CN110717958A - Image reconstruction method, device, equipment and medium - Google Patents
Image reconstruction method, device, equipment and medium Download PDFInfo
- Publication number
- CN110717958A CN110717958A CN201910967757.0A CN201910967757A CN110717958A CN 110717958 A CN110717958 A CN 110717958A CN 201910967757 A CN201910967757 A CN 201910967757A CN 110717958 A CN110717958 A CN 110717958A
- Authority
- CN
- China
- Prior art keywords
- image reconstruction
- reconstruction model
- data
- target image
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000005070 sampling Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 12
- 230000009466 transformation Effects 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000001131 transforming effect Effects 0.000 claims description 2
- 238000013528 artificial neural network Methods 0.000 abstract description 14
- 230000008569 process Effects 0.000 abstract description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 238000003384 imaging method Methods 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000012512 characterization method Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- G06T2211/00—Image generation
- G06T2211/40—Computed tomography
- G06T2211/416—Exact reconstruction
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses an image reconstruction method, an image reconstruction device, image reconstruction equipment and an image reconstruction medium, wherein the method comprises the following steps: acquiring acquired under-sampled data, and inputting the under-sampled data into a pre-trained target image reconstruction model, wherein the target image reconstruction model is obtained by generalizing an iterative relation obtained by iteratively solving an original image reconstruction model and then solving the iterative relation; and acquiring a reconstructed image output by the target image reconstruction model. According to the image reconstruction method provided by the embodiment of the invention, the iteration relation after the iteration solution is carried out on the original image reconstruction model is generalized and then is solved to obtain the target image reconstruction model, and the reconstructed image is obtained based on the obtained target image reconstruction model and the undersampled data, so that the network freedom of a neural network is improved, the data consistency in the image reconstruction process is ensured, and the reconstructed image quality is improved.
Description
Technical Field
The embodiments of the present invention relate to the field of image reconstruction, and in particular, to an image reconstruction method, apparatus, device, and medium.
Background
Magnetic resonance images human tissue using static and radio frequency magnetic fields, which not only provides rich tissue contrast, but also is harmless to the human body, thus becoming a powerful tool for medical clinical diagnosis. However, the low imaging speed is a major bottleneck restricting the rapid development of the imaging device, and how to increase the scanning speed and reduce the scanning time is particularly important on the premise that the imaging quality is clinically acceptable.
In the fast imaging aspect, the deep learning method is adopted for magnetic resonance image reconstruction, and more attention is paid. The deep learning method utilizes a neural network to learn the optimal parameters required by reconstruction from a large amount of training data or directly learn the mapping relation from undersampled data to fully-acquired images, thereby obtaining better imaging quality and higher acceleration times than the traditional parallel imaging or compressed sensing method. The iterative soft threshold algorithm is a solving algorithm for an optimization problem constrained by L1, and is widely applied to solving an inverse problem. The ISTA-net method combining deep learning and the ISTA algorithm adopts a deep neural network to learn parameters and sparse transformation in the algorithm, and can obtain better effects than the traditional method in the problems of image reconstruction, denoising and the like. However, the existing deep neural network model is relatively fixed, and data consistency in the image reconstruction process may not be effectively ensured.
Disclosure of Invention
The embodiment of the invention provides an image reconstruction method, an image reconstruction device, image reconstruction equipment and an image reconstruction medium, which are used for guaranteeing data consistency in an image reconstruction process and improving reconstructed image quality.
In a first aspect, an embodiment of the present invention provides an image reconstruction method, including:
acquiring acquired under-sampled data, and inputting the under-sampled data into a pre-trained target image reconstruction model, wherein the target image reconstruction model is obtained by generalizing an iterative relation obtained by iteratively solving an original image reconstruction model and then solving the iterative relation;
and acquiring a reconstructed image output by the target image reconstruction model.
In a second aspect, an embodiment of the present invention further provides an image reconstruction apparatus, including:
the system comprises an under-sampling data acquisition module, a target image reconstruction model and a data processing module, wherein the under-sampling data acquisition module is used for acquiring acquired under-sampling data and inputting the under-sampling data into a pre-trained target image reconstruction model, and the target image reconstruction model is obtained by generalizing an iterative relation obtained by iteratively solving an original image reconstruction model;
and the reconstructed image acquisition module is used for acquiring a reconstructed image output by the target image reconstruction model.
In a third aspect, an embodiment of the present invention further provides a computer device, where the computer device includes:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement an image reconstruction method as provided by any of the embodiments of the invention.
In a fourth aspect, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the image reconstruction method according to any of the embodiments of the present invention.
The method comprises the steps of determining the corresponding relation between knowledge point data and video frames in a video to be segmented by acquiring the video to be segmented; and segmenting the video to be segmented according to the corresponding relation to obtain at least one video segment, and segmenting the video to be segmented according to the knowledge point data in the video to be segmented, so that the segmentation process of the video is simplified, and the segmentation accuracy of the video is improved.
The method comprises the steps of acquiring acquired under-sampled data, inputting the under-sampled data into a pre-trained target image reconstruction model, wherein the target image reconstruction model is obtained by generalizing an iterative relation obtained after an original image reconstruction model is iteratively solved; and acquiring a reconstructed image output by the target image reconstruction model. According to the image reconstruction method provided by the embodiment of the invention, the data fidelity item of the original image reconstruction model is generalized and then solved to obtain the target image reconstruction model, and the reconstructed image is obtained based on the obtained target image reconstruction model and the undersampled data, so that the network freedom of a neural network is improved, the data consistency in the image reconstruction process is ensured, and the reconstructed image quality is improved.
Drawings
Fig. 1 is a flowchart of an image reconstruction method according to an embodiment of the present invention;
fig. 2a is a flowchart of an image reconstruction method according to a second embodiment of the present invention;
fig. 2b is a schematic network structure diagram of a target image reconstruction model according to a second embodiment of the present invention;
FIG. 2c is a diagram of the reconstruction effect of image reconstruction by the image reconstruction method according to the second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an image reconstruction apparatus according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of an image reconstruction method according to an embodiment of the present invention. The embodiment is applicable to the situation when the acquired undersampled K-space data is subjected to image reconstruction. The method may be performed by an image reconstruction apparatus, which may be implemented in software and/or hardware, for example, which may be configured in a computer device. As shown in fig. 1, the method includes:
s110, acquiring the acquired under-sampled data, and inputting the under-sampled data into a pre-trained target image reconstruction model, wherein the target image reconstruction model is obtained by generalizing and then solving a data fidelity item of an original image reconstruction model.
In this embodiment, the acquired undersampled data is learned through a machine learning algorithm, so as to obtain a reconstructed image corresponding to the undersampled data. Specifically, the undersampled data is input into a trained target image reconstruction model, and a reconstructed image output by the target image reconstruction model is obtained. Optionally, the target image reconstruction model is constructed based on a neural network. The Neural Network is a module constructed based on an Artificial Neural Network (ANN). The artificial neural network is formed by connecting a large number of nodes (or called neurons) with each other. Each node represents a particular output function, called the excitation function. Each connection between two nodes represents a weighted value, called weight, for the signal passing through the connection. The neural network comprises a data input layer, a middle hiding layer and a data output layer. In this embodiment, the Neural network may be a Convolutional Neural Network (CNN), a Generic Adaptive Network (GAN) or other types of Neural network models. Optionally, the undersampled data may be undersampled K-space data obtained by scanning the magnetic resonance apparatus in the region to be imaged.
It should be noted that, in the embodiment of the present invention, the target image reconstruction model is obtained by generalizing and then solving the data fidelity term of the original image reconstruction model, and is obtained by generalizing again, and the data fidelity term of the original image reconstruction model is solved and then generalized to obtain the target image reconstruction model, which overcomes the disadvantage that the data in the original image reconstruction model needs to be established on the premise of linear unbiased estimation, so that the applicability of the target image reconstruction model is wider, and the network freedom of the neural network is improved.
And S120, acquiring a reconstructed image output by the target image reconstruction model.
In this embodiment, after the under-sampled data is input to the trained target image reconstruction model, the reconstructed image output by the target image reconstruction model is acquired, and the acquired reconstructed image is used as the image corresponding to the under-sampled data.
The method comprises the steps of acquiring acquired under-sampled data, inputting the under-sampled data into a pre-trained target image reconstruction model, wherein the target image reconstruction model is obtained by generalizing an iterative relation obtained after an original image reconstruction model is iteratively solved; the method comprises the steps of obtaining a reconstructed image output by the target image reconstruction model, generalizing an iteration relation obtained after iteration solving is conducted on an original image reconstruction model, and then solving to obtain a target image reconstruction model, and obtaining a reconstructed image based on the obtained target image reconstruction model and undersampled data, so that the network freedom of a neural network is improved, the data consistency in the image reconstruction process is guaranteed, and the quality of the reconstructed image is improved.
Example two
Fig. 2a is a flowchart of an image reconstruction method according to a second embodiment of the present invention. The present embodiment is optimized based on the above embodiments. As shown in fig. 2a, the method comprises:
s210, generalizing the data fidelity item in the original image reconstruction model to obtain a generalized image reconstruction model.
In the present embodiment, the original image reconstruction model is an image reconstruction model used in a conventional magnetic resonance image reconstruction method based on deep learning. The data fidelity item in the original image reconstruction model defines the relationship among the coding matrix, the image to be reconstructed and the undersampled K-space data. Generally, the data fidelity term in the original image reconstruction model is characterized by using a 2-norm between a reconstructed K space and a sampling point, but the least square constraint of the characterization is established on the premise of linear unbiased estimation, so that the data consistency in the image reconstruction process may not be effectively guaranteed by the above characterization method. In order to solve the above defects, in this embodiment, before solving the original image reconstruction model through the iterative soft threshold algorithm, the data fidelity term in the original image reconstruction model is generalized, and then the generalized original image reconstruction model is solved to obtain the target image reconstruction model, so that the target image reconstruction model has a wider application range, the network freedom of the neural network is improved, and the data consistency in the image reconstruction process is ensured.
In one embodiment, the original image reconstruction model is:
the method comprises the steps that Am-f is a data fidelity item of an original image reconstruction model, m is an image to be reconstructed, A is a coding matrix, f is undersampled data, lambda is a regular parameter, psi represents sparse transformation, and | Am-f | survival2Representing the 2 norm of Am-f. Generalizing the data fidelity item Am-F in the original image reconstruction model to obtain F (Am, F), wherein the generalized image reconstruction model is obtained by:
s220, converting the generalized image reconstruction model by using an iterative soft threshold algorithm, and obtaining the target image reconstruction model according to the converted image reconstruction model.
In this embodiment, after obtaining the generalized image reconstruction model, an iterative soft-threshold (ISTA) algorithm is used to convert the generalized image reconstruction model, and the obtained converted image reconstruction model is:
wherein m is(n)Representing the image to be reconstructed of the nth iteration, wherein rho is the step length, and F' is the data fidelityFirst order partial derivatives of the term F (Am, F).
On the basis of the above scheme, the obtaining a substituted image reconstruction model by using a convolutional neural network to substitute for the first-order partial derivative of the data fidelity term in the converted image reconstruction model includes:
replacing the first order partial derivatives F' of the data fidelity items by d(n+1)＝Γ(Am(n)And f), obtaining a substituted image reconstruction model:
correspondingly, the generalizing the iterative relationship in the replaced image reconstruction model to obtain the target image reconstruction model includes:
reconstructing r in the replaced image model(n+1)＝m(n)-ρATd(n+1)Generalized as r(n+1)＝Λ(m(n)，ATd(n+1)) And obtaining the target image reconstruction model:
wherein d is(n+1)A first order partial derivative representing the data fidelity term,
representing a forward transformation, G representing a reverse transformation, and θ being a soft threshold parameter.
And S230, acquiring sample undersampled data and a sample full-sampling image corresponding to the sample undersampled data.
S240, generating a training sample pair based on the sample undersampled data and a sample full-sampling image corresponding to the sample undersampled data, and training the target image reconstruction model by using the training sample pair to obtain a trained target image reconstruction model.
Optionally, the same part to be imaged can be subjected to undersampling and full sampling respectively, and the same part to be imaged can be subjected to undersampling and full samplingUsing undersampled data of an imaging part and an image reconstructed by full sampling as a sample pair, training the constructed target image reconstruction model by using the acquired sample pair, and determining forward transformation G and reverse transformation in the target image reconstruction model
And obtaining the values of parameters such as the step rho, the soft threshold parameter theta and the like to obtain the trained target image reconstruction model.
Fig. 2b is a schematic network structure diagram of a target image reconstruction model according to a second embodiment of the present invention. As shown in fig. 2b, the input of the target image reconstruction model is the undersampled K-space data f, and after N iterations, the output reconstructed image m is obtained. And in each data iteration process, calculating by adopting a target image reconstruction model. In one embodiment, the number of iterations is 10, the convolution kernel size of each convolutional neural network is 3 × 3, the activation function is a linear rectification function (Relu), the data fidelity layer d and the residual error layer r each include 2 convolutional layers, the number of convolution kernels is (32, 2), the forward transform G has 2 convolutional layers, the number of convolution kernels is (32, 32), and the reverse transform G has 2 convolutional layers
There are 2 convolutional layers, the number of convolutional kernels is (32, 2). Since the magnetic resonance signals are complex signals, all data in the target image reconstruction model are divided into a real part channel and an imaginary part channel for processing, that is, the number of channels for outputting data is 2. Alternatively, the loss function may be a mean square error function:
wherein,
for network output, xrefFor the corresponding full capture image.
And S250, acquiring the acquired under-sampled data, and inputting the under-sampled data into a pre-trained target image reconstruction model.
And S260, acquiring an image output by the target image reconstruction model.
Fig. 2c is a reconstruction effect diagram of image reconstruction performed by using the image reconstruction method provided by the second embodiment of the present invention. Figure 2c is a reconstructed image from a retrospective 10-fold undersampling experiment performed on a 3T magnetic resonance system. As shown in fig. 2c, the reference image, the reconstructed image obtained by the conventional image reconstruction model, and the reconstructed image obtained by the target image reconstruction model provided by the embodiment of the present invention are respectively shown from left to right. As can be seen from fig. 2c, the reconstructed image obtained by the target image reconstruction model provided in the embodiment of the present invention is clearer than the reconstructed images obtained by the reference image and the conventional image reconstruction model, and is better in visual effect and index.
According to the technical scheme of the embodiment of the invention, the original image reconstruction model is specified according to the construction composition of the target image reconstruction model, the data fidelity item in the original image reconstruction model is generalized to obtain the generalized image reconstruction model, the generalized image reconstruction model is converted by using an iterative soft threshold algorithm, and the converted image reconstruction model is generalized again to obtain the target image reconstruction model, so that the constructed target image reconstruction model is more widely applicable and has higher network freedom.
EXAMPLE III
Fig. 3 is a schematic structural diagram of an image reconstruction apparatus according to a third embodiment of the present invention. The image reconstruction apparatus may be implemented in software and/or hardware, for example, the image reconstruction apparatus may be configured in a computer device. As shown in fig. 3, the apparatus includes an undersampled data acquisition module 310 and a reconstructed image acquisition module 320, wherein:
the under-sampling data acquisition module 310 is configured to acquire acquired under-sampling data, and input the under-sampling data into a pre-trained target image reconstruction model, where the target image reconstruction model is obtained by generalizing an iterative relation obtained by iteratively solving an original image reconstruction model;
a reconstructed image obtaining module 320, configured to obtain an image output by the target image reconstruction model.
The method comprises the steps of acquiring acquired under-sampled data through an under-sampled data acquisition module, and inputting the under-sampled data into a pre-trained target image reconstruction model, wherein the target image reconstruction model is obtained by generalizing an iterative relation obtained after an original image reconstruction model is iteratively solved; the reconstructed image obtaining module obtains an image output by the target image reconstruction model, generalizes an iteration relation obtained by iteratively solving the original image reconstruction model, and then solves the generalized image to obtain the target image reconstruction model, and obtains a reconstructed image based on the obtained target image reconstruction model and undersampled data, so that the data consistency in the image reconstruction process is ensured, and the quality of the reconstructed image is improved.
On the basis of the above scheme, the apparatus further comprises a model building module, configured to:
generalizing the data fidelity item in the original image reconstruction model to obtain a generalized image reconstruction model;
and transforming the generalized image reconstruction model by using an iterative soft threshold algorithm, and obtaining the target image reconstruction model according to the transformed image reconstruction model.
On the basis of the above scheme, the solution result includes the first-order partial derivative of the data fidelity term, and the model building module is specifically configured to:
replacing the first-order partial derivative of the data fidelity term in the converted image reconstruction model by using a convolutional neural network to obtain a replaced image reconstruction model;
and generalizing the iterative relation in the replaced image reconstruction model to obtain the target image reconstruction model.
On the basis of the scheme, the original image reconstruction model is as follows:
the generalized image reconstruction model is as follows: minmF(Am,f)+λ||Ψm||1Wherein m is an image to be reconstructed,a is an encoding matrix, f is undersampled data, lambda is a regular parameter, and psi represents sparse transformation.
On the basis of the above scheme, the obtaining a substituted image reconstruction model by using a convolutional neural network to substitute for the first-order partial derivative of the data fidelity term in the converted image reconstruction model includes:
replacing the first order partial derivatives F' of the data fidelity items by d(n+1)＝Γ(Am(n)And f), obtaining a substituted image reconstruction model:
correspondingly, the generalizing the iterative relationship in the replaced image reconstruction model to obtain the target image reconstruction model includes:
reconstructing r in the replaced image model(n+1)＝m(n)-ρATd(n+1)Generalized as r(n+1)＝Λ(m(n)，ATd(n+1)) And obtaining the target image reconstruction model:
wherein d is(n+1)A first order partial derivative representing the data fidelity term,
representing a forward transformation, G representing a reverse transformation, and θ being a soft threshold parameter.
On the basis of the above scheme, the apparatus further comprises a model training module, configured to:
acquiring sample undersampled data and a sample full-sampling image corresponding to the sample undersampled data;
generating a training sample pair based on the sample undersampled data and a sample full-sampling image corresponding to the sample undersampled data, and training the target image reconstruction model by using the training sample pair to obtain a trained target image reconstruction model.
The image reconstruction device provided by the embodiment of the invention can execute the image reconstruction method provided by any embodiment, and has the corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention. FIG. 4 illustrates a block diagram of an exemplary computer device 412 suitable for use in implementing embodiments of the present invention. The computer device 412 shown in FIG. 4 is only one example and should not impose any limitations on the functionality or scope of use of embodiments of the present invention.
As shown in FIG. 4, computer device 412 is in the form of a general purpose computing device. Components of computer device 412 may include, but are not limited to: one or more processors 416, a system memory 428, and a bus 418 that couples the various system components (including the system memory 428 and the processors 416).
Bus 418 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and processor 416, or a local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Computer device 412 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by computer device 412 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 428 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)430 and/or cache memory 432. The computer device 412 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage 434 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 4, and commonly referred to as a "hard drive"). Although not shown in FIG. 4, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 418 by one or more data media interfaces. Memory 428 can include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 440 having a set (at least one) of program modules 442 may be stored, for instance, in memory 428, such program modules 442 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. The program modules 442 generally perform the functions and/or methodologies of the described embodiments of the invention.
The computer device 412 may also communicate with one or more external devices 414 (e.g., keyboard, pointing device, display 424, etc.), with one or more devices that enable a user to interact with the computer device 412, and/or with any devices (e.g., network card, modem, etc.) that enable the computer device 412 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interfaces 422. Also, computer device 412 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet) through network adapter 420. As shown, network adapter 420 communicates with the other modules of computer device 412 over bus 418. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the computer device 412, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processor 416 executes programs stored in the system memory 428 to perform various functional applications and data processing, such as implementing an image reconstruction method provided by an embodiment of the present invention, the method including:
acquiring acquired under-sampled data, and inputting the under-sampled data into a pre-trained target image reconstruction model, wherein the target image reconstruction model is obtained by generalizing an iterative relation obtained by iteratively solving an original image reconstruction model and then solving the iterative relation;
and acquiring a reconstructed image output by the target image reconstruction model.
Of course, those skilled in the art will understand that the processor may also implement the technical solution of the image reconstruction method provided in any embodiment of the present invention.
EXAMPLE five
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the image reconstruction method provided in the embodiment of the present invention, and the method includes:
acquiring acquired under-sampled data, and inputting the under-sampled data into a pre-trained target image reconstruction model, wherein the target image reconstruction model is obtained by generalizing an iterative relation obtained by iteratively solving an original image reconstruction model and then solving the iterative relation;
and acquiring a reconstructed image output by the target image reconstruction model.
Of course, the computer program stored on the computer-readable storage medium provided by the embodiments of the present invention is not limited to the method operations described above, and may also perform related operations in the image reconstruction method provided by any embodiments of the present invention.
Computer storage media for embodiments of the invention may employ 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. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. 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. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. An image reconstruction method, comprising:
acquiring acquired under-sampled data, and inputting the under-sampled data into a pre-trained target image reconstruction model, wherein the target image reconstruction model is obtained by generalizing an iterative relation obtained by iteratively solving an original image reconstruction model and then solving the iterative relation;
and acquiring a reconstructed image output by the target image reconstruction model.
2. The method of claim 1, wherein the constructing of the target image reconstruction model comprises:
generalizing the data fidelity item in the original image reconstruction model to obtain a generalized image reconstruction model;
and transforming the generalized image reconstruction model by using an iterative soft threshold algorithm, and obtaining the target image reconstruction model according to the transformed image reconstruction model.
3. The method of claim 2, wherein the transformed image reconstruction model includes a first-order partial derivative of the data fidelity term, and wherein obtaining the target image reconstruction model from the transformed image reconstruction model includes:
replacing the first-order partial derivative of the data fidelity term in the converted image reconstruction model by using a convolutional neural network to obtain a replaced image reconstruction model;
and generalizing the iterative relation in the replaced image reconstruction model to obtain the target image reconstruction model.
4. The method of claim 3, wherein the original image reconstruction model is:the generalized image reconstruction model is as follows: minmF(Am,f)+λ||Ψm||1Wherein m is an image to be reconstructed, A is a coding matrix, f is undersampled data, lambda is a regular parameter, and psi represents sparse transformation.
5. The method of claim 4, wherein the generalized image reconstruction model is transformed using an iterative soft threshold algorithm to obtain a transformed image reconstruction model:
wherein m is(n)And representing the image to be reconstructed of the nth iteration, wherein rho is a step length, and F' is a first-order partial derivative of the data fidelity item.
6. The method of claim 5, wherein the using a convolutional neural network to replace the first-order partial derivatives of the data fidelity terms in the transformed image reconstruction model to obtain a replaced image reconstruction model comprises:
replacing the first order partial derivatives F' of the data fidelity items by d(n+1)＝Γ(Am(n)And f), obtaining a substituted image reconstruction model:
correspondingly, the generalizing the iterative relationship in the replaced image reconstruction model to obtain the target image reconstruction model includes:
reconstructing r in the replaced image model(n+1)＝m(n)-ρATd(n+1)Generalized as r(n+1)＝Λ(m(n)，ATd(n +1)) And obtaining the target image reconstruction model:
wherein d is(n+1)A first order partial derivative representing the data fidelity term,
representing a forward transformation, G representing a reverse transformation, and θ being a soft threshold parameter.
7. The method of claim 6, further comprising:
acquiring sample undersampled data and a sample full-sampling image corresponding to the sample undersampled data;
generating a training sample pair based on the sample undersampled data and a sample full-sampling image corresponding to the sample undersampled data, and training the target image reconstruction model by using the training sample pair to obtain a trained target image reconstruction model.
8. An image reconstruction apparatus, comprising:
the system comprises an under-sampling data acquisition module, a target image reconstruction model and a data processing module, wherein the under-sampling data acquisition module is used for acquiring acquired under-sampling data and inputting the under-sampling data into the pre-trained target image reconstruction model, and the image reconstruction model is obtained by generalizing and then solving a data fidelity term of an original image reconstruction model;
and the reconstructed image acquisition module is used for acquiring a reconstructed image output by the target image reconstruction model.
9. A computer device, the device comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the image reconstruction method of any of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the image reconstruction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910967757.0A CN110717958A (en) | 2019-10-12 | 2019-10-12 | Image reconstruction method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910967757.0A CN110717958A (en) | 2019-10-12 | 2019-10-12 | Image reconstruction method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110717958A true CN110717958A (en) | 2020-01-21 |
Family
ID=69212573
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910967757.0A Pending CN110717958A (en) | 2019-10-12 | 2019-10-12 | Image reconstruction method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110717958A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112213674A (en) * | 2020-09-11 | 2021-01-12 | 上海东软医疗科技有限公司 | Magnetic resonance compressed sensing reconstruction method and device |
| WO2021114216A1 (en) * | 2019-12-12 | 2021-06-17 | 深圳先进技术研究院 | Image reconstruction method, computer readable storage medium, and computer device |
| CN113781365A (en) * | 2021-10-26 | 2021-12-10 | 中国科学院自动化研究所 | MPI system matrix restoration method based on depth image prior |
| CN115311174A (en) * | 2022-10-10 | 2022-11-08 | 深圳大学 | Training method and device for image recovery network and computer readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325985A (en) * | 2018-09-18 | 2019-02-12 | 上海联影智能医疗科技有限公司 | MR image reconstruction method, apparatus and computer readable storage medium |
| CN109993809A (en) * | 2019-03-18 | 2019-07-09 | 杭州电子科技大学 | Rapid magnetic resonance imaging method based on residual error U-net convolutional neural networks |
| CN110151181A (en) * | 2019-04-16 | 2019-08-23 | 杭州电子科技大学 | Rapid magnetic resonance imaging method based on the U-shaped network of recurrence residual error |
-
2019
- 2019-10-12 CN CN201910967757.0A patent/CN110717958A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325985A (en) * | 2018-09-18 | 2019-02-12 | 上海联影智能医疗科技有限公司 | MR image reconstruction method, apparatus and computer readable storage medium |
| CN109993809A (en) * | 2019-03-18 | 2019-07-09 | 杭州电子科技大学 | Rapid magnetic resonance imaging method based on residual error U-net convolutional neural networks |
| CN110151181A (en) * | 2019-04-16 | 2019-08-23 | 杭州电子科技大学 | Rapid magnetic resonance imaging method based on the U-shaped network of recurrence residual error |
Non-Patent Citations (4)
| Title |
|---|
| DONG LIANG等: "Deep MRI Reconstruction: Unrolled Optimization Algorithms Meet Neural Networks", 《HTTPS://ARXIV.ORG/ABS/1907.11711V1》 * |
| JING CHENG等: "Model-based Deep Medical Imaging: the roadmap of generalizing iterative reconstruction model using deep learning", 《EXTENSION://BFDOGPLMNDIDLPJFHOIJCKPAKKDJKKIL/PDF/VIEWER.HTML?FILE=HTTPS%3A%2F%2FARXIV.ORG%2FFTP%2FARXIV%2FPAPERS%2F1906%2F1906.08143.PDF》, pages 1 - 21 * |
| MICHAEL LUSTIG等: "Sparse MRI: The Application of Compressed Sensing for Rapid MR Imaging", 《EXTENSION://BFDOGPLMNDIDLPJFHOIJCKPAKKDJKKIL/PDF/VIEWER.HTML?FILE=HTTPS%3A%2F%2FECE-CLASSES.USC.EDU%2FEE691%2FREAD%2FLUSTIG2007P121.PDF》 * |
| 赵世华: "《心血管病磁共振诊断学》", 人民军医出版社, pages: 12 - 13 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021114216A1 (en) * | 2019-12-12 | 2021-06-17 | 深圳先进技术研究院 | Image reconstruction method, computer readable storage medium, and computer device |
| CN112213674A (en) * | 2020-09-11 | 2021-01-12 | 上海东软医疗科技有限公司 | Magnetic resonance compressed sensing reconstruction method and device |
| CN113781365A (en) * | 2021-10-26 | 2021-12-10 | 中国科学院自动化研究所 | MPI system matrix restoration method based on depth image prior |
| CN115311174A (en) * | 2022-10-10 | 2022-11-08 | 深圳大学 | Training method and device for image recovery network and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110766769B (en) | Magnetic resonance image reconstruction method, device, equipment and medium | |
| CN110766768B (en) | Magnetic resonance image reconstruction method, device, equipment and medium | |
| CN112132959B (en) | Digital rock core image processing method and device, computer equipment and storage medium | |
| CN110717958A (en) | Image reconstruction method, device, equipment and medium | |
| CN113159056B (en) | Image segmentation method, device, equipment and storage medium | |
| WO2020114329A1 (en) | Fast magnetic resonance parametric imaging and device | |
| CN113870104A (en) | Super-resolution image reconstruction | |
| CN113674172B (en) | Image processing method, system, device and storage medium | |
| CN111242952B (en) | Image segmentation model training method, image segmentation device and computing equipment | |
| Muhammad et al. | Multi-scale Xception based depthwise separable convolution for single image super-resolution | |
| CN117011673B (en) | Electrical impedance tomography image reconstruction method and device based on noise diffusion learning | |
| CN110728732A (en) | Image reconstruction method, device, equipment and medium | |
| CN113723618A (en) | SHAP optimization method, equipment and medium | |
| Graham et al. | Unsupervised 3d out-of-distribution detection with latent diffusion models | |
| CN115115723A (en) | Image reconstruction model generation method, image reconstruction device, image reconstruction equipment and medium | |
| US11460528B2 (en) | MRI reconstruction with image domain optimization | |
| Zhang et al. | Deep external and internal learning for noisy compressive sensing | |
| CN113486939A (en) | Method, device, terminal and storage medium for processing pictures | |
| CN113408694A (en) | Weight demodulation for generative neural networks | |
| CN112241001A (en) | Radar human body action recognition method and device, electronic equipment and storage medium | |
| US20240046422A1 (en) | Pseudoinverse guidance for data restoration with diffusion models | |
| WO2022193378A1 (en) | Image reconstruction model generation method and apparatus, image reconstruction method and apparatus, device, and medium | |
| Zhang et al. | Distributed compressive sensing via LSTM-Aided sparse Bayesian learning | |
| CN114494484B (en) | Training method of data recognition model, data recognition method, device and equipment | |
| CN117218031A (en) | Image reconstruction method, device and medium based on DeqNLNet algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200121 |