CN107292816A - A kind of method for correcting image, system and computer readable medium - Google Patents

A kind of method for correcting image, system and computer readable medium Download PDF

Info

Publication number
CN107292816A
CN107292816A CN201710469730.XA CN201710469730A CN107292816A CN 107292816 A CN107292816 A CN 107292816A CN 201710469730 A CN201710469730 A CN 201710469730A CN 107292816 A CN107292816 A CN 107292816A
Authority
CN
China
Prior art keywords
correction
image
correction matrix
described image
image data
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
Application number
CN201710469730.XA
Other languages
Chinese (zh)
Other versions
CN107292816B (en
Inventor
赵恩伟
刘振中
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai United Imaging Healthcare Co Ltd
Original Assignee
Shanghai United Imaging Healthcare Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai United Imaging Healthcare Co Ltd filed Critical Shanghai United Imaging Healthcare Co Ltd
Priority to CN201710469730.XA priority Critical patent/CN107292816B/en
Publication of CN107292816A publication Critical patent/CN107292816A/en
Application granted granted Critical
Publication of CN107292816B publication Critical patent/CN107292816B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00Geometric image transformations in the plane of the image
    • G06T3/04Context-preserving transformations, e.g. by using an importance map

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)
  • Image Processing (AREA)

Abstract

The invention discloses a kind of method for correcting image, a kind of image correction system and a kind of computer readable medium of storage image bearing calibration.This method includes:Obtain view data;Determine whether the correction matrix related to described image data;When judging the not correction matrix related to described image data, according to view data, uncorrected image is generated;Described image is corrected, the image after generation correction;According to the image after non-correction chart picture and correction, the correction matrix is generated.When judging to have the correction matrix related to described image data, the correction matrix is obtained;According to the correction matrix and described image data, the image after generation correction.This method makes same or analogous image only by once correcting the display that can be achieved to repeat, it is to avoid repeats to correct, improves service efficiency.

Description

A kind of method for correcting image, system and computer readable medium
Technical field
It is more particularly to a kind of only to can be achieved to repeat to show by once correcting the present invention relates to a kind of method for correcting image Method for correcting image, system and computer readable medium.
Background technology
During medical scanning, patient may it is long or ill sweep time due to, it is impossible to for a long time Normal posture is maintained to be scanned.Rather than the image that normal posture scanning is scanned with normal posture may have relatively big difference, shadow Ring judgement of the doctor to the state of an illness.Existing scheme would generally be carried out manual correction (such as rotation) by doctor to image, but right In same image, each display again is required for doctor to re-start a manual correction, very inconvenient.
The content of the invention
In view of the above-mentioned problems, only can be achieved by once correcting present invention aims to same or analogous image The display repeated.
To achieve the above object of the invention, the technical scheme that the present invention is provided is as follows:
A kind of method for correcting image, it is characterised in that including:Obtain view data;Determine whether and described image number According to related correction matrix;When judging the not correction matrix related to described image data, according to view data, generation Uncorrected image;And described image is corrected, the image after generation correction.
In the present invention, when judging to have the correction matrix related to described image data, the correction matrix is obtained; And according to the correction matrix and described image data, the image after generation correction.
In the present invention, described image is corrected, after the image after generation correction, according to non-correction chart picture and school Image after just, generates correction matrix.
In the present invention, the non-correction chart picture of the basis and the image after correction, generating the correction matrix includes:Obtain One or more mark points on image after the non-correction chart picture and the correction;And according to one or more of marks The corresponding relation of point is noted, the correction matrix is generated.
In the present invention, the non-correction chart picture of the basis and the image after correction, generating the correction matrix includes:By institute State the image after non-correction chart picture and the correction and carry out registration;And the correction matrix is generated according to registration result.
In the present invention, the correction includes:Segmentation, scaling, displacement, rotation, cutting, filtering, toning, average or flat It is sliding.
In the present invention, described image data are medical image datas.
In the present invention, the medical image data includes:PET-CT view data, DR view data, CT view data, MRI image data, US view data, PET image data or PET-MRI view data.
In the present invention, described according to view data, generating the method for uncorrected image includes multiplanar reconstruction (multiplanar reformatting, MPR), Volume rendering (volume rendering, VR), many plane Volume renderings (multiplanar volume rendering, MPVR), curve reestablishing (curved planar reformatting, CPR), MIP (maximum intensity projection, MIP) or shaded surface method (shaded surface display,SSD)。
In the present invention, methods described further comprises that the image array to the generation puts on sequence number.
In the present invention, it is described determine whether the correction matrix related to described image data comprised determining whether with The related sequence number of described image data.
In the present invention, sequence number of the Serial No. based on dicom standard.
In the present invention, methods described further comprises:Obtain standard picture template;And according to the figure after the correction Picture and the standard picture template, generate standard picture correction matrix.
Invention further discloses a kind of image correction system.The system can include scanning device and processing equipment.This is swept View data can be obtained by retouching equipment.The processing equipment can decide whether the correction matrix related to described image data; When judging the not correction matrix related to described image data:The processing equipment can be generated according to view data Uncorrected image;And described image is corrected, the image after generation correction;Judging have and described image data During the correction matrix of correlation:The processing equipment obtains the correction matrix;And according to the correction matrix and described image Data, the image after generation correction.
Invention further discloses the permanent computer-readable medium that one has computer program, the computer program bag Instruction is included, the instruction can be realized a kind of method by least one computing device, methods described includes:Obtain view data; Determine whether the correction matrix related to described image data;Judging correction square not related to described image data During battle array:According to view data, uncorrected image is generated;And described image is corrected, the image after generation correction; When judging to have the correction matrix related to described image data:Obtain the correction matrix;And according to the correction matrix With described image data, the image after generation correction.
Brief description of the drawings
Fig. 1 is a kind of schematic diagram of the image correction system provided according to the present invention;
Fig. 2 is a kind of flow chart of the image rectification provided according to the present invention;
Fig. 3 is a kind of flow chart of the generation correction matrix provided according to the present invention.
Fig. 1 is marked:110 be scanning device, and 120 be processing equipment, and 130 be network, and 140 be storage device, and 150 be display Equipment.
Embodiment
In order to illustrate more clearly of the technical scheme of embodiments herein, below by specific embodiment and with reference to accompanying drawing The present invention is described further.
As shown in figure 1, image correction system 100 can include scanning device 110, processing equipment 120, storage device 140 With display device 150.Each equipment can be interconnected or communicated by network 130 in described image correction system 100.
Scanning device 110 can be scanned to an object.The object can be object, human body, organ, tissue Deng.The scanning device can be a medical image equipment.In certain embodiments, the scanning device 110 can be magnetic Resonance imager (magnetic resonance imaging, MRI), computed tomographic scanner (computed Tomography, CT), positron e mission computed tomography instrument (positron emission computed Tomography, PET), B ultrasound instrument (b-scan ultrasonography), hot OCT (Thermal texture Maps, TTM), medical electronic endoscope (medical electronic endoscope, MEE) etc..In certain embodiments, The scanning device 110 can also be the combination of above-mentioned plurality of devices, such as PET-CT scanners, PET-MRI scanners etc..Scanning Equipment 110 can produce view data corresponding with the object after scanning.Further, scanning device 110 will can be obtained View data sent by network 130 to processing equipment 120, storage device 140 or display device 150.
Processing equipment 120 can be handled view data.Described image data can be scanned by scanning device 110 Obtain, can also be obtained from storage device 140.In certain embodiments, view data can be the solution for representing sweep object Cut open and/or function information two dimension or 3 d image data.The processing can include rebuilding view data generating Image.The method of the reconstruction can include but is not limited to multiplanar reconstruction (multiplanar reformatting, MPR), Volume rendering (volume rendering, VR), many plane Volume renderings (multiplanar volume rendering, MPVR), curve reestablishing (curved planar reformatting, CPR), MIP (maximum intensity Projection, MIP), one or more combinations in shaded surface method (shaded surface display, SSD) etc.. The processing can also include being corrected processing to the image of view data or generation.The correction process can include dividing Cut, scale, it is displacement, rotation, cutting, filtering, toning, average, smooth etc..In certain embodiments, processing equipment 120 can be right The view data of acquisition is pre-processed.The pretreatment can include down-sampled, data compression etc..In certain embodiments, Processing equipment 120 can generate a correction matrix according to the image after uncorrected image and correction.The correction matrix can To represent a change procedure or corresponding relation.The correction matrix can be sent to storage device 140 by processing equipment 120 Row storage.
Network 130 can be the connected mode of any two or more equipment of connection.For example, network 130 can be wired Network or wireless network.In certain embodiments, network 130 can be the combination of single network or multiple network. For example, the network 130 can include LAN, wide area network, common network, dedicated network, WLAN, virtual network, One or more of combinations in public phone network etc..Each module in image correction system 100 can be by connecting network 130, realize the interaction of information.
Storage device 140 can be with data storage and/or information.For example, storage device 140 can store scanning device 110 The view data of generation, can also store image that processing equipment 120 rebuild or the correction matrix of generation, can also store aobvious Show user's input or instruction that equipment 150 is received.In certain embodiments, storage device 140 can be local storage, outside The storage connect, cloud storage etc..
Display device 150 can be used for being shown image.The display device 150 can include display screen, touch Screen etc..In certain embodiments, the display device 150 can include an interactive interface, and the interactive interface can receive use Family or the input of doctor.In certain embodiments, the display device 150 can include input equipment, such as touch pad, touch Touch screen, mouse, keyboard, microphone etc..The input of user can be sent to processing equipment 120 and be handled by display device 150 Or transmission to storage device 140 is stored.
In certain embodiments, display device 150 can show an image, and user can pass through the interactive interface pair The image is corrected (for example, being rotated or displacement).Display device 150 can be by after the correct operation of user and correction Image send to processing equipment 120.Processing equipment 120 can pass through display device 150 according to uncorrected image and user Image (or image after the correction of processing equipment 120) one correction matrix of generation after correction.The correction matrix can represent one The change procedure or corresponding relation of individual image.The correction matrix can be stored in storage device 140.In same or analogous figure As needing when display, it can be changed according to the correction matrix with the direct image formed after correction.Specific correction Matrix formation and the method called may be referred to the description of other parts of the present invention.For example, may be referred to Fig. 2 and its description.
Fig. 2 is a kind of flow chart of the image rectification provided according to the present invention.In certain embodiments, flow 200 can be with Realized by processing equipment 120.In step 210, view data can be obtained.The view data can pass through scanning device 110 obtain, and can also be obtained from storage device 140.
In a step 220, it can be determined that whether have in the equipment (for example, storage device 140) of image correction system 100 with The related correction matrix of described image data.If the correction matrix, then step 250 is performed;Otherwise, then step is performed 230.In certain embodiments, if the determination requirement for having the correction matrix related to described image data can be judged whether Have identical with described image data, similar or belong to same type or the correction matrix with position with described image data. More specifically, image correction system 100 can put on sequence number when obtaining or generating correction matrix to correction matrix, enter And the judgement for whether having a correction matrix related to described image data can judge storage device 140 or network 130 In whether have the correction matrix of same or similar sequence number.The sequence number can be sequence number general or common in industry, Such as based on digital imaging and communications in medicine (Digital imaging and Communications in Medicine, DICOM the sequence number that sequence number or the inside of image correction system 100) is used.In certain embodiments, a school Positive matrices can correspond to the multiple images (i.e. multiple images likely correspond to same image sequence) of single pass acquisition and fit Correction for multiple images.For example, after the correction matrix of an image is obtained, it is corresponding in same correction matrix Multiple images the correction matrix can also be used to be corrected, such as simultaneously carry out go bed, rotation, window width and window level adjustment school Positive processing.In certain embodiments, a correction matrix likely corresponds to some specific position, the head of such as patient, chest Portion, upper limbs, lower limb, stomach etc..If generating the correction matrix of the privileged site of some patient, the identical portions of other patients The correction of position can also use the correction matrix.Similar deformation will not be repeated here in the protection domain of the application.
In step 230, image can be generated according to view data.For example, can be directly reconstructed according to view data Image.Described image rebuild method can include but is not limited to multiplanar reconstruction (multiplanar reformatting, MPR), Volume rendering (volume rendering, VR), many plane Volume rendering (multiplanar volume Rendering, MPVR), curve reestablishing (curved planar reformatting, CPR), MIP (maximum Intensity projection, MIP), one kind in shaded surface method (shaded surface display, SSD) etc. or A variety of combinations.In certain embodiments, the image after the reconstruction may not be corrected or there are problems that, such as out of alignment Really, poor direction is true, size is incorrect, be off color really, comprising unnecessary object, comprising artifact etc..
In step 240, can it not corrected or image of problems is corrected to described.The correction process can be with Including segmentation, scaling, displacement, rotation, cutting, filtering, toning, average, smooth etc..The correction process can be led to by user Cross the input of display device 150 or voluntarily being generated by processing equipment 120, or the combination of the two.
In step 250, correction matrix can be obtained.In certain embodiments, first time school is being carried out to an image The correction matrix can be generated according to the image after non-correction chart picture and correction after just.Subsequently need show the image when Time can directly obtain the correction matrix without regenerating.The method of correction matrix generation may refer to walk in Fig. 3 Rapid 330 and its description.
In step 260, the image after correction can be automatically generated according to the correction matrix and view data.At some In embodiment, uncorrected image can be first generated further according to the image after uncorrected image and correction matrix generation correction. In certain embodiments, the image after directly being corrected according to view data and correction matrix.In certain embodiments, Image after correction can be shown by display device 150, so that doctor need not carry out manual correction to non-correction chart picture, The diagnosis time is saved, while improving quality of diagnosis.
Fig. 3 is a kind of flow chart of the generation correction matrix provided according to the present invention.In certain embodiments, flow 300 It can be realized by processing equipment 120.Step 310 and step 320 are corresponding with step 230 and step 240 respectively, no longer go to live in the household of one's in-laws on getting married herein State.In certain embodiments, flow 300 can be combined with flow 200, for example, step 330 can be held after step 240 in fig. 2 OK.
In a step 330, correction matrix can be generated according to the image after uncorrected image and correction.In some realities Apply in example, can uncorrected image with correction after image on several corresponding mark points are set respectively.The mark Point can be located at edge, summit, center, center of gravity of image after the uncorrected image and correction etc..According to uncorrected Position a little or the corresponding relation of angle are marked on image after image and correction, the correction matrix can be generated.At some In embodiment, the image after correction and non-correction chart picture can be carried out registration to generate the correction matrix.Optionally, can be with Obtain a standard picture template.The standard picture template can be the orientation and size in associated picture region for average value or Close to the template of major part image.The standard picture template can be registering with the image progress after the correction to generate standard Image rectification matrix.Based on correction matrix, the image after non-correction chart picture and correction can be changed mutually.For example, non-correction chart The pixel value of picture is multiplied by the pixel value for the image that correction matrix is equal to after correction.Image after non-correction chart picture or correction can also The image of normal orientation and size is converted to according to the standard picture correction matrix.
Being preferable to carry out for the present invention is the foregoing is only, is not intended to limit the invention, for the technology of this area For personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies Change, equivalent substitution, improvement etc., should be included in the scope of the protection.

Claims (10)

1. a kind of method for correcting image, it is characterised in that including:
Obtain view data;
Determine whether the correction matrix related to described image data;
When judging the not correction matrix related to described image data:
According to view data, uncorrected image is generated;And
Described image is corrected, the image after generation correction;
When judging to have the correction matrix related to described image data:
Obtain the correction matrix;And
According to the correction matrix and described image data, the image after generation correction.
2. method for correcting image according to claim 1, it is characterised in that judge not with described image data phase During the correction matrix of pass, further according to the image after the uncorrected image and correction, the correction matrix is generated.
3. method for correcting image according to claim 2, it is characterised in that the non-correction chart of basis as and correction after Image, generating the correction matrix includes:
Obtain one or more mark points on the image after the non-correction chart picture and the correction;And
According to the corresponding relation of one or more of mark points, the correction matrix is generated.
4. method for correcting image according to claim 2, it is characterised in that the non-correction chart of basis as and correction after Image, generating the correction matrix includes:
Image after the non-correction chart picture and the correction is subjected to registration;And
The correction matrix is generated according to registration result.
5. method for correcting image according to claim 1, it is characterised in that described image data include:PET-CT images Data, DR view data, CT view data, MRI image data, US view data, PET image data or PET-MRI picture numbers According to.
6. method for correcting image according to claim 1, it is characterised in that described according to view data, generation is not corrected Image method include multiplanar reconstruction, Volume rendering, many plane Volume renderings, curve reestablishing, MIP or table Face covering method.
7. method for correcting image according to claim 1, it is characterised in that further comprise:Image to the generation Matrix puts on sequence number;And
It is described to determine whether that the correction matrix related to described image data includes:Determine whether and described image data phase The sequence number of pass.
8. method for correcting image according to claim 1, it is characterised in that further comprise:
Obtain standard picture template;And
According to the image after the correction and the standard picture template, standard picture correction matrix is generated.
9. a kind of image correction system, it is characterised in that including:
Scanning device, the scanning device obtains view data;And
Processing equipment, the processing equipment determines whether the correction matrix related to described image data;
When judging the not correction matrix related to described image data:
The processing equipment generates uncorrected image according to view data;And
Described image is corrected, the image after generation correction;
When judging to have the correction matrix related to described image data:
The processing equipment obtains the correction matrix;And
According to the correction matrix and described image data, the image after generation correction.
10. a permanent computer readable medium for having computer program, the computer program includes instruction, the instruction can By at least one computing device to realize a kind of method, methods described includes:
Obtain view data;
Determine whether the correction matrix related to described image data;
When judging the not correction matrix related to described image data:
According to view data, uncorrected image is generated;And
Described image is corrected, the image after generation correction;
When judging to have the correction matrix related to described image data:
Obtain the correction matrix;And
According to the correction matrix and described image data, the image after generation correction.
CN201710469730.XA 2017-06-20 2017-06-20 Image correction method, system and computer readable medium Active CN107292816B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710469730.XA CN107292816B (en) 2017-06-20 2017-06-20 Image correction method, system and computer readable medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710469730.XA CN107292816B (en) 2017-06-20 2017-06-20 Image correction method, system and computer readable medium

Publications (2)

Publication Number Publication Date
CN107292816A true CN107292816A (en) 2017-10-24
CN107292816B CN107292816B (en) 2021-04-20

Family

ID=60097738

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710469730.XA Active CN107292816B (en) 2017-06-20 2017-06-20 Image correction method, system and computer readable medium

Country Status (1)

Country Link
CN (1) CN107292816B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6016168A (en) * 1996-07-25 2000-01-18 Samsung Electronics Co., Ltd. Color correction device
CN101026675A (en) * 2006-02-24 2007-08-29 佛山市顺德区顺达电脑厂有限公司 Image correcting system and method for image access device
CN103792011A (en) * 2014-01-27 2014-05-14 无锡艾立德智能科技有限公司 Method and device for compensating for temperature drift through thermal infrared imager in a self-adaptation mode
CN104811688A (en) * 2014-01-28 2015-07-29 聚晶半导体股份有限公司 Image acquisition device and image deformation detection method thereof
CN105260733A (en) * 2015-09-11 2016-01-20 北京百度网讯科技有限公司 Method and device for processing image information

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6016168A (en) * 1996-07-25 2000-01-18 Samsung Electronics Co., Ltd. Color correction device
CN101026675A (en) * 2006-02-24 2007-08-29 佛山市顺德区顺达电脑厂有限公司 Image correcting system and method for image access device
CN103792011A (en) * 2014-01-27 2014-05-14 无锡艾立德智能科技有限公司 Method and device for compensating for temperature drift through thermal infrared imager in a self-adaptation mode
CN104811688A (en) * 2014-01-28 2015-07-29 聚晶半导体股份有限公司 Image acquisition device and image deformation detection method thereof
CN105260733A (en) * 2015-09-11 2016-01-20 北京百度网讯科技有限公司 Method and device for processing image information

Also Published As

Publication number Publication date
CN107292816B (en) 2021-04-20

Similar Documents

Publication Publication Date Title
CN106056537B (en) A kind of medical image joining method and device
US11276166B2 (en) Systems and methods for patient structure estimation during medical imaging
US10470733B2 (en) X-ray CT device and medical information management device
US8787648B2 (en) CT surrogate by auto-segmentation of magnetic resonance images
JP5337354B2 (en) System and method for geometric registration
CN109567843A (en) A kind of image scanning automatic positioning method, device, equipment and medium
CN106725570A (en) Imaging method and system
CN105813567B (en) Volumetric image data processing based on three-dimensional (3D) prescan
CN107106099B (en) Imaging system for imaging an elongated region of interest of an object
CN104751502B (en) One kind is for expanding wide-field CT image rebuilding methods
Studholme et al. Automated 3D Registration of Truncated MR and CT Images of the Head.
US20130182008A1 (en) Symmetry-Based Visualization for Enhancing Anomaly Detection
Qi et al. Performance studies of four-dimensional cone beam computed tomography
US10929706B2 (en) Image processing device and projection system
US11819427B2 (en) Systems and methods for orthosis design
CN102361596B (en) Hybrid dual-modality image processing system and method
Tomaževič et al. “Gold standard” data for evaluation and comparison of 3D/2D registration methods
Ikeda et al. Novel 3-dimensional analysis to evaluate temporomandibular joint space and shape
US11495346B2 (en) External device-enabled imaging support
Abella et al. Enabling tomography with low-cost C-arm systems
CN110301928B (en) Method, device and system for reconstructing PET (positron emission tomography) image
CN107292816A (en) A kind of method for correcting image, system and computer readable medium
Groisser et al. 3d reconstruction of scoliotic spines from stereoradiography and depth imaging
EP4052651A1 (en) Image-based planning of tomographic scan
CN109363695B (en) Imaging method and system

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