CN109544657A - Medical image iterative reconstruction approach, device, computer equipment and storage medium - Google Patents
Medical image iterative reconstruction approach, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109544657A CN109544657A CN201811480554.0A CN201811480554A CN109544657A CN 109544657 A CN109544657 A CN 109544657A CN 201811480554 A CN201811480554 A CN 201811480554A CN 109544657 A CN109544657 A CN 109544657A
- Authority
- CN
- China
- Prior art keywords
- initial pictures
- regularization term
- parameter
- direction information
- threshold
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 claims abstract description 22
- 230000006870 function Effects 0.000 claims description 60
- 238000004590 computer program Methods 0.000 claims description 22
- 230000008859 change Effects 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 7
- 238000000926 separation method Methods 0.000 claims description 4
- 230000001419 dependent effect Effects 0.000 claims description 3
- 241000208340 Araliaceae Species 0.000 claims description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 2
- 235000008434 ginseng Nutrition 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 description 8
- 230000005484 gravity Effects 0.000 description 4
- 238000002059 diagnostic imaging Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000003325 tomography 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/003—Reconstruction from projections, e.g. tomography
- G06T11/005—Specific pre-processing for tomographic reconstruction, e.g. calibration, source positioning, rebinning, scatter correction, retrospective gating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2211/00—Image generation
- G06T2211/40—Computed tomography
- G06T2211/424—Iterative
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
This application involves a kind of medical image iterative reconstruction approach, device, computer equipment and storage mediums.The described method includes: obtaining initial pictures；The Z-direction information of the initial pictures is calculated according to the initial pictures；Regularization term parameter is obtained according to the Z-direction information of the initial pictures, and objective function is determined according to regularization term parameter number；Reconstruction is iterated according to the initial pictures and objective function.The above method can be according to the Z-direction information dynamic adjustment regularization term in image volume, regularization term, which is adjusted, by dynamic adapts it to the Z-direction value at different pixels, to achieve the purpose that accelerate iterative approximation, and it can effectively retain image edge information, additionally it is possible to eliminate to the artifact at image border.
Description
Technical field
This application involves Image Reconstruction Technology fields, more particularly to a kind of medical image iterative reconstruction approach, device, meter
Calculate machine equipment and storage medium.
Background technique
Iterative approximation uses original data space iteration, by iteration several times, gradually carries out to image to be processed
Improve.Image resolution ratio is improved in the case where high contrast；Noise is reduced in the case where low contrast.The mistake of iterative approximation
Due to the presence of regularization term in journey, if the three-dimensional regularization strong using edge retention performance, on the big ground of Z-direction information
Side causes image unnatural artifact occur since Z-direction edge is kept.
The faultage image that ct apparatus obtains is cross-sectional image, that is, the image of X/Y plane, Z-direction
For the direction perpendicular to X/Y plane.According to the voxel of several tomographic image reconstructing 3-D images XYZ space arrangement.It is above-mentioned this
The generation of kind artifact, is primarily due to three-dimensional regularization term and contains Z-direction, and is all the side Z in the region that artifact occurs in Z-direction
The place bigger to information, the noise reduction effect that edge retention performance will lead to this partial region die down, thus in iterative process
Middle noise reduction effect is poor, to show edge after the completion of iteration in Z-direction and keep very well, because actually in z-direction just
Then change item and plays the role of image that is small, and just can be appreciated that unnatural appearance artifact in X, Y-direction.
Current traditional technology carrys out reconstruction image usually using very thin thickness, due to using thinner thickness, just reduces
Z-direction information, can also reduce artifact.But problem brought by thinner thickness image is that reconstruction speed is slow, and is facing
In bed medicine, rebuilding speed is its widely used key factor.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide a kind of doctor that can be eliminated artifact and accelerate to rebuild speed
Learn image iterative reconstruction method, device, computer equipment and storage medium.
A kind of medical image iterative reconstruction approach, which comprises obtain initial pictures；According to the initial pictures meter
Calculate the Z-direction information of the initial pictures；Regularization term parameter is obtained according to the Z-direction information of the initial pictures, and according to
Regularization term parameter determines objective function；Reconstruction is iterated according to the initial pictures and objective function.
The Z-direction information according to the initial pictures obtains regularization term parameter packet in one of the embodiments,
It includes: according to the Z-direction information and preset function relationship of the initial pictures, regularization term parameter, the regularization is calculated
Item parameter includes Z-direction parameter.
The Z-direction information of the initial pictures includes that the Z-direction pixel value of initial pictures becomes in one of the embodiments,
Change information；The preset function relationship makes when the variation of the Z-direction pixel value of the initial pictures increases, the regularization term
Parameter reduction or constant.
The preset function is to be joined using Z-direction pixel value as independent variable with regularization term in one of the embodiments,
Monotonic nondecreasing function of the number as dependent variable.
The preset function is the piecewise function with one or more separations in one of the embodiments,.
In one of the embodiments, the preset function include: preset first threshold, second threshold and
Default Z-direction parameter, and the first threshold is greater than the second threshold.
If the preset function includes: that the Z-direction information is greater than first threshold in one of the embodiments,
Z-direction parameter in the regularization term is adjusted to default Z-direction parameter, obtains the regularization term；If the Z-direction letter
When breath is less than or equal to first threshold and is more than or equal to second threshold, by the Z-direction parameter in the regularization term according to default song
Line carries out dynamic adjustment, obtains the regularization term；If the Z-direction information is less than second threshold, in the regularization term
Z-direction parameter remain unchanged, obtain the regularization term.
A kind of medical image iterative approximation device, described device includes: acquisition module, for obtaining initial pictures；It calculates
Module, for calculating the Z-direction information of the initial pictures according to the initial pictures；Regularization term module, for according to institute
The Z-direction information for stating initial pictures obtains regularization term parameter, and determines objective function according to regularization term parameter；Rebuild mould
Block, for being iterated reconstruction according to the initial pictures and objective function.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device realizes following methods step when executing the computer program: obtaining initial pictures；According to initial pictures calculating
The Z-direction information of initial pictures；Regularization term parameter is obtained according to the Z-direction information of the initial pictures, and according to regularization
Item parameter determines objective function；Reconstruction is iterated according to the initial pictures and objective function.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of method described in realizing any of the above-described kind when row.
Above-mentioned medical image iterative reconstruction approach, device, computer equipment and storage medium, by obtaining initial pictures,
Its Z-direction information is obtained further according to initial pictures, regularization term is obtained according to Z-direction information, and true according to regularization term parameter
Set the goal function.Reconstruction is finally iterated according to initial pictures and objective function.The above method can be according to image volume
In Z-direction information obtain the regularization term of different Z-direction parameters, so that regularization term is can adapt to the side Z at different pixels
To value, to achieve the purpose that accelerate iterative approximation, and the artifact that can preferably eliminate iterative approximation when generates.
Detailed description of the invention
Fig. 1 is the flow diagram of one embodiment traditional Chinese medicine image iterative reconstruction method；
Fig. 2 is the image that original iterative reconstruction approach obtains in one embodiment；
Fig. 3 is the image that iterative reconstruction approach obtains after adjusting Z-direction parameter in one embodiment；
Fig. 4 is the image that original iterative reconstruction approach obtains in another embodiment；
Fig. 5 is the image that iterative reconstruction approach obtains after adjusting Z-direction parameter in another embodiment；
Fig. 6 is the image that original iterative reconstruction approach obtains in another embodiment；
Fig. 7 is the image that iterative reconstruction approach obtains after adjusting Z-direction parameter in another embodiment；
Fig. 8 is the structural block diagram of one embodiment traditional Chinese medicine Image Iterative reconstructing device；
Fig. 9 is the internal structure chart of computer equipment in one embodiment.
Appended drawing reference: it obtains module 100, computing module 200, regularization term module 300, rebuild module 400.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Image reconstruction mainly includes the content of several aspects such as denoising, deblurring, interpolation and super-resolution rebuilding, and this is several
The content of a aspect belongs to the scope of ill indirect problem, and direct solution can not obtain effectively stable solution, some classics
Smoothing algorithm often destroy many detailed information at edge.And ill indirect problem is solved based on regularization, by choosing most
Excellent regularization parameter, which carries out image reconstruction, can effectively retain image edge information, but can to the artifact at image border into
Row is eliminated.
In one embodiment, as shown in Figure 1, providing a kind of medical image iterative reconstruction approach, comprising the following steps:
Step S102 obtains initial pictures.
Specifically, initial pictures are the image generated after medical imaging device is scanned object to be scanned.Wherein, it cures
Treating equipment can appoint for CT (ct apparatus), PET-CT (position emissron tomography equipment), magnetic resonance equipment etc.
A kind of medical imaging device.
Step S104 calculates the Z-direction information of the initial pictures according to the initial pictures.
Specifically, according to obtained initial pictures；The Z-direction information of corresponding initial pictures is calculated, wherein the initial graph
The Z-direction information of picture includes the Z-direction pixel value change information of initial pictures.
The formula of Z-direction information is calculated in one of the embodiments, are as follows:
zgradx,y,z=Ux,y,z-Ux,y,z+1
Wherein, zgradX, y, zIndicate the side's Z information, Ux,y,zPixel value at indicates coordinate (x, y, z).
At present in iterative approximation widely used regularization term have total variation regularization (Total Variation,
) and the regularization based on Markov random field (Markov Random Fields, GGMRF) etc. TV.
The calculation formula of total variation regularization (Total Variation, TV) in one of the embodiments, are as follows:
Wherein, Ux,y,zPixel value at indicates coordinate (x, y, z)；ΔxIndicate regularization term X-direction parameter, it is specific to indicate
Size of each voxel in the direction x in current volume；ΔyIt indicates regularization term Y-direction parameter, specifically indicates current volume
In each voxel the direction y size；ΔzIndicate regularization term Z-direction parameter, it is specific to indicate every individual in current volume
Size of the element in the direction z；ε is the parameter value of a very little, leads division in the calculating led with second order in single order for avoiding
There is the case where except zero.
In one of the embodiments, the regularization based on Markov random field (Markov Random Fields,
GGMRF calculation formula) are as follows:
Wherein, (xj, yj, zj) indicate j-th of pixel three-dimensional coordinate；(xk, yk, zk) indicate that the three-dimensional of k-th of pixel is sat
Mark；UjIndicate the pixel value of j-th of pixel；UkIndicate the pixel value of k-th of pixel；ΔxIndicate regularization term X-direction parameter, tool
Body surface shows that each voxel is in the size in the direction x in current volume；ΔyIndicate regularization term Y-direction parameter, it is specific to indicate to work as
Size of each voxel in the direction y in front volume；ΔzIndicate regularization term Z-direction parameter, it is specific to indicate in current volume
Size of each voxel in the direction z；ε, p, r, c indicate regularization parameter.
Before being iterated reconstruction, regularization term parameter is obtained first, and target letter is determined according to regularization term parameter
Number, by adjusting regularization term parameter on the basis of keeping edge detail information, reduction image border at artifact.
Step S106 obtains regularization term parameter according to the Z-direction information of the initial pictures, and is joined according to regularization term
Number determines objective function.
Specifically, according to the Z-direction information of the initial pictures and preset function relationship, regularization term ginseng is calculated
Number, the regularization term parameter includes Z-direction parameter.Wherein, the Z-direction information of the initial pictures includes the Z of initial pictures
Direction pixel value change information；The preset function relationship makes when the variation of the Z-direction pixel value of the initial pictures increases,
The regularization term parameter reduction or constant.The variation of Z-direction pixel value can be indicated with pixel value gradient, can also use adjacent picture
Plain value difference expression etc..And the preset function is using Z-direction pixel value as independent variable, using regularization term parameter as because becoming
The monotonic nondecreasing function of amount.And the preset function is the piecewise function with one or more separations.
According to above-mentioned total variation regularization (Total Variation, TV) calculation formula and based on markov with
Regularization (Markov Random Fields, the GGMRF) calculation formula on airport, when Z-direction thickness is very big, ΔzAlso can
It is very big, that is to say, that when Z-direction thickness levels off to infinity, ΔzIt can consider infinity, then Δ in formulazItem is unlimited
Close to zero.In order to reduce Z-direction information it is big caused by artifact, by ΔzBecome one with Z-direction information relevant variable, Z
The big place of directional information is by ΔzBecome larger, that is, the big place of Z-direction information keeps the Z-direction parameter of regularization term infinitely great；
The small local Δ of Z-direction informationzIt remains unchanged, maintains regularization term.That is, if the Z-direction information is greater than threshold value, by institute
It states the Z-direction parameter in regularization term and is adjusted to default Z-direction parameter, obtain the regularization term, determined according to regularization term
Objective function；If the Z-direction information is less than or equal to threshold value, the regularization term is calculated according to Z-direction information, according to
Regularization term determines objective function.Wherein, threshold value is to be determined according to actual clinical human body information.
More specifically, first threshold, second threshold and default Z-direction parameter are preset.Wherein, first threshold is greater than
Second threshold, and default Z-direction parameter is greater than the original Z-direction parameter in regularization term.If the Z-direction information is greater than the
When one threshold value, the Z-direction parameter in the regularization term is adjusted to default Z-direction parameter, obtains the regularization term, according to
Regularization term determines objective function.Wherein biggish default Z-direction parameter is infinitely close to the Z-direction information in regularization term
Zero.If the Z-direction information is less than or equal to first threshold and is more than or equal to second threshold, by the side Z in the regularization term
Dynamic adjustment is carried out according to pre-programmed curve to parameter, the regularization term is obtained, objective function is determined according to regularization term；If institute
When stating Z-direction information less than second threshold, the Z-direction parameter in the regularization term is remained unchanged, and obtains the regularization term,
Objective function is determined according to regularization term.
The formula of Z-direction parameter is adjusted in one of the embodiments, are as follows:
Wherein, Δ 'zFor Z-direction parameter adjusted；zlimitTo preset Z-direction parameter；zgradFor Z-direction information；T2For
First threshold；T1For second threshold.Z-direction information be less than or equal to first threshold and be more than or equal to second threshold when, by it is described just
Then change a Z-direction parameter and dynamic adjustment is carried out according to pre-programmed curve, pre-programmed curve can be linearity curve, be also possible to after tested
Any reasonable curve.Wherein, first threshold, second threshold are determined according to actual clinical human body information.Pre-programmed curve is to reality
Border clinical data carries out the curve that machine learning obtains.
Above-mentioned total variation regularization (Total Variation, TV) calculation formula and it is based on Markov random field
Regularization (Markov Random Fields, GGMRF) calculation formula, directly according to the size of Z-direction information, by ΔzIt adjusts
It is whole for Δ 'z, regularization term is obtained, and establish determining objective function.
In one of the embodiments, can to total variation regularization (Total Variation, TV) calculation formula and
Regularization (Markov Random Fields, GGMRF) calculation formula based on Markov random field, should multiplied by a coefficient
The size of coefficient is related to Z-direction information.Coefficient is determined according to Z-direction information, obtains regularization term, and establishes determining target letter
Number.Such as the pixel gradient of the coefficient and initial pictures establishes functional relation, changes the coefficient with initial pictures pixel
Increase and reduce.
Step S108 is iterated reconstruction according to the initial pictures and objective function.
The objective function of iterative approximation in one of the embodiments, are as follows:
Wherein, X is the image obtained after solving；Y is input picture；A is the matrix of current medical imaging system；W be according to
The weighting coefficient being added according to noise statistics model；R (X) is regularization term；β is regularization term coefficient.
Initial pictures are inputted first, obtain the image after solving for the first time；Image after obtained first time is solved again
Input, the image after obtaining second of solution, each time input of iteration is all using the preceding solution image once obtained as defeated
Enter, obtains newest solution image.Until obtained solution image meets the demand of image reconstruction, completion iterative approximation.
Specifically, the initial pictures that will acquire and obtained regularization term, are iterated according to above-mentioned objective function
It rebuilds, obtains that marginal information is complete, and eliminate the image of artifact.
Above-mentioned medical image iterative reconstruction approach, first acquisition initial pictures calculate described initial further according to initial pictures
The Z-direction information of image, according to Z-direction parameter in the determination regularization term of Z-direction information self-adapting, and according to Z-direction parameter
It determines objective function, reconstruction is being iterated according to initial pictures and objective function.That is, big for Z-direction information
Corresponding highdensity place, makes the specific gravity of the Z-direction in regularization term be substantially equal to zero；Correspondence small for Z-direction information
Low-density place, so that the specific gravity of Z-direction in regularization term is kept normal；The place medium for Z-direction information, makes canonical
Changing Z-direction specific gravity in item can reduce.It can be existed in the case where thickness is constant according to the determination Z-direction of Z-direction information self-adapting
Specific gravity in regularization term weakens artifact while keeping low-density characteristic good.
As illustrated in figs. 2-7, Fig. 2 is the image that original iterative reconstruction approach obtains in one embodiment；Fig. 3 is an implementation
The image that iterative reconstruction approach obtains after adjustment Z-direction parameter in example；Fig. 4 is original iterative reconstruction approach in another embodiment
Obtained image；Fig. 5 is the image that iterative reconstruction approach obtains after adjusting Z-direction parameter in another embodiment；Fig. 6 is another
The image that original iterative reconstruction approach obtains in a embodiment；Fig. 7 is that iteration weight after Z-direction parameter is adjusted in another embodiment
The image that construction method obtains.Can significantly it be found out according to above-mentioned image, the iterative reconstruction approach after adjusting Z-direction parameter is rebuild
The image low-density characteristic obtained afterwards is good, and can achieve the purpose that weaken artifact.
It should be understood that although each step in the flow chart of Fig. 1 is successively shown according to the instruction of arrow, this
A little steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly state otherwise herein, these steps
It executes there is no the limitation of stringent sequence, these steps can execute in other order.Moreover, at least part in Fig. 1
Step may include that perhaps these sub-steps of multiple stages or stage are executed in synchronization to multiple sub-steps
It completes, but can execute at different times, the execution sequence in these sub-steps or stage, which is also not necessarily, successively to be carried out,
But it can be executed in turn or alternately at least part of the sub-step or stage of other steps or other steps.
In one embodiment, as shown in figure 8, providing a kind of medical image iterative approximation device, comprising: obtain module
100, computing module 200, regularization term module 300 and reconstruction module 400, in which:
Module 100 is obtained, for obtaining initial pictures；
Computing module 200, for calculating the Z-direction information of the initial pictures according to the initial pictures；
Regularization term module 300 obtains regularization term parameter, and root for the Z-direction information according to the initial pictures
Objective function is determined according to regularization term parameter；
Module 400 is rebuild, for being iterated reconstruction according to the initial pictures and objective function.
Regularization term module 300 is also used to Z-direction information and preset function relationship according to the initial pictures, calculates
Regularization term parameter is obtained, the regularization term parameter includes Z-direction parameter.
The Z-direction information of the initial pictures includes the Z-direction pixel value change information of initial pictures.The preset function
Relationship makes the regularization term parameter reduction or constant when the variation of the Z-direction pixel value of the initial pictures increases.It is described
Preset function is the monotonic nondecreasing function using Z-direction pixel value as independent variable, using regularization term parameter as dependent variable.It is described
Preset function is the piecewise function with one or more separations.
Iterative approximation device further include: presetting module, for presetting first threshold, second threshold and the default side Z
To parameter, and the first threshold is greater than the second threshold.
Regularization term module 300, if be also used to the Z-direction information greater than first threshold, by the regularization term
In Z-direction parameter be adjusted to default Z-direction parameter, obtain the regularization term；If the Z-direction information is less than or equal to first
Threshold value and be more than or equal to second threshold when, by the Z-direction parameter in the regularization term according to pre-programmed curve carry out dynamic adjustment,
Obtain the regularization term；If the Z-direction information is less than second threshold, the Z-direction parameter in the regularization term is kept
It is constant, obtain the regularization term.
Specific restriction about medical image iterative approximation device may refer to above for medical image iterative approximation
The restriction of method, details are not described herein.Modules in above-mentioned medical image iterative approximation device can be fully or partially through
Software, hardware and combinations thereof are realized.Above-mentioned each module can be embedded in the form of hardware or independently of the place in computer equipment
It manages in device, can also be stored in a software form in the memory in computer equipment, in order to which processor calls execution or more
The corresponding operation of modules.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in Figure 9.The computer equipment includes processor, the memory, network interface, display connected by system bus
Screen and input unit.Wherein, the processor of the computer equipment is for providing calculating and control ability.The computer equipment is deposited
Reservoir includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system and computer journey
Sequence.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The network interface of machine equipment is used to communicate with external terminal by network connection.When the computer program is executed by processor with
Realize a kind of medical image iterative reconstruction approach.The display screen of the computer equipment can be liquid crystal display or electric ink
Display screen, the input unit of the computer equipment can be the touch layer covered on display screen, be also possible to outside computer equipment
Key, trace ball or the Trackpad being arranged on shell can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in Fig. 9, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor perform the steps of when executing computer program
Obtain initial pictures；The Z-direction information of the initial pictures is calculated according to the initial pictures；According to described initial
The Z-direction information of image obtains regularization term parameter, and determines objective function according to regularization term parameter；According to the initial graph
Picture and objective function are iterated reconstruction.
In one embodiment, it is also performed the steps of when processor executes computer program
According to the Z-direction information and preset function relationship of the initial pictures, be calculated regularization term parameter, it is described just
Then changing a parameter includes Z-direction parameter.
In one embodiment, it is also performed the steps of when processor executes computer program
If the Z-direction information is greater than threshold value, the Z-direction parameter in the regularization term is adjusted to default Z-direction
Parameter obtains the regularization term；If the Z-direction information is less than or equal to threshold value, it is calculated according to Z-direction information described
Regularization term.
In one embodiment, it is also performed the steps of when processor executes computer program
If the Z-direction information is greater than first threshold, the Z-direction parameter in the regularization term is adjusted to default
Z-direction parameter obtains the regularization term；If the Z-direction information is less than or equal to first threshold and is more than or equal to second threshold
When, the Z-direction parameter in the regularization term is subjected to dynamic adjustment according to pre-programmed curve, obtains the regularization term；If institute
When stating Z-direction information less than second threshold, the Z-direction parameter in the regularization term is remained unchanged, and obtains the regularization term.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
Obtain initial pictures；The Z-direction information of the initial pictures is calculated according to the initial pictures；According to described initial
The Z-direction information of image obtains regularization term parameter, and determines objective function according to regularization term parameter；According to the initial graph
Picture and objective function are iterated reconstruction.
In one embodiment, it is also performed the steps of when computer program is executed by processor
According to the Z-direction information and preset function relationship of the initial pictures, be calculated regularization term parameter, it is described just
Then changing a parameter includes Z-direction parameter.
In one embodiment, it is also performed the steps of when computer program is executed by processor
If the Z-direction information is greater than threshold value, the Z-direction parameter in the regularization term is adjusted to default Z-direction
Parameter obtains the regularization term；If the Z-direction information is less than or equal to threshold value, it is calculated according to Z-direction information described
Regularization term.
In one embodiment, it is also performed the steps of when computer program is executed by processor
If the Z-direction information is greater than first threshold, the Z-direction parameter in the regularization term is adjusted to default
Z-direction parameter obtains the regularization term；If the Z-direction information is less than or equal to first threshold and is more than or equal to second threshold
When, the Z-direction parameter in the regularization term is subjected to dynamic adjustment according to pre-programmed curve, obtains the regularization term；If institute
When stating Z-direction information less than second threshold, the Z-direction parameter in the regularization term is remained unchanged, and obtains the regularization term.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of medical image iterative reconstruction approach, which is characterized in that the described method includes:
Obtain initial pictures；
The Z-direction information of the initial pictures is calculated according to the initial pictures；
Regularization term parameter is obtained according to the Z-direction information of the initial pictures, and target letter is determined according to regularization term parameter
Number；
Reconstruction is iterated according to the initial pictures and objective function.
2. the method according to claim 1, wherein described obtain according to the Z-direction information of the initial pictures
Regularization term parameter includes:
According to the Z-direction information and preset function relationship of the initial pictures, regularization term parameter, the regularization is calculated
Item parameter includes Z-direction parameter.
3. according to the method described in claim 2, it is characterized in that,
The Z-direction information of the initial pictures includes the Z-direction pixel value change information of initial pictures；
The preset function relationship makes when the variation of the Z-direction pixel value of the initial pictures increases, the regularization term ginseng
Number reduction or constant.
4. according to the method described in claim 3, it is characterized in that,
The preset function is using Z-direction pixel value as independent variable, using regularization term parameter as the monotonic nondecreasing of dependent variable
Function.
5. according to the method described in claim 3, it is characterized in that, the preset function is with one or more separations
Piecewise function.
6. according to the method described in claim 3, it is characterized in that, the preset function includes:
First threshold, second threshold and default Z-direction parameter are preset, and the first threshold is greater than second threshold
Value.
7. according to the method described in claim 6, it is characterized in that, the preset function includes:
If the Z-direction information is greater than first threshold, the Z-direction parameter in the regularization term is adjusted to the default side Z
To parameter, the regularization term is obtained；
If the Z-direction information is less than or equal to first threshold and is more than or equal to second threshold, by the side Z in the regularization term
Dynamic adjustment is carried out according to pre-programmed curve to parameter, obtains the regularization term；
If the Z-direction information is less than second threshold, the Z-direction parameter in the regularization term is remained unchanged, and is obtained described
Regularization term.
8. a kind of medical image iterative approximation device, which is characterized in that described device includes:
Module is obtained, for obtaining initial pictures；
Computing module, for calculating the Z-direction information of the initial pictures according to the initial pictures；
Regularization term module, for obtaining regularization term parameter according to the Z-direction information of the initial pictures, and according to regularization
Item parameter determines objective function；
Module is rebuild, for being iterated reconstruction according to the initial pictures and objective function.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the processor realizes following methods step when executing the computer program:
Obtain initial pictures；
The Z-direction information of the initial pictures is calculated according to the initial pictures；
Regularization term parameter is obtained according to the Z-direction information of the initial pictures, and target letter is determined according to regularization term parameter
Number；
Reconstruction is iterated according to the initial pictures and objective function.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811480554.0A CN109544657B (en) | 2018-12-05 | 2018-12-05 | Medical image iterative reconstruction method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811480554.0A CN109544657B (en) | 2018-12-05 | 2018-12-05 | Medical image iterative reconstruction method, device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109544657A true CN109544657A (en) | 2019-03-29 |
| CN109544657B CN109544657B (en) | 2023-11-28 |
Family
ID=65853763
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811480554.0A Active CN109544657B (en) | 2018-12-05 | 2018-12-05 | Medical image iterative reconstruction method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109544657B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111311184A (en) * | 2020-02-14 | 2020-06-19 | 中国平安人寿保险股份有限公司 | Data judgment method and device based on matching degree value and computer equipment |
| CN111833364A (en) * | 2019-04-19 | 2020-10-27 | 湖北民族大学 | X-ray image edge detection method and device, computer equipment and storage medium |
| CN112017258A (en) * | 2020-09-16 | 2020-12-01 | 上海联影医疗科技有限公司 | PET image reconstruction method, apparatus, computer device, and storage medium |
| CN112347452A (en) * | 2020-11-10 | 2021-02-09 | 上海祺鲲信息科技有限公司 | Electronic contract signing method, electronic equipment and storage medium |
| CN112507546A (en) * | 2020-12-03 | 2021-03-16 | 中国石油天然气股份有限公司 | Indication information determining method and device |
| CN112634388A (en) * | 2020-11-30 | 2021-04-09 | 明峰医疗***股份有限公司 | Optimization method of CT iterative reconstruction cost function, CT image reconstruction method and system and CT |
| CN113961124A (en) * | 2021-09-27 | 2022-01-21 | 上海联影医疗科技股份有限公司 | Medical image display method, medical image display device, computer equipment and storage medium |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7423430B1 (en) * | 2007-04-06 | 2008-09-09 | The Board Of Trustees Of The University Of Illinois | Adaptive parallel acquisition and reconstruction of dynamic MR images |
| US20080247511A1 (en) * | 2007-04-03 | 2008-10-09 | Wernick Miles N | Method for detecting a mass density image of an object |
| US20110262054A1 (en) * | 2006-06-26 | 2011-10-27 | General Electric Company | System and method for iterative image reconstruction |
| US20120027281A1 (en) * | 2010-07-29 | 2012-02-02 | Jang Kwang-Eun | Method and apparatus for processing image, and medical image system employing the apparatus |
| CN102831594A (en) * | 2011-04-29 | 2012-12-19 | 三菱电机株式会社 | Method for segmenting images using superpixels and entropy rate clustering |
| CN103186890A (en) * | 2011-12-30 | 2013-07-03 | 上海联影医疗科技有限公司 | Method for removing ring artifact of CT (computed tomography) reconstructed image |
| CN103185878A (en) * | 2011-12-27 | 2013-07-03 | 上海联影医疗科技有限公司 | Magnetic resonance parallel image acquisition and image reconstruction method |
| US20130259342A1 (en) * | 2012-03-28 | 2013-10-03 | Siemens Aktiengesellschaft | Method for iterative image reconstruction for bi-modal ct data |
| US8593480B1 (en) * | 2011-03-15 | 2013-11-26 | Dolby Laboratories Licensing Corporation | Method and apparatus for image data transformation |
| US20160048983A1 (en) * | 2014-08-12 | 2016-02-18 | Toshiba Medical Systems Corporation | Method and system for substantially reducing cone beam artifacts based upon image domain differentiation in circular computer tomography (ct) |
| US20160278678A1 (en) * | 2012-01-04 | 2016-09-29 | The Trustees Of Dartmouth College | Method and apparatus for quantitative and depth resolved hyperspectral fluorescence and reflectance imaging for surgical guidance |
| CN106251380A (en) * | 2016-07-29 | 2016-12-21 | 上海联影医疗科技有限公司 | Image rebuilding method |
| US20170024855A1 (en) * | 2015-07-26 | 2017-01-26 | Macau University Of Science And Technology | Single Image Super-Resolution Method Using Transform-Invariant Directional Total Variation with S1/2+L1/2-norm |
| US20170097399A1 (en) * | 2015-10-06 | 2017-04-06 | Toshiba Medical Systems Corporation | Mri apparatus, image processing apparatus, and image processing method |
| CN106683144A (en) * | 2016-12-30 | 2017-05-17 | 上海联影医疗科技有限公司 | Image iteration reconstruction method and device |
| CN106780649A (en) * | 2016-12-16 | 2017-05-31 | 上海联影医疗科技有限公司 | The artifact minimizing technology and device of image |
-
2018
- 2018-12-05 CN CN201811480554.0A patent/CN109544657B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110262054A1 (en) * | 2006-06-26 | 2011-10-27 | General Electric Company | System and method for iterative image reconstruction |
| US20080247511A1 (en) * | 2007-04-03 | 2008-10-09 | Wernick Miles N | Method for detecting a mass density image of an object |
| US7423430B1 (en) * | 2007-04-06 | 2008-09-09 | The Board Of Trustees Of The University Of Illinois | Adaptive parallel acquisition and reconstruction of dynamic MR images |
| US20120027281A1 (en) * | 2010-07-29 | 2012-02-02 | Jang Kwang-Eun | Method and apparatus for processing image, and medical image system employing the apparatus |
| US8593480B1 (en) * | 2011-03-15 | 2013-11-26 | Dolby Laboratories Licensing Corporation | Method and apparatus for image data transformation |
| CN102831594A (en) * | 2011-04-29 | 2012-12-19 | 三菱电机株式会社 | Method for segmenting images using superpixels and entropy rate clustering |
| CN103185878A (en) * | 2011-12-27 | 2013-07-03 | 上海联影医疗科技有限公司 | Magnetic resonance parallel image acquisition and image reconstruction method |
| CN103186890A (en) * | 2011-12-30 | 2013-07-03 | 上海联影医疗科技有限公司 | Method for removing ring artifact of CT (computed tomography) reconstructed image |
| US20160278678A1 (en) * | 2012-01-04 | 2016-09-29 | The Trustees Of Dartmouth College | Method and apparatus for quantitative and depth resolved hyperspectral fluorescence and reflectance imaging for surgical guidance |
| US20130259342A1 (en) * | 2012-03-28 | 2013-10-03 | Siemens Aktiengesellschaft | Method for iterative image reconstruction for bi-modal ct data |
| US20160048983A1 (en) * | 2014-08-12 | 2016-02-18 | Toshiba Medical Systems Corporation | Method and system for substantially reducing cone beam artifacts based upon image domain differentiation in circular computer tomography (ct) |
| US20170024855A1 (en) * | 2015-07-26 | 2017-01-26 | Macau University Of Science And Technology | Single Image Super-Resolution Method Using Transform-Invariant Directional Total Variation with S1/2+L1/2-norm |
| US20170097399A1 (en) * | 2015-10-06 | 2017-04-06 | Toshiba Medical Systems Corporation | Mri apparatus, image processing apparatus, and image processing method |
| CN106251380A (en) * | 2016-07-29 | 2016-12-21 | 上海联影医疗科技有限公司 | Image rebuilding method |
| CN106780649A (en) * | 2016-12-16 | 2017-05-31 | 上海联影医疗科技有限公司 | The artifact minimizing technology and device of image |
| CN106683144A (en) * | 2016-12-30 | 2017-05-17 | 上海联影医疗科技有限公司 | Image iteration reconstruction method and device |
Non-Patent Citations (4)
| Title |
|---|
| 张翼飞等: "基于超分辨率重建的图像增强算法研究", 《应用光学》 * |
| 张翼飞等: "基于超分辨率重建的图像增强算法研究", 《应用光学》, no. 02, 15 March 2011 (2011-03-15) * |
| 李伟等: "航空重力梯度数据向下延拓的正则化方法及参数选取研究", 《大地测量与地球动力学》 * |
| 李伟等: "航空重力梯度数据向下延拓的正则化方法及参数选取研究", 《大地测量与地球动力学》, no. 02, 15 February 2017 (2017-02-15) * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111833364A (en) * | 2019-04-19 | 2020-10-27 | 湖北民族大学 | X-ray image edge detection method and device, computer equipment and storage medium |
| CN111311184A (en) * | 2020-02-14 | 2020-06-19 | 中国平安人寿保险股份有限公司 | Data judgment method and device based on matching degree value and computer equipment |
| CN112017258A (en) * | 2020-09-16 | 2020-12-01 | 上海联影医疗科技有限公司 | PET image reconstruction method, apparatus, computer device, and storage medium |
| CN112017258B (en) * | 2020-09-16 | 2024-04-30 | 上海联影医疗科技股份有限公司 | PET image reconstruction method, PET image reconstruction device, computer equipment and storage medium |
| CN112347452A (en) * | 2020-11-10 | 2021-02-09 | 上海祺鲲信息科技有限公司 | Electronic contract signing method, electronic equipment and storage medium |
| CN112347452B (en) * | 2020-11-10 | 2023-08-04 | 上海祺鲲信息科技有限公司 | Electronic contract signing method, electronic equipment and storage medium |
| CN112634388A (en) * | 2020-11-30 | 2021-04-09 | 明峰医疗***股份有限公司 | Optimization method of CT iterative reconstruction cost function, CT image reconstruction method and system and CT |
| CN112634388B (en) * | 2020-11-30 | 2024-01-02 | 明峰医疗***股份有限公司 | Optimization method of CT iterative reconstruction cost function, CT image reconstruction method, system and CT |
| CN112507546A (en) * | 2020-12-03 | 2021-03-16 | 中国石油天然气股份有限公司 | Indication information determining method and device |
| CN112507546B (en) * | 2020-12-03 | 2022-11-01 | 中国石油天然气股份有限公司 | Indication information determining method and device |
| CN113961124A (en) * | 2021-09-27 | 2022-01-21 | 上海联影医疗科技股份有限公司 | Medical image display method, medical image display device, computer equipment and storage medium |
| CN113961124B (en) * | 2021-09-27 | 2024-02-27 | 上海联影医疗科技股份有限公司 | Medical image display method, medical image display device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109544657B (en) | 2023-11-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109544657A (en) | Medical image iterative reconstruction approach, device, computer equipment and storage medium | |
| Xie et al. | Artifact removal using improved GoogLeNet for sparse-view CT reconstruction | |
| Park et al. | Computed tomography super-resolution using deep convolutional neural network | |
| Min et al. | Fast global image smoothing based on weighted least squares | |
| CN110717956B (en) | L0 norm optimization reconstruction method guided by limited angle projection superpixel | |
| EP2556490B1 (en) | Generation of multi-resolution image pyramids | |
| CN107481297B (en) | CT image reconstruction method based on convolutional neural network | |
| US8547389B2 (en) | Capturing image structure detail from a first image and color from a second image | |
| US9147229B2 (en) | Method and system for image denoising using discrete total variation (TV) minimization with one-direction condition | |
| Chen et al. | A trusted medical image super-resolution method based on feedback adaptive weighted dense network | |
| US8908942B2 (en) | Filtered backprojection image reconstruction with characteristics of an iterative map algorithm | |
| Pei et al. | Non-rigid craniofacial 2D-3D registration using CNN-based regression | |
| Ertas et al. | An iterative tomosynthesis reconstruction using total variation combined with non-local means filtering | |
| CN110415310A (en) | Medical scanning imaging method, device, storage medium and computer equipment | |
| CN108460723B (en) | Bilateral total variation image super-resolution reconstruction method based on neighborhood similarity | |
| Cui et al. | TPET: two-stage perceptual enhancement transformer network for low-light image enhancement | |
| CN109712213B (en) | PET image reconstruction method, system, readable storage medium and apparatus | |
| Xu et al. | A performance-driven study of regularization methods for gpu-accelerated iterative ct | |
| CN109118439B (en) | Cone beam CT deblurring method based on line integral | |
| Abascal et al. | A novel prior-and motion-based compressed sensing method for small-animal respiratory gated CT | |
| CN106846250A (en) | A kind of super resolution ratio reconstruction method based on multi-scale filtering | |
| CN112883806B (en) | Video style migration method and device based on neural network, computer equipment and storage medium | |
| CN113706583A (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN111476854B (en) | Image reconstruction method, device, terminal and storage medium | |
| CN108898582A (en) | Cardiac image method for reconstructing, device and computer equipment |
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 | ||
| CB02 | Change of applicant information |
Address after: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant after: Shanghai Lianying Medical Technology Co.,Ltd. Address before: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |