CN109671036A - A kind of method for correcting image, device, computer equipment and storage medium - Google Patents
A kind of method for correcting image, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109671036A CN109671036A CN201811604321.7A CN201811604321A CN109671036A CN 109671036 A CN109671036 A CN 109671036A CN 201811604321 A CN201811604321 A CN 201811604321A CN 109671036 A CN109671036 A CN 109671036A
- Authority
- CN
- China
- Prior art keywords
- image
- processed
- brightness
- model
- gamma correction
- 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 title claims abstract description 41
- 238000012937 correction Methods 0.000 claims abstract description 50
- 239000004615 ingredient Substances 0.000 claims abstract description 21
- 230000005291 magnetic effect Effects 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 28
- 238000010801 machine learning Methods 0.000 claims description 11
- 238000003702 image correction Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 230000001788 irregular Effects 0.000 abstract description 14
- 238000007323 disproportionation reaction Methods 0.000 abstract description 8
- 238000009826 distribution Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 9
- 238000012545 processing Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 5
- 238000002059 diagnostic imaging Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000000007 visual effect Effects 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
- G06T5/80—Geometric correction
-
- 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
- G06T2207/20081—Training; Learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The embodiment of the invention discloses a kind of method for correcting image, device, computer equipment and storage mediums.Wherein, method includes: the image to be processed for obtaining target object;The image to be processed is input to brightness of image calibration model;Obtain the gamma correction image corresponding with the image to be processed exported from described image gamma correction model.The image to be processed that the embodiment of the present invention passes through the target object that will acquire is input to preparatory trained brightness of image calibration model, to obtain corrected image to be processed, it solves the problems, such as in the prior art as the low efficiency of radiofrequency field brightness of image unevenness caused by uneven and ineffective, it realizes and accurately the irregular ingredient of radiofrequency field is put forward and removed from image contrast information, the brightness disproportionation ingredient as caused by radiofrequency field unevenness in image is quickly corrected on the basis of retaining picture contrast, improves the efficiency and calibration accuracy of image rectification.
Description
Technical field
The present embodiments relate to Medical Image Processing more particularly to a kind of method for correcting image, device, computers
Equipment and storage medium.
Background technique
High-field magnetic resonance system in clinical scanning there are serious radiofrequency field (B1) is irregular, including transmitting radiofrequency field and
Reception radio-frequency field distribution is irregular, so that the luminance information on image is outside one's consideration in addition to tissue contrast there is also additional uneven luminance,
Magnetic resonance image quality is seriously affected, the diagnosis of clinical disease is interfered.Radio-frequency field distribution is irregular on different patients
Degree and performance are different, so the correction that different patients are carried out with radiofrequency field is needed to optimize, the process of correction is needed figure
Radiofrequency field uneven luminance ingredient as in is removed from image, and retains the contrast information in magnetic resonance image to diagnose disease
Disease.
In traditional irregular correcting algorithm of radiofrequency field, a kind of method is to be distributed for low frequency based on radiofrequency field is irregular, and scheme
Image contrast information is high frequency distribution it is assumed that do not distinguish the irregular source of launching site and received field, by image it is irregular at
Divide and be corrected together, the radio-frequency field distribution information in image is sought out from image to be corrected, without influencing image
Contrast information.But when facing tissue or the slightly larger scene of structural area, the contrast information of different tissues will also become
At low-frequency information, radio-frequency field distribution can not accurately be separated from contrast information, the contrast of image will be by broken
It is bad, influence the diagnosis of clinician.
Another method is to be corrected respectively to launching site and received field respectively, passes through the width to each channel of transmitting coil
Phase parameter logistic is adjusted, so that the launching site acted on human body tends to uniformly, but because transmitting coil port number is limited,
And the interaction of human body and radiofrequency field is complicated and uncertain, it is often limited to the calibration result at launching site.The school of received field
Positive to need to carry out quick prescan to different patients to obtain body coil image as relatively uniform with reference to figure, prescan is simultaneously
The local coil image of same scan parameter is acquired, the two is divided by, the received field distributions ratios of local coil and body coil are obtained,
The approximation that can be used as local coil received field is corrected.But in high field systems body coil image itself often there is also
The irregular problem of radiofrequency field, body coil launching site and received field have certain inhomogeneities, so calibration result still remains reference
The irregular ingredient of image.
Summary of the invention
The present invention provides a kind of method for correcting image, device, computer equipment and storage medium, is retaining image to realize
The brightness disproportionation ingredient as caused by radiofrequency field unevenness in image is quickly corrected on the basis of contrast, improves the effect of image rectification
Rate and calibration accuracy.
In a first aspect, the embodiment of the invention provides a kind of method for correcting image, this method comprises:
Obtain the image to be processed of target object;
The image to be processed is input to brightness of image calibration model;
Obtain the gamma correction image corresponding with the image to be processed exported from described image gamma correction model.
Optionally, the image to be processed is the magnetic resonance image scanned by magnetic resonance system.
Optionally, described image gamma correction model is the network model based on machine learning.
Optionally, before the image to be processed is input to brightness of image calibration model, the method also includes:
Described image gamma correction model is trained;
Correspondingly, being trained to described image gamma correction model, comprising:
Using include brightness irregularities ingredient the first image and corresponding brightness uniformity the second image as training
Sample is input to described image gamma correction model and carries out model training.
Optionally, the first image and second image are under identical image scanning parameter to same target
The image that same area scans.
Optionally, the first image and the collection process of second image include:
Obtain the scan image acquired in Low Magnetic field MRI system by local coil and body coil;
Using the scan image of local coil acquisition as the first image, by brightness in the scan image of body coil acquisition
The highest image of the uniformity is as the second image corresponding with the first image.
Second aspect, the embodiment of the invention also provides a kind of image correction apparatus, which includes:
Image collection module, for obtaining the image to be processed of target object;
Mode input module, for the image to be processed to be input to brightness of image calibration model;
Correction module, for the output brightness school corresponding with the image to be processed from described image gamma correction model
Positive result.
Optionally, the image to be processed is the magnetic resonance image scanned by magnetic resonance system.
Optionally, described image gamma correction model is the network model based on machine learning.
Optionally, described device further include:
Model training module, for being trained to described image gamma correction model.
Optionally, it will include the first image of brightness irregularities ingredient and corresponding that model training module, which is specifically used for,
Second image of brightness uniformity is input to described image gamma correction model as training sample and carries out model training.
Optionally, the first image and second image are under identical image scanning parameter to same target
The image that same area scans.
Optionally, the first image and the collection process of second image include:
Obtain the scan image acquired in Low Magnetic field MRI system by local coil and body coil;
Using the scan image of local coil acquisition as the first image, by brightness in the scan image of body coil acquisition
The highest image of the uniformity is as the second image corresponding with the first image.
The third aspect, the embodiment of the invention also provides a kind of computer equipment, which includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes any method for correcting image in the embodiment of the present invention.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program realizes the method for correcting image as described in any in inventive embodiments when the program is executed by processor, this method comprises:
Obtain the image to be processed of target object;
Brightness of image calibration model of the training based on machine learning
The image to be processed is input to brightness of image calibration model;
Obtain the gamma correction image corresponding with the image to be processed exported from described image gamma correction model.
The embodiment of the present invention is input to preparatory trained image by the image to be processed for the target object that will acquire
Gamma correction model needs first to obtain target object compared with the existing technology to obtain corrected image to be processed
Body coil and the received pre-scan images of local coil, calculate local coil and body coil received field distributions ratios, according to than
Value is again corrected brightness of image, and the present invention is solved without expending patient's online prescan time in the prior art by penetrating
The low efficiency of brightness of image unevenness caused by frequency field is uneven and ineffective problem, realize accurately that radiofrequency field is irregular
Ingredient puts forward and removes from image contrast information, quickly corrected on the basis of retaining picture contrast in image due to
Brightness disproportionation ingredient caused by radiofrequency field is uneven, improves the efficiency and calibration accuracy of image rectification.
Detailed description of the invention
Fig. 1 a is the flow chart of the method for correcting image in the embodiment of the present invention one;
Fig. 1 b is the schematic diagram of the magnetic resonance image brightness disproportionation correction result in the embodiment of the present invention one;
Fig. 2 a is the flow chart of the method for correcting image in the embodiment of the present invention two;
Fig. 2 b is the schematic diagram of the training of brightness of image calibration model and image rectification in the embodiment of the present invention two;
Fig. 3 is the structural schematic diagram of the image correction apparatus in the embodiment of the present invention three;
Fig. 4 is the structural schematic diagram of the computer equipment in the embodiment of the present invention four.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is the method for correcting image flow chart that the embodiment of the present invention one provides, and the present embodiment is applicable to clinical medicine
The case where image procossing, this method can be executed by image correction apparatus, which can integrate in any carry out picture number
According to the computer equipment in the equipment of data processing, being optionally connected with medical imaging devices.Specifically comprise the following steps:
S110, the image to be processed for obtaining target object.
Wherein, target object is the human or animal for needing to carry out medical imaging, and the image to be processed of target object can be
The magnetic resonance image scanned by magnetic resonance system.
Optionally, image to be processed is obtained in the case where main field strength is higher than 1.5T.Since image to be processed is
It is obtained in high-field magnetic resonance system, radio-frequency field distribution unevenness results in the uneven luminance of image to be processed.It needs further
The ingredient of radio-frequency distributed unevenness is corrected.
S120, the image to be processed is input to brightness of image calibration model.
Specifically, brightness of image calibration model is the network model based on machine learning.The brightness of image calibration model is
By acquiring a large amount of training sample, the result trained in advance using training sample.This brightness of image calibration model being capable of essence
Quasi- puts forward the non-uniform ingredient of radiofrequency field and removes from image contrast information to be processed.The model can also be used in not
Image conformity with position corrects, and can be used for the image conformity correction of high field systems.
The gamma correction corresponding with the image to be processed that S130, acquisition are exported from described image gamma correction model
Image.
After having input image to be processed in brightness of image calibration model, correspondingly, the model can export it is corrected
Image.
Illustratively, it can refer to content shown in Fig. 1 a.Fig. 1 a is the magnetic resonance image brightness disproportionation school in embodiment one
The schematic diagram of positive result, wherein 101 and 103 be two images to be processed, and 102 and 104 are respectively corresponding to 101 and 103
The image corrected by brightness of image calibration model 105.It can intuitively be observed from Fig. 1 a 102 relative to 101 and 104
Brightness relative to 103 is more uniform, and image effect is more preferably.
The technical solution of the present embodiment is input to by the image to be processed for the target object that will acquire and is trained in advance
Brightness of image calibration model need first to obtain target compared with the existing technology to obtain corrected image to be processed
The received pre-scan images of body coil and local coil of object calculate the received field distributions ratios of local coil and body coil,
Brightness of image is corrected again according to ratio, the present invention solves the prior art without expending patient's online prescan time
The middle low efficiency for correcting the brightness of image unevenness as caused by radiofrequency field unevenness and ineffective problem, realizing will accurately penetrate
The irregular ingredient in frequency field puts forward and removes from image contrast information, quickly corrects on the basis of retaining picture contrast
The brightness disproportionation ingredient as caused by radiofrequency field unevenness, improves the efficiency and calibration accuracy of image rectification in image.
Embodiment two
Fig. 2 a shows a kind of method for correcting image flow chart provided by Embodiment 2 of the present invention, the present embodiment to above-mentioned or
Each optional embodiment in following embodiments advanced optimizes, and illustrates the mistake being trained to brightness of image calibration model
Journey, specifically includes the following steps:
S210, brightness of image calibration model is trained.
Specifically, first having to acquire a large amount of training sample during model training.It is directed to brightness of image straightening die
Type, training sample be include the first image of brightness irregularities ingredient and the second image of corresponding brightness uniformity.
Optionally, multiple training samples are to being obtained in Low Magnetic field MRI system, wherein Low Magnetic field MRI system is
Refer to that main field strength is the magnetic resonance system less than or equal to 1.5T.Specifically, obtaining in Low Magnetic field MRI system by local coil
With the scan image of body coil acquisition;Since local coil is generally placed all close from position to be detected, the energy of signal is received
Power is stronger, and signal-to-noise ratio can be improved, and which results in very high in the brightness of local coil covering part, other position brightness are very
It is low, so image is irregular, using the scan image of local coil acquisition as the first image;Body coil and local line in clinic
Circle can retain the image that body coil receives simultaneously in use, body coil only does transmitting coil, but in the present embodiment,
Using the highest image of luminance uniformity in the scan image of body coil acquisition as the second image corresponding with the first image.First
Image and the second image are that the same area of same patient passes through the image of identical image parameter scanning arrived, and the two is most significant
Difference is the difference of radio-frequency field distribution uniformity, to ensure that the two in addition to uniformity, does not introduce structure and comparison
The difference of degree.Wherein, identical image parameter includes such as the image scanning visual field (Field of View, FOV), human body information pair
Than degree etc..
It further, will include the first image of brightness irregularities ingredient and corresponding after obtaining training sample
Brightness uniformity the second image be input to brightness of image calibration model carry out model training.The machine learning model was learning
The mapping relations between the first image and the second image data are obtained in journey, determine that machine learning is corresponding according to the mapping relations
Model parameter, to obtain the brightness of image calibration model based on machine learning.Optionally, radiofrequency field includes launching site
(body coil generation) and received field (local coil generation), mapping relations then include launching site and the corresponding uniformity school of received field
Positive coefficient.
In addition, online (online) data training mode also can be used in the brightness of image calibration model, will acquire every time
The image to be corrected arrived is as new data Retraining algorithm model.
S220, the image to be processed for obtaining target object.
S230, the image to be processed is input to brightness of image calibration model.
The gamma correction corresponding with the image to be processed that S240, acquisition are exported from described image gamma correction model
Image.
Step S220-S240 particular content can refer to particular content in the embodiment of the present invention one.
Fig. 2 b is the schematic diagram of the training of brightness of image calibration model and image rectification, as shown, 201 be in training sample
The first image, 202 be the second image corresponding with the first image, by 201 and 202 be input in model to be trained simultaneously into
Brightness of image calibration model can be obtained in row deep learning.It, can be directly by the to be processed of target object during image rectification
Image 203 is input to brightness of image calibration model, thus obtain brightness of image calibration model output by gamma correction
Image 204.
The technical solution of the present embodiment, by the scan image that acquires local coil as the first image, by body coil
The highest image of luminance uniformity is as the second image corresponding with the first image in the scan image of acquisition, and utilizes the first figure
Picture and the second image are trained brightness of image compared with positive model, the image to be processed input for the target object that then will acquire
To preparatory trained brightness of image calibration model, to obtain corrected image to be processed, solution is entangled in the prior art
The just low efficiency of the brightness of image unevenness as caused by radiofrequency field unevenness and ineffective problem, realize radiofrequency field accurately
Non-uniform ingredient puts forward and removes from image contrast information, quick correction chart on the basis of retaining picture contrast
The brightness disproportionation ingredient as caused by radiofrequency field unevenness, improves the efficiency and calibration accuracy of image rectification as in.
Embodiment three
Fig. 3 shows a kind of structural schematic diagram of image correction apparatus of the offer of the embodiment of the present invention three, which can be with
It is integrated in any equipment for carrying out image data processing, the computer being optionally connected with medical imaging devices is set
It is standby.The embodiment of the present invention is applicable to the case where medical image is obtained in clinic.
As shown in figure 3, the device includes: image collection module 310, mode input module 320 and correction module 330.
Wherein, image collection module 310, for obtaining the image to be processed of target object;Mode input module 320 is used
In the image to be processed is input to brightness of image calibration model;Correction module 330 is used for from described image gamma correction mould
Output gamma correction result corresponding with the image to be processed in type.
The technical solution of the present embodiment is input to by the image to be processed for the target object that will acquire and is trained in advance
Brightness of image calibration model need first to obtain target compared with the existing technology to obtain corrected image to be processed
The received pre-scan images of body coil and local coil of object calculate the received field distributions ratios of local coil and body coil,
Brightness of image is corrected again according to ratio, the present invention solves the prior art without expending patient's online prescan time
The middle low efficiency for correcting the brightness of image unevenness as caused by radiofrequency field unevenness and ineffective problem, realizing will accurately penetrate
The irregular ingredient in frequency field puts forward and removes from image contrast information, quickly corrects on the basis of retaining picture contrast
The brightness disproportionation ingredient as caused by radiofrequency field unevenness, improves the efficiency and calibration accuracy of image rectification in image.
Optionally, image to be processed is the magnetic resonance image scanned by magnetic resonance system.
Optionally, brightness of image calibration model is the network model based on machine learning.
Optionally, image correction apparatus further include:
Model training module, for being trained to described image gamma correction model.
Optionally, it will include the first image of brightness irregularities ingredient and corresponding that model training module, which is specifically used for,
Second image of brightness uniformity is input to described image gamma correction model as training sample and carries out model training.
Optionally, the first image and second image are under identical image scanning parameter to same target
The image that same area scans.
Optionally, the first image and the collection process of second image include:
Obtain the scan image acquired in Low Magnetic field MRI system by local coil and body coil;
Using the scan image of local coil acquisition as the first image, by brightness in the scan image of body coil acquisition
The highest image of the uniformity is as the second image corresponding with the first image.
Image calibration provided by any embodiment of the invention can be performed in image correction apparatus provided by the embodiment of the present invention
Correction method has the corresponding functional module of execution method and beneficial effect.
Example IV
Fig. 4 is the structural schematic diagram of the computer equipment in the embodiment of the present invention four.Fig. 4, which is shown, to be suitable for being used to realizing this
The block diagram of the exemplary computer device 412 of invention embodiment.The computer equipment 412 that Fig. 4 is shown is only an example,
Should not function to the embodiment of the present invention and use scope bring any restrictions.The computer equipment is preferably and medical imaging
The computer equipment that equipment is connected can be directly obtained doctor obtained from medical imaging devices are scanned target object
Learn image.
As shown in figure 4, computer equipment 412 is showed in the form of universal computing device.The component of computer equipment 412 can
To include but is not limited to: one or more processor or processing unit 416, system storage 428 connect not homologous ray group
The bus 418 of part (including system storage 428 and processing unit 416).
Bus 418 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.Show
Example property, computer equipment 412 can be connected with MR imaging apparatus, the data of MR imaging apparatus acquisition are received,
And the use of the input control MR imaging apparatus according to user.
Computer equipment 412 typically comprises a variety of computer system readable media.These media can be it is any can
The usable medium accessed by computer equipment 412, including volatile and non-volatile media, moveable and immovable Jie
Matter.
System storage 428 may include the computer system readable media of form of volatile memory, such as deposit at random
Access to memory (RAM) 430 and/or cache memory 432.Computer equipment 412 may further include it is other it is removable/
Immovable, volatile/non-volatile computer system storage medium.Only as an example, storage system 434 can be used for reading
Write immovable, non-volatile magnetic media (Fig. 4 do not show, commonly referred to as " hard disk drive ").Although not shown in fig 4,
The disc driver for reading and writing to removable non-volatile magnetic disk (such as " floppy disk ") can be provided, and non-easy to moving
The CD drive that the property lost CD (such as CD-ROM, DVD-ROM or other optical mediums) is read and write.In these cases, each
Driver can be connected by one or more data media interfaces with bus 418.Memory 428 may include at least one
Program product, the program product have one group of (for example, at least one) program module, these program modules are configured to perform this
Invent the function of each embodiment.
Program/utility 440 with one group of (at least one) program module 442, can store in such as memory
In 428, such program module 442 includes but is not limited to operating system, one or more application program, other program modules
And program data, it may include the realization of network environment in each of these examples or certain combination.Program module 442
Usually execute the function and/or method in embodiment described in the invention.
Computer equipment 412 can also be with one or more external equipments 414 (such as keyboard, sensing equipment, display
424 etc.) it communicates, the equipment interacted with the computer equipment 412 communication can be also enabled a user to one or more, and/or
(such as network interface card is adjusted with any equipment for enabling the computer equipment 412 to be communicated with one or more of the other calculating equipment
Modulator-demodulator etc.) communication.This communication can be carried out by input/output (I/O) interface 422.Also, computer equipment
412 can also by network adapter 420 and one or more network (such as local area network (LAN), wide area network (WAN) and/or
Public network, such as internet) communication.As shown, network adapter 420 passes through its of bus 418 and computer equipment 412
The communication of its module.It should be understood that although not shown in fig 4, other hardware and/or soft can be used in conjunction with computer equipment 412
Part module, including but not limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system,
Tape drive and data backup storage system etc..
Processing unit 416 by the program that is stored in system storage 428 of operation, thereby executing various function application with
And data processing, such as realize method for correcting image provided by the embodiment of the present invention, this method specifically includes that
Obtain the image to be processed of target object;
The image to be processed is input to brightness of image calibration model;
Obtain the gamma correction image corresponding with the image to be processed exported from described image gamma correction model.
Embodiment five
The embodiment of the present invention five additionally provides a kind of computer readable storage medium, is stored thereon with computer program, should
The method for correcting image as provided by the embodiment of the present invention is realized when program is executed by processor, this method specifically includes that
Obtain the image to be processed of target object;
Brightness of image calibration model of the training based on machine learning
The image to be processed is input to brightness of image calibration model;
Obtain the gamma correction image corresponding with the image to be processed exported from described image gamma correction model.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool
There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of method for correcting image characterized by comprising
Obtain the image to be processed of target object;
The image to be processed is input to brightness of image calibration model;
Obtain the gamma correction image corresponding with the image to be processed exported from described image gamma correction model.
2. the method according to claim 1, wherein the image to be processed is to scan by magnetic resonance system
The magnetic resonance image arrived.
3. the method according to claim 1, wherein described image gamma correction model is based on machine learning
Network model.
4. method according to claim 1 to 3, which is characterized in that the image to be processed is being input to image
Before gamma correction model, the method also includes:
Described image gamma correction model is trained;
Correspondingly, being trained to described image gamma correction model, comprising:
Using include brightness irregularities ingredient the first image and corresponding brightness uniformity the second image as training sample
It is input to described image gamma correction model and carries out model training.
5. according to the method described in claim 4, it is characterized in that, the first image with second image is identical
The image that the same area of same target is scanned under image scanning parameter.
6. according to the method described in claim 4, it is characterized in that, the collection process of the first image and second image
Include:
Obtain the scan image acquired in Low Magnetic field MRI system by local coil and body coil;
Using the scan image of local coil acquisition as the first image, by brightness uniformity in the scan image of body coil acquisition
Highest image is spent as the second image corresponding with the first image.
7. a kind of image correction apparatus characterized by comprising
Image collection module, for obtaining the image to be processed of target object;
Mode input module, for the image to be processed to be input to brightness of image calibration model;
Correction module, for the output gamma correction knot corresponding with the image to be processed from described image gamma correction model
Fruit.
8. device according to claim 7, which is characterized in that described device further include:
Model training module, for being trained to described image gamma correction model.
9. a kind of computer equipment, which is characterized in that the computer equipment includes:
One or more processors;
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as method for correcting image of any of claims 1-6.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
Following method for correcting image is realized when execution:
Obtain the image to be processed of target object;
Brightness of image calibration model of the training based on machine learning
The image to be processed is input to brightness of image calibration model;
Obtain the gamma correction image corresponding with the image to be processed exported from described image gamma correction model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811604321.7A CN109671036B (en) | 2018-12-26 | 2018-12-26 | Image correction method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811604321.7A CN109671036B (en) | 2018-12-26 | 2018-12-26 | Image correction method, device, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109671036A true CN109671036A (en) | 2019-04-23 |
CN109671036B CN109671036B (en) | 2023-07-14 |
Family
ID=66147625
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811604321.7A Active CN109671036B (en) | 2018-12-26 | 2018-12-26 | Image correction method, device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109671036B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110428415A (en) * | 2019-08-05 | 2019-11-08 | 上海联影医疗科技有限公司 | Medical image quality evaluation method, device, equipment and storage medium |
CN110428377A (en) * | 2019-07-26 | 2019-11-08 | 北京百度网讯科技有限公司 | Data extending method, apparatus, equipment and medium |
CN110458770A (en) * | 2019-07-26 | 2019-11-15 | 复旦大学附属中山医院 | A kind of medical image brightness homogenization bearing calibration |
CN111968056A (en) * | 2020-08-18 | 2020-11-20 | 中国银行股份有限公司 | Online check deposit business processing method, client, cloud server and system |
CN111968065A (en) * | 2020-10-23 | 2020-11-20 | 浙江科技学院 | Self-adaptive enhancement method for image with uneven brightness |
CN112766314A (en) * | 2020-12-31 | 2021-05-07 | 上海联影智能医疗科技有限公司 | Anatomical structure recognition method, electronic device, and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1115628A (en) * | 1993-07-22 | 1996-01-31 | 株式会社岛津制作所 | Magnetic resonance imaging apparatus |
CN103424727A (en) * | 2012-05-23 | 2013-12-04 | 深圳市贝斯达医疗器械有限公司 | Magnetic resonance image brightness non-uniformity modification algorithm |
US20150077105A1 (en) * | 2010-10-06 | 2015-03-19 | Uri Rapoport | Method for providing high resolution, high contrast fused mri images |
CN105283780A (en) * | 2013-03-15 | 2016-01-27 | 俄亥俄州创新基金会 | Method and apparatus for signal inhomogeneity correction and performance evaluation |
US20160245882A1 (en) * | 2015-02-24 | 2016-08-25 | Siemens Aktiengesellschaft | Method and magnetic resonance apparatus for determining absolute receive sensitivity maps for reception coils |
CN106934426A (en) * | 2015-12-29 | 2017-07-07 | 三星电子株式会社 | The method and apparatus of the neutral net based on picture signal treatment |
CN107862723A (en) * | 2016-11-07 | 2018-03-30 | 上海联影医疗科技有限公司 | Image reconstruction system and method in magnetic resonance imaging |
-
2018
- 2018-12-26 CN CN201811604321.7A patent/CN109671036B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1115628A (en) * | 1993-07-22 | 1996-01-31 | 株式会社岛津制作所 | Magnetic resonance imaging apparatus |
US20150077105A1 (en) * | 2010-10-06 | 2015-03-19 | Uri Rapoport | Method for providing high resolution, high contrast fused mri images |
CN103424727A (en) * | 2012-05-23 | 2013-12-04 | 深圳市贝斯达医疗器械有限公司 | Magnetic resonance image brightness non-uniformity modification algorithm |
CN105283780A (en) * | 2013-03-15 | 2016-01-27 | 俄亥俄州创新基金会 | Method and apparatus for signal inhomogeneity correction and performance evaluation |
US20160245882A1 (en) * | 2015-02-24 | 2016-08-25 | Siemens Aktiengesellschaft | Method and magnetic resonance apparatus for determining absolute receive sensitivity maps for reception coils |
CN106934426A (en) * | 2015-12-29 | 2017-07-07 | 三星电子株式会社 | The method and apparatus of the neutral net based on picture signal treatment |
CN107862723A (en) * | 2016-11-07 | 2018-03-30 | 上海联影医疗科技有限公司 | Image reconstruction system and method in magnetic resonance imaging |
Non-Patent Citations (4)
Title |
---|
JAZZWONG: "《近线圈效应(SCIC,PURE,HC,CLEAR)》", 《HTTP://WWW.360DOC.COM/CONTENT/17/1215/09/29483956_713242448.SHTML》 * |
JAZZWONG: "《近线圈效应(SCIC,PURE,HC,CLEAR)》", 《HTTP://WWW.360DOC.COM/CONTENT/17/1215/09/29483956_713242448.SHTML》, 15 December 2017 (2017-12-15), pages 1 - 5 * |
N.J.TUSTISON ET AL: "N4ITK:Improved N3 bias correction", IEEE TRANS, vol. 29, no. 6, pages 1310 - 1320 * |
亢科: "MRI中低噪声前置放大器的研制及磁共振图像非均匀场校正算法研究", 信息科技, no. 7 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110428377A (en) * | 2019-07-26 | 2019-11-08 | 北京百度网讯科技有限公司 | Data extending method, apparatus, equipment and medium |
CN110458770A (en) * | 2019-07-26 | 2019-11-15 | 复旦大学附属中山医院 | A kind of medical image brightness homogenization bearing calibration |
CN110428377B (en) * | 2019-07-26 | 2023-06-30 | 北京康夫子健康技术有限公司 | Data expansion method, device, equipment and medium |
CN110428415A (en) * | 2019-08-05 | 2019-11-08 | 上海联影医疗科技有限公司 | Medical image quality evaluation method, device, equipment and storage medium |
CN110428415B (en) * | 2019-08-05 | 2022-05-13 | 上海联影医疗科技股份有限公司 | Medical image quality evaluation method, device, equipment and storage medium |
CN111968056A (en) * | 2020-08-18 | 2020-11-20 | 中国银行股份有限公司 | Online check deposit business processing method, client, cloud server and system |
CN111968065A (en) * | 2020-10-23 | 2020-11-20 | 浙江科技学院 | Self-adaptive enhancement method for image with uneven brightness |
CN112766314A (en) * | 2020-12-31 | 2021-05-07 | 上海联影智能医疗科技有限公司 | Anatomical structure recognition method, electronic device, and storage medium |
CN112766314B (en) * | 2020-12-31 | 2024-05-28 | 上海联影智能医疗科技有限公司 | Anatomical structure recognition method, electronic device, and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109671036B (en) | 2023-07-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109671036A (en) | A kind of method for correcting image, device, computer equipment and storage medium | |
CN109961491B (en) | Multi-mode image truncation compensation method, device, computer equipment and medium | |
CN109709503B (en) | Magnetic resonance system control method, magnetic resonance system and computer equipment | |
CN109567843B (en) | Imaging scanning automatic positioning method, device, equipment and medium | |
CN110211111A (en) | A kind of method, apparatus of vessel extraction, image processing equipment and storage medium | |
US11250543B2 (en) | Medical imaging using neural networks | |
US20200093460A1 (en) | Method, device, ultrasonic probe and terminal for adjusting detection position | |
CN101596110B (en) | Automatic determination of field of view in cardiac Mri | |
US11900594B2 (en) | Methods and systems for displaying a region of interest of a medical image | |
US9865059B2 (en) | Medical image processing method and apparatus for determining plane of interest | |
CN110458837B (en) | Image post-processing method and device, electronic equipment and storage medium | |
CN111989710A (en) | Automatic slice selection in medical imaging | |
US20110123074A1 (en) | Systems and methods for suppressing artificial objects in medical images | |
CN111904379B (en) | Scanning method and device for multi-mode medical equipment | |
US6449390B1 (en) | Image processing apparatus and method therefor | |
CN109157239A (en) | Position scan method, CT scanning method, device, equipment and the medium of image | |
CN109152549A (en) | Image diagnosing system and image acquisition method | |
CN113870178A (en) | Plaque artifact correction and component analysis method and device based on artificial intelligence | |
CN113658175A (en) | Method and device for determining symptom data | |
CN112634309B (en) | Image processing method, device, electronic equipment and storage medium | |
CN110197496A (en) | A kind of medical system control method, device, equipment and medium | |
CN109147927A (en) | A kind of man-machine interaction method, device, equipment and medium | |
CN114782364A (en) | Image detection method, device and system and detection equipment | |
CN109493396B (en) | CT image display method, device, equipment and medium | |
KR20150113286A (en) | Medical image storage and transmission system tagging simultaneously with recording |
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 | ||
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. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |