CN109712186A - The method, computer equipment and storage medium of area-of-interest are delineated in image - Google Patents
The method, computer equipment and storage medium of area-of-interest are delineated in image Download PDFInfo
- Publication number
- CN109712186A CN109712186A CN201811510804.0A CN201811510804A CN109712186A CN 109712186 A CN109712186 A CN 109712186A CN 201811510804 A CN201811510804 A CN 201811510804A CN 109712186 A CN109712186 A CN 109712186A
- Authority
- CN
- China
- Prior art keywords
- area
- interest
- image
- present image
- original 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
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
This application involves methods, computer equipment and storage medium that area-of-interest is delineated in a kind of image.The described method includes: the area-of-interest in acquisition original image is in the position of present image；According to position of the area-of-interest in present image, region subject to registration is intercepted in present image；Area-of-interest in the original image is registrated with the region subject to registration, obtains deformation matrix；Data are delineated according to the basis of the area-of-interest in the deformation matrix and the original image, corresponding basis is generated in the present image and is delineated.Delineating in present image can be quickly generated according to delineating in original image using this method.
Description
Technical field
This application involves radiation therapy technology field, more particularly to delineated in a kind of image area-of-interest method,
Computer equipment and storage medium.
Background technique
In adaptive radiation therapy system, CT (Computed Tomography, the electronic computer to acquisition are needed
Tomoscan) image drawing, to calibrate organ and knub position in need for the treatment of.Wherein, delineate including basis delineate with it is auxiliary
It helps and delineates, it is to be obtained by doctor or physics teacher in radiotherapy treatment planning system according to CT image hand drawn that basis, which is delineated,
Delineate, usually vitals or tumour are delineated；Auxiliary, which is delineated, to be generally based on basis and delineates, such as is delineated to basis
Merge, ask friendship, subduction or scaling etc. obtain after operation it is new delineate, for the optimization to radiotherapy planning is formulated.Wherein, it makes
The general process for determining radiotherapy planning is, doctor provides prescription and therapeutic scheme, doctor and physics teacher drawing target outline and jeopardizes organ,
Physics teacher delineates formulation radiotherapy according to doctor formula, therapeutic scheme and area-of-interest (Region of Interest, ROI)
Plan.Therefore, extremely important to the formulation of area-of-interest delineated to radiotherapy treatment planning.
It at present for the former CT image and freshly harvested CT image of same patient acquisition, requires to be delineated, and newly adopts
It is delineated if the CT image of collection re-starts, can there is the problems such as low inefficiency, accuracy, waste of resource.
Summary of the invention
Based on this, it is necessary in view of the above technical problems, provide one kind and can be improved medical image and delineate efficiency and accurate
The method, computer equipment and storage medium of area-of-interest are delineated in the image of degree.
The method of area-of-interest is delineated in a kind of image, which comprises
The area-of-interest in original image is obtained in the position of present image；
According to position of the area-of-interest in present image, region subject to registration is intercepted in present image；
Area-of-interest in the original image is registrated with the region subject to registration, obtains deformation matrix；
Data are delineated according to the basis of the area-of-interest in the deformation matrix and the original image, described current
Corresponding basis is generated in image to delineate.
The method of area-of-interest is delineated in a kind of image, which comprises
The area-of-interest in original image is obtained in the position of present image；
According to position of the area-of-interest in present image, second area is intercepted in present image；
According to the second area, corresponding basis is generated in the present image by the method for organs automatic segmentation
It delineates.
The method of multiple semi-cylindrical hills is delineated in a kind of medical image, which comprises to described each interested
Region individually generates correspondence according to the method for delineating area-of-interest in any of the above-described described image in the present image
Basis delineate.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
Device performs the steps of when executing the computer program
The area-of-interest in original image is obtained in the position of present image；
According to position of the area-of-interest in present image, region subject to registration is intercepted in present image；
Area-of-interest in the original image is registrated with the region subject to registration, obtains deformation matrix；
Data are delineated according to the basis of the area-of-interest in the deformation matrix and the original image, described current
Corresponding basis is generated in image to delineate.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
It is performed the steps of when row
The area-of-interest in original image is obtained in the position of present image；
According to position of the area-of-interest in present image, region subject to registration is intercepted in present image；
Area-of-interest in the original image is registrated with the region subject to registration, obtains deformation matrix；
Data are delineated according to the basis of the area-of-interest in the deformation matrix and the original image, described current
Corresponding basis is generated in image to delineate.
The method, computer equipment and storage medium that area-of-interest is delineated in above-mentioned image, by intercepting in the picture
Region subject to registration is registrated by area-of-interest with region subject to registration, to improve the accuracy for newly delineating generation；And
When for delineating multiple semi-cylindrical hills, whole image is divided into multiple organic regions, then independent independent to multiple organic regions
According to registration mode, basis corresponding with original image is generated in present image and is delineated, the interference of similar gray-value is reduced, is improved
The accuracy of generation is delineated on basis in present image；By delineating multiple semi-cylindrical hills parallel, efficiency can be improved.
Detailed description of the invention
Fig. 1 is the flow diagram for delineating the method for area-of-interest in one embodiment in image；
Fig. 2 is that registration obtains the flow diagram of deformation matrix step in one embodiment；
Fig. 3 is the flow diagram for delineating the method for area-of-interest in another embodiment in image；
Fig. 4 is the structural block diagram for delineating the device of area-of-interest in one embodiment in image；
Fig. 5 is the structural block diagram for delineating the device of area-of-interest in another embodiment in image；
Fig. 6 is the internal structure chart of computer equipment in one embodiment.
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.
In existing adaptive radiation therapy system, present image and original image are carried out according to complete CT image
Registration, to obtain deformation matrix, i.e., contained in complete CT image organized or organ information.In the process of registration
In, there are the accuracys that similar information (such as similar gray value) may interfere with registration result between different tissues or organ, together
When, complete CT image will lead to excessive variable to slow down the convergence rate of registration.On the other hand, include in original image
Basis is delineated and auxiliary is delineated, if the auxiliary in original image delineates the auxiliary directly generated in present image using deformation matrix
It delineates, then may destroy very much original create-rule for assisting delineating greatly, for example, the ring that auxiliary is delineated to delineate around basis
Shape region such as directly generates auxiliary using deformable registration in present image and delineates, may obtain greatly very much in irregular shape
Auxiliary is delineated, this is that those skilled in the art are undesirable；For another example some jeopardizes organ, there are laps with target area, are
Guarantee that the optimization process for formulating radiotherapy planning does not conflict, will usually jeopardize part Chong Die with target area in organ from jeopardizing organ
Then the middle optimization reduced for formulating radiotherapy planning is delineated according to the auxiliary in original image and is directly generated using deformation matrix
Auxiliary in present image is delineated, and may cause that jeopardize organ be overlapped again with target area, therefore, whole by original image and new images
Body, which is registrated, determines deformation matrix, then directly generates that the basis in present image is delineated and auxiliary is delineated, meeting using deformation matrix
Largely influence the formulation of radiotherapy planning.
In one embodiment, as shown in Figure 1, providing that delineate the method for area-of-interest in a kind of image include following
Step:
Step S110 obtains the area-of-interest in original image in the position of present image.
Specifically, including at least one area-of-interest in original image, the present image includes and the original image pair
The area-of-interest answered.The corresponding organic region of the area-of-interest delineates region.In section Example of the invention
In, organ and area-of-interest title can replace.
Wherein, it is described obtain original image in area-of-interest the position of present image include: by the original image with
Present image carries out Rigid Registration, obtains position of the area-of-interest in the present image in the original image；Or
Interception includes the first area of the area-of-interest in original image, and the first area is carried out rigidity with present image and is matched
Standard, to obtain position of the area-of-interest in present image；Or by the area-of-interest and present image in original image
Rigid Registration is carried out, to obtain position of the area-of-interest in present image.
Area-of-interest corresponding with the area-of-interest in original image can be found in present image, to look for
To approximate location of the area-of-interest in present image.
Rigid Registration is that the area-of-interest in the original image is translated or is rotated in currently by upper and lower, left and right
The Position Approximate that the area-of-interest is found in image, using the Position Approximate as the area-of-interest in present image
In base position.
Basis delineate be by doctor or physics teacher in adaptive radiation therapy planning system, drawn manually according to CT image
What is be made delineates, or is obtained by automatic delineation algorithms and by doctor or physics Shi Xiugai and what is confirmed delineate, usually
Vitals or tumour are delineated；Auxiliary, which is delineated, to be generally based on basis and delineates, and is delineated to basis and is merged, ask friendship, subtract
Remove or scale etc. obtain after operation it is new delineate, for the optimization to radiotherapy planning is formulated.Wherein, it is delineated according to the basis of organ
Position and region of the organ in original image can be found.
The first area can be the large area that includes area-of-interest in original image, described in this large area ratio
The region that area-of-interest is covered is big and smaller than original image.
Step S120 is intercepted subject to registration according to position of the area-of-interest in present image in present image
Region.
Specifically, the position according to the area-of-interest in present image, with the shape for being greater than the area-of-interest
Shape intercepts certain area as region subject to registration, so that the region subject to registration includes the area-of-interest in the position.
Area-of-interest in the original image is registrated with the region subject to registration, obtains deformation by step S130
Matrix.
Wherein, what the gray value that the process of registration is normally based on the pixel of image carried out, the purpose is to will currently scheme
As upper pixel is corresponding with the pixel on original image so that the gray value of corresponding pixel as close as.At this
In embodiment, deformable registration is carried out by the region subject to registration in the area-of-interest and present image in original image, obtains shape
Bending moment battle array.The deformation matrix has recorded between the pixel in pixel and the region subject to registration in area-of-interest
Transformation relation.
Match in one of the embodiments, by the area-of-interest in the original image with the region subject to registration
On time, it can be directly registrated using area-of-interest in the original image with the region subject to registration, institute can also be used
The large area (first area as escribed above) stated in original image is registrated with the region subject to registration, the large area
Include the area-of-interest.
Step S140 delineates data according to the basis of the area-of-interest in the deformation matrix and the original image,
Corresponding basis is generated in the present image to delineate.
Wherein, basis is delineated data and can be stored separately through the mode of matrix in the original image, by deformation square
Data are delineated on the basis that battle array is applied in original image, so that data are delineated on the basis being transformed into present image, according to current figure
Data are delineated on basis as in can delineate basis of formation in present image.
The method for delineating area-of-interest in described image in one of the embodiments, further comprises the steps of:
Step S150 obtains the create-rule for delineating in original image according to basis and generating auxiliary and delineating.
Wherein, the create-rule includes delineating the operation such as to merge, ask friendship, subduction or scaling to basis.
Step S160 is delineated according to the basis in the present image according to the create-rule and is generated corresponding auxiliary
It delineates.
It delineates in above-mentioned image in the method for area-of-interest, by intercepting region subject to registration in present image, passes through
The area-of-interest of original image is registrated with the region subject to registration of present image, to avoid the pixel except region subject to registration
Registration is interfered, the accuracy for newly delineating generation is improved.
In one embodiment, as shown in Fig. 2, in step s 130, the area-of-interest by the original image
It is registrated with the region subject to registration, obtains deformation matrix, comprising steps of
Step S131 obtains the characteristic value of expression variation tendency of the area-of-interest from original image to present image.
Different Organs intracorporal for test object, variation tendency may be different.In some embodiments, the sense is emerging
The variation tendency in interesting region include in the change in location trend, volume change trend and change in shape trend of the organ at least
It is a kind of.
Wherein, typically, original image and present image are the images that test object is acquired in different times, therefore same
Organ had in original image and present image in difference, such as organ site, shape, size etc. at least one of change
Become, but these variations are limited to the characteristic of organ.The characteristic of Different Organs may be different.Therefore, in some embodiments, may be used
The characteristic value for indicating the variation tendency of organ is obtained with the mark according to organ.Optionally, the mark of organ can be organ name
Title, type etc., can be according to Organ naming and/or the variation tendency of type determiner official, that is, determining indicates that the variation of organ becomes
The characteristic value of gesture.Such as incidence organ shape may change, but constancy of volume, and the position of opposite head is not yet
Become, it at this time can be using the position of the volume of incidence organ and/or the opposite head of incidence organ as constraint condition.For example,
The position of the organs such as stomach, bladder is constant, but because can expand or shrink, volume can become, in this case can be with
Its location information is obtained as constraint condition.For example, the shape and constancy of volume of the organs such as eyeball, bone, spinal cord, but position
It may change, therefore can be using shape and/or volume information as constraint condition.
In some embodiments, the characteristic value for indicating the variation tendency of organ can be obtained according to neural network.Specifically,
Data (same organs) are delineated by the image pattern basis for acquiring multiple at least two time points of patient, are input to neural network
Model obtains the variation characteristic value of the organ by neural network model training, these characteristic values can indicate the organ
Variation tendency, and record the characteristic value of the expression variation tendency of the organ.
Step S132, using the characteristic value for indicating variation tendency as the constraint condition of registration, in the original image
Area-of-interest is registrated with the region subject to registration, obtains deformation matrix.
Specifically, can be using the characteristic value of the variation tendency for the expression organ trained as the constraint condition of registration, it will
Area-of-interest is registrated with the region subject to registration in the original image, obtains deformation matrix.Image registration needs to undergo
Iterative process considers the variation tendency of organ in this process, and pixel is enabled to meet specific feature side in optimization process
Journey, the parameter in the equation can be according to the feature by organ mark determining characteristic value or being obtained by above-mentioned neural metwork training
Value is given, so as to improve the accuracy of registration.Deformable registration is the known technology of this field, and details are not described herein.
In one of the embodiments, in the step s 120, it is described according to the area-of-interest in present image
Position intercepts region subject to registration in present image, comprising: according to position of the area-of-interest in present image,
The region surrounded according to regular shape is intercepted in the present image, the region surrounded according to regular shape includes the sense
Interest region.Specifically, the size of the regular shape can just wrap the organ.Wherein, the regular shape packet
Include round and rectangle.
In one embodiment, as shown in figure 3, providing a kind of method for delineating area-of-interest in image, including with
Lower step:
Step S310 obtains the area-of-interest in original image in the position of present image.
Specifically, including at least one area-of-interest in original image, the present image includes and the original image pair
The area-of-interest answered.The corresponding organic region of the area-of-interest delineates region.In section Example of the invention
In, the title of organ and area-of-interest can replace.
Wherein, it is described obtain original image in area-of-interest the position of present image include: by the original image with
Present image carries out Rigid Registration, obtains position of the area-of-interest in the present image in the original image；Or
Interception includes the first area of the area-of-interest in original image, and the first area is carried out rigidity with present image and is matched
Standard, to obtain position of the area-of-interest in present image；Or by the area-of-interest and present image in original image
Rigid Registration is carried out, to obtain position of the area-of-interest in present image.
Area-of-interest corresponding with the area-of-interest in original image can be found in present image, to look for
To approximate location of the area-of-interest in present image.
Rigid Registration is that the area-of-interest in the original image is translated or is rotated in currently by upper and lower, left and right
The Position Approximate that the area-of-interest is found in image, using the Position Approximate as the area-of-interest in present image
In base position.
Basis delineate be by doctor or physics teacher in adaptive radiation therapy planning system, drawn manually according to CT image
What is be made delineates, and usually vitals or tumour are delineated；Auxiliary, which is delineated, to be generally based on basis and delineates, and is hooked to basis
Picture merge, ask friendship, subduction or scaling etc. obtain after operation it is new delineate, for the optimization to radiotherapy planning is formulated.Wherein,
The position and region that can find the organ in original image are delineated according to the basis of organ.
The first area can be the large area that includes area-of-interest in original image, described in this large area ratio
The region that area-of-interest is covered is big and smaller than original image.
Step S320 intercepts the secondth area according to position of the area-of-interest in present image in present image
Domain.
Specifically, the position according to the area-of-interest in present image, with the shape for being greater than the area-of-interest
Shape intercepts certain area as second area, so that the second area includes the area-of-interest in the position.
Step S330 is generated in the present image according to the second area by the method for organs automatic segmentation
Corresponding basis is delineated.
Specifically, according to the attribute value of CT image, being able to know that the big of image pixel in the method for organs automatic segmentation
It is small, since gray value of each organ in CT image is different, CT image can be divided by multiple organic regions according to gray value,
Each organic region represents corresponding organ.According to the edge of organic region, basis can be automatically generated and delineated.
Wherein, the method for organs automatic segmentation can realize that organ divides automatically using known organs automatic segmentation algorithm
Cutting algorithm can be stored to area-of-interest (Region of Interest, ROI) in database as customized internal data, into
The automatic segmentation work of the correlation organ such as row skin.Organs automatic segmentation refers to the position for going out organ according to manikin Primary Location
It sets, such as left lung, heart, vertebra etc., then according to the different organic image values (such as CT value) in three-dimensional data file
Difference, application image processing in edge extracting scheduling algorithm, required organ is marked.In an embodiment of the present invention,
Known organs automatic segmentation algorithm can be used come the step for implementation, it is not reinflated herein.
In one of the embodiments, in step s 320, it is described according to the area-of-interest in present image
Position intercepts second area in present image, comprising: according to position of the area-of-interest in present image, in institute
The region that interception is surrounded according to regular shape in present image is stated, the region surrounded according to regular shape includes that the sense is emerging
Interesting region.Specifically, the size of the regular shape can just wrap the area-of-interest.Wherein, the regular shape
Shape includes round and rectangle.
The method of area-of-interest is delineated in described image in one of the embodiments, further include:
S340 obtains the create-rule for delineating in original image according to basis and generating auxiliary and delineating.
Wherein, the create-rule includes delineating the operation such as to merge, ask friendship, subduction or scaling to basis.
S350 delineates the corresponding auxiliary of generation according to the basis in the present image and delineates according to the create-rule.
It is delineated in above-mentioned image in the method for area-of-interest, by, according to automatic partitioning scheme, working as to organic region
Basis corresponding with original image is generated in preceding image to delineate, and improves accuracy and effect that generation is delineated on basis in present image
Rate.
In one embodiment, the method for multiple semi-cylindrical hills is delineated in a kind of medical image, wherein to described each
Area-of-interest individually generates corresponding basis according to method described in above-described embodiment in the present image and delineates.
It wherein, may include that the basis of multiple organs and organ is delineated in original image, each basis is delineated can be single
Solely according to the method for delineating area-of-interest in image a kind of in above-described embodiment, corresponding basis is generated in present image and is hooked
It draws.
In some embodiments, when in image including multiple semi-cylindrical hills, due to can between each area-of-interest
Can mutually exist influence, therefore for multiple semi-cylindrical hills according to any embodiment of the present invention (for example, above-mentioned Fig. 1 and/or figure
2) when method is delineated, priority can be set for multiple semi-cylindrical hills.Preferably, it is less susceptible to by other region of interest
The priority that domain influences is higher, and more holding, susceptible priority is lower.For example, the area-of-interest priority of spontaneous variation is most
The priority of height, the area-of-interest influenced by the variation of other area-of-interests is lower.For example, bone is typically all certainly first
The organ of variation is sent out, and is easy registration, highest priority；Secondly, bladder, heart, stomach belong to the organ of spontaneous variation, preferentially
Grade is higher；Thirdly, large intestine, small intestine belong to the organ influenced vulnerable to other organs, and priority is lower；Finally, target area is due to needing
To be judged in conjunction with other organs, therefore the setting of its priority is minimum.It can be delineated according to above-mentioned priority orders more
A area-of-interest.
During delineating area-of-interest, the registration result of the high area-of-interest of priority can be used as priority
The constraint of low area-of-interest.For example, the high area-of-interest of priority delineates result as low interested of priority
The constraint in region.For example, the first area-of-interest influences the second area-of-interest, first with any embodiment of the present invention
In method generate the basis of the first area-of-interest in present image and delineate.It is delineated to the second area-of-interest
When, consider the range of the first area-of-interest in present image, avoids the second area-of-interest for delineating and delineated
The overlapping of first area-of-interest.Alternatively, due to the relative position of the first area-of-interest and the second area-of-interest be it is fixed,
When delineating the second area-of-interest, need to keep keeping solid with the relative position for the first area-of-interest delineated
It is fixed.For another example, the registration matrix of the high area-of-interest of priority can be used as the constraint of the low area-of-interest of priority.Example
Property, the first area-of-interest is affixed with the second region of interest border, and the first area-of-interest is from original image according to deformation square
Battle array arrives present image, and boundary produces variation, and the second area-of-interest is from original image to present image, the boundary corresponding position Ye Yingzuo
Reason.
In the above-described embodiments, can be to each area-of-interest for the image comprising multiple semi-cylindrical hills, it can be with
It is independently delineated according to method described in any embodiment of the present invention, avoids the interference of similar gray-value between different zones.
In some embodiments, parallel processing can be delineated to multiple and different area-of-interests, thus when saving is delineated
Between, it improves efficiency.
It should be understood that although each step in the flow chart of Fig. 1-3 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. 1-3
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 figure 4, providing the device for delineating area-of-interest in a kind of image, comprising: position
It sets acquisition module 410, interception module 420, registration module 430 and basis and delineates generation module 440, in which:
Position acquisition module 410, for obtaining the area-of-interest in original image in the position of present image.
Interception module 420 intercepts in present image for the position according to the area-of-interest in present image
Region subject to registration.
Registration module 430 is obtained for the area-of-interest in the original image to be registrated with the region subject to registration
To deformation matrix.
Generation module 440 is delineated on basis, for according to the area-of-interest in the deformation matrix and the original image
Basis delineate data, corresponding basis is generated in the region in the present image and is delineated.
The device of area-of-interest is delineated in described image in one of the embodiments, further include: auxiliary delineates generation
Rule acquisition module, for obtaining the create-rule for delineating in original image according to basis and generating auxiliary and delineating；Auxiliary delineates generation
Module, for delineating the corresponding auxiliary of generation according to the basis in the present image and delineating according to the create-rule.
The registration module 430 includes: variation tendency acquiring unit in one of the embodiments, described for obtaining
The characteristic value of expression variation tendency of the area-of-interest from original image to present image；Deformation matrix acquiring unit is used for institute
State indicate variation tendency characteristic value as be registrated constraint condition, to area-of-interest in the original image with it is described subject to registration
Region is registrated, and deformation matrix is obtained.
The interception module 420 in one of the embodiments, specifically for being schemed according to the area-of-interest currently
Position as in, intercept the region that surrounds according to regular shape in the present image, described to surround according to regular shape
Region includes the area-of-interest.Specifically, the size of the regular shape can just wrap the organ.Wherein,
The regular shape includes round and rectangle.
In another embodiment, as shown in figure 5, providing the device for delineating area-of-interest in a kind of image, comprising:
Generation module 530 is delineated on position acquisition module 510, interception module 520 and basis, in which:
Position acquisition module 510, for obtaining the area-of-interest in original image in the position of present image.
Interception module 520 intercepts in present image for the position according to the area-of-interest in present image
Second area.
Generation module 530 is delineated on basis, is used for according to the second area, by the method for organs automatic segmentation described
Corresponding basis is generated in present image to delineate.
The interception module 520 in one of the embodiments, specifically for being schemed according to the area-of-interest currently
Position as in, intercept the region that surrounds according to regular shape in the present image, described to surround according to regular shape
Region includes the area-of-interest.Specifically, the size of the regular shape can just wrap the organ.Wherein,
The regular shape includes round and rectangle.
The device of area-of-interest is delineated in described image in one of the embodiments, further include: auxiliary delineates generation
Rule acquisition module, for obtaining the create-rule for delineating in original image according to basis and generating auxiliary and delineating；Auxiliary delineates generation
Module generates corresponding auxiliary and delineates for being delineated according to the basis in the present image according to the create-rule.
Specific restriction about the device for delineating area-of-interest in above-mentioned image may refer to above in image
The restriction of the method for area-of-interest is delineated, details are not described herein.It is delineated in above-mentioned image each in the device of area-of-interest
A module can be realized fully or partially through software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware or
Independently of in the processor in computer equipment, can also be stored in a software form in the memory in computer equipment, with
It is called convenient for processor and executes the corresponding operation of the above modules.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 6.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include 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 for storing CT image data.The network interface of the computer equipment is used to pass through net with external terminal
Network connection communication.To realize a kind of method for delineating area-of-interest in image when the computer program is executed by processor.
It will be understood by those skilled in the art that structure shown in Fig. 6, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, is stored in memory
Computer program, the processor perform the steps of when executing computer program
The area-of-interest in original image is obtained in the position of present image；
According to position of the area-of-interest in present image, region subject to registration is intercepted in present image；
Area-of-interest in the original image is registrated with the region subject to registration, obtains deformation matrix；
Data are delineated according to the basis of the area-of-interest in the deformation matrix and the original image, described current
Corresponding basis is generated in image to delineate.
The processor is parallel processor in one of the embodiments, can be parallel to multiple semi-cylindrical hills
Execute the method that area-of-interest is delineated in image described in above-described embodiment.
In one embodiment, it is also performed the steps of when processor executes computer program and obtains basis in original image
Basis, which is delineated, generates the create-rule that auxiliary is delineated；According to the create-rule, delineated according to the basis in the present image,
Corresponding auxiliary is generated to delineate.
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
The area-of-interest in original image is obtained in the position of present image；
According to position of the area-of-interest in present image, region subject to registration is intercepted in present image；
Area-of-interest in the original image is registrated with the region subject to registration, obtains deformation matrix；
Data are delineated according to the basis of the area-of-interest in the deformation matrix and the original image, described current
Corresponding basis is generated in image to delineate.
In one embodiment, it is also performed the steps of when computer program is executed by processor and obtains root in original image
The create-rule for generating auxiliary and delineating is delineated according to basis；According to the create-rule, hooked according to the basis in the present image
It draws, generates corresponding auxiliary and delineate.
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 (14)
1. delineating the method for area-of-interest in a kind of image, which is characterized in that the described method includes:
The area-of-interest in original image is obtained in the position of present image；
According to position of the area-of-interest in present image, region subject to registration is intercepted in present image；
Area-of-interest in the original image is registrated with the region subject to registration, obtains deformation matrix；
Data are delineated according to the basis of the area-of-interest in the deformation matrix and the original image, in the present image
It is middle to generate corresponding basis and delineate.
2. the method according to claim 1, wherein the area-of-interest obtained in original image is schemed currently
The position of picture includes:
The original image and present image are subjected to Rigid Registration, obtain the area-of-interest in the original image described current
Position in image；Or
Interception includes the first area of the area-of-interest in original image, the first area and present image is carried out rigid
Property registration, to obtain position of the area-of-interest in present image；Or
By the area-of-interest and present image progress Rigid Registration in original image, schemed with obtaining the area-of-interest currently
Position as in.
3. the method according to claim 1, wherein further include:
Obtain the create-rule for delineating in original image according to basis and generating auxiliary and delineating；
According to the create-rule, the corresponding auxiliary of generation is delineated according to the basis in the present image and is delineated.
4. the method according to claim 1, wherein the area-of-interest by the original image with it is described
Region subject to registration is registrated, and deformation matrix is obtained, comprising:
Obtain the characteristic value of expression variation tendency of the area-of-interest from original image to present image；
Using the characteristic value for indicating variation tendency as the constraint condition of registration, to area-of-interest in the original image and institute
It states region subject to registration to be registrated, obtains deformation matrix.
5. according to the method described in claim 4, it is characterized in that, the variation tendency includes the position of the area-of-interest
At least one in the change in shape trend of variation tendency, the volume change trend of the area-of-interest and the area-of-interest
Kind.
6. the method according to claim 1, wherein it is described according to the area-of-interest in present image
Position intercepts region subject to registration in present image, comprising:
According to position of the area-of-interest in present image, intercepts in the present image and surrounded according to regular shape
Region, the region surrounded according to regular shape include the area-of-interest.
7. delineating the method for area-of-interest in a kind of image, which is characterized in that the described method includes:
The area-of-interest in original image is obtained in the position of present image；
According to position of the area-of-interest in present image, second area is intercepted in present image；
According to the second area, corresponding basis is generated in the present image by the method for organs automatic segmentation and is hooked
It draws.
8. the method according to the description of claim 7 is characterized in that further include:
Obtain the create-rule for delineating in original image according to basis and generating auxiliary and delineating；
It according to the create-rule, is delineated according to the basis in the present image, generates corresponding auxiliary and delineate.
9. the method according to the description of claim 7 is characterized in that it is described according to the area-of-interest in present image
Position intercepts second area in present image, comprising:
According to position of the area-of-interest in present image, intercepts in the present image and surrounded according to regular shape
Region, the region surrounded according to regular shape include the area-of-interest.
10. delineating the method for multiple semi-cylindrical hills in a kind of medical image, which is characterized in that each area-of-interest
Corresponding basis is individually generated in the present image according to any one of claim 1-9 the method to delineate.
11. according to the method described in claim 10, it is characterized in that, the method also includes for the multiple area-of-interest
Priority, the constraint of the registration result of the high area-of-interest of the priority area-of-interest low as priority are set.
12. 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 11 the method when executing the computer program.
13. computer equipment according to claim 12, which is characterized in that the processor is parallel processor, can
To require any one of 1 to 11 the method to the parallel perform claim of multiple semi-cylindrical hills.
14. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 11 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811510804.0A CN109712186B (en) | 2018-12-11 | 2018-12-11 | Method, computer device and storage medium for delineating a region of interest in an image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811510804.0A CN109712186B (en) | 2018-12-11 | 2018-12-11 | Method, computer device and storage medium for delineating a region of interest in an image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109712186A true CN109712186A (en) | 2019-05-03 |
| CN109712186B CN109712186B (en) | 2021-10-22 |
Family
ID=66255720
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811510804.0A Active CN109712186B (en) | 2018-12-11 | 2018-12-11 | Method, computer device and storage medium for delineating a region of interest in an image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109712186B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111784705A (en) * | 2020-06-24 | 2020-10-16 | 上海联影医疗科技有限公司 | Method, device and equipment for delineating region of interest and storage medium |
| CN112419338A (en) * | 2020-12-08 | 2021-02-26 | 深圳大学 | Head and neck endangered organ segmentation method based on anatomical prior knowledge |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103048331A (en) * | 2012-12-20 | 2013-04-17 | 石家庄印钞有限公司 | Printing defect detection method based on flexible template registration |
| CN103247046A (en) * | 2013-04-19 | 2013-08-14 | 深圳先进技术研究院 | Automatic target volume sketching method and device in radiotherapy treatment planning |
| CN104117151A (en) * | 2014-08-12 | 2014-10-29 | 章桦 | Optimization method of online self-adaption radiotherapy plan |
| CN105488804A (en) * | 2015-12-14 | 2016-04-13 | 上海交通大学 | Brain ASL (Arterial Spin Labeling), SPECT (Single-Photon Emission Computed Tomography) and MRI (Magnetic Resonance Imaging) image registration and fusion conjoint analysis method and system |
| CN106902475A (en) * | 2015-12-18 | 2017-06-30 | 光线搜索实验室公司 | Radiation therapy method, computer program and computer system |
| CN106920234A (en) * | 2017-02-27 | 2017-07-04 | 北京连心医疗科技有限公司 | A kind of method of the automatic radiotherapy planning of combined type |
| CN107590808A (en) * | 2016-07-06 | 2018-01-16 | 上海联影医疗科技有限公司 | Prostate dividing method in medical image |
-
2018
- 2018-12-11 CN CN201811510804.0A patent/CN109712186B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103048331A (en) * | 2012-12-20 | 2013-04-17 | 石家庄印钞有限公司 | Printing defect detection method based on flexible template registration |
| CN103247046A (en) * | 2013-04-19 | 2013-08-14 | 深圳先进技术研究院 | Automatic target volume sketching method and device in radiotherapy treatment planning |
| CN104117151A (en) * | 2014-08-12 | 2014-10-29 | 章桦 | Optimization method of online self-adaption radiotherapy plan |
| CN105488804A (en) * | 2015-12-14 | 2016-04-13 | 上海交通大学 | Brain ASL (Arterial Spin Labeling), SPECT (Single-Photon Emission Computed Tomography) and MRI (Magnetic Resonance Imaging) image registration and fusion conjoint analysis method and system |
| CN106902475A (en) * | 2015-12-18 | 2017-06-30 | 光线搜索实验室公司 | Radiation therapy method, computer program and computer system |
| CN107590808A (en) * | 2016-07-06 | 2018-01-16 | 上海联影医疗科技有限公司 | Prostate dividing method in medical image |
| CN106920234A (en) * | 2017-02-27 | 2017-07-04 | 北京连心医疗科技有限公司 | A kind of method of the automatic radiotherapy planning of combined type |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111784705A (en) * | 2020-06-24 | 2020-10-16 | 上海联影医疗科技有限公司 | Method, device and equipment for delineating region of interest and storage medium |
| CN111784705B (en) * | 2020-06-24 | 2024-04-02 | 上海联影医疗科技股份有限公司 | Method, device, equipment and storage medium for delineating region of interest |
| CN112419338A (en) * | 2020-12-08 | 2021-02-26 | 深圳大学 | Head and neck endangered organ segmentation method based on anatomical prior knowledge |
| CN112419338B (en) * | 2020-12-08 | 2021-12-07 | 深圳大学 | Head and neck endangered organ segmentation method based on anatomical prior knowledge |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109712186B (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12094115B2 (en) | System and method of mitral valve quantification | |
| CN109544566B (en) | Coronary image segmentation method, device, computer equipment and storage medium | |
| US10357316B2 (en) | Systems and methods for planning hair transplantation | |
| KR101751165B1 (en) | Systems and methods for planning hair transplantation | |
| US7778488B2 (en) | Image deformation using multiple image regions | |
| CN107392897A (en) | Organ contours acquisition methods, image documentation equipment, radiotherapy planning system and storage medium | |
| WO2020033355A1 (en) | Deep-learning-based method for metal reduction in ct images and applications of same | |
| US9547906B2 (en) | System and method for data driven editing of rib unfolding | |
| CN115131487A (en) | Medical image processing method, system, computer device and storage medium | |
| CN109712186A (en) | The method, computer equipment and storage medium of area-of-interest are delineated in image | |
| JP7409624B2 (en) | Information processing device, information processing method, and program | |
| KR102216455B1 (en) | Apparatus and method for measuring left atrium thickness of heart | |
| CN111612867A (en) | Motion artifact correction method, motion artifact correction device, computer equipment and readable storage medium | |
| JP2003030624A (en) | Automatic surