CN110310314A - Method for registering images, device, computer equipment and storage medium - Google Patents
Method for registering images, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110310314A CN110310314A CN201910231937.2A CN201910231937A CN110310314A CN 110310314 A CN110310314 A CN 110310314A CN 201910231937 A CN201910231937 A CN 201910231937A CN 110310314 A CN110310314 A CN 110310314A
- Authority
- CN
- China
- Prior art keywords
- image
- original
- floating
- morphosis
- floating 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/37—Determination of transform parameters for the alignment of images, i.e. image registration using transform domain methods
-
- 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
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
This application involves a kind of method for registering images, device, computer equipment and storage mediums, by carrying out identical morphosis enhancing to original reference image and original floating image, it obtains enhancing reference picture and enhances floating image, then the enhancing reference picture and enhancing floating image are registrated, obtain floating image spatial alternation to reference picture space spatial transformation parameter, further according to the spatial transformation parameter carry out original floating image to original reference image registration.Before being registrated to original floating image and original reference image, the enhancing for first having carried out structural information and morphologic information to original floating image and original reference image is handled, so that morphosis region to be registered and other regional correlations in image are more obvious, facilitate the realization registration of more accurate robust, therefore the accuracy and robustness of registration result are greatly strengthened to the registration of original floating image to original reference image according to the spatial transformation parameter.
Description
Technical field
This application involves technical field of image processing, more particularly to a kind of method for registering images, device, computer equipment
And storage medium.
Background technique
Image registration refers to two images (two images comprising same mode or different modalities or same diagnosis and treatment
Object/difference diagnosis and treatment object two images) carry out the matched process of space structure.Given two images to be registered include ginseng
Image and floating image are examined, image registration is by seeking a kind of spatial alternation, so that floating image and reference picture after registration
Reach maximum structural similarity.
Conventional images registration technique can be divided into three classes: the image registration based on gray level image, the image based on segmented image
Registration and the image registration based on deep learning.Wherein, for the method for registering images based on gray level image, work as gray level image
In contrast between each organ it is lower when, i.e., when gray difference is lesser, can not effectively measure registration accuracy, therefore nothing
Method obtains accurate registration result.For the method for registering images based on segmented image, due to the organ after segmentation in addition to segmentation
Outside, remaining anatomical information is lost, it is difficult to guarantee the registration accuracy of other organs, thus it cannot be guaranteed that the registration of general image
Precision and robustness.And for the method for registering images based on deep learning, after establishing mapping model, although bringing speed
Spend the optimization of aspect, but it is still to be gray level image or segmented image as input picture, however it remains gray level image and divide
Cut the defect that image influences registration accuracy and robustness.
Therefore, existing image registration techniques not can guarantee the precision and robustness of registration result.
Summary of the invention
Based on this, it is necessary to not can guarantee the precision and robustness of registration result for above-mentioned existing image registration techniques
The technical issues of, a kind of method for registering images, device, computer equipment and storage medium are provided.
In a first aspect, the embodiment of the present application provides a kind of method for registering images, this method comprises:
Obtain original reference image to be registered and original floating image;
Enhancing processing is carried out at least one identical morphosis in original reference image and original floating image respectively,
It obtains enhancing reference picture and enhances floating image;
Enhancing reference picture and enhancing floating image are registrated, obtain floating image spatial alternation to reference picture sky
Between spatial transformation parameter;
According to floating image spatial alternation to the spatial transformation parameter in reference picture space, original floating image is changed to
Original reference image space, complete original floating image to original reference image registration.
It is above-mentioned identical at least one in original reference image and original floating image respectively in one of the embodiments,
Morphosis carry out enhancing processing, obtain enhancing reference picture and enhance floating image, comprising:
At least one identical morphosis in original reference image and original floating image is split respectively, is obtained
Corresponding segmented image;Wherein, original reference image and original floating image are gray level image;
According to segmented image, respectively at least one identical morphosis in original reference image and original floating image
Enhancing processing is carried out, enhancing reference picture is obtained and enhances floating image.
It is above-mentioned respectively at least one of original reference image and original floating image phase in one of the embodiments,
Same morphosis is split, and obtains corresponding segmented image, comprising:
The region of each morphosis is determined from original reference image and original floating image respectively;
Using the region of each morphosis as prospect, will in original reference image and original floating image except morphosis with
Outer region obtains segmented image as background.
It is above-mentioned using the region of each morphosis as prospect in one of the embodiments, by original reference image and original
Region in beginning floating image in addition to morphosis obtains segmented image as background, comprising:
Preset prospect gray value is set by the region of each morphosis, by original reference image and original floating image
In region in addition to morphosis be set as preset background gray levels, obtain segmented image;Wherein, prospect gray value includes
At least one gray value.
It is above-mentioned according to segmented image in one of the embodiments, in original reference image and original floating image extremely
A few identical morphosis carries out enhancing processing, comprising:
It is identical at least one in original reference image and original floating image respectively using preset image superposition method
Morphosis carries out enhancing processing.
It is above-mentioned in one of the embodiments, to use preset image superposition method, respectively to original reference image and original
The identical morphosis of at least one in floating image carries out enhancing processing, comprising:
According to preset weight rule, the weight of each segmented image is determined;
It is identical at least one in original reference image and original floating image respectively according to the weight of each segmented image
Morphosis carries out enhancing processing.
It is above-mentioned according to segmented image in one of the embodiments, in original reference image and original floating image extremely
A few identical morphosis carries out enhancing processing, further includes:
Using preset grey scale converter technique or logarithm method, respectively in original reference image and original floating image
At least one identical morphosis carries out enhancing processing.
Second aspect, the embodiment of the present application provide a kind of image registration device, and described device includes:
Original image obtains module, for obtaining original reference image to be registered and original floating image;
Original image enhances module, for identical at least one in original reference image and original floating image respectively
Morphosis carries out enhancing processing, obtains enhancing reference picture and enhances floating image;
Transformation parameter obtains module, for being registrated to enhancing reference picture and enhancing floating image, obtains floating figure
Image space transforms to the spatial transformation parameter in reference picture space;
Original image registration module, for being joined according to the spatial alternation of floating image spatial alternation to reference picture space
Number, original floating image is changed to original reference image space, complete original floating image to original reference image registration.
The third aspect, the embodiment of the present application provide a kind of computer equipment, including memory and processor, memory storage
There is computer program, processor realizes the step for any one method that above-mentioned first aspect embodiment provides when executing computer program
Suddenly.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, are stored thereon with computer program,
The step of any one method that above-mentioned first aspect embodiment provides is realized when computer program is executed by processor.
A kind of method for registering images, device, computer equipment and storage medium provided by the embodiments of the present application, by obtaining
The original reference image and original floating image taken carries out at least one identical morphosis enhancing, obtains enhancing reference picture
With enhancing floating image, then the enhancing reference picture and enhancing floating image are registrated, obtain the change of floating image space
The spatial transformation parameter for changing to reference picture space carries out original floating image to original reference further according to the spatial transformation parameter
The registration of image.It is first right before being registrated due to computer equipment to original floating image and original reference image in this method
Original floating image and original reference image have carried out the enhancing processing of structural information and morphologic information, so that shape to be registered
State structural region and other regional correlations in image are more obvious, therefore the realization registration for facilitating more accurate robust calculates
Machine equipment according to enhancing reference picture and enhance the obtained floating image spatial alternation of floating image to reference picture space sky
Between transformation parameter to the registration of original floating image to original reference image, greatly strengthen the accuracy and robust of registration result
Property.
Detailed description of the invention
Fig. 1 is a kind of applied environment figure for method for registering images that one embodiment provides;
Fig. 2 is a kind of flow diagram for method for registering images that one embodiment provides;
Fig. 3 is a kind of flow diagram for method for registering images that one embodiment provides;
Fig. 4 is the schematic diagram that a kind of morphosis that one embodiment provides divides Enhancement Method;
Fig. 5 is a kind of flow diagram for method for registering images that one embodiment provides;
Fig. 6 is a kind of flow diagram for method for registering images that one embodiment provides;
Fig. 7 is a kind of structural block diagram for image registration device that one embodiment provides;
Fig. 8 is a kind of structural block diagram for image registration device that one embodiment provides;
Fig. 9 is a kind of structural block diagram for image registration device that one embodiment provides;
Figure 10 is a kind of structural block diagram for image registration device that one embodiment provides.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
A kind of method for registering images provided by the present application, can be applied in application environment as shown in Figure 1, the computer
Equipment can be server, which includes processor, the memory, network interface sum number connected by system bus
According to library.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory of the computer equipment includes
Non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is used to store the data of method for registering images.The network interface of the computer equipment is used for and external its
He passes through network connection communication at equipment.To realize a kind of method for registering images when the computer program is executed by processor.
Embodiments herein provides a kind of method for registering images, device, computer equipment and storage medium, and there are existing
Image registration techniques the technical issues of not can guarantee the precision and robustness of registration result.Embodiment will be passed through below and combined
Attached drawing specifically carries out in detail to how the technical solution of the technical solution of the application and the application solves above-mentioned technical problem
Explanation.These specific embodiments can be combined with each other below, may be certain for the same or similar concept or process
It is repeated no more in embodiment.It should be noted that a kind of method for registering images provided by the invention, the executing subject of Fig. 2-Fig. 6
For computer equipment, wherein its executing subject can also be image registration device, and wherein the device can pass through software, hardware
Or the mode of software and hardware combining realizes some or all of of image registration.
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.
In one embodiment, Fig. 2 provides a kind of method for registering images, and what is involved is computer equipment roots for the present embodiment
Floating image spatial alternation is obtained to reference picture space according to original reference image to be registered and original floating image according to elder generation
Spatial transformation parameter original reference image and original floating image are registrated then according to the spatial transformation parameter
Detailed process, as shown in Figure 2, which comprises
S101 obtains original reference image to be registered and original floating image.
In the present embodiment, original reference image to be registered and original floating image refer to same mode or different moulds
The two images etc. of the two images of state and same diagnosis and treatment object or different diagnosis and treatment objects, can be the two of the same modality
Width figure, such as: two CT images, two MRI images or two PET images, it can also be used to multi-modality image registration, such as:
CT and MRI image etc., the present embodiment does not limit this, as long as in the two images including same target to be registered.
Illustratively, in practical applications, the mode that computer equipment obtains the original reference image and original floating image, which can be, to be connect
Receive user or other equipment input or it is direct be acquired and handle by image collecting device, then after processing
Image in determine that the original reference image and original floating image, the present embodiment are not specifically limited in this embodiment.
S102 respectively enhances at least one identical morphosis in original reference image and original floating image
Processing obtains enhancing reference picture and enhances floating image.
In this step, wherein morphosis indicates target to be registered in two width figures, such as: same organs, same group
Knit or non-human other morphosis etc., what enhancing processing indicated be to enhancing morphosis in original reference image and
Structural information and morphologic information in original floating image, so that the morphosis and other regions of surrounding enhance contrast differences
It is different.Then in practical applications, it is set based on the original reference image and original floating image, computer obtained in above-mentioned S101 step
It is standby that enhancing processing is carried out at least one identical morphosis in the original reference image and original floating image, enhanced
Reference picture and enhancing floating image, the mode this embodiment that wherein computer equipment is enhanced without limitation, such as can be with
It is to enhance contrast using image treating, is also possible to the original reference image and original floating image being input to preparatory instruction
Neural network model perfecting, for enhancing morphosis in original image directly obtains enhancing reference picture and floating figure
Picture.It is understood that computer equipment when enhancing morphosis, can be to an identical morphosis into
Row enhancing, is also possible to enhance multiple identical morphosis, the present embodiment does not limit this.
S103 is registrated enhancing reference picture and enhancing floating image, obtains floating image spatial alternation to reference
The spatial transformation parameter of image space.
In this step, the spatial transformation parameter of floating image spatial alternation to reference picture space indicates original floating image
Place space to original reference image parameters such as mapping mode, such as linear translation, rotation between the spaces or non-thread
The Deformation Field etc. of property.Then in practical applications, based on enhancing reference picture obtained in S102 step and enhancing floating image, meter
It calculates machine equipment to be registrated the enhancing reference picture and enhancing floating image, obtains floating image spatial alternation to reference picture
The mode of the spatial transformation parameter in space can be, and computer equipment is opposite with enhancing floating image according to the enhancing reference picture
The characteristic point answered, the floating image spatial alternation for determining the enhancing reference picture and enhancing between floating image are empty to reference picture
Between spatial transformation parameter.
S104, according to floating image spatial alternation to the spatial transformation parameter in reference picture space, by original floating image
Be changed to original reference image space, complete original floating image to original reference image registration.
Based in above-mentioned S103 step determine floating image spatial alternation to reference picture space spatial transformation parameter,
Original floating image is changed to original reference image space by computer equipment, completes original floating image to original reference image
Registration.Illustratively, computer equipment carries out original floating image can be to the process of registration of original reference image, calculate
Machine equipment does space change to original floating image according to the spatial transformation parameter of floating image spatial alternation to reference picture space
It changes, original floating image is changed to original reference image space, so that the original floating image exists with the original reference image
In the same space coordinate system, to complete original floating image to the registration etc. of original reference image, it can also be other modes,
Such as: deep learning neural network, gray level image or segmented image extract characteristic point objective function etc., the present embodiment pair
This without limitation, as long as can be completed according to the spatial transformation parameter of the floating image spatial alternation to reference picture space original floating
Registration of the motion video to original reference head portrait.
Method for registering images provided in this embodiment, computer equipment pass through original reference image to acquisition and original floating
Motion video carries out at least one identical morphosis enhancing, obtains enhancing reference picture and enhances floating image, then to this
Enhancing reference picture and enhancing floating image are registrated, and are obtained floating image spatial alternation and are become to the space in reference picture space
Change parameter, further according to the spatial transformation parameter carry out original floating image to original reference image registration.In this method, due to
Before computer equipment is registrated original floating image and original reference image, first to original floating image and original reference figure
Enhancing processing as having carried out structural information and morphologic information, so that other areas in morphosis region to be registered and image
Domain comparison it is more obvious, facilitate more accurate robust realization registration, in this way, computer equipment according to enhancing reference picture and
The obtained floating image spatial alternation of enhancing floating image to reference picture space spatial transformation parameter to original floating image
To the registration of original reference image, the accuracy and robustness of registration result can be greatly enhanced.
Computer equipment carries out at least one same modality structure in original reference image and original floating image
Enhancing the mode of processing, the application will be described in detail in following embodiment, then based on the above embodiment, the application
A kind of method for registering images is additionally provided, as shown in figure 3, above-mentioned S102 step includes:
S201 respectively divides at least one identical morphosis in original reference image and original floating image
It cuts, obtains corresponding segmented image;Wherein, original reference image and original floating image are gray level image.
In the present embodiment, computer equipment is at least one identical form in original reference image and original floating image
Structure, which is split, to be equivalent to the identical morphosis location of at least one in original reference image and original floating image
Domain is determined as the process of area-of-interest, and wherein at least one identical morphosis is subject to registration in the application image registration
Structure, set in advance.Wherein the original reference image and original floating image are the ash handled well
Spend image.Then in practical applications, computer equipment point is respectively at least one in original reference image and original floating image
Identical morphosis is split, and it is true in original reference image and original floating image for obtaining corresponding segmented image
The image at least one identical morphosis region is determined.
S202, according to segmented image, respectively at least one identical shape in original reference image and original floating image
State structure carries out enhancing processing, obtains enhancing reference picture and enhances floating image.
Based in above-mentioned S201 step, computer equipment is according to the segmented image, respectively to original reference image and original
The identical morphosis of at least one in floating image carries out enhancing processing, obtains enhancing reference picture and enhances floating image,
Illustratively, computer equipment, which obtains enhancing reference picture and the mode of enhancing floating image, can be form knot in segmented image
In the region enhancing to original reference/floating gray level image of structure, the enhanced gray level image of morphosis is obtained, i.e. enhancing reference
Image and enhancing floating image.Wherein, the enhancing operation of computer equipment includes but is not limited to gray value addition, subtracts each other, or
Multiplied by or divided by some scale etc., the present embodiment does not limit this person's gray value.
It illustratively, include original gradation CT image, bladder segmented image in figure with female pelvic cavity CT data instance in Fig. 4
With enhanced CT image.Wherein Fig. 4-(a) is original gradation CT image, and soft group of organ intensity value is close in image, each organ comparison
Spend it is unobvious, therefore when organ have larger deformation when, can not effectively obtain accurate registration result.Fig. 4-(b) is bladder
Segmented image, if only using segmented image, remaining all anatomical information be will be unable to for being registrated.Fig. 4-(c) is enhancing
Image afterwards, as seen from the figure, image object organ morphology is closed clear after enhancing, remaining anatomical structure retains in image, is facilitated
To accurately and effectively registration result.Therefore, method for registering provided by the embodiments of the present application inputs image subject to registration by improving
Quality is enhanced the accuracy and robustness of registration Algorithm, is not registrated using segmented image directly, but is based on segmentation figure
As enhancing original-gray image, on the basis of enhancing certain organs structure and morphologic information, remain original
All anatomical informations of image, therefore the organ enhanced will not be only registrated in registration process, it can comprehensively consider all
Anatomical information, and registration process will in enhancing to original-gray image if the organ of a certain enhancing has biggish deformation
Help to reduce the distortion of the peripheral organs in registration process.
In above-described embodiment, computer equipment is identical at least one in original reference image and original floating image respectively
The process that is split of morphosis, a kind of method for registering images provided by the present application, as shown in figure 5, above-mentioned S201 step
Include:
S301 determines the region of each morphosis from original reference image and original floating image respectively.
In the present embodiment, computer equipment determines each morphosis from original reference image and original floating image respectively
Region, it is to be understood that if morphosis to be registered be one, it is determined that the region of this morphosis, if
Morphosis to be registered is multiple, it is determined that goes out the region of this multiple morphosis.In practical applications, computer equipment from
Determine that the mode in the region of each morphosis can be using common interested in original reference image and original floating image
The method that region determines can also use other modes, such as: it is determined according to the coordinate position of morphosis region in the picture
Deng the present embodiment does not limit this.
S302 will remove form using the region of each morphosis as prospect in original reference image and original floating image
Region other than structure obtains segmented image as background.
Based on the region of each morphosis determined in above-mentioned S301 step, computer equipment is according to each morphosis
Region is obtained as prospect using the region in original reference image and original floating image in addition to morphosis as background
Segmented image, wherein the mode that computer equipment is split can be based on morphologic segmentation, point based on deep learning
Segmentation method etc..The present embodiment does not limit this.Wherein, using the region of each morphosis as prospect, by original reference image
It is in order to by the region of each morphosis and except form with the region in original floating image in addition to morphosis as background
Region other than structure distinguishes, and for the specific value of prospect value and background value, the present embodiment is not limited this.Under
List a kind of achievable mode specifically divided in face:
Optionally, a kind of achievable mode of S302 step includes: before setting preset for the region of each morphosis
The region in original reference image and original floating image in addition to morphosis is set preset background ash by scape gray value
Angle value obtains segmented image;Wherein, prospect gray value includes at least one gray value.In present embodiment, computer equipment will
Each pixel value is set as preset prospect gray value in the region of each morphosis, by picture each in the region in addition to morphosis
Plain value is set as preset background gray levels.Wherein prospect sum of the grayscale values background gray levels respectively include at least one gray value,
It is understood that if morphosis to be registered be one, the prospect gray value only one, background gray levels also only have
One, the segmented image eventually formed is a prospect gray value (region of each morphosis is as prospect) and background gray scale
It is worth the binarization segmentation image that (region in addition to morphosis is as background) is formed.If morphosis to be registered is more
A, then the prospect gray value has multiple, and background gray levels are one, i.e., the region of multiple morphosis is respectively set multiple
Prospect gray value, background gray levels are constant, then the segmented image formed in this way can be an intermediate segmented image.
Such as: by taking morphosis is an organ (bladder) as an example, if I indicates original reference/floating gray level image space,
U indicates a certain pixel (2D image space) or voxel (3D rendering space) in image space, and I (u) indicates the gray scale of pixel u
Value, Mi(u) it indicates by original reference/floating gray level image I organ segmentation generated as a result, i=1,2,3....N be organ rope
Draw, such as M1Indicate bladder segmentation result, M2Indicate rectum segmentation result, M3Indicate bone segmentation result etc..Two then are carried out to image
After value segmentation, Mi(u) it is a bianry image, divides the image into prospect (target organ is prospect) and background, then it is expressed
Formula are as follows:
Method for registering images provided in this embodiment, computer equipment is respectively from original reference image and original floating image
The region of middle each morphosis of determination, and using the region of each morphosis as prospect, by original reference image and original floating
Region in image in addition to morphosis obtains segmented image as background, in this way, first dividing structural form structural region
Out, then using the segmented image at least one identical morphosis in original reference image and original floating image
Carry out enhancing processing, it is ensured that guarantee that morphosis is more accurate in enhanced image significantly.
In above-described embodiment, computer equipment is according to segmented image respectively in original reference image and original floating image
At least one identical morphosis carries out the process of enhancing processing, and the embodiment of the present application provides two kinds of embodiments, wherein one
Kind embodiment are as follows: preset image superposition method is used, respectively at least one phase in original reference image and original floating image
Same morphosis carries out enhancing processing.Optionally, as shown in fig. 6, the embodiment specifically includes:
S401 determines the weight of each segmented image according to preset weight rule.
In the present embodiment, computer equipment determines the weight of each segmented image according to preset weight rule, wherein the power
Weight-normality is then the rule set previously according to experience or big data rule, and the present embodiment does not limit the particular content of the rule
Fixed, wherein the weight may be greater than 0, be equal to 0 or less than 0 etc., can according to the actual situation depending on.
S402, according to the weight of each segmented image, respectively at least one in original reference image and original floating image
Identical morphosis carries out enhancing processing.
Based on the weight of each segmented image determined in above-mentioned S401 step, computer equipment is to original reference image and original
The identical morphosis of at least one in beginning floating image carries out enhancing processing, optionally, if the weight is greater than 0, will divide
The gray value of the prospect of image is cut using the weight as multiple, the gray scale of be added to respectively original floating image and original reference image
In value;If weight is less than 0, by the gray value of the prospect of segmented image using weight as multiple, respectively from original floating image and
It is reduced in the gray value of original reference image.
Such as: the enhancing image generated in an image superimposition mannerIt may be expressed as:
Wherein, ω is weight.As ω=0, enhance imageAs original-gray image;As ω > 0, segmentation figure
As prospect value will be added to original-gray image with the multiple of ω;As ω < 0, segmented image prospect value by with the multiple of ω from
It is reduced in the gray value of original image.No matter ω>0 or ω<0, can all increase target organ (morphosis subject to registration) in original
In beginning gray level image with the difference of structures surrounding, and then enhance target organ (morphosis subject to registration) structural information with
Morphologic information.
In another embodiment, using preset grey scale converter technique or logarithm method, respectively to original reference
At least one identical morphosis carries out enhancing processing in image and original floating image.Wherein, computer equipment is using pre-
If grey scale converter technique or logarithm method, at least one identical form in original reference image and original floating image
Structure carries out enhancing processing, and optionally, computer equipment can determine original reference according to preset grey scale rule respectively
The grey scale coefficient of image and original floating image;If grey scale coefficient is not equal to 0, pass through the prospect to segmented image
Gray value is enhanced multiplied by the grey scale coefficient.
Such as: the enhancing image generated using grey scale mapping modeIt may be expressed as:
Mi(u)=1
Wherein, α can be any real number.Enhancing image as α=1 is original-gray image, when for other values (α ≠ 1)
When, the corresponding gray value of target organ (morphosis subject to registration) can be increased multiplied by scale coefficient α, and then increase the organ
The difference of (morphosis subject to registration) and other structures.
Method for registering images provided in this embodiment, computer equipment use image superposition method or grey scale converter technique
Original reference image and original floating image are enhanced, can increase morphosis to be registered in original-gray image
With the difference of structures surrounding, and then enhance the structural information and morphologic information of morphosis to be registered.In this way, enhancing
Morphosis form to be registered is closed clear in image afterwards, remaining anatomical structure retains in image, helps to obtain accurate and effective
Registration result.
It should be understood that although each step in the flow chart of Fig. 2-6 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-6
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in fig. 7, providing a kind of image registration device, comprising: original image obtains module
10, original image enhancing module 11, transformation parameter obtain module 12 and original image registration module 13, wherein
Original image obtains module 10, for obtaining original reference image to be registered and original floating image;
Original image enhances module 11, for identical at least one in original reference image and original floating image respectively
Morphosis carry out enhancing processing, obtain enhancing reference picture and enhance floating image;
Transformation parameter obtains module 12, for being registrated to enhancing reference picture and enhancing floating image, is floated
Spatial transformation parameter of the Image space transformation to reference picture space;
Original image registration module 13, for being joined according to the spatial alternation of floating image spatial alternation to reference picture space
Number, original floating image is changed to original reference image space, complete original floating image to original reference image registration.
A kind of image registration device provided by the above embodiment, implementing principle and technical effect and above method embodiment
Similar, details are not described herein.
In one of the embodiments, as shown in figure 8, the embodiment of the present application provides a kind of image registration device, above-mentioned original
Beginning image enhancement module 11 includes: cutting unit 111 and enhancement unit 112, wherein
Cutting unit 111, for respectively at least one identical form in original reference image and original floating image
Structure is split, and obtains corresponding segmented image;Wherein, original reference image and original floating image are gray level image;
Enhancement unit 112 is used for according to segmented image, respectively in original reference image and original floating image at least one
A identical morphosis carries out enhancing processing, obtains enhancing reference picture and enhances floating image.
A kind of image registration device provided by the above embodiment, implementing principle and technical effect and above method embodiment
Similar, details are not described herein.
In one of the embodiments, as shown in figure 9, the embodiment of the present application provides a kind of image registration device, above-mentioned point
Cutting unit 111 includes: that region determines subelement 1111 and segmentation subelement 1112, wherein
Region determines subelement 1111, for determining each form knot from original reference image and original floating image respectively
The region of structure;
Divide subelement 1112, for using the region of each morphosis be used as prospect, by original reference image and it is original float
Region in motion video in addition to morphosis obtains segmented image as background.
A kind of image registration device provided by the above embodiment, implementing principle and technical effect and above method embodiment
Similar, details are not described herein.
In one embodiment, above-mentioned segmentation subelement 1112 is specifically used for setting default for the region of each morphosis
Prospect gray value, set preset back for the region in original reference image and original floating image in addition to morphosis
Scape gray value, obtains segmented image;Wherein, prospect gray value includes at least one gray value.
A kind of image registration device provided by the above embodiment, implementing principle and technical effect and above method embodiment
Similar, details are not described herein.
Above-mentioned enhancement unit 112 is specifically used for using preset image superposition method in one of the embodiments, right respectively
At least one identical morphosis carries out enhancing processing in original reference image and original floating image.
A kind of image registration device provided by the above embodiment, implementing principle and technical effect and above method embodiment
Similar, details are not described herein.
In one of the embodiments, as shown in Figure 10, the embodiment of the present application provides a kind of image registration device, above-mentioned increasing
Strong unit 112 includes: that weight determines subelement 1121 and enhanson 1122, wherein
Weight determines subelement 1121, for determining the weight of each segmented image according to preset weight rule;
Enhanson 1122, for the weight according to each segmented image, respectively to original reference image and original floating
The identical morphosis of at least one in image carries out enhancing processing.
A kind of image registration device provided by the above embodiment, implementing principle and technical effect and above method embodiment
Similar, details are not described herein.
Above-mentioned enhancement unit 112 is specifically also used to using preset grey scale converter technique in one of the embodiments,
Or logarithm method, at least one identical morphosis in original reference image and original floating image is carried out at enhancing respectively
Reason.
A kind of image registration device provided by the above embodiment, implementing principle and technical effect and above method embodiment
Similar, details are not described herein.
Specific about image registration device limits the restriction that may refer to above for method for registering images, herein not
It repeats again.Modules in above-mentioned image registration device can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be terminal, internal structure
Figure can be as shown in Figure 1 above.The computer equipment include by system bus connect processor, memory, network interface,
Display screen and input unit.Wherein, the processor of the computer equipment is for providing calculating and control ability.The computer equipment
Memory include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system and calculating
Machine program.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.It should
The network interface of computer equipment is used to communicate with external terminal by network connection.The computer program is executed by processor
When to realize a kind of method for registering images.The display screen of the computer equipment can be liquid crystal display or electric ink is shown
Screen, the input unit of the computer equipment can be the touch layer covered on display screen, be also possible on computer equipment shell
Key, trace ball or the Trackpad of setting can also be external keyboard, Trackpad or mouse etc..
It will be understood by those skilled in the art that structure shown in above-mentioned Fig. 1, only portion relevant to application scheme
The block diagram of separation structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer
Equipment may include perhaps combining certain components or with different component cloth than more or fewer components as shown in the figure
It sets.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor perform the steps of when executing computer program
Obtain original reference image to be registered and original floating image;
Enhancing processing is carried out at least one identical morphosis in original reference image and original floating image respectively,
It obtains enhancing reference picture and enhances floating image;
The enhancing reference picture and the enhancing floating image are registrated, obtain floating image spatial alternation to ginseng
Examine the spatial transformation parameter of image space;
According to the spatial transformation parameter of the floating image spatial alternation to reference picture space, the original floating is schemed
As being changed to the original reference image space, the registration of the completion original floating image to the original reference image.
A kind of computer equipment provided by the above embodiment, implementing principle and technical effect and above method embodiment class
Seemingly, details are not described herein.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
Obtain original reference image to be registered and original floating image;
Enhancing processing is carried out at least one identical morphosis in original reference image and original floating image respectively,
It obtains enhancing reference picture and enhances floating image;
The enhancing reference picture and the enhancing floating image are registrated, obtain floating image spatial alternation to ginseng
Examine the spatial transformation parameter of image space;
According to the spatial transformation parameter of the floating image spatial alternation to reference picture space, the original floating is schemed
As being changed to the original reference image space, the registration of the completion original floating image to the original reference image.
A kind of computer readable storage medium provided by the above embodiment, implementing principle and technical effect and the above method
Embodiment is similar, and details are not described herein.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of method for registering images, which is characterized in that the described method includes:
Obtain original reference image to be registered and original floating image;
Enhancing processing is carried out at least one identical morphosis in original reference image and original floating image respectively, is obtained
Enhance reference picture and enhancing floating image;
The enhancing reference picture and the enhancing floating image are registrated, obtain floating image spatial alternation to reference to figure
The spatial transformation parameter of image space;
According to the spatial transformation parameter of the floating image spatial alternation to reference picture space, the original floating image is become
Change to the original reference image space, the registration of the completion original floating image to the original reference image.
2. the method according to claim 1, wherein described respectively to original reference image and original floating image
In at least one identical morphosis carry out enhancing processing, obtain enhancing reference picture and enhance floating image, comprising:
At least one identical morphosis in the original reference image and the original floating image is split respectively,
Obtain corresponding segmented image;The original reference image and the original floating image are gray level image;
It is identical at least one in the original reference image and the original floating image respectively according to the segmented image
Morphosis carries out enhancing processing, obtains the enhancing reference picture and the enhancing floating image.
3. according to the method described in claim 2, it is characterized in that, described respectively to the original reference image and described original
The identical morphosis of at least one of floating image is split, and obtains corresponding segmented image, comprising:
The region of each morphosis is determined from the original reference image and the original floating image respectively;
Using the region of each morphosis as prospect, institute will be removed in the original reference image and the original floating image
The region other than morphosis is stated as background, obtains the segmented image.
4. according to the method described in claim 3, it is characterized in that, described using the region of each morphosis as prospect,
Using the region in the original reference image and the original floating image in addition to the morphosis as background, institute is obtained
State segmented image, comprising:
Preset prospect gray value is set by the region of each morphosis, by the original reference image and described original
Region in floating image in addition to the morphosis is set as preset background gray levels, obtains the segmented image;Institute
The prospect gray value of stating includes at least one gray value.
5. according to the described in any item methods of claim 2-4, which is characterized in that it is described according to the segmented image, to described
At least one identical morphosis carries out enhancing processing in original reference image and the original floating image, comprising:
Using preset image superposition method, respectively at least one phase in the original reference image and the original floating image
Same morphosis carries out enhancing processing.
6. according to the method described in claim 5, it is characterized in that, described use preset image superposition method, respectively to described
At least one identical morphosis carries out enhancing processing in original reference image and the original floating image, comprising:
According to preset weight rule, the weight of each segmented image is determined;
According to the weight of each segmented image, respectively in the original reference image and the original floating image at least one
A identical morphosis carries out enhancing processing.
7. according to the described in any item methods of claim 2-4, which is characterized in that it is described according to the segmented image, to described
At least one identical morphosis carries out enhancing processing in original reference image and the original floating image, further includes:
Using preset grey scale converter technique or logarithm method, the original reference image and the original floating are schemed respectively
At least one identical morphosis carries out enhancing processing as in.
8. a kind of image registration device, which is characterized in that described device includes:
Original image obtains module, for obtaining original reference image to be registered and original floating image;
Original image enhances module, for respectively at least one identical form in original reference image and original floating image
Structure carries out enhancing processing, obtains enhancing reference picture and enhances floating image;
Transformation parameter obtains module and is floated for being registrated to the enhancing reference picture and the enhancing floating image
Spatial transformation parameter of the motion video spatial alternation to reference picture space;
Original image registration module, for being joined according to the spatial alternation of the floating image spatial alternation to reference picture space
Number, is changed to the original reference image space for the original floating image, obtains the floating image and described with reference to figure
The registration image of picture.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 8 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any item of the claim 1 to 8 is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910231937.2A CN110310314B (en) | 2019-03-26 | 2019-03-26 | Image registration method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910231937.2A CN110310314B (en) | 2019-03-26 | 2019-03-26 | Image registration method and device, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110310314A true CN110310314A (en) | 2019-10-08 |
CN110310314B CN110310314B (en) | 2022-01-25 |
Family
ID=68074754
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910231937.2A Active CN110310314B (en) | 2019-03-26 | 2019-03-26 | Image registration method and device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110310314B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111951311A (en) * | 2020-07-27 | 2020-11-17 | 上海联影智能医疗科技有限公司 | Image registration method, computer device, and storage medium |
CN112750152A (en) * | 2021-01-18 | 2021-05-04 | 上海联影医疗科技股份有限公司 | Image registration method and device, computer equipment and storage medium |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080037843A1 (en) * | 2006-08-11 | 2008-02-14 | Accuray Incorporated | Image segmentation for DRR generation and image registration |
CN102507592A (en) * | 2011-11-01 | 2012-06-20 | 河海大学常州校区 | Fly-simulation visual online detection device and method for surface defects |
CN102868811A (en) * | 2012-09-04 | 2013-01-09 | 青岛大学 | Mobile phone screen control method based on real-time video processing |
CN103337077A (en) * | 2013-07-01 | 2013-10-02 | 武汉大学 | Registration method for visible light and infrared images based on multi-scale segmentation and SIFT (Scale Invariant Feature Transform) |
CN104881858A (en) * | 2014-02-27 | 2015-09-02 | 上海联影医疗科技有限公司 | Method and device for extracting background parenchymal enhancement in breast |
CN105447838A (en) * | 2014-08-27 | 2016-03-30 | 北京计算机技术及应用研究所 | Method and system for infrared and low-level-light/visible-light fusion imaging |
CN106408509A (en) * | 2016-04-29 | 2017-02-15 | 上海联影医疗科技有限公司 | Registration method and apparatus |
CN107133975A (en) * | 2017-04-14 | 2017-09-05 | 西安电子科技大学 | Heart CT TEE method for registering based on valve alignment and probability graph |
CN107837076A (en) * | 2017-11-27 | 2018-03-27 | 东北大学 | A kind of near-infrared self registration vein displaying is as device and method |
CN109087297A (en) * | 2018-08-10 | 2018-12-25 | 成都工业职业技术学院 | A kind of MR method for registering images based on adaptive neighborhood selection |
-
2019
- 2019-03-26 CN CN201910231937.2A patent/CN110310314B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080037843A1 (en) * | 2006-08-11 | 2008-02-14 | Accuray Incorporated | Image segmentation for DRR generation and image registration |
CN102507592A (en) * | 2011-11-01 | 2012-06-20 | 河海大学常州校区 | Fly-simulation visual online detection device and method for surface defects |
CN102868811A (en) * | 2012-09-04 | 2013-01-09 | 青岛大学 | Mobile phone screen control method based on real-time video processing |
CN103337077A (en) * | 2013-07-01 | 2013-10-02 | 武汉大学 | Registration method for visible light and infrared images based on multi-scale segmentation and SIFT (Scale Invariant Feature Transform) |
CN104881858A (en) * | 2014-02-27 | 2015-09-02 | 上海联影医疗科技有限公司 | Method and device for extracting background parenchymal enhancement in breast |
CN105447838A (en) * | 2014-08-27 | 2016-03-30 | 北京计算机技术及应用研究所 | Method and system for infrared and low-level-light/visible-light fusion imaging |
CN106408509A (en) * | 2016-04-29 | 2017-02-15 | 上海联影医疗科技有限公司 | Registration method and apparatus |
CN107133975A (en) * | 2017-04-14 | 2017-09-05 | 西安电子科技大学 | Heart CT TEE method for registering based on valve alignment and probability graph |
CN107837076A (en) * | 2017-11-27 | 2018-03-27 | 东北大学 | A kind of near-infrared self registration vein displaying is as device and method |
CN109087297A (en) * | 2018-08-10 | 2018-12-25 | 成都工业职业技术学院 | A kind of MR method for registering images based on adaptive neighborhood selection |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111951311A (en) * | 2020-07-27 | 2020-11-17 | 上海联影智能医疗科技有限公司 | Image registration method, computer device, and storage medium |
CN111951311B (en) * | 2020-07-27 | 2024-05-28 | 上海联影智能医疗科技有限公司 | Image registration method, computer device, and storage medium |
CN112750152A (en) * | 2021-01-18 | 2021-05-04 | 上海联影医疗科技股份有限公司 | Image registration method and device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN110310314B (en) | 2022-01-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liu et al. | Robust color guided depth map restoration | |
CN110148192B (en) | Medical image imaging method, device, computer equipment and storage medium | |
CN111192356B (en) | Method, device, equipment and storage medium for displaying region of interest | |
CN113516659B (en) | Medical image automatic segmentation method based on deep learning | |
CN109978037A (en) | Image processing method, model training method, device and storage medium | |
CN111161269B (en) | Image segmentation method, computer device, and readable storage medium | |
CN111899185A (en) | Training method and device of image noise reduction model, electronic equipment and storage medium | |
Siadati et al. | A new exemplar-based image inpainting algorithm using image structure tensors | |
CN113610752A (en) | Mammary gland image registration method, computer device and storage medium | |
CN110310314A (en) | Method for registering images, device, computer equipment and storage medium | |
CN113487536A (en) | Image segmentation method, computer device and storage medium | |
CN110930386B (en) | Image processing method, device, equipment and storage medium | |
Guo et al. | Multi-scale feature guided low-light image enhancement | |
CN111223158A (en) | Artifact correction method for heart coronary image and readable storage medium | |
CN113313728B (en) | Intracranial artery segmentation method and system | |
CN116228753B (en) | Tumor prognosis evaluation method, device, computer equipment and storage medium | |
CN117496352A (en) | Remote sensing change detection method, device and equipment based on gradual fusion of adjacent features | |
CN110766661B (en) | Water-fat separation method for magnetic resonance imaging, magnetic resonance imaging method and equipment | |
CN108447066B (en) | Biliary tract image segmentation method, terminal and storage medium | |
CN111091504B (en) | Image offset field correction method, computer device, and storage medium | |
CN111311531A (en) | Image enhancement method and device, console equipment and medical imaging system | |
CN116128895A (en) | Medical image segmentation method, apparatus and computer readable storage medium | |
CN115546270A (en) | Image registration method, model training method and equipment for multi-scale feature fusion | |
CN112561802B (en) | Interpolation method of continuous sequence images, interpolation model training method and system thereof | |
CN114972382A (en) | Brain tumor segmentation algorithm based on lightweight UNet + + network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |