CN107507149A - A kind of noise-reduction method and device of Magnetic resonance imaging image - Google Patents
A kind of noise-reduction method and device of Magnetic resonance imaging image Download PDFInfo
- Publication number
- CN107507149A CN107507149A CN201710769256.2A CN201710769256A CN107507149A CN 107507149 A CN107507149 A CN 107507149A CN 201710769256 A CN201710769256 A CN 201710769256A CN 107507149 A CN107507149 A CN 107507149A
- Authority
- CN
- China
- Prior art keywords
- magnetic resonance
- image
- resonance imaging
- local
- imaging image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000002595 magnetic resonance imaging Methods 0.000 title claims abstract description 95
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000003044 adaptive effect Effects 0.000 claims abstract description 65
- 238000011946 reduction process Methods 0.000 claims abstract description 43
- 230000009467 reduction Effects 0.000 claims abstract description 25
- 238000012876 topography Methods 0.000 claims abstract description 9
- 238000004590 computer program Methods 0.000 claims description 20
- 238000003860 storage Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 230000005311 nuclear magnetism Effects 0.000 claims description 3
- 238000005481 NMR spectroscopy Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 12
- 230000006870 function Effects 0.000 description 16
- 210000004556 brain Anatomy 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000009792 diffusion process Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002440 hepatic effect Effects 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000003706 image smoothing Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000004549 pulsed laser deposition Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10088—Magnetic resonance imaging [MRI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20004—Adaptive image processing
- G06T2207/20012—Locally adaptive
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The present invention is applied to technical field of image processing, there is provided a kind of noise-reduction method and device of Magnetic resonance imaging image, including：Obtain the local image characteristics of Magnetic resonance imaging image；Adaptive regularization parameter is obtained according to the local image characteristics；Noise reduction process is carried out to the Magnetic resonance imaging image according to the adaptive regularization parameter.By establishing local generalized Total Variation and carrying out noise reduction process to Magnetic resonance imaging image according to adaptive regularization parameter, noise reduction process is carried out using corresponding adaptive regularization parameter to the different topographies of Magnetic resonance imaging image, noise reduction process is carried out using small adaptive regularization parameter for even grain region, noise reduction process is carried out using big adaptive regularization parameter for non-homogeneous texture region, noise reduction effectively can either be carried out to image, and can effectively retains the local feature of Magnetic resonance imaging image.
Description
Technical field
The invention belongs to technical field of image processing, more particularly to a kind of noise-reduction method and dress of Magnetic resonance imaging image
Put.
Background technology
During obtaining and transmitting image, due to being influenceed by various factors, image can be led by noise pollution
Cause bigger difficulty be present in the image processing process such as image registration and feature extraction, very abundant especially to characteristic information
Magnetic resonance imaging image.The method generally use smoothing filter of existing image noise reduction carries out noise reduction process to image, or
Person uses full variation image denoising method, image noise reduction is modeled as to the minimization problem of an energy function, and then make image
Reach smooth state, but this method can make image lose many detailed information, thus it is not particularly suited for edge, texture information
Very abundant Magnetic resonance imaging image, noise reduction are poor.
In summary, existing image denoising method, which exists, is not suitable for Magnetic resonance imaging image and noise reduction difference
Problem.
The content of the invention
In view of this, the invention provides a kind of noise-reduction method and device of Magnetic resonance imaging image, it is intended to solves existing
With the presence of image denoising method be not suitable for Magnetic resonance imaging image and noise reduction difference the problem of.
The first aspect of the embodiment of the present invention provides a kind of noise-reduction method of Magnetic resonance imaging image, and the nuclear-magnetism is total to
The noise-reduction method of image of shaking includes：
Obtain the local image characteristics of Magnetic resonance imaging image；
Adaptive regularization parameter is obtained according to the local image characteristics；
Noise reduction process is carried out to the Magnetic resonance imaging image according to the adaptive regularization parameter.
The second aspect of the embodiment of the present invention provides a kind of denoising device of Magnetic resonance imaging image, described device bag
Include：
Feature acquisition module, for obtaining the local image characteristics of Magnetic resonance imaging image；
Parameter acquisition module, for obtaining adaptive regularization parameter according to the local image characteristics；
Noise reduction process module, for being dropped according to the adaptive regularization parameter to the Magnetic resonance imaging image
Make an uproar processing.
The third aspect of the embodiment of the present invention provides a kind of terminal device, including memory, processor and is stored in
In the memory and the computer program that can run on the processor, described in the computing device during computer program
Realize following steps：
Obtain the local image characteristics of Magnetic resonance imaging image；
Adaptive regularization parameter is obtained according to the local image characteristics；
Noise reduction process is carried out to the Magnetic resonance imaging image according to the adaptive regularization parameter.
The fourth aspect of the embodiment of the present invention provides a kind of computer-readable recording medium, the computer-readable storage
Media storage has computer program, and the computer program realizes following steps when being executed by processor：
Obtain the local image characteristics of Magnetic resonance imaging image；
Adaptive regularization parameter is obtained according to the local image characteristics；
Noise reduction process is carried out to the Magnetic resonance imaging image according to the adaptive regularization parameter.
The noise-reduction method and device of a kind of Magnetic resonance imaging image provided by the invention, are become entirely by establishing local generalized
Sub-model simultaneously carries out noise reduction process according to adaptive regularization parameter to Magnetic resonance imaging image, to Magnetic resonance imaging image
Different topographies noise reduction process is carried out using corresponding adaptive regularization parameter, for even grain region using small
Adaptive regularization parameter carries out noise reduction process, is dropped for non-homogeneous texture region using big adaptive regularization parameter
Make an uproar processing, noise reduction effectively can either be carried out to image, and can effectively retain the local feature of Magnetic resonance imaging image, have
Solve the problems, such as to effect that existing image denoising method is present and be not suitable for Magnetic resonance imaging image and noise reduction difference.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
In the required accompanying drawing used be briefly described, it should be apparent that, drawings in the following description be only the present invention some
Embodiment, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these
Accompanying drawing obtains other accompanying drawings.
Fig. 1 is a kind of implementation process figure of the noise-reduction method for Magnetic resonance imaging image that the embodiment of the present invention one provides；
Fig. 2 is a kind of structured flowchart of the denoising device for Magnetic resonance imaging image that the embodiment of the present invention two provides；
Fig. 3 is a kind of structural representation for terminal device that the embodiment of the present invention three provides.
Embodiment
In describing below, in order to illustrate rather than in order to limit, it is proposed that such as tool of particular system structure, technology etc
Body details, thoroughly to understand the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention can also be realized in the other embodiments of details.In other situations, omit to well-known system, device, electricity
Road and the detailed description of method, in case unnecessary details hinders description of the invention.
Magnetic resonance imaging image and noise reduction are not suitable for it to solve existing image denoising method presence
The problem of poor, a kind of noise-reduction method and device of Magnetic resonance imaging image provided in an embodiment of the present invention are local by establishing
Broad sense Total Variation simultaneously carries out noise reduction process according to adaptive regularization parameter to Magnetic resonance imaging image, to nuclear magnetic resonance
The different topographies of image carry out noise reduction process using corresponding adaptive regularization parameter, for even grain region
Noise reduction process is carried out using small adaptive regularization parameter, joined for non-homogeneous texture region using big adaptive regularization
Number carries out noise reduction process, effectively can either carry out noise reduction to image, and can effectively retains the office of Magnetic resonance imaging image
Portion's feature.
In order to illustrate technical scheme, illustrated below by specific embodiment.
Embodiment one：
Fig. 1 shows a kind of flow chart of the noise-reduction method for Magnetic resonance imaging image that the embodiment of the present invention one provides,
Details are as follows：
As shown in figure 1, a kind of noise-reduction method of Magnetic resonance imaging image comprises the following steps：
In step S101, the local image characteristics of Magnetic resonance imaging image are obtained.
It should be noted that Magnetic resonance imaging image is a width width gray image, each pixel is represented by gray value
The color of point, Magnetic resonance imaging image can be got by the gray value of each pixel of Magnetic resonance imaging image
Local image characteristics., can be by magnetic resonance imaging image according to local image characteristics as a kind of implementation of the present embodiment
It is divided into even grain region and non-homogeneous texture region, even grain region refers to that noise is weaker, image texture characteristic ratio
More unified image-region, non-homogeneous texture region refer to that noise is stronger, the irregular image-region of image texture characteristic, show
Example property, the hepatic portion of Healthy People has unified textural characteristics, i.e. image-region corresponding to the hepatic portion of Healthy People is
Even grain region, the brain ditch gyrus part of brain have irregular textural characteristics, i.e. the brain ditch gyrus part of brain corresponds to
Image-region be non-homogeneous texture region.It should be noted that in order to distinguish even grain region and non-homogeneous texture region
Noise threshold can be set, illustrate that the image-region is non-homogeneous line if the noise of a certain image-region is more than the noise threshold
Region is managed, illustrates that the image-region is even grain region if the noise of the image-region is not more than the noise threshold, also needs
It is noted that noise threshold can be configured by the gray value of Magnetic resonance imaging image.
Preferably as a kind of implementation of the present embodiment, above-mentioned steps S101 comprises the following steps S1011 extremely
S1012：
S1011, obtain the image intensity value of Magnetic resonance imaging image；
S1012, local image characteristics are obtained according to described image gray value.
In step s 102, adaptive regularization parameter is obtained according to the local image characteristics.
If it should be noted that joined when carrying out noise reduction process to Magnetic resonance imaging image using unified regularization
Number is handled, and noise reduction process, even grain region are carried out to Magnetic resonance imaging image according to larger regularization parameter
Image can realize noise reduction, but can cause non-homogeneous texture region image fault and lose details；According to smaller
Regularization parameter to Magnetic resonance imaging image carry out noise reduction process, although the image of non-homogeneous texture region can be ensured not
Distortion simultaneously retains details, can the noise reduction in even grain region then can unobvious.It can be distinguished by local image characteristics
Even texture region and non-homogeneous texture region, the local image characteristics of different local image regions are different, according to topography
Feature obtains adaptive regularization parameter corresponding to the local image region, and then obtains and adapt to the adaptive of the local image region
Regularization parameter is answered, specifically, it is adaptive to obtain the adaptation even grain region according to the local image characteristics in even grain region
The regularization parameter answered, obtained according to the local image characteristics of non-homogeneous texture region and adapt to the adaptive of the non-homogeneous texture region
Answer regularization parameter.
Preferably as a kind of implementation of the present embodiment, above-mentioned steps S102 comprises the following steps S1021 extremely
S1023：
S1021, the local value fidelity item of Magnetic resonance imaging image is obtained according to the local image characteristics；
S1022, local generalized Total Variation is obtained according to the local value fidelity item；
S1023, the local variance based on the local generalized Total Variation obtain the adaptive regularization parameter.
It should be noted that existing full variation image denoising method, is that image noise reduction is modeled as into an energy function
Minimization problem, specifically, the model can be represented using below equation：
Wherein, Ω represents a bounded open set of Magnetic resonance imaging image, and f represents noisy image, and u is indicated without making an uproar
Acoustic image.λ>0 is a regularization parameter, is suppressed by regularization parameter balances noise and image smoothing.BV (Ω) is bounded
The space of the function of change, σ2The variance of Gaussian noise is represented, wherein λ is a changeless parameter.
In order to obtain adaptive regularization parameter, introduce×Gaussian function K and the local value fidelity for producing image
Item is as follows：
Wherein, symmetrical Gaussian function K meets following condition：
K (w-x, z-y)=K (x-w, y-z), ∫ K (x, y) dxdy=1.
Local generalized Total Variation is obtained according to local value fidelity item (formula (2)), become entirely for local generalized below
The expression formula of sub-model：
It should be noted that in formula (3), the right Section 1 is regular terms, can be suppressed during minimum
Noise, the right Section 2 can suppress to treat noise-reduced image and the similarity with noise picture, avoid image noise reduction to approach fidelity item
Occurs excessive deviation after processing.
Local value fidelity item (formula (2)) is substituted into local generalized Total Variation, gets the full variation of local generalized
The expression formula of model is as follows：
It should be noted thatConvolution is represented, makes ψ (°)=I1(°)/I0(°), on formula (4) both sides to noise-free picture
U seeks local derviation, and it is as follows to obtain Euler-Lagrange equation：
Wherein,For diffusion coefficient, in order to handle the degenerate problem of diffusion coefficient, order
Wherein ε takes a very small positive number, makes its sufficiently small, can be effectively prevented from influenceing the noise reduction of local generalized Total Variation
Effect.
After establishing local generalized Total Variation, the local variance based on local generalized Total Variation obtains adaptive
Regularization parameter, based on Neumann boundary conditions, adaptive regularization parametric solution formula is as follows：
Wherein
Replaced with ψ (u)S (x, y) expression formula is as follows：
Wherein σsvRepresentation space variable noise standard deviation, LV (x, y) represent local variance.
