CN112489155B - Image reconstruction method and device, electronic equipment and machine-readable storage medium - Google Patents
Image reconstruction method and device, electronic equipment and machine-readable storage medium Download PDFInfo
- Publication number
- CN112489155B CN112489155B CN202011440541.8A CN202011440541A CN112489155B CN 112489155 B CN112489155 B CN 112489155B CN 202011440541 A CN202011440541 A CN 202011440541A CN 112489155 B CN112489155 B CN 112489155B
- Authority
- CN
- China
- Prior art keywords
- data
- image
- image data
- target image
- cycle
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 147
- 238000003860 storage Methods 0.000 title claims description 9
- 230000008569 process Effects 0.000 claims abstract description 98
- 238000001914 filtration Methods 0.000 claims abstract description 58
- 238000012937 correction Methods 0.000 claims abstract description 48
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 4
- 238000003384 imaging method Methods 0.000 description 7
- 238000002595 magnetic resonance imaging Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000005457 optimization Methods 0.000 description 6
- 239000002131 composite material Substances 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000001629 suppression Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000009795 derivation Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 210000003484 anatomy Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
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
Abstract
The invention discloses an image reconstruction method, which comprises the following steps: the following loop process is performed until the loop end condition is satisfied: filtering the image data and the data residual error of the target image in the previous cycle based on the target image structure filter to obtain first image data in the current cycle; filtering the target image data and the data residual error in the previous cycle based on the guide image structure filter to obtain second image data in the current cycle; obtaining image data of a target image in the circulation process according to the first image data and the second image data; obtaining a data residual error in the current circulation process according to the undersampled data of the K space, the image data of the target image in the current circulation process and the residual error correction factor; when the cycle end condition is not satisfied, the image data and the data residual of the target image in the current cycle process are used as the image data and the data residual in the next cycle process.
Description
Technical Field
The present invention relates to the field of image processing technology, and in particular, to an image reconstruction method, an image reconstruction apparatus, an electronic device, and a machine-readable storage medium.
Background
Magnetic resonance imaging, an important diagnostic imaging technique, has limited the development of advanced clinical applications including multi-contrast imaging and dynamic cine-heart imaging due to its slow imaging speed. Therefore, it has been a serious problem in the magnetic resonance field to study how to shorten the imaging time while maintaining high resolution of the image.
Compressed sensing is used as a classical acceleration magnetic resonance imaging method based on a signal undersampling mechanism, and under the condition that signal sparsity is met and a sampling matrix is irrelevant to a sparse transformation basis, data which is far lower than Nyquist sampling amount is used, and good recovery of an original image is obtained through a nonlinear reconstruction algorithm. The standard compressed sensing imaging method is to solve an L 1 The method of norm regularization is also known as LASSO regression. Whereas optimization algorithm research for LASSO-like problems has focused mainly on first-order optimization algorithms with lower computational cost and faster convergence characteristics. For example, after introduction of Nesterov acceleration policy, have o (1/k 2 ) A rapid iterative soft threshold algorithm of convergence rate; the combination variable can be used for solving the alternate direction multiplier method of the large-scale problem in a separating way. Such algorithms have good application to weak convexities, including even some non-convexity problems.
Recently, iterative thresholding algorithms based on Plug-and-Play priors (PPP) replace the original thresholding with an image denoising filter (filtering priors is Plug-and-Play priors), i.e. coupling the image denoising to an image restoration framework based on a forward model. Iterative thresholding algorithms based on plug and play priors show superior imaging quality over traditional optimization algorithms.
However, the conventional iterative threshold algorithm based on the plug-and-play prior is only based on the iterative threshold algorithm of a single type of plug-and-play prior, and more types of plug-and-play prior are not considered, so that a reconstructed image with good balance in the aspects of artifact suppression and structural protection cannot be obtained, and therefore, the image reconstruction performance cannot be improved.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention provides an image reconstruction method and an image reconstruction device which are combined with more types of plug and play prior.
An image reconstruction method provided according to an aspect of an embodiment of the present invention includes: the following loop process is performed until the loop end condition is satisfied:
filtering the image data and the data residual error of the target image obtained in the previous cycle based on the target image structure filter to obtain first image data in the current cycle; filtering the target image data and the data residual error obtained in the previous cycle based on the guide image structure filter to obtain second image data in the current cycle; obtaining image data of a target image in the circulation process according to the first image data and the second image data in the circulation process; obtaining a data residual error in the current circulation process according to the undersampled data of the K space, the image data of the target image in the current circulation process and the target image data and the data residual error obtained in the previous circulation process;
and when the cycle ending condition is not met, the image data and the data residual error of the target image obtained in the current cycle process are used as the image data and the data residual error of the target image in the next cycle process.
In an example of the image reconstruction method provided in the above aspect, the obtaining the data residual error in the current cycle according to the undersampled data of the K space, the image data of the target image in the current cycle, and the target image data and the data residual error obtained in the previous cycle includes: obtaining a first residual correction factor in the circulation process according to the image data and the data residual of the target image obtained in the previous circulation process and through the divergence estimation of the target image structure filtering; obtaining a second residual correction factor in the circulation process according to the image data and the data residual of the target image obtained in the previous circulation process and through guiding the divergence estimation of the image structure filtering; obtaining a residual correction factor in the circulation process according to the first residual correction factor and the second residual correction factor in the circulation process; and obtaining the data residual error in the current circulation process according to the undersampled data of the K space, the image data of the target image in the current circulation process and the residual error correction factor.
In one example of the image reconstruction method provided in the above aspect, the image data and the data residual of the target image obtained in the previous loop are subjected to the filtering processing based on the target image structure filter and according to the following equation 1 to obtain the first image data in the present loop,
[1]
wherein,representing said first image data during the present cycle,/or->Representing a filtering operator, x, based on a target image structure filter t-1 Image data, z, representing the target image obtained during the previous cycle t-1 The data residual error obtained in the previous cycle process, wherein A represents an undersampled Fourier transform matrix;
and/or filtering the target image data and the data residual obtained in the previous cycle based on the guide image structure filter according to the following equation 2 to obtain second image data in the present cycle;
[2]
wherein,representing said second image data during the present cycle,/or->Representing a guided image structure filter basedFiltering operator, x t-1 Image data, z, representing the target image obtained during the previous cycle t-1 The data residual obtained in the previous cycle, a, represents the undersampled fourier transform matrix.
In one example of the image reconstruction method provided in the above aspect, the image data of the target image in the present loop is calculated from the first image data and the second image data in the present loop by using the following equation 3,
[3]
wherein α represents a weight parameter, and 0<α<1，x t Image data representing the target image during the present cycle.
In one example of the image reconstruction method provided in the above aspect, the first residual correction factor in the present loop is obtained from the image data and the data residual of the target image obtained in the previous loop, using the following equation 4,
[4]
wherein,a first residual correction factor based on a target image structure filter filtering priori in the circulation process is represented, delta represents a measurement constant of underdetermined degree of a problem, and +.>Representing a divergence operator corresponding to a filtering operator based on a target image structure filter, x t-1 Image data, z, representing the target image obtained during the previous cycle t-1 The data residual error obtained in the previous cycle process, wherein A represents an undersampled Fourier transform matrix;
and/or, obtaining a second residual correction factor based on the guide image structure filter filtering priori in the circulation process according to the image data and the data residual of the target image obtained in the previous circulation process and using the following formula 5,
[5]
wherein,a second residual correction factor based on a guide image structure filter filtering priori during the present cycle, delta representing a measure constant of underdetermined degree of the problem, +.>Representing a divergence operator, x, corresponding to a filtering operator based on a guided image structure filter t-1 Image data, z, representing the target image obtained during the previous cycle t-1 The data residual obtained in the previous cycle, a, represents the undersampled fourier transform matrix.
In one example of the image reconstruction method provided in the above aspect, according to the first residual correction factor and the second residual correction factor in the present loop, and the residual correction factor in the present loop is calculated using the following equation 6,
[6]
wherein o is t Representing the residual correction factor during the present cycle, alpha represents the weight parameter, and 0<α<1。
In one example of the image reconstruction method provided in the above aspect, the data residual in the present cycle is calculated according to the undersampled data of the K space, the image data of the target image in the present cycle, and the residual correction factor by using the following equation 7,
[7]z t ＝b-Ax t +o t
wherein z is t And b represents undersampled data of the K space.
An image reconstruction apparatus provided according to another aspect of an embodiment of the present invention includes: the method comprises the steps of circularly operating until a target image structure filter, a guide image structure filter, a target image data acquisition module and a data residual error acquisition module of a circulation ending condition are met;
the target image structure filter is used for carrying out filtering processing on the image data and the data residual error of the target image obtained in the previous cycle process so as to obtain first image data in the present cycle process; the guide image structure filter is used for carrying out filtering processing on the target image data and the data residual error obtained in the previous cycle process so as to obtain second image data in the cycle process; the target image data acquisition module is used for acquiring image data of a target image in the circulation process according to the first image data and the second image data in the circulation process; the data residual error acquisition module is used for acquiring a data residual error in the current circulation process according to the undersampled data of the K space, the image data of the target image in the current circulation process and the target image data and the data residual error acquired in the previous circulation process;
and when the cycle ending condition is not met, the image data and the data residual error of the target image obtained in the current cycle process are used as the image data and the data residual error of the target image in the next cycle process.
According to still another aspect of an embodiment of the present invention, there is provided an electronic apparatus including: at least one processor, and a memory coupled to the at least one processor, the memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform the image reconstruction method as described above.
According to yet another aspect of embodiments of the present invention there is provided a machine-readable storage medium storing executable instructions that when executed cause the machine to perform an image reconstruction method as described above.
The beneficial effects are that: the invention adopts the composite plug and play prior, can help to obtain the image with good balance in the aspects of artifact inhibition and structure protection, and can also improve the image reconstruction performance.
Drawings
The above and other aspects, features and advantages of embodiments of the present invention will become more apparent from the following description when taken in conjunction with the accompanying drawings in which:
fig. 1 is a flowchart illustrating an image reconstruction method according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating one exemplary method of acquiring data residuals during a current cycle in an image reconstruction method according to an embodiment of the invention;
fig. 3 is a block diagram showing an image reconstruction apparatus according to an embodiment of the present invention;
fig. 4 is a block diagram showing an electronic device implementing an image reconstruction method according to an embodiment of the present invention.
Detailed Description
Hereinafter, specific embodiments of the present invention will be described in detail with reference to the accompanying drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the specific embodiments set forth herein. Rather, these embodiments are provided to explain the principles of the invention and its practical application so that others skilled in the art will be able to understand the invention for various embodiments and with various modifications as are suited to the particular use contemplated.
As used herein, the term "comprising" and variations thereof mean open-ended terms, meaning "including, but not limited to. The terms "based on", "in accordance with" and the like mean "based at least in part on", "in part in accordance with". The terms "one embodiment" and "an embodiment" mean "at least one embodiment. The term "another embodiment" means "at least one other embodiment". The terms "first," "second," and the like, may refer to different or the same object. Other definitions, whether explicit or implicit, may be included below. Unless the context clearly indicates otherwise, the definition of a term is consistent throughout this specification.
As described above, the iterative threshold algorithm based on the plug-and-play priors is only based on a single type of iterative threshold algorithm, and more types of plug-and-play priors are not considered. In this case, a reconstructed image well-balanced in terms of artifact suppression and structural protection cannot be obtained, and thus image reconstruction performance cannot be improved.
In order to obtain a reconstructed image that is well balanced in terms of artifact suppression and structural protection, thereby improving image reconstruction performance, an image reconstruction method and an image reconstruction apparatus are provided according to an embodiment of the present invention that combine more types of plug and play priors for image reconstruction. The image reconstruction method may be performed by an electronic device that performs the following loop process until a loop end condition is satisfied: filtering the image data and the data residual error of the target image obtained in the previous cycle based on the target image structure filter to obtain first image data in the current cycle; filtering the target image data and the data residual error obtained in the previous cycle based on the guide image structure filter to obtain second image data in the current cycle; obtaining image data of a target image in the circulation process according to the first image data and the second image data in the circulation process; obtaining a data residual error in the current circulation process according to the undersampled data of the K space, the image data of the target image in the current circulation process and the target image data and the data residual error obtained in the previous circulation process; and when the cycle ending condition is not met, the image data and the data residual error of the target image obtained in the current cycle process are used as the image data and the data residual error of the target image in the next cycle process.
Therefore, in the image reconstruction method, the composite plug and play prior of the target image structure filter and the guide image structure filter is adopted to filter the image, so that the image with good balance in artifact suppression and structure protection can be obtained, and the image reconstruction performance can be improved.
In the description of the image reconstruction method according to the embodiment of the present invention, magnetic resonance imaging is exemplified. Next, some basic concepts and process derivations applied in the image reconstruction method according to the embodiment of the present invention will be described by taking magnetic resonance imaging as an example.
The task of image reconstruction for MR accelerated imaging can be considered to solve for an L 1 Normative LASSO regression problem whose solution cost function includes a data fitting term based on noise Gaussian distribution assumptions and L with respect to image coefficients in the transform domain 1 And (5) norm constraint.
First, constructing a PPP (plug and play prior) -AMP (approximate message passing ) algorithm framework for solving the optimization problem, and focusing on designing and coupling two types of plug and play prior: one class is the structure filtering prior from the target image itself, and the other class is the guided image structure filtering prior from other modalities or parameters. The weighted two classes of plug-and-play priors act as composite plug-and-play priors and are coupled to the forward model framework of the AMP algorithm.
In particular, the magnetic resonance imaging data acquisition procedure based on the K-space undersampling mechanism may be represented discretely as the following equation 1.
[ formula 1]b =ax+ζ
Here the number of the elements is the number,for image data of the target image to be reconstructed, +.>For K-space undersampled data, < >>For the undersampled fourier transform matrix +.>To assume noise subject to gaussian distribution.
Solving the underdetermined problem is often difficult, and under the framework of compressed sensing theory, L of a certain sparse transform domain coefficient is based on a target image 1 Norm regularization may take into account near perfect recovery (or weighing) of the original target image x from the K-space undersampled data b. For solution, an unconstrained optimization model is constructed, which is represented as equation 2 below.
[ formula 2]]
Here λ is a normal number constant that balances data fitting and sparse regularization. R (·) represents a certain sparse variation domain.
A series of Iterative algorithms with lower computational cost were proposed for solving the convex optimization problem of equation 2, where a specific algorithm, a representative algorithm being the Iterative Soft-threshold algorithm (ISTA), can be represented as equation 3 and equation 4 below.
[ type 3]x t ＝S τ (A H z t-1 +x t-1 )
[ type 4]]z t ＝b-Ax t
Here, the soft threshold algorithm S is iterated τ (y)＝(|y|-τ) + sign(y),x t Represents the x-estimate of the t-th time (i.e., the image data of the target image reconstructed after the t-th iteration), τ represents the threshold parameter. The approximate message passing algorithm as a variant of the ISTA, the core of which is the introduction of Onsager correction terms to account for the residual z t And the method is performed with Gaussian, so that the algorithm performance is further improved. Thus, the approximate messaging algorithm can be expressed as the following equations 5, 6 and 7.
[ formula 5]]x t ＝S τ (A H z t-1 +x t-1 )
[ type 6]
[ formula 7]]z t ＝b-Ax t +o t
Here the number of the elements is the number,for Onsager correction term, S τ ' S τ Delta is a measure constant of the degree of underdetermined problem,<·>representing a vector mean operation.
Next, a generalized denoising operator (i.e., a filtering operator) is introduced to construct a PPP-AMP algorithm framework, and the constructed PPP-AMP algorithm can be expressed as the following equations 8, 9 and 10.
[ formula 8 ]]
[ type 9 ]]
[ 10 ]]z t ＝b-Ax t +o t
Here the number of the elements is the number,for denoising operator, ++>And a corresponding divergence operator for the denoising operator.
In an embodiment according to the invention, two different types of denoising priors are coupled to construct a performance-enhanced composite plug-and-play prior-based approximation message passing algorithm for image reconstruction.
In one example, a first type of plug and play prior selects a block matching 3D filtering (Block Matching and 3D Filtering,BM3D) based algorithm as the self-structure filtering prior from the target image x, wherein the BM3D algorithm aims to construct a three-dimensional matrix by performing metric matching of euclidean distance with adjacent image blocks, integrally filters in a three-dimensional space, and inversely transforms the filtering result to a two-dimensional image.
In one example, the second class isThe interactive guided image filtering (Mutually Guided Image Filtering, muGIF) algorithm is selected a priori as the guided image x from other modalities or parameters r The muGIF aims to obtain anatomical structure information shared between the target image and the guide image through the interactivity measurement of the guide image structure information similar to the target image, and strengthen main structural features of the target image while effectively suppressing image artifacts. On one hand, interactive guiding filtering realizes that guiding image structure information is fully introduced, and on the other hand, detail filtering deviation caused by different image contents is avoided.
The foregoing is a detailed description of some of the basic concepts and process derivations applied to the image reconstruction method according to embodiments of the invention, taking magnetic resonance imaging as an example.
Next, an image reconstruction method and an image reconstruction apparatus that incorporate a composite plug and play prior for image reconstruction according to embodiments of the present invention will be described in detail with reference to the accompanying drawings.
The image reconstruction method according to the embodiment of the present invention may be performed by an electronic device, which may include a smart phone, a tablet computer, a personal computer, a cloud server, a server, and the like.
Fig. 1 is a flowchart illustrating an image reconstruction method according to an embodiment of the present invention.
Referring to fig. 1, in step S110, image data and a data residual of a target image obtained in a previous cycle are subjected to a filtering process based on a target image structure filter to obtain first image data in the present cycle.
In one example, the target image structure filter has the block-matched 3D based filtering algorithm described above, which may implement self structure filtering a priori from the target image.
In one example, the image data and the data residual of the target image obtained during the previous cycle are filtered based on the target image structure filter according to the following equation 11 to obtain the first image data during the present cycle.
[ formula 11 ]]
Wherein,representing said first image data in the present loop (t-th iteration,)>Representing a filtering operator, x, based on a target image structure filter t-1 Image data representing the target image obtained in the last iteration (t-1 st iteration), z t-1 The data residual obtained in the previous cycle, a, represents the undersampled fourier transform matrix.
In step S120, the target image data and the data residual obtained in the previous cycle are filtered based on the guide image structure filter to obtain second image data in the present cycle.
In one example, the guided image structure filter has the interactive guided image filtering algorithm described above, which may implement structure filtering a priori for guided images from other modalities or parameters. In one example, the guide image is similar to the target image.
In one example, the target image data and the data residual obtained during the previous loop are filtered based on a guided image structure filter and according to the following equation 12 to obtain the second image data during the present loop.
[ type 12]
Wherein,representing said second image data during the present cycle,/or->Representing a filtering operator based on a guided image structure filter.
In step S130, image data of a target image in the present cycle is obtained from the first image data and the second image data in the present cycle.
In one example, the image data of the target image in the present cycle is calculated from the first image data and the second image data in the present cycle using the following equation 13.
[ formula 13 ]]
Wherein α represents a weight parameter, and 0<α<1，x t Image data representing the target image during the present cycle.
In step S140, a data residual in the current cycle is obtained according to the undersampled data of the K space, the image data of the target image in the current cycle, and the target image data and the data residual obtained in the previous cycle.
In one example, the K-space undersampled data may be, for example, data undersampled acquired by a magnetic resonance imaging device.
Fig. 2 is a flowchart illustrating an exemplary method of acquiring a data residual during a current cycle in an image reconstruction method according to an embodiment of the present invention.
Referring to fig. 2, in step S141, a first residual correction factor in the present loop is obtained from image data and data residuals of the target image obtained in the previous loop and by divergence estimation of target image structure filtering.
In one example, the first residual correction factor in the present loop is obtained from the image data and the data residual of the target image obtained in the previous loop, using the following equation 14.
[ formula 14 ]]
Wherein,a first residual correction factor based on a target image structure filter filtering priori in the circulation process is represented, delta represents a measurement constant of underdetermined degree of a problem, and +.>Representing a corresponding divergence operator based on the filter operator of the target image structure filter.
In step S142, a second residual correction factor in the present loop is obtained from the image data and the data residual of the target image obtained in the previous loop and by guiding the divergence estimation of the image structure filtering.
In one example, the second residual correction factor in the present loop is obtained from the image data and the data residual of the target image obtained in the previous loop, using the following equation 15.
[ formula 15 ]]
Wherein,a second residual correction factor representing the filtering a priori based on a guided image structure filter during the present loop,/->Representing a corresponding divergence operator based on the filtering operator of the guided image structure filter.
In step S143, a residual correction factor in the present cycle is obtained according to the first residual correction factor and the second residual correction factor in the present cycle.
In one example, the residual correction factor during the present cycle is calculated from the first residual correction factor and the second residual correction factor during the present cycle using equation 16 below.
[ formula 16 ]]
Wherein o is t Representing the residual correction factor during this cycle.
In step S144, the data residual error in the current cycle is obtained according to the undersampled data of the K space, the image data of the target image in the current cycle, and the residual error correction factor.
In one example, the data residual in the current cycle is calculated according to the undersampled data of the K space, the image data of the target image in the current cycle, and the residual correction factor by using the following equation 17.
[ formula 17 ]]z t ＝b-Ax t +o t
Wherein z is t And b represents undersampled data of the K space.
With continued reference to fig. 1, in step S150, it is determined whether the cycle end condition is satisfied. If yes, ending the reconstruction; if not, the image data and the data residual of the target image obtained in the current cycle process are used as the image data and the data residual of the target image in the next cycle process, and the step S110 is performed.
Here, the cycle end condition may be specified. In one example, the loop end condition may include reaching a predetermined number of loops (or iterations).
Fig. 3 is a block diagram illustrating an image reconstruction apparatus according to an embodiment of the present invention.
The image reconstruction apparatus 300 is applied to an electronic device to be executed by the electronic device. Referring to fig. 3, the image reconstruction apparatus 300 includes: a target image structure filter 310, a guide image structure filter 320, a target image data acquisition module 330, and a data residual acquisition module 340. The target image structure filter 310, the guide image structure filter 320, the target image data acquisition module 330, and the data residual acquisition module 340 are cycled until a cycle end condition is satisfied. Wherein the cycle end condition may be specified. In one example, the loop end condition may include reaching a predetermined number of loops (or iterations).
The target image structure filter 310 is configured to filter image data and data residuals of the target image obtained in the previous cycle to obtain the first image data in the present cycle. In one example, the target image structure filter 310 may be configured to filter the target image data and the data residual obtained during the previous loop to obtain the first image data during the present loop according to equation 11 above.
The leading image structure filter 320 is configured to filter the target image data and the data residual obtained during the previous cycle to obtain the second image data during the present cycle. In one example, the guided image structure filter 320 may be configured to filter the target image data and the data residual obtained during the previous loop to obtain the second image data during the present loop according to equation 12 above.
The target image data acquisition module 330 is configured to obtain image data of a target image during the present cycle from the first image data and the second image data during the present cycle. In one example, the target image data acquisition module 330 may be configured to calculate the image data of the target image during the present loop from the first image data and the second image data during the present loop using equation 13 above.
The data residual error obtaining module 340 is configured to obtain a data residual error in the current cycle according to the undersampled data of the K space, the image data of the target image in the current cycle, and the target image data and the data residual error obtained in the previous cycle. In one example, the data residual obtaining module 340 may be configured to calculate the data residual in the current cycle according to the undersampled data of the K space, the image data of the target image in the current cycle, and the target image data and the data residual obtained in the previous cycle, using the above equations 15, 16, and 17.
An image reconstruction method and an image reconstruction apparatus according to embodiments of the present invention are described above with reference to fig. 1 to 3.
The image reconstruction apparatus according to the embodiment of the present invention may be implemented in hardware, or may be implemented in software or a combination of hardware and software. Taking software implementation as an example, the device in a logic sense is formed by reading corresponding computer program instructions in a memory into a memory by a processor of a device where the device is located. In an embodiment of the invention, the use of means for image reconstruction may be implemented, for example, by means of an electronic device.
Fig. 4 is a block diagram showing an electronic device implementing an image reconstruction method according to an embodiment of the present invention.
Referring to fig. 4, an electronic device 400 may include at least one processor 410, a memory (e.g., a non-volatile memory) 420, a memory 430, and a communication interface 440, and the at least one processor 410, the memory 420, the memory 430, and the communication interface 440 are connected together via a bus 450. The at least one processor 410 executes at least one computer-readable instruction (i.e., the elements described above as being implemented in software) stored or encoded in memory.
In one example, computer-executable instructions are stored in memory that, when executed, cause the at least one processor 410 to perform the following loop processes until the loop end condition is met: filtering the image data and the data residual error of the target image obtained in the previous cycle based on the target image structure filter to obtain first image data in the current cycle; filtering the target image data and the data residual error obtained in the previous cycle based on the guide image structure filter to obtain second image data in the current cycle; obtaining image data of a target image in the circulation process according to the first image data and the second image data in the circulation process; obtaining a data residual error in the current circulation process according to the undersampled data of the K space, the image data of the target image in the current circulation process and the target image data and the data residual error obtained in the previous circulation process; and when the cycle ending condition is not met, the image data and the data residual error of the target image obtained in the current cycle process are used as the image data and the data residual error of the target image in the next cycle process.
It should be appreciated that the computer-executable instructions stored in the memory, when executed, cause the at least one processor 410 to perform the various operations and functions described above in connection with fig. 1-3 in accordance with various embodiments of the invention.
According to one embodiment, a program product, such as a machine-readable medium, is provided. The machine-readable medium may have instructions (i.e., elements described above implemented in software) that, when executed by a machine, cause the machine to perform various operations and functions described above in connection with fig. 1-3 in various embodiments of the invention.
In particular, a system or apparatus provided with a readable storage medium having stored thereon software program code implementing the functions of any of the above embodiments may be provided, and a computer or processor of the system or apparatus may be caused to read out and execute instructions stored in the readable storage medium.
In this case, the program code itself read from the readable medium may implement the functions of any of the above-described embodiments, and thus the machine-readable code and the readable storage medium storing the machine-readable code form part of the embodiments of the present invention.
Examples of readable storage media include floppy disks, hard disks, magneto-optical disks, optical disks (e.g., CD-ROMs, CD-R, CD-RWs, DVD-ROMs, DVD-RAMs, DVD-RWs), magnetic tapes, nonvolatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer or cloud by a communications network.
The foregoing describes specific embodiments of the present invention. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
Not all steps or units in the above-mentioned flowcharts and system configuration diagrams are necessary, and some steps or units may be omitted according to actual needs. The order of execution of the steps is not fixed and may be determined as desired. The apparatus structures described in the above embodiments may be physical structures or logical structures, that is, some units may be implemented by the same physical entity, or some units may be implemented by multiple physical entities, or may be implemented jointly by some components in multiple independent devices.
The terms "exemplary," "example," and the like, as used throughout this specification, mean "serving as an example, instance, or illustration," and do not mean "preferred" or "advantageous" over other embodiments. The detailed description includes specific details for the purpose of providing an understanding of the described technology. However, the techniques may be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form in order to avoid obscuring the concepts of the described embodiments.
The alternative implementation of the embodiment of the present invention has been described in detail above with reference to the accompanying drawings, but the embodiment of the present invention is not limited to the specific details of the foregoing implementation, and various simple modifications may be made to the technical solutions of the embodiment of the present invention within the scope of the technical concept of the embodiment of the present invention, and these simple modifications all fall within the protection scope of the embodiment of the present invention.
The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. An image reconstruction method, characterized in that the image reconstruction method comprises:
the following loop process is performed until the loop end condition is satisfied:
filtering the image data and the data residual error of the target image obtained in the previous cycle based on the target image structure filter to obtain first image data in the current cycle;
filtering the target image data and the data residual error obtained in the previous cycle based on the guide image structure filter to obtain second image data in the current cycle;
obtaining image data of a target image in the circulation process according to the first image data and the second image data in the circulation process;
obtaining a data residual error in the current circulation process according to the undersampled data of the K space, the image data of the target image in the current circulation process and the target image data and the data residual error obtained in the previous circulation process;
when the cycle ending condition is not met, the image data and the data residual error of the target image obtained in the current cycle process are used as the image data and the data residual error of the target image in the next cycle process;
the method for obtaining the data residual error in the current circulation process according to the undersampled data of the K space, the image data of the target image in the current circulation process and the target image data and the data residual error obtained in the previous circulation process comprises the following steps:
obtaining a first residual correction factor in the circulation process according to the image data and the data residual of the target image obtained in the previous circulation process and through the divergence estimation of the target image structure filtering;
obtaining a second residual correction factor in the circulation process according to the image data and the data residual of the target image obtained in the previous circulation process and through guiding the divergence estimation of the image structure filtering;
obtaining a residual correction factor in the circulation process according to the first residual correction factor and the second residual correction factor in the circulation process;
obtaining a data residual error in the current circulation process according to the undersampled data of the K space, the image data of the target image in the current circulation process and the residual error correction factor;
wherein, according to the image data and the data residual error of the target image obtained in the previous cycle process, the first residual error correction factor in the present cycle process is obtained by using the following equation [4],
[4]
wherein,a first residual correction factor based on a target image structure filter filtering priori in the circulation process is represented, delta represents a measurement constant of underdetermined degree of a problem, and +.>Representing a divergence operator corresponding to a filtering operator based on a target image structure filter, x t-1 Image data, z, representing the target image obtained during the previous cycle t-1 The data residual error obtained in the previous cycle process, wherein A represents an undersampled Fourier transform matrix;
and obtaining a second residual correction factor in the present cycle by using the following equation [5] based on the image data and the data residual of the target image obtained in the previous cycle,
[5]
wherein,a second residual correction factor based on a guide image structure filter filtering priori during the present cycle, delta representing a measure constant of underdetermined degree of the problem, +.>Representing a divergence operator, x, corresponding to a filtering operator based on a guided image structure filter t-1 Image data, z, representing the target image obtained during the previous cycle t-1 The data residual obtained in the previous cycle, a, represents the undersampled fourier transform matrix.
2. The image reconstruction method according to claim 1, wherein the image data and the data residual of the target image obtained during the previous cycle are subjected to a filtering process based on the target image structure filter and according to the following equation [1] to obtain the first image data during the present cycle,
[1]
wherein,representing said first image data during the present cycle,/or->Representing a filtering operator, x, based on a target image structure filter t-1 Image data, z, representing the target image obtained during the previous cycle t-1 The data residual error obtained in the previous cycle process, wherein A represents an undersampled Fourier transform matrix;
and filtering the target image data and the data residual obtained in the previous cycle based on the guide image structure filter according to the following equation [2] to obtain second image data in the present cycle;
[2]
wherein,representing said second image data during the present cycle,/or->Representing a filtering operator based on a guided image structure filter, x t-1 Image data, z, representing the target image obtained during the previous cycle t-1 The data residual obtained in the previous cycle, a, represents the undersampled fourier transform matrix.
3. The image reconstruction method according to claim 2, wherein the image data of the target image in the present cycle is calculated from the first image data and the second image data in the present cycle by using the following equation [3],
[3]
wherein α represents a weight parameter, and 0<α<1，x t Image data representing the target image during the present cycle.
4. The image reconstruction method according to claim 1, wherein the residual correction factor in the present cycle is calculated from the first residual correction factor and the second residual correction factor in the present cycle using the following equation [6],
[6]
wherein o is t Representing the residual correction factor during the present cycle, alpha represents the weight parameter, and 0<α<1。
5. The image reconstruction method according to claim 4, wherein the data residual in the present cycle is calculated from the undersampled data of the K space, the image data of the target image in the present cycle, and the residual correction factor by using the following equation [7],
[7]z t ＝b-Ax t +o t
wherein z is t Data residual error in the current circulation process, b represents undersampled data of K space, and x t Image data representing the target image during the present cycle.
6. An image reconstruction apparatus, wherein the image reconstruction apparatus performs the image reconstruction method according to any one of claims 1 to 5, the image reconstruction apparatus comprising a target image structure filter, a guide image structure filter, a target image data acquisition module, a data residual acquisition module, which are operated cyclically until a cycle end condition is satisfied;
the target image structure filter is used for carrying out filtering processing on the image data and the data residual error of the target image obtained in the previous cycle process so as to obtain first image data in the present cycle process;
the guide image structure filter is used for carrying out filtering processing on the target image data and the data residual error obtained in the previous cycle process so as to obtain second image data in the cycle process;
the target image data acquisition module is used for acquiring image data of a target image in the circulation process according to the first image data and the second image data in the circulation process;
the data residual error acquisition module is used for acquiring a data residual error in the current circulation process according to the undersampled data of the K space, the image data of the target image in the current circulation process and the target image data and the data residual error acquired in the previous circulation process;
and when the cycle ending condition is not met, the image data and the data residual error of the target image obtained in the current cycle process are used as the image data and the data residual error of the target image in the next cycle process.
7. An electronic device, comprising:
at least one processor, and
a memory coupled to the at least one processor, the memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform the image reconstruction method of any one of claims 1 to 5.
8. A machine readable storage medium storing executable instructions that, when executed, cause the machine to perform the image reconstruction method of any one of claims 1 to 5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011440541.8A CN112489155B (en) | 2020-12-07 | 2020-12-07 | Image reconstruction method and device, electronic equipment and machine-readable storage medium |
| PCT/CN2020/136550 WO2022120899A1 (en) | 2020-12-07 | 2020-12-15 | Image reconstruction method and apparatus, electronic device and machine-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011440541.8A CN112489155B (en) | 2020-12-07 | 2020-12-07 | Image reconstruction method and device, electronic equipment and machine-readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112489155A CN112489155A (en) | 2021-03-12 |
| CN112489155B true CN112489155B (en) | 2024-01-26 |
Family
ID=74941504
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011440541.8A Active CN112489155B (en) | 2020-12-07 | 2020-12-07 | Image reconstruction method and device, electronic equipment and machine-readable storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN112489155B (en) |
| WO (1) | WO2022120899A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113192151B (en) * | 2021-04-08 | 2022-12-27 | 广东工业大学 | MRI image reconstruction method based on structural similarity |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485764A (en) * | 2016-11-02 | 2017-03-08 | 中国科学技术大学 | The quick exact reconstruction methods of MRI image |
| CN109671129A (en) * | 2018-12-14 | 2019-04-23 | 深圳先进技术研究院 | A kind of the dynamic magnetic resonance image method for reconstructing and device of auto-adaptive parameter study |
| CN111798391A (en) * | 2020-06-29 | 2020-10-20 | 东软医疗系统股份有限公司 | Image processing method and device, medical imaging equipment and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9734601B2 (en) * | 2014-04-04 | 2017-08-15 | The Board Of Trustees Of The University Of Illinois | Highly accelerated imaging and image reconstruction using adaptive sparsifying transforms |
| CN110148215B (en) * | 2019-05-22 | 2023-05-19 | 哈尔滨工业大学 | Four-dimensional magnetic resonance image reconstruction method based on smooth constraint and local low-rank constraint model |
| CN111192214B (en) * | 2019-12-27 | 2024-03-26 | 上海商汤智能科技有限公司 | Image processing method, device, electronic equipment and storage medium |
-
2020
- 2020-12-07 CN CN202011440541.8A patent/CN112489155B/en active Active
- 2020-12-15 WO PCT/CN2020/136550 patent/WO2022120899A1/en active Application Filing
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106485764A (en) * | 2016-11-02 | 2017-03-08 | 中国科学技术大学 | The quick exact reconstruction methods of MRI image |
| CN109671129A (en) * | 2018-12-14 | 2019-04-23 | 深圳先进技术研究院 | A kind of the dynamic magnetic resonance image method for reconstructing and device of auto-adaptive parameter study |
| CN111798391A (en) * | 2020-06-29 | 2020-10-20 | 东软医疗系统股份有限公司 | Image processing method and device, medical imaging equipment and system |
Non-Patent Citations (1)
| Title |
|---|
| 基于深度先验及非局部相似性的压缩感知核磁共振成像;宗春梅 等;计算机应用;第40卷(第10期);第3054页第1段-第3058页右栏第1段 * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022120899A1 (en) | 2022-06-16 |
| CN112489155A (en) | 2021-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Schlemper et al. | A deep cascade of convolutional neural networks for dynamic MR image reconstruction | |
| Ongie et al. | Deep learning techniques for inverse problems in imaging | |
| Ongie et al. | Off-the-grid recovery of piecewise constant images from few Fourier samples | |
| Tezcan et al. | MR image reconstruction using deep density priors | |
| Chung et al. | Come-closer-diffuse-faster: Accelerating conditional diffusion models for inverse problems through stochastic contraction | |
| Ravishankar et al. | Efficient blind compressed sensing using sparsifying transforms with convergence guarantees and application to magnetic resonance imaging | |
| Kamilov et al. | Plug-and-play methods for integrating physical and learned models in computational imaging: Theory, algorithms, and applications | |
| Mardani et al. | Neural proximal gradient descent for compressive imaging | |
| Trinh et al. | Novel example-based method for super-resolution and denoising of medical images | |
| Ravishankar et al. | Low-rank and adaptive sparse signal (LASSI) models for highly accelerated dynamic imaging | |
| Ma | Improved iterative curvelet thresholding for compressed sensing and measurement | |
| Maggioni et al. | Nonlocal transform-domain filter for volumetric data denoising and reconstruction | |
| Trzasko et al. | Highly Undersampled Magnetic Resonance Image Reconstruction via Homotopic $\ell_ {0} $-Minimization | |
| Cole et al. | Unsupervised MRI reconstruction with generative adversarial networks | |
| Lanza et al. | A generalized Krylov subspace method for \ell_p-\ell_q minimization | |
| Klosowski et al. | Image denoising for real‐time MRI | |
| Elad et al. | Image denoising: The deep learning revolution and beyond—a survey paper | |
| Zosso et al. | A primal-dual projected gradient algorithm for efficient Beltrami regularization | |
| Kelkar et al. | Compressible latent-space invertible networks for generative model-constrained image reconstruction | |
| Kelkar et al. | Prior image-constrained reconstruction using style-based generative models | |
| CN112489155B (en) | Image reconstruction method and device, electronic equipment and machine-readable storage medium | |
| Ravula et al. | Optimizing sampling patterns for compressed sensing MRI with diffusion generative models | |
| Cui et al. | Fast hierarchical deep unfolding network for image compressed sensing | |
| Fermanian et al. | PnP-ReG: Learned regularizing gradient for plug-and-play gradient descent | |
| Huang et al. | Model-based reconstruction with learning: From unsupervised to supervised and beyond |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |