WO2022193378A1 - Procédé et appareil de génération de modèle de reconstruction d'image, procédé et appareil de reconstruction d'image, dispositif et support - Google Patents

Procédé et appareil de génération de modèle de reconstruction d'image, procédé et appareil de reconstruction d'image, dispositif et support Download PDF

Info

Publication number
WO2022193378A1
WO2022193378A1 PCT/CN2021/085551 CN2021085551W WO2022193378A1 WO 2022193378 A1 WO2022193378 A1 WO 2022193378A1 CN 2021085551 W CN2021085551 W CN 2021085551W WO 2022193378 A1 WO2022193378 A1 WO 2022193378A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
reconstruction
resolution
network model
super
Prior art date
Application number
PCT/CN2021/085551
Other languages
English (en)
Chinese (zh)
Inventor
梁栋
朱燕杰
黄文麒
贾森
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 WO2022193378A1 publication Critical patent/WO2022193378A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G06T11/003—Reconstruction from projections, e.g. tomography
    • G06T11/006—Inverse problem, transformation from projection-space into object-space, e.g. transform methods, back-projection, algebraic methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T11/00—2D [Two Dimensional] image generation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4046—Scaling of whole images or parts thereof, e.g. expanding or contracting using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2211/00—Image generation
    • G06T2211/40—Computed tomography
    • G06T2211/424—Iterative

Definitions

  • the present application relates 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 Imaging is an advanced imaging technology that is widely used in clinical diagnosis and medical research.
  • the hardware for realizing magnetic resonance, human activities and the degree of human tolerance due to the physical characteristics of magnetic resonance, the hardware for realizing magnetic resonance, human activities and the degree of human tolerance, the spatial resolution of magnetic resonance imaging is often limited, and it is impossible to accurately evaluate some cardiovascular and cerebrovascular diseases, such as some small Cerebrovascular wall thickening and plaque conditions. Therefore, it is particularly important to improve the spatial resolution of magnetic resonance imaging.
  • High-resolution magnetic resonance images correspond to high-density k-space sampling matrices, but it takes a lot of time to acquire a large number of k-space points.
  • the methods of obtaining high-resolution MRI images are mainly divided into two schemes.
  • the first one is from the perspective of Compressed Sensing (CS) reconstruction, using prior information such as the sparsity of MRI images to highly undersample the K-space. , in order to save the scanning time, and then use the CS reconstruction algorithm to reconstruct the high-resolution image.
  • Another scheme is based on the image super-resolution technology in computer vision, first collect and reconstruct low-resolution MRI images, and then use the image super-resolution algorithm to generate high-resolution images.
  • This type of method has two steps. The first step is to collect low-resolution k-space information, and use the reconstruction algorithm to obtain low-resolution images.
  • the second step is to input the low-resolution MRI image into the image super-resolution algorithm model to obtain High
  • the present application provides an image reconstruction model generation method and apparatus, an image reconstruction method and apparatus, equipment, and medium, so as to achieve high-resolution image reconstruction and improve image quality while increasing the sampling acceleration multiple.
  • An image reconstruction model generation method including:
  • Acquire full-sampling magnetic resonance k-space data and obtain under-sampling k-space data corresponding to the full-sampling magnetic resonance k-space data based on a preset low-resolution sampling model; input the under-sampling k-space data to, according to the The inverse problem of the preset low-resolution model is solved to obtain a sub-problem, the established super-resolution reconstruction generates a network model, and an under-sampling reconstructed image is obtained;
  • the fully sampled reconstructed image is simultaneously input to the discriminant network model associated with the super-resolution reconstruction and generation network model, and the super-resolution reconstruction and generation network model is trained according to the output result of the discriminant network model until the loss function of the discriminant network model is reached. If the preset conditions are met, the training of the super-resolution reconstruction generation network model is completed, and the trained super-resolution reconstruction generation network model is used as the target image reconstruction model.
  • the sub-problems are obtained by solving the inverse problem of the preset low-resolution model, and the super-resolution reconstruction generation network model is established, including:
  • the two sub-problems are solved separately, and the solution result is networked to obtain the super-score reconstruction generation network model, including:
  • the two sub-problems are solved by the approaching gradient method respectively, and the iterative representation of the solution of the auxiliary variable and the solution of the inverse problem is obtained; the process of the iterative representation is networked to obtain the super-score reconstruction generation network Model.
  • the super-resolution reconstruction generation network model includes a refinement module and a data consistency module, wherein the refinement module is a neural network module associated with the auxiliary variable.
  • the discriminant network model is a pooled pyramid network; and the loss function is an adversarial generation network gradient penalty penalty loss function.
  • the preset low-resolution sampling model is determined by a preset low-resolution undersampling operator, a Fourier transform operator, and a coil sensitivity parameter.
  • An image reconstruction method including:
  • an image reconstruction model generation device comprising:
  • the sample processing module is configured to obtain full-sampled magnetic resonance K-space data, and obtain under-sampled K-space data corresponding to the full-sampled magnetic resonance K-space data based on a preset low-resolution sampling model;
  • the sample input module is configured to The under-sampling K-space data is input to, and the sub-problem is obtained by solving the inverse problem of the preset low-resolution model, the established super-resolution reconstruction generates a network model, and an under-sampling reconstructed image is obtained;
  • the model generation module is set to The under-sampled reconstructed image and the fully-sampled reconstructed image corresponding to the fully-sampled magnetic resonance K-space data are simultaneously input to the discriminant network model associated with the super-score reconstruction generation network model, and trained according to the output result of the discriminant network model The super-score reconstruction generation network model, until the loss function of the discriminant network model satisfies the preset condition, completes the training of the super-score reconstruction
  • an image reconstruction device comprising:
  • the data acquisition module is configured to obtain the under-sampled K-space data obtained by sampling based on the preset low-resolution sampling model; the image reconstruction module is configured to input the under-sampled K-space data to be obtained by the above-mentioned image reconstruction model generation method In the target image reconstruction model of , 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 a super-division 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 flow chart of a method for generating an image reconstruction model according to Embodiment 1 of the present application. This embodiment is applicable to the case of image reconstruction model training based on fully sampled magnetic resonance K-space data.
  • 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 magnetic resonance k-space data is pre-collected sample data, and a high-resolution magnetic resonance image can be obtained by reconstructing the full-sampled magnetic resonance k-space data.
  • the preset low-resolution sampling model can be determined by the preset low-resolution undersampling operator, the Fourier transform operator and the coil sensitivity parameter according to the requirement of the acceleration multiple.
  • the acceleration multiple refers to the acceleration multiple of collecting the original data, that is, the full-sampled magnetic resonance K-space data, that is, the under-sampling multiple. It can be determined by dividing the total number of data points of the fully sampled magnetic resonance k-space data by the number of acquired data points.
  • the acceleration factor can reach more than 12 times, that is to say, through the image reconstruction model generated in this embodiment, a reconstructed image with sufficiently high resolution can be reconstructed even if the acceleration factor is more than 12 times.
  • the level of resolution depends on the size of the sampling matrix (sampling operator).
  • step S110 the full-sampled magnetic resonance K-space data can be used as x
  • C can be estimated by algorithms such as ESPIRiT or Walsh
  • F is the operator of Fourier transform
  • M is a vector composed of 0 and 1, which determines which Points are collected, which points are not collected, and the value of the points not collected is 0.
  • S120 Input the undersampled K-space data into the sub-problem obtained by optimizing and solving the inverse problem of the preset low-resolution model, and obtain the undersampling reconstructed image based on the established super-resolution reconstruction generation network model.
  • the super-resolution reconstruction generative network model is constructed based on the results of the optimal solution of the inverse problem of the preset low-resolution model, including the following steps:
  • the inverse problem of the preset low-resolution model is optimized and solved under preset constraints to obtain the optimization problem.
  • the operator MHFC in formula (1) can be denoted as A.
  • the inverse problem corresponding to formula (1) can be obtained by solving the optimization problem to obtain formula (2).
  • R(x) is the generalized image domain constraint.
  • the denominator is set to 2.
  • the 2 derived from the derivative of the second norm can be eliminated with it, and s is an auxiliary variable.
  • the alternating linearization minimization algorithm can be used to determine the two sub-problems of the optimization problem according to the penalty function, and formula (4) can be obtained.
  • the reason why the solution algorithm is called the alternating linearization minimum algorithm is that in the solution process, the After linearization, it can be recorded that in, are the linearized quadratic coefficients. ⁇ can be replaced by another letter, but, in this embodiment, in order to simplify the derived formula (5) in form, the linearized quadratic term coefficient is taken as
  • the approaching gradient method can be used to solve the two sub-problems respectively to obtain the iterative steps of the two sub-problems, as shown in formula (5).
  • Prox R is the approximation operator related to the image domain regularization operator R (ie, the image domain constraint); ⁇ is the update step size; is the representation of the image K-space residual in the image domain, which can be expressed by formula (6):
  • SRR-Net Super Resolution Reconstruction Network
  • Sk refinement module
  • X k data consistency module
  • the approximation operator Prox R in formula (5) is networked into a residual three-dimensional convolutional neural network (3Dimension residual Convolutional Neural Networks, 3D residual CNN) C.
  • C is a three-layer convolutional neural network, and ⁇ controls the degree of retention of residuals. Both ⁇ and step size ⁇ are learnable network parameters that bring more flexibility to the model. It can be determined from formula (7) that only x 0 needs to be initialized in this model. After x 0 is initialized, s 1 can be calculated according to x 0 , and then x 1 can be calculated according to s 1 to realize the loop iteration process. In this embodiment, the initialization value of x 0 is the zero-padding map data corresponding to the undersampled K-space data.
  • S130 Simultaneously input the under-sampled reconstructed image and the fully-sampled reconstructed image corresponding to the fully-sampled magnetic resonance K-space data into a discriminant network model associated with the super-score reconstruction generation network model, and according to the discriminant network model The output result trains the super-resolution reconstruction generation network model, until the loss function of the discriminant network model satisfies a preset condition, completes the super-resolution reconstruction generation network model training, and generates a target image reconstruction model.
  • a discriminant network is introduced, and based on the idea of a generative adversarial network, the super-score reconstruction generative network model is trained.
  • the discriminant network model adopts the pooling pyramid network, and adopts the adversarial generation network gradient penalty loss function (Wasserstein Generative Adversarial Networks-Gradient Penalty loss, WGAN-GP loss) as the loss function of the pooling pyramid network.
  • the discriminant network model will judge the difference between the under-sampled reconstructed image and the fully-sampled reconstructed image.
  • the difference corresponds to
  • the value of the loss function satisfies the preset convergence condition
  • the model training process is completed, and the target image reconstruction model is obtained.
  • the fully sampled magnetic resonance k-space data is processed by using a preset low-resolution sampling model to obtain corresponding under-sampled k-space data, and then the under-sampled k-space data is input into, according to the preset
  • the inverse problem of the low-resolution model is optimized and solved to obtain the super-resolution reconstruction generative network model established by the sub-problem, and the under-sampled reconstructed image is obtained; the under-sampled reconstructed image and the fully-sampled reconstructed image corresponding to the fully-sampled magnetic resonance K-space data are simultaneously input to
  • the discriminant network model associated with the super-resolution reconstruction generation network model train the super-resolution reconstruction and generation network model according to the output result of the discriminant network model, until the loss function of the discriminant network model satisfies the preset condition, complete the super-resolution reconstruction and generate the network model Train to generate a target image reconstruction model for use in magnetic resonance image reconstruction.
  • Fig. 3 is a flow chart of an image reconstruction method provided in Embodiment 2 of the present application, and this embodiment is applicable to the case of performing medical image reconstruction on undersampled magnetic resonance k-space data.
  • 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 requirements of the sampling speed.
  • the preset low-resolution model is determined by the preset low-resolution undersampling operator, Fourier transform operator and coil sensitivity parameters .
  • the preset low-resolution undersampling operator determines how fast the sampling is doubled.
  • the central part information (low-frequency information) of the K-space corresponding to the high-resolution image corresponds to the K-space of the low-resolution image.
  • the level of resolution depends on the size of the sampling matrix (sampling operator).
  • the full-sampled magnetic resonance K-space data can be used as x
  • C can be estimated by algorithms such as ESPIRiT or Walsh
  • F is the operator of Fourier transform
  • M is a vector composed of 0 and 1, which determines which Points are collected, which points are not collected, and the value of the points not collected is 0.
  • the target image reconstruction model obtained by the image reconstruction model generation method described in any of the above embodiments can reconstruct and output low-resolution K-space data to obtain a high-resolution image.
  • the acceleration factor of the undersampled low-resolution K-space data can reach more than 12 times, that is to say, with the image reconstruction model generated in this embodiment, a reconstructed image with sufficiently high resolution can be reconstructed even if the acceleration factor is more than 12 times.
  • sampling is performed by a preset low-resolution sampling model, and then the sampling data is input into the trained image reconstruction model to obtain a high-resolution reconstructed image; it solves the problem of accelerating the reconstruction of magnetic resonance images in the related art.
  • the problem is that the multiple is limited and the quality of the reconstructed image needs to be improved, so that the high-resolution image can be reconstructed and the image quality can be improved while increasing the sampling acceleration multiple.
  • FIG. 4 is a schematic structural diagram of an image reconstruction model generating apparatus according to Embodiment 3 of the present application. This embodiment is applicable to the case of image reconstruction model training based on fully sampled magnetic resonance K-space data.
  • the image reconstruction model generation apparatus includes a sample processing module 310, a sample input module 320 and a model generation module 330.
  • the sample processing module 310 is configured to obtain full-sampled magnetic resonance k-space data, and obtain under-sampled K-space data corresponding to the full-sampled magnetic resonance K-space data based on a preset low-resolution sampling model;
  • the sample input module 320 is configured to Inputting the under-sampling K-space data to the sub-problem by optimizing and solving the inverse problem of the preset low-resolution model, the established super-resolution reconstruction generates a network model, and obtains an under-sampling reconstructed image;
  • model generation module 330 is set to simultaneously input the under-sampled reconstructed image and the fully-sampled reconstructed image corresponding to the fully-sampled magnetic resonance k-space data into the discriminant network model associated with the super-score reconstruction generation network model, according to the discriminant network model The output result of training the super-resolution reconstruction generation network model, until the loss function of the discriminant network model satisfies the preset condition, the super-resolution reconstruction generation
  • the fully sampled magnetic resonance k-space data is processed by using a preset low-resolution sampling model to obtain corresponding under-sampled k-space data, and then the under-sampled k-space data is input into, according to the preset
  • the inverse problem of the low-resolution model is optimized and solved to obtain the super-resolution reconstruction generative network model established by the sub-problem, and the under-sampled reconstructed image is obtained; the under-sampled reconstructed image and the fully-sampled reconstructed image corresponding to the fully-sampled magnetic resonance K-space data are simultaneously input to
  • the discriminant network model associated with the super-resolution reconstruction generation network model train the super-resolution reconstruction and generation network model according to the output result of the discriminant network model, until the loss function of the discriminant network model satisfies the preset condition, complete the super-resolution reconstruction and generate the network model Train to generate a target image reconstruction model for use in magnetic resonance image reconstruction.
  • the image reconstruction model generation device further includes a model construction module, which is configured to: establish a super-resolution reconstruction generation network model according to the sub-problems obtained by optimally solving the inverse problem of the preset low-resolution model.
  • a model construction module which is configured to: establish a super-resolution reconstruction generation network model according to the sub-problems obtained by optimally solving the inverse problem of the preset low-resolution model.
  • model construction module is set to:
  • model construction module is further set to:
  • the two sub-problems are solved by the approaching gradient method respectively, and the iterative representation of the solution of the auxiliary variable and the solution of the inverse problem is obtained; the process of the iterative representation is networked to obtain the super-score reconstruction generation network Model.
  • the super-resolution reconstruction generation network model includes a refinement module and a data consistency module, wherein the refinement module is a neural network module associated with the auxiliary variable.
  • the discriminant network model is a pooled pyramid network; and the loss function is an adversarial generation network gradient penalty penalty loss function.
  • the preset low-resolution sampling model is determined by a preset low-resolution undersampling operator, a Fourier transform operator, and a coil sensitivity parameter.
  • 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. This embodiment can be applied to the case of performing medical image reconstruction on undersampled magnetic resonance K-space data.
  • 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 undersampled K-space data obtained by sampling based on a preset low-resolution sampling model; the image reconstruction module 420 is configured to input the K-space data into the image described in any of the embodiments.
  • the target image reconstruction model obtained by the reconstruction model generation method a reconstructed image corresponding to the undersampled K-space data is obtained.
  • sampling is performed by a preset low-resolution sampling model, and then the sampling data is input into the trained image reconstruction model to obtain a high-resolution reconstructed image; it solves the problem of accelerating the reconstruction of magnetic resonance images in the related art.
  • the problem is that the multiple is limited and the quality of the reconstructed image needs to be improved, so that the high-resolution image can be reconstructed and the image quality can be improved while increasing the sampling acceleration multiple.
  • 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 computer through any kind of network, including a LAN or a wide area network 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

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Algebra (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)

Abstract

Procédé et appareil de génération de modèle de reconstruction d'image, procédé et appareil de reconstruction d'image, dispositif et support. Le procédé de génération de modèle de reconstruction d'image consiste à : obtenir des données d'espace K de résonance magnétique complètement échantillonnées et obtenir des données d'espace K sous-échantillonnées correspondant aux données d'espace K de résonance magnétique complètement échantillonnées sur la base d'un modèle d'échantillonnage à basse résolution prédéfini ; entrer les données d'espace K sous-échantillonnées dans un modèle de réseau de génération de reconstruction à super-résolution qui est établi par résolution d'un problème inverse du modèle à basse résolution prédéfini pour obtenir un sous-problème, afin d'obtenir une image reconstruite sous-échantillonnée ; et entrer simultanément l'image reconstruite sous-échantillonnée et une image reconstruite complètement échantillonnée correspondant aux données d'espace K de résonance magnétique complètement échantillonnées dans un modèle de réseau de discrimination associé au modèle de réseau de génération de reconstruction à super-résolution, entraîner le modèle de réseau de génération de reconstruction à super-résolution en fonction d'un résultat de sortie du modèle de réseau de discrimination, achever l'entraînement du modèle de réseau de génération de reconstruction à super-résolution et utiliser le modèle de réseau de génération de reconstruction à super-résolution entraîné en tant que modèle de reconstruction d'image cible.
PCT/CN2021/085551 2021-03-17 2021-04-06 Procédé et appareil de génération de modèle de reconstruction d'image, procédé et appareil de reconstruction d'image, dispositif et support WO2022193378A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110285759.9 2021-03-17
CN202110285759.9A CN115115722A (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

Publications (1)

Publication Number Publication Date
WO2022193378A1 true WO2022193378A1 (fr) 2022-09-22

Family

ID=83321863

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/085551 WO2022193378A1 (fr) 2021-03-17 2021-04-06 Procédé et appareil de génération de modèle de reconstruction d'image, procédé et appareil de reconstruction d'image, dispositif et support

Country Status (2)

Country Link
CN (1) CN115115722A (fr)
WO (1) WO2022193378A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115880157B (zh) * 2023-01-06 2023-05-26 中国海洋大学 一种k空间金字塔特征融合的立体图像超分辨率重建方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
US20200333416A1 (en) * 2019-04-19 2020-10-22 Regents Of The University Of Minnesota Scalable self-calibrated interpolation of undersampled magnetic resonance imaging data

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200333416A1 (en) * 2019-04-19 2020-10-22 Regents Of The University Of Minnesota Scalable self-calibrated interpolation of undersampled magnetic resonance imaging data
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

Also Published As

Publication number Publication date
CN115115722A (zh) 2022-09-27

Similar Documents

Publication Publication Date Title
CN109325985B (zh) 磁共振图像重建方法、装置和计算机可读存储介质
CN106780372B (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
CN104933683B (zh) 一种用于磁共振快速成像的非凸低秩重建方法
WO2021077557A1 (fr) Procédé et appareil de reconstruction d'image par résonance magnétique, dispositif, et support
WO2020114329A1 (fr) Imagerie paramétrique par résonance magnétique rapide et dispositif
WO2020135014A1 (fr) Procédé de construction de modèle d'imagerie médicale, dispositif, appareil et support de mémoire
WO2022193379A1 (fr) Procédé et appareil de génération de modèle de reconstruction d'image, procédé et appareil de reconstruction d'image, dispositif et support
WO2022193378A1 (fr) Procédé et appareil de génération de modèle de reconstruction d'image, procédé et appareil de reconstruction d'image, dispositif et support
Yang et al. Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging--Mini Review, Comparison and Perspectives
WO2021104954A1 (fr) Reconstruction d'image de détection compressée hybride
CN111784792A (zh) 基于双域卷积神经网络的快速磁共振重建系统及其训练方法与应用
CN112700508B (zh) 一种基于深度学习的多对比度mri图像重建方法
WO2024021796A1 (fr) Procédé et appareil de traitement d'image, dispositif électronique, support de stockage et produit de programme
WO2020253138A1 (fr) Dispositif, appareil, et procédé de classification, et support d'informations
WO2024051018A1 (fr) Procédé et appareil d'amélioration d'image de paramètre tep, dispositif et support d'enregistrement
CN111161370A (zh) 一种基于ai的人体多核dwi联合重建方法
WO2023050249A1 (fr) Procédé et système d'imagerie par résonance magnétique basés sur l'apprentissage profond, terminal et support de stockage
CN112669400B (zh) 基于深度学习预测和残差架构的动态mr重建方法
WO2021129235A1 (fr) Procédé et dispositif d'imagerie de paramètres de résonance magnétique tridimensionnelle rapide
US20230055826A1 (en) Systems and methods for magnetic resonance image reconstruction from incomplete k-space data
CN113592973A (zh) 一种基于多频复数卷积的磁共振图像重建方法及装置
Sun et al. DIR3D: Cascaded Dual-Domain Inter-Scale Mutual Reinforcement 3D Network for highly accelerated 3D MR image reconstruction
JP2021099794A (ja) ディープニューラルネットワークおよび測定データの再帰的間引きを使用して医用画像を再構築するためのシステムおよび方法
WO2022206021A1 (fr) Procédé et appareil de génération de modèle de reconstruction d'image, procédé et appareil de reconstruction d'image, dispositif et support
WO2023029087A1 (fr) Procédé d'imagerie par résonance magnétique rapide à faible champ, équipement terminal et support de stockage informatique

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: 21930966

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: 21930966

Country of ref document: EP

Kind code of ref document: A1