Local variance LV (x, y) texture local variance LVtexture(x, y) and spatially-variable noise variance's
Summation carrys out approximate representation, obtains：
So as to obtain adapting to the adaptive regularization parameter of local image region.
In step s 103, the Magnetic resonance imaging image is carried out at noise reduction according to the adaptive regularization parameter
Reason.
It should be noted that being based on above-mentioned local generalized Total Variation, the Local map is obtained according to local image characteristics
The adaptive regularization parameter as corresponding to region, the adaptive regularization parameter for adapting to the local image region is got, then
Noise reduction process is carried out using corresponding adaptive regularization parameter to the different topographies of the Magnetic resonance imaging image, specifically
, even grain region carries out noise reduction process, non-homogeneous texture region using the adaptive regularization parameter in even grain region
Noise reduction process is carried out using the adaptive regularization parameter of non-homogeneous texture region.It should also be noted that, even grain region
The adaptive regularization parameter of feature is less than the adaptive regularization parameter of the non-homogeneous texture region.
Preferably as a kind of implementation of the present embodiment, above-mentioned steps S103 comprises the following steps S1031 extremely
S1032：
S1031, establish local generalized Total Variation；
S1032, the different topographies based on the local generalized Total Variation to the Magnetic resonance imaging image
Noise reduction process is carried out using corresponding adaptive regularization parameter.
It should be noted that the adaptive regularization parameter that the present embodiment provides is obtained based on 2D Magnetic resonance imaging images
, it is also necessary to explanation, the noise-reduction method of the Magnetic resonance imaging image of the present embodiment, which can equally be expanded, is applied to 3D
Magnetic resonance imaging image.
The noise-reduction method for the Magnetic resonance imaging image that the present embodiment provides, by establishing local generalized Total Variation simultaneously
Noise reduction process is carried out to Magnetic resonance imaging image according to adaptive regularization parameter, to the different offices of Magnetic resonance imaging image
Portion's image carries out noise reduction process using corresponding adaptive regularization parameter, for even grain region using it is small it is adaptive just
Then change parameter and carry out noise reduction process, noise reduction process is carried out using big adaptive regularization parameter for non-homogeneous texture region,
Noise reduction effectively can either be carried out to image, and can effectively retains the local feature of Magnetic resonance imaging image, effectively solved
The problem of not being suitable for Magnetic resonance imaging image and noise reduction difference be present in existing image denoising method of having determined.
Embodiment two：
A kind of noise-reduction method of the Magnetic resonance imaging image provided corresponding to the embodiment one shown in Fig. 1, Fig. 2 are shown
The structured flowchart of the denoising device for the Magnetic resonance imaging image that the embodiment of the present invention two provides, for convenience of description, only shows
The part related to the embodiment of the present invention.
Reference picture 2, a kind of above-mentioned denoising device 20 of Magnetic resonance imaging image, including feature acquisition module 21, parameter
Acquisition module 22 and noise reduction process module 23.
Feature acquisition module 21 is used for the local image characteristics for obtaining Magnetic resonance imaging image.
Parameter acquisition module 22 is used to obtain adaptive regularization parameter according to the local image characteristics.
Noise reduction process module 23 is used to carry out the Magnetic resonance imaging image according to the adaptive regularization parameter
Noise reduction process.
Preferably as a kind of implementation of the present embodiment, features described above acquisition module 21 includes gray value and obtains list
Member and feature acquiring unit.
Gray value acquiring unit, for obtaining the image intensity value of Magnetic resonance imaging image；
Feature acquiring unit, for obtaining local image characteristics according to described image gray value.
Preferably as a kind of implementation of the present embodiment, above-mentioned parameter acquisition module 22 includes：First obtains list
Member, second acquisition unit and the 3rd acquiring unit.
First acquisition unit, the local value for obtaining Magnetic resonance imaging image according to the local image characteristics are protected
True item；
Second acquisition unit, for obtaining local generalized Total Variation according to the local value fidelity item；
3rd acquiring unit, for the local variance based on the local generalized Total Variation obtain it is described it is adaptive just
Then change parameter.
Preferably as a kind of implementation of the present embodiment, above-mentioned noise reduction process module 23 establishes unit including model
And noise reduction processing unit.
Model establishes unit, for establishing local generalized Total Variation；
Noise reduction processing unit, for based on the local generalized Total Variation to the Magnetic resonance imaging image not
Noise reduction process is carried out using corresponding adaptive regularization parameter with topography.
Those skilled in the art can be understood that, for convenience of description and succinctly, only with above-mentioned each function
The division progress of module, can be as needed and by above-mentioned function distribution by different function lists for example, in practical application
Member, module are completed, i.e., the internal structure of the installation method of application program are divided into different functional units or module, to complete
All or part of function described above.Each functional module in embodiment can be integrated in a processing unit, also may be used
To be that unit is individually physically present, can also two or more units it is integrated in a unit, it is above-mentioned integrated
Unit can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.In addition, each functional module
Specific name also only to facilitate mutually distinguish, be not limited to the protection domain of the application.
It should be noted that the denoising device of Magnetic resonance imaging image provided in an embodiment of the present invention, due to this hair
Embodiment of the method shown in bright Fig. 1 is based on same design, its technique effect brought and embodiment of the method phase shown in Fig. 1 of the present invention
Together, particular content can be found in the narration in embodiment of the method shown in Fig. 1 of the present invention, and here is omitted.
Therefore, the denoising device for a kind of Magnetic resonance imaging image that the present embodiment provides, can equally pass through foundation office
Portion's broad sense Total Variation simultaneously carries out noise reduction process according to adaptive regularization parameter to Magnetic resonance imaging image, and nuclear-magnetism is total to
Shake image different topographies using corresponding adaptive regularization parameter carry out noise reduction process, for even grain area
Domain carries out noise reduction process using small adaptive regularization parameter, and big adaptive regularization is used for non-homogeneous texture region
Parameter carries out noise reduction process, effectively can either carry out noise reduction to image, and can effectively retains Magnetic resonance imaging image
Local feature, efficiently solve existing image denoising method presence and be not suitable for Magnetic resonance imaging image and noise reduction
The problem of poor.
Embodiment three：
Fig. 3 is the schematic diagram for the terminal device that one embodiment of the invention provides.As shown in figure 3, the terminal of the embodiment is set
Standby 3 include：Processor 30, memory 31 and it is stored in the meter that can be run in the memory 31 and on the processor 30
Calculation machine program 32, such as the program of the method for above-mentioned unloading application program.The processor 30 performs the computer program 32
Step in the embodiment of the method for the above-mentioned each unloading application programs of Shi Shixian, such as the step S101 to S103 shown in Fig. 1.Or
Person, the processor 30 realize the function of each module/unit in above-mentioned each device embodiment when performing the computer program 32,
Such as the function of module 21 to 23 shown in Fig. 2.
Exemplary, the computer program 32 can be divided into one or more module/units, it is one or
Multiple module/units are stored in the memory 31, and are performed by the processor 30, to complete the present invention.Described one
Individual or multiple module/units can be the series of computation machine programmed instruction section that can complete specific function, and the instruction segment is used for
Implementation procedure of the computer program 32 in the terminal device 3 is described.For example, the computer program 32 can be divided
Feature acquisition module, parameter acquisition module and noise reduction process module are cut into, each module concrete function is as follows：
Feature acquisition module, for obtaining the local image characteristics of Magnetic resonance imaging image；
Parameter acquisition module, for obtaining adaptive regularization parameter according to the local image characteristics；
Noise reduction process module, for being dropped according to the adaptive regularization parameter to the Magnetic resonance imaging image
Make an uproar processing.
The terminal device 3 can be that the calculating such as desktop PC, notebook, palm PC and cloud server are set
It is standby.The terminal device may include, but be not limited only to, processor 30, memory 31.It will be understood by those skilled in the art that Fig. 3
The only example of terminal device 3, the restriction to terminal device 3 is not formed, can included than illustrating more or less portions
Part, some parts or different parts are either combined, such as the terminal device can also include input-output equipment, net
Network access device, bus etc..
Alleged processor 30 can be CPU (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other PLDs, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor
Deng.
The memory 31 can be the internal storage unit of the terminal device 3, such as the hard disk of terminal device 3 or interior
Deposit.The memory 31 can also be the External memory equipment of the terminal device 3, such as be equipped with the terminal device 3
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, dodge
Deposit card (Flash Card) etc..Further, the memory 31 can also both include the storage inside list of the terminal device 3
Member also includes External memory equipment.The memory 31 is used to store needed for the computer program and the terminal device
Other programs and data.The memory 31 can be also used for temporarily storing the data that has exported or will export.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and is not described in detail or remembers in some embodiment
The part of load, it may refer to the associated description of other embodiments.
Those of ordinary skill in the art are it is to be appreciated that the list of each example described with reference to the embodiments described herein
Member and algorithm steps, it can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
Performed with hardware or software mode, application-specific and design constraint depending on technical scheme.Professional technique
Personnel can realize described function using distinct methods to each specific application program, but this realization should not
Think beyond the scope of this invention.
In embodiment provided by the present invention, it should be understood that disclosed device/terminal device and method, can be with
Realize by another way.For example, device described above/terminal device embodiment is only schematical, for example, institute
The division of module or unit is stated, only a kind of division of logic function, there can be other dividing mode when actually realizing, such as
Multiple units or component can combine or be desirably integrated into another system, or some features can be ignored, or not perform.Separately
A bit, shown or discussed mutual coupling or direct-coupling or communication connection can be by some interfaces, device
Or INDIRECT COUPLING or the communication connection of unit, can be electrical, mechanical or other forms.
The unit illustrated as separating component can be or may not be physically separate, show as unit
The part shown can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple
On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also
That unit is individually physically present, can also two or more units it is integrated in a unit.Above-mentioned integrated list
Member can both be realized in the form of hardware, can also be realized in the form of SFU software functional unit.
If the integrated module/unit realized in the form of SFU software functional unit and as independent production marketing or
In use, it can be stored in a computer read/write memory medium.Based on such understanding, the present invention realizes above-mentioned implementation
All or part of flow in example method, by computer program the hardware of correlation can also be instructed to complete, described meter
Calculation machine program can be stored in a computer-readable recording medium, and the computer program can be achieved when being executed by processor
The step of stating each embodiment of the method.
Wherein, the computer program includes computer program code, and the computer program code can be source code
Form, object identification code form, executable file or some intermediate forms etc..The computer-readable medium can include：Can
Carry any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disc, CD, the computer of the computer program code
Memory, read-only storage (ROM, Read-Only Memory), random access memory (RAM, Random Access
Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that the computer-readable medium
Comprising content appropriate increase and decrease can be carried out according to legislation in jurisdiction and the requirement of patent practice, such as in some departments
Method administrative area, according to legislation and patent practice, it is electric carrier signal and telecommunication signal that computer-readable medium, which does not include,.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although with reference to foregoing reality
Example is applied the present invention is described in detail, it will be understood by those within the art that：It still can be to foregoing each
Technical scheme described in embodiment is modified, or carries out equivalent substitution to which part technical characteristic；And these are changed
Or replace, the essence of appropriate technical solution is departed from the spirit and scope of various embodiments of the present invention technical scheme, all should
Within protection scope of the present invention.
Claims (10)
- A kind of 1. noise-reduction method of Magnetic resonance imaging image, it is characterised in that the noise reduction side of the Magnetic resonance imaging image Method includes：Obtain the local image characteristics of Magnetic resonance imaging image；Adaptive regularization parameter is obtained according to the local image characteristics；Noise reduction process is carried out to the Magnetic resonance imaging image according to the adaptive regularization parameter.
- 2. the noise-reduction method of Magnetic resonance imaging image according to claim 1, it is characterised in that the acquisition nuclear-magnetism is total to The local image characteristics of image of shaking include：Obtain the image intensity value of Magnetic resonance imaging image；Local image characteristics are obtained according to described image gray value.
- 3. the noise-reduction method of Magnetic resonance imaging image according to claim 1, it is characterised in that described according to the office Portion's characteristics of image, which obtains adaptive regularization parameter, to be included：The local value fidelity item of Magnetic resonance imaging image is obtained according to the local image characteristics；Local generalized Total Variation is obtained according to the local value fidelity item；Local variance based on the local generalized Total Variation obtains the adaptive regularization parameter.
- 4. the noise-reduction method of Magnetic resonance imaging image according to claim 1, it is characterised in that the nuclear magnetic resonance into As image includes even grain region and non-homogeneous texture region；The adaptive regularization parameter of the even grain provincial characteristics is less than the self-adapting regular of the non-homogeneous texture region Change parameter.
- 5. the noise-reduction method of Magnetic resonance imaging image according to claim 1, it is characterised in that described in the basis certainly Adapt to regularization parameter includes to Magnetic resonance imaging image progress noise reduction process：Establish local generalized Total Variation；Based on the local generalized Total Variation to the different topographies of the Magnetic resonance imaging image using corresponding Adaptive regularization parameter carries out noise reduction process.
- A kind of 6. denoising device of Magnetic resonance imaging image, it is characterised in that the noise reduction dress of the Magnetic resonance imaging image Put including：Feature acquisition module, for obtaining the local image characteristics of Magnetic resonance imaging image；Parameter acquisition module, for obtaining adaptive regularization parameter according to the local image characteristics；Noise reduction process module, for being carried out according to the adaptive regularization parameter to the Magnetic resonance imaging image at noise reduction Reason.
- 7. the denoising device of Magnetic resonance imaging image according to claim 6, it is characterised in that the feature obtains mould Block includes：Gray value acquiring unit, for obtaining the image intensity value of Magnetic resonance imaging image；Feature acquiring unit, for obtaining local image characteristics according to described image gray value.
- 8. the denoising device of Magnetic resonance imaging image according to claim 6, it is characterised in that the parameter acquiring mould Block includes：First acquisition unit, for obtaining the local value fidelity of Magnetic resonance imaging image according to the local image characteristics ；Second acquisition unit, for obtaining local generalized Total Variation according to the local value fidelity item；3rd acquiring unit, the adaptive regularization is obtained for the local variance based on the local generalized Total Variation Parameter.
- 9. a kind of terminal device, including memory, processor and it is stored in the memory and can be on the processor The computer program of operation, it is characterised in that realize such as claim 1 to 5 described in the computing device during computer program The step of method described in any one.
- 10. a kind of computer-readable recording medium, the computer-readable recording medium storage has computer program, and its feature exists In the step of method as described in claim 1 to 5 any one is realized when the computer program is executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710769256.2A CN107507149A (en) | 2017-08-31 | 2017-08-31 | A kind of noise-reduction method and device of Magnetic resonance imaging image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710769256.2A CN107507149A (en) | 2017-08-31 | 2017-08-31 | A kind of noise-reduction method and device of Magnetic resonance imaging image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107507149A true CN107507149A (en) | 2017-12-22 |
Family
ID=60694545
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710769256.2A Pending CN107507149A (en) | 2017-08-31 | 2017-08-31 | A kind of noise-reduction method and device of Magnetic resonance imaging image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107507149A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460810A (en) * | 2018-02-11 | 2018-08-28 | 南京邮电大学 | A kind of parallel MR image method for fast reconstruction of full variation |
| CN110926425A (en) * | 2019-11-01 | 2020-03-27 | 宁波大学 | Navigation logistics transportation system of 3D structured light camera and control method thereof |
| CN114186584A (en) * | 2021-12-06 | 2022-03-15 | 无锡鸣石峻致医疗科技有限公司 | Method and equipment for denoising magnetic resonance signal based on extended exponential model |
| US20220188602A1 (en) * | 2019-04-24 | 2022-06-16 | University Of Virginia Patent Foundation | Denoising magnetic resonance images using unsupervised deep convolutional neural networks |
| WO2023065665A1 (en) * | 2021-10-21 | 2023-04-27 | 深圳市慧鲤科技有限公司 | Image processing method and apparatus, device, storage medium and computer program product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103236046A (en) * | 2013-04-28 | 2013-08-07 | 南京理工大学 | Fractional order adaptive coherent speckle filtering method based on image form fuzzy membership degree |
| US20160247263A1 (en) * | 2015-02-24 | 2016-08-25 | Siemens Aktiengesellschaft | Simultaneous Edge Enhancement And Non-Uniform Noise Removal Using Refined Adaptive Filtering |
| US9569843B1 (en) * | 2015-09-09 | 2017-02-14 | Siemens Healthcare Gmbh | Parameter-free denoising of complex MR images by iterative multi-wavelet thresholding |
| CN106651983A (en) * | 2016-12-27 | 2017-05-10 | 四川大学 | Magnetic resonance image reconstruction method and apparatus |
| CN106981051A (en) * | 2015-12-11 | 2017-07-25 | 西门子保健有限责任公司 | For the system and method for the MRI for moving parsing |
-
2017
- 2017-08-31 CN CN201710769256.2A patent/CN107507149A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103236046A (en) * | 2013-04-28 | 2013-08-07 | 南京理工大学 | Fractional order adaptive coherent speckle filtering method based on image form fuzzy membership degree |
| US20160247263A1 (en) * | 2015-02-24 | 2016-08-25 | Siemens Aktiengesellschaft | Simultaneous Edge Enhancement And Non-Uniform Noise Removal Using Refined Adaptive Filtering |
| US9569843B1 (en) * | 2015-09-09 | 2017-02-14 | Siemens Healthcare Gmbh | Parameter-free denoising of complex MR images by iterative multi-wavelet thresholding |
| CN106981051A (en) * | 2015-12-11 | 2017-07-25 | 西门子保健有限责任公司 | For the system and method for the MRI for moving parsing |
| CN106651983A (en) * | 2016-12-27 | 2017-05-10 | 四川大学 | Magnetic resonance image reconstruction method and apparatus |
Non-Patent Citations (2)
| Title |
|---|
| 余丽红: "基于全变分的磁共振图像去噪算法的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 陈明举 等: "基于正则化与保真项全变分自适应图像去噪模型", 《重庆邮电大学学报(自然科学版)》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108460810A (en) * | 2018-02-11 | 2018-08-28 | 南京邮电大学 | A kind of parallel MR image method for fast reconstruction of full variation |
| US20220188602A1 (en) * | 2019-04-24 | 2022-06-16 | University Of Virginia Patent Foundation | Denoising magnetic resonance images using unsupervised deep convolutional neural networks |
| US11954578B2 (en) * | 2019-04-24 | 2024-04-09 | University Of Virginia Patent Foundation | Denoising magnetic resonance images using unsupervised deep convolutional neural networks |
| CN110926425A (en) * | 2019-11-01 | 2020-03-27 | 宁波大学 | Navigation logistics transportation system of 3D structured light camera and control method thereof |
| WO2023065665A1 (en) * | 2021-10-21 | 2023-04-27 | 深圳市慧鲤科技有限公司 | Image processing method and apparatus, device, storage medium and computer program product |
| CN114186584A (en) * | 2021-12-06 | 2022-03-15 | 无锡鸣石峻致医疗科技有限公司 | Method and equipment for denoising magnetic resonance signal based on extended exponential model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107507149A (en) | A kind of noise-reduction method and device of Magnetic resonance imaging image | |
| Lu et al. | Cross-based local multipoint filtering | |
| CN107358586A (en) | A kind of image enchancing method, device and equipment | |
| Kou et al. | Gradient domain guided image filtering | |
| Mrázek et al. | On robust estimation and smoothing with spatial and tonal kernels | |
| Rodríguez | Total variation regularization algorithms for images corrupted with different noise models: a review | |
| Coupé et al. | 3D wavelet subbands mixing for image denoising | |
| Barbu et al. | A PDE variational approach to image denoising and restoration | |
| Yin et al. | Fast and efficient implementation of image filtering using a side window convolutional neural network | |
| CN107506754A (en) | Iris identification method, device and terminal device | |
| Pan et al. | Dual convolutional neural networks for low-level vision | |
| Phophalia et al. | Rough set based bilateral filter design for denoising brain MR images | |
| CN109785246A (en) | A kind of noise-reduction method of non-local mean filtering, device and equipment | |
| Lin et al. | An efficient structure‐aware bilateral texture filtering for image smoothing | |
| JP7171087B2 (en) | A mesh denoising method based on graph convolutional networks | |
| Zhang et al. | Multiple-step local Wiener filter with proper stopping in wavelet domain | |
| Duan et al. | A fast operator-splitting method for Beltrami color image denoising | |
| CN111192204A (en) | Image enhancement method, system and computer readable storage medium | |
| Gilboa et al. | Image enhancement segmentation and denoising by time dependent nonlinear diffusion processes | |
| Park et al. | Feature-aware filtering for point-set surface denoising | |
| Jose et al. | Bilateral edge detectors | |
| CN113012058A (en) | Eye image noise removing method and system | |
| CN107633506A (en) | A kind of image symmetrical characteristic detection method, device and terminal device | |
| CN114445273A (en) | Magnetic resonance image processing method, computer device, and storage medium | |
| Hou et al. | Denoising point cloud |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171222 |
|
| RJ01 | Rejection of invention patent application after publication |