021085552-appb-000010
的表示中，尖括号表示求尖括号内两个矩阵的内积。相当于函数泰勒展开中的第0阶项，不过这里是矩阵，所以要写成内积的形式。
Figure PCTCN2021085552-appb-000011
那么公式(5)中的子问题可以改写成：
Figure PCTCN2021085552-appb-000012
每一个子问题可以用迫近梯度法求解，基于
Figure PCTCN2021085552-appb-000013
上述子问题可以写作下列迭代步骤：
Figure PCTCN2021085552-appb-000014
其中，
Figure PCTCN2021085552-appb-000015
是奇异值软阈值算子。
Figure PCTCN2021085552-appb-000016
其中，
Figure PCTCN2021085552-appb-000017
是软阈值算子，X＝UΣV *是X的奇异值分解，Σ是奇异值矩阵，U和V分别是左右矩阵，*表示共轭转置；
Figure PCTCN2021085552-appb-000018
是与稀疏变换D相关的迫近算子，若D是正交变换，
Figure PCTCN2021085552-appb-000019
则是软阈值算子，若D为非正交变换，那么P的形式无法直接写出解析解；γ是更新步长，γ＝1/(1+ηρ)。每一个迭代步中，
Figure PCTCN2021085552-appb-000020
通过削减小于阈值λ L的奇异值，使得L具有低秩性；公式(9)中X迭代步骤中，
Figure PCTCN2021085552-appb-000021
是重建图像和输入K空间数据在K空间中的残差，用于数据一致性修正。
虽然迭代解的形式可以如公式9所示，但是仍然有三个问题需要解决：第一，迭代需要很长的时间收敛，重建速度慢，尤其是奇异值分解的计算加入到迭代过程中后；第二，正则化参数难以调节，需要耗费大量时间尝试，尤其是L+S有两个分量，如果λ L相比λ S太大，重建图像的S部分将不够稀疏，包含大量静态成分，如果λ L相比λ S太小，重建图像中L部分将包含许多动态信息，与模型相违背；第三，只有在稀疏变换D具有正交性时，
Figure PCTCN2021085552-appb-000022
的显式解才能写出，在稀疏变换D不具有正交性时无法得到
Figure PCTCN2021085552-appb-000023
的计算方式，但是正交的稀疏变换会极大限制稀疏变换的选择范围，可能导致重建性能受限。
因此，将公式(9)中的迭代过程网络化，展开成为低秩+稀疏网络(L+S-Net)，L+S-Net包含多个网络块，每一个网络块包含图2所示的三个网络模块，分别是低秩模块L k、稀疏模块S k、数据一致性模块X k：
Figure PCTCN2021085552-appb-000024
低秩模块L k+1对X k-S k进行可学习的奇异值软阈值操作(Learned Singular Value Threshold，LSVT)，该操作与公式(10)中所示一致，但是阈值换成了可学习的变量：
H β(X)＝UΛ T(β,Σ)(Σ)V *     (12)
其中，软阈值算子的阈值为：
T(β,Σ)＝β·σ 1(13)
其中，σ 1是最大的奇异值，β是可学习的阈值因子。公式(11)中的稀疏模块中，使用一个可学习的卷积神经网络C来代替迫近算子
Figure PCTCN2021085552-appb-000025
每个网络块中，阈值因子β、卷积神经网络C、更新步长γ都是独立可学习的，在网络训练中，将X 0和L 0初始化为欠采K空间数据y对应的补零图，S 0采用全0初始化，这些可学习参数不断优化，最后得到高质量的重建结果，生成图像重建模型。
S130、当所述图像重建模型生成的重建图像，与所述全采样K空间数据对应的重建图像间的均方误差满足预设条件时，完成模型训练，得到目标图像重建模型。
全采样K空间数据对应的重建图像为重建质量高的标准图像，图像重建模型训练的过程，也就是对模型中参数进行学习更新的过程，参数的优化使模型输出的图像越来越接近标准图像。当图像重建模型生成的重建图像，与全采样K空间数据对应的重建图像间的均方误差满足预设条件，也就是模型收敛时，便可以得到目标图像重建模型，完成模型训练过程。
本实施例的技术方案，通过根据预设欠采样模型对获取到的动态磁共振图像序列的全采样K空间数据样本进行处理，得到全采样K空间数据对应的欠采样K空间数据；然后，将欠采样K空间数据输入至，根据对全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题进行求解得到的子问题，建立的图像重建模型，对模型进行训练；当图像重建模型生成的重建图像，与全采样K空间数据对应的重建图像间的均方误差满足预设条件时，完成模型训练，得到目标图像重建模型。解决了相关技术中图像重建时间长或不能充分利用采样数据特性进行图像重建的问题，实现了在加快图像重建速度的同时，能够充分利用采样数据的低秩特性与稀疏特性，建立图像重建模型，以提升重建图像质量。
实施例二
图3为本申请实施例二提供的一种图像重建方法的流程图，本实施例可适用于对医学图像重建的情况。该方法可以由图像重建装置执行，该装置可以由软件和/或硬件的方式来实现，集成于具有应用开发功能的计算机设备中。
如图3所示，图像重建方法包括以下步骤：
S210、获取基于预设欠采样模型得到的动态磁共振图像序列的欠采样K空间数据。
在进行磁共振扫描采样的过程中，可以根据采样速度的需求设置采样的模型，预设欠采样模型由预设欠采样算子、傅里叶变换算子及线圈敏感度参数确定。预设欠采样算子决定了采样的加倍速度。
预设欠采样模型可以表示为y＝MFCX；其中，M为欠采样算子，F是傅里叶变换算子，C是线圈敏感度矩阵(sensitivity maps)，X是将全采样的动态磁共振图像序列中的每一帧图像拉伸成一维向量，多个一维向量按图像帧顺序作为列顺序拼接在一起，形成的一个图像矩阵，y是欠采样K空间数据。在步骤S210中，首先，将动态磁共振图像序列的全采样K空间数据中，每一帧图像对应的全采样K空间数据的多列数据按照列的顺序拼接成为一个只有一列的数据；然后，将所有图像帧对应的列数据按照图像帧的顺序进行拼接，得到X。C可以通过ESPIRiT或者Walsh等算法估计出来，F就是傅里叶变换的算子，M是由0和1构成的向量，决定哪些点采集，哪些点不采集，不采集的点数值为0。
在进行磁共振扫描时，可以通过上述采样模型得到欠采样的K空间数据。例如，获取心脏动态的磁共振采样数据。
S220、将所述欠采样K空间数据输入至任一实施例所述的图像重建模型生成方法得到的目标图像重建模型中，得到所述欠采样K空间数据对应的重建图像。
目标图像重建模型是在低秩特性以及稀疏特性的约束下进行图像重建的模型，能够重建得到高质量的图像。
本实施例的技术方案，通过根据预设的采样模型进行采样，并将采样数据输入至训练好的图像重建模型中，得到重建图像；解决了相关技术中图像重建时间长或不能充分利用采样数据特性进行图像重建的问题，实现了在加快图像重建速度的同时，能够充分利用采样数据的低秩特性与稀疏特性，建立图像重建模型，以提升重建图像质量。
实施例三
图4为本申请实施例三提供的一种图像重建模型生成装置的结构示意图，本实施例可适用于以磁共振动态图像的全采样图像为样本，训练图像重建模型的情况。
如图4所示，图像重建模型生成装置包括数据预处理模块310、数据输入模块320和模型生成模块330。
数据预处理模块310，设置为获取动态磁共振图像序列的全采样K空间数据，并基于预设欠采样模型得到所述全采样K空间数据对应的欠采样K空间数据；数据输入模块320，设置为将所述欠采样K空间数据输入至，根据对所述全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题进行求解得到的子问题，建立的图像重建模型，对模型进行训练；模型生成模块330，设置为当所述图像重建模型生成的重建图像，与所述全采样K空间数据对 应的重建图像间的均方误差满足预设条件时，完成模型训练，得到目标图像重建模型。
本实施例的技术方案，通过根据预设欠采样模型对获取到的动态磁共振图像序列的全采样K空间数据样本进行处理，得到全采样K空间数据对应的欠采样K空间数据；然后，将欠采样K空间数据输入至，根据对全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题进行求解得到的子问题，建立的图像重建模型，对模型进行训练；当图像重建模型生成的重建图像，与全采样K空间数据对应的重建图像间的均方误差满足预设条件时，完成模型训练，得到目标图像重建模型。解决了相关技术中图像重建时间长或不能充分利用采样数据特性进行图像重建的问题，实现了在加快图像重建速度的同时，能够充分利用采样数据的低秩特性与稀疏特性，建立图像重建模型，以提升重建图像质量。
可选的，所述图像重建模型生成装置还包括模型构造模块，设置为根据对所述全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题求解得到的子问题，建立图像重建模型。
可选的，所述模型构造模块设置为于：
根据磁共振扫描对象运动在时间上的周期性，将所述全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题模型化表示；设置所述磁共振图像重建问题的表示模型的辅助变量，并基于所述辅助变量确定所述表示模型的罚函数；根据所述罚函数确定所述表示模型的三个子问题；对所述三个子问题分别进行求解，并网络化得到所述图像重建模型。
可选的，所述模型构造模块还可设置为：
分别对所述三个子问题进行优化改写；采用迫近梯度法分别对优化改写后的三个子问题进行求解，得到每个子问题的解的迭代表示；将所述迭代表示的过程网络化，得到所述图像重建模型。
可选的，所述模型构造模块还可设置为通过如下方式分别对所述三个子问题进行优化改写，包括：
根据所述罚函数在数据保真项的预设数值展开表示的结果，分别对所述三个子问题进行优化改写。
可选的，所述图像重建模型包括低秩网络模块、稀疏网络模块和数据一致性网络模块。
本申请实施例所提供的图像重建模型生成装置可执行本申请任意实施例所提供的图像重建模型生成方法，具备执行方法相应的功能模块和效果。
实施例四
图5为本申请实施例四提供的一种图像重建装置的结构示意图，本实施例可适用于的情况。
如图5所示，图像重建装置包括数据获取模块410和图像重建模块420。
数据获取模块410，设置为获取基于预设欠采样模型得到的动态磁共振图像序列的欠采样K空间数据；图像重建模块420，设置为将所述欠采样K空间数据输入至由任一实施例所述的图像重建模型生成方法得到的目标图像重建模型中，得到所述欠采样K空间数据对应的重建图像。
本实施例的技术方案，通过根据预设的采样模型进行采样，并将采样数据输入至训练好的图像重建模型中，得到重建图像；解决了相关技术中图像重建时间长或不能充分利用采样数据特性进行图像重建的问题，实现了在加快图像重建速度的同时，能够充分利用采样数据的低秩特性与稀疏特性，建立图像重建模型，以提升重建图像质量。
本申请实施例所提供的图像重建装置可执行本申请任意实施例所提供的图像重建方法，具备执行方法相应的功能模块和效果。
实施例五
图6为本申请实施例五提供的一种计算机设备的结构示意图。图6示出了适于用来实现本申请实施方式的示例性计算机设备12的框图。图6显示的计算机设备12仅仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。计算机设备12可以任意具有计算能力的终端设备，如智能控制器及服务器、手机等终端设备。
如图6所示，计算机设备12以通用计算设备的形式表现。计算机设备12的组件可以包括但不限于：一个或者多个处理器或者处理单元16，系统存储器28，连接不同系统组件(包括系统存储器28和处理单元16)的总线18。
总线18表示几类总线结构中的一种或多种，包括存储器总线或者存储器控制器，外围总线，图形加速端口，处理器或者使用多种总线结构中的任意总线结构的局域总线。举例来说，这些体系结构包括但不限于工业标准体系结构(Industrial Standard Architecture，ISA)总线，微通道体系结构(Micro Channel Architecture，MAC)总线，增强型ISA总线、视频电子标准协会(Video Electronics Standards Association，VESA)局域总线以及外围组件互连(Peripheral Component Interconnect，PCI)总线。
计算机设备12例如包括多种计算机系统可读介质。这些介质可以是任何能够被计算机设备12访问的可用介质，包括易失性和非易失性介质，可移动的和 不可移动的介质。
系统存储器28可以包括易失性存储器形式的计算机系统可读介质，例如随机存取存储器(Random Access Memory，RAM)30和/或高速缓存存储器32。计算机设备12可以包括其它可移动/不可移动的、易失性/非易失性计算机系统存储介质。仅作为举例，存储系统34可以设置为读写不可移动的、非易失性磁介质(图6未显示，通常称为“硬盘驱动器”)。尽管图6中未示出，可以提供设置为对可移动非易失性磁盘(例如“软盘”)读写的磁盘驱动器，以及对可移动非易失性光盘(例如光盘只读存储器(Compact Disc Read-Only Memory，CD-ROM)，数字多功能盘只读存储器(Digital Versatile Disc Read-Only Memory，DVD-ROM)或者其它光介质)读写的光盘驱动器。在这些情况下，每个驱动器可以通过一个或者多个数据介质接口与总线18相连。系统存储器28可以包括至少一个程序产品，该程序产品具有一组(例如至少一个)程序模块，这些程序模块被配置以执行本申请实施例的功能。
具有一组(至少一个)程序模块42的程序/实用工具40，可以存储在例如系统存储器28中，这样的程序模块42包括但不限于操作系统、一个或者多个应用程序、其它程序模块以及程序数据，这些示例中的每一个或一种组合中可能包括网络环境的实现。程序模块42通常执行本申请所描述的实施例中的功能和/或方法。
计算机设备12也可以与一个或多个外部设备14(例如键盘、指向设备、显示器24等)通信，还可与一个或者多个使得用户能与该计算机设备12交互的设备通信，和/或与使得该计算机设备12能与一个或多个其它计算设备进行通信的任何设备(例如网卡，调制解调器等等)通信。这种通信可以通过输入/输出(Input/Output，I/O)接口22进行。并且，计算机设备12还可以通过网络适配器20与一个或者多个网络(例如局域网(Local Area Network，LAN)，广域网(Wide Area Network，WAN)和/或公共网络，例如因特网)通信。如图所示，网络适配器20通过总线18与计算机设备12的其它模块通信。应当明白，尽管图6中未示出，可以结合计算机设备12使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、磁盘阵列(Redundant Arrays of Independent Disks，RAID)系统、磁带驱动器以及数据备份存储系统等。
处理单元16通过运行存储在系统存储器28中的程序，从而执行多种功能应用以及数据处理，例如实现本发实施例所提供的一种图像重建模型生成方法步骤，该方法包括：
获取动态磁共振图像序列的全采样K空间数据，并基于预设欠采样模型得 到所述全采样K空间数据对应的欠采样K空间数据；将所述欠采样K空间数据输入至，根据对所述全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题进行求解得到的子问题，建立的图像重建模型，对模型进行训练；当所述图像重建模型生成的重建图像，与所述全采样K空间数据对应的重建图像间的均方误差满足预设条件时，完成模型训练，得到目标图像重建模型。
或者，还可以实现本发实施例所提供的一种图像重建方法步骤，该方法包括：
获取基于预设欠采样模型得到的动态磁共振图像序列的欠采样K空间数据；将所述欠采样K空间数据输入至由任一实施例所述的图像重建模型生成方法得到的目标图像重建模型中，得到所述欠采样K空间数据对应的重建图像。
实施例六
本实施例六提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如本申请任意实施例所提供的图像重建模型生成方法，包括：
获取动态磁共振图像序列的全采样K空间数据，并基于预设欠采样模型得到所述全采样K空间数据对应的欠采样K空间数据；将所述欠采样K空间数据输入至，根据对所述全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题进行求解得到的子问题，建立的图像重建模型，对模型进行训练；当所述图像重建模型生成的重建图像，与所述全采样K空间数据对应的重建图像间的均方误差满足预设条件时，完成模型训练，得到目标图像重建模型。
或者，还可以实现本发实施例所提供的一种图像重建方法步骤，该方法包括：
获取基于预设欠采样模型得到的动态磁共振图像序列的欠采样K空间数据；将所述欠采样K空间数据输入至由任一实施例所述的图像重建模型生成方法得到的目标图像重建模型中，得到所述欠采样K空间数据对应的重建图像。
本申请实施例的计算机存储介质，可以采用一个或多个计算机可读的介质的任意组合。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质。计算机可读存储介质例如可以是但不限于：电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、RAM、ROM、可擦式可编程只读存储器(Erasable Programmable  Read-Only Memory，EPROM或闪存)、光纤、CD-ROM、光存储器件、磁存储器件、或者上述的任意合适的组合。在本文件中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。
计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、射频(Radio Frequency，RF)等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本申请操作的计算机程序代码，所述程序设计语言包括面向对象的程序设计语言，诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言，诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络，包括LAN或WAN，连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
上述的本申请的多个模块或多个步骤可以用通用的计算装置来实现，它们可以集中在单个计算装置上，或者分布在多个计算装置所组成的网络上，可选地，他们可以用计算机装置可执行的程序代码来实现，从而可以将它们存储在存储装置中由计算装置来执行，或者将它们分别制作成多个集成电路模块，或者将它们中的多个模块或步骤制作成单个集成电路模块来实现。这样，本申请不限制于任何特定的硬件和软件的结合。

Claims (10)

  1. 一种图像重建模型生成方法，包括：
    获取动态磁共振图像序列的全采样K空间数据，并基于预设欠采样模型得到所述全采样K空间数据对应的欠采样K空间数据；
    将所述欠采样K空间数据输入至，根据对所述全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题进行求解得到的子问题，建立的图像重建模型，对所述图像重建模型进行训练；
    在所述图像重建模型生成的重建图像，与所述全采样K空间数据对应的重建图像间的均方误差满足预设条件的情况下，完成对所述图像重建模型的训练，将训练后的图像重建模型作为目标图像重建模型。
  2. 根据权利要求1所述的方法，其中，所述根据对所述全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题求解得到的子问题，建立图像重建模型，包括：
    根据磁共振扫描对象运动在时间上的周期性，将所述全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题模型化表示；
    设置所述磁共振图像重建问题的表示模型的辅助变量，并基于所述辅助变量确定所述表示模型的罚函数；
    根据所述罚函数确定所述表示模型的三个子问题；
    对所述三个子问题分别进行求解，并对求解结果网络化得到所述图像重建模型。
  3. 根据权利要求2所述的方法，其中，所述对所述三个子问题分别进行求解，并对求解结果网络化得到所述图像重建模型，包括：
    分别对所述三个子问题进行改写；
    采用迫近梯度法分别对改写后的三个子问题进行求解，得到每个子问题的解的迭代表示；
    将每个子问题的解的迭代表示的过程网络化，得到所述图像重建模型。
  4. 根据权利要求3所述的方法，其中，所述分别对所述三个子问题进行改写，包括：
    根据所述罚函数在数据保真项的预设数值展开表示的结果，分别对所述三个子问题进行改写。
  5. 根据权利要求1-4中任一项所述的方法，其中，所述图像重建模型包括低秩网络模块、稀疏网络模块和数据一致性网络模块。
  6. 一种图像重建方法，包括：
    获取基于预设欠采样模型得到的动态磁共振图像序列的欠采样K空间数据；
    将所述欠采样K空间数据输入至由权利要求1-5中任一项所述的图像重建模型生成方法得到的目标图像重建模型中，得到所述欠采样K空间数据对应的重建图像。
  7. 一种图像重建模型生成装置，包括：
    数据预处理模块，设置为获取动态磁共振图像序列的全采样K空间数据，并基于预设欠采样模型得到所述全采样K空间数据对应的欠采样K空间数据；
    数据输入模块，设置为将所述欠采样K空间数据输入至，根据对所述全采样K空间数据，在低秩特性和稀疏特性约束下进行磁共振图像重建问题进行求解得到的子问题，建立的图像重建模型，对所述图像重建模型进行训练；
    模型生成模块，设置为在所述图像重建模型生成的重建图像，与所述全采样K空间数据对应的重建图像间的均方误差满足预设条件的情况下，完成对所述图像重建模型的训练，将训练后的图像重建模型作为目标图像重建模型。
  8. 一种图像重建装置，包括：
    数据获取模块，设置为获取基于预设欠采样模型得到的动态磁共振图像序列的欠采样K空间数据；
    图像重建模块，设置为将所述欠采样K空间数据输入至由权利要求1-5中任一项所述的图像重建模型生成方法得到的目标图像重建模型中，得到所述欠采样K空间数据对应的重建图像。
  9. 一种计算机设备，包括：
    至少一个处理器；
    存储器，设置为存储至少一个程序；
    当所述至少一个程序被所述至少一个处理器执行，使得所述至少一个处理器实现如权利要求1-6中任一项所述的方法。
  10. 一种计算机可读存储介质，存储有计算机程序，其中，所述程序被处理器执行时实现如权利要求1-6中任一项所述的方法。
PCT/CN2021/085552 2021-03-17 2021-04-06 图像重建模型生成及装置、图像重建方法及装置、设备、介质 Ceased WO2022193379A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110287100.7A CN115115723B (zh) 2021-03-17 2021-03-17 图像重建模型生成及图像重建方法、装置、设备和介质
CN202110287100.7 2021-03-17

Publications (1)

Publication Number Publication Date
WO2022193379A1 true WO2022193379A1 (zh) 2022-09-22

Family

ID=83321852

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/085552 Ceased WO2022193379A1 (zh) 2021-03-17 2021-04-06 图像重建模型生成及装置、图像重建方法及装置、设备、介质

Country Status (2)

Country Link
CN (1) CN115115723B (zh)
WO (1) WO2022193379A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116012475A (zh) * 2022-12-21 2023-04-25 上海交通大学 磁共振图像欠采样重建方法、系统、介质、电子设备
CN118397126A (zh) * 2024-04-29 2024-07-26 上海交通大学 动态磁共振图像无校准重建方法、系统、介质、电子设备
CN121392063A (zh) * 2025-12-24 2026-01-23 南京钺曦医疗科技有限公司 适用于核磁共振成像设备的图像重建方法和系统

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024092387A1 (zh) * 2022-10-31 2024-05-10 中国科学院深圳先进技术研究院 基于部分可分函数自适应动态磁共振快速成像方法及装置
CN116725515B (zh) * 2023-08-14 2024-01-26 山东奥新医疗科技有限公司 一种磁共振快速成像方法
CN119810231B (zh) * 2024-12-18 2026-03-27 华中科技大学 一种磁共振声辐射力成像重建方法及其系统
CN119625111B (zh) * 2025-02-14 2025-09-16 中国科学院深圳先进技术研究院 低场磁共振扩散成像重建方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102309328A (zh) * 2011-10-19 2012-01-11 中国科学院深圳先进技术研究院 弥散张量成像方法及系统
US20120081114A1 (en) * 2009-05-27 2012-04-05 Daniel Weller System for Accelerated MR Image Reconstruction
CN104714199A (zh) * 2013-12-17 2015-06-17 西门子(深圳)磁共振有限公司 一种磁共振成像方法和装置
US20180306884A1 (en) * 2017-04-21 2018-10-25 Mayo Foundation For Medical Education And Research Accelerated dynamic magnetic resonance imaging using low rank matrix completion
CN111157935A (zh) * 2019-12-31 2020-05-15 上海联影智能医疗科技有限公司 磁共振成像方法、装置、存储介质及计算机设备

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103654789B (zh) * 2013-12-10 2015-12-30 深圳先进技术研究院 磁共振快速参数成像方法和系统
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
CN108447102A (zh) * 2018-02-11 2018-08-24 南京邮电大学 一种低秩与稀疏矩阵分解的动态磁共振成像方法
CN109671129B (zh) * 2018-12-14 2022-10-14 深圳先进技术研究院 一种自适应参数学习的动态磁共振图像重建方法和装置
CN110728732A (zh) * 2019-10-12 2020-01-24 深圳先进技术研究院 一种图像重建方法、装置、设备及介质
CN110717958A (zh) * 2019-10-12 2020-01-21 深圳先进技术研究院 一种图像重建方法、装置、设备及介质
CN110766768B (zh) * 2019-10-23 2023-08-04 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
CN111714124B (zh) * 2020-06-18 2023-11-03 中国科学院深圳先进技术研究院 磁共振电影成像方法、装置、成像设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120081114A1 (en) * 2009-05-27 2012-04-05 Daniel Weller System for Accelerated MR Image Reconstruction
CN102309328A (zh) * 2011-10-19 2012-01-11 中国科学院深圳先进技术研究院 弥散张量成像方法及系统
CN104714199A (zh) * 2013-12-17 2015-06-17 西门子(深圳)磁共振有限公司 一种磁共振成像方法和装置
US20180306884A1 (en) * 2017-04-21 2018-10-25 Mayo Foundation For Medical Education And Research Accelerated dynamic magnetic resonance imaging using low rank matrix completion
CN111157935A (zh) * 2019-12-31 2020-05-15 上海联影智能医疗科技有限公司 磁共振成像方法、装置、存储介质及计算机设备

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116012475A (zh) * 2022-12-21 2023-04-25 上海交通大学 磁共振图像欠采样重建方法、系统、介质、电子设备
CN118397126A (zh) * 2024-04-29 2024-07-26 上海交通大学 动态磁共振图像无校准重建方法、系统、介质、电子设备
CN121392063A (zh) * 2025-12-24 2026-01-23 南京钺曦医疗科技有限公司 适用于核磁共振成像设备的图像重建方法和系统

Also Published As

Publication number Publication date
CN115115723B (zh) 2025-02-21
CN115115723A (zh) 2022-09-27

Similar Documents

Publication Publication Date Title
CN115115723B (zh) 图像重建模型生成及图像重建方法、装置、设备和介质
CN111714124B (zh) 磁共振电影成像方法、装置、成像设备及存储介质
CN110766769B (zh) 一种磁共振图像重建方法、装置、设备和介质
CN109633502B (zh) 磁共振快速参数成像方法及装置
CN109961491A (zh) 多模态图像截断补偿方法、装置、计算机设备和介质
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
CN110766768B (zh) 一种磁共振图像重建方法、装置、设备和介质
WO2018099321A1 (zh) 一种基于广义树稀疏的权重核范数磁共振成像重建方法
CN115115722B (zh) 图像重建模型生成及图像重建方法、装置、设备和介质
CN109658468B (zh) 磁共振参数成像方法、装置、设备及存储介质
CN110717958A (zh) 一种图像重建方法、装置、设备及介质
CN108447102A (zh) 一种低秩与稀疏矩阵分解的动态磁共振成像方法
CN110490947B (zh) 核磁共振图像重建方法、装置、存储介质及终端设备
CN117670703A (zh) 一种基于多任务联合训练的磁共振图像恢复方法
CN115170418B (zh) 符合退化的低秩高维图像填充模型及其填充方法与系统
CN112991483A (zh) 一种非局部低秩约束的自校准并行磁共振成像重构方法
CN113050009B (zh) 三维磁共振快速参数成像方法和装置
CN110728732A (zh) 一种图像重建方法、装置、设备及介质
CN116381580A (zh) 基于对数范数和先验信息的核磁共振图像重构方法及系统
WO2023050249A1 (zh) 基于深度学习的磁共振成像方法、系统、终端及存储介质
CN114037631A (zh) 一种图像纹理增强方法、装置、电子设备及存储介质
CN119904545A (zh) 一种基于低秩稀疏的动态并行mri图像重建方法、装置、系统及介质
WO2023029087A1 (zh) 一种低场磁共振快速成像方法、终端设备及计算机存储介质
CN114862984A (zh) 基于锐度增强的磁共振图像重建方法、系统、介质及设备
CN120852204B (zh) 一种多块磁粒子成像方法和系统

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: 21930967

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: 21930967

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 21930967

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 1205A DATED 27/05/2024)

122 Ep: pct application non-entry in european phase

Ref document number: 21930967

Country of ref document: EP

Kind code of ref document: A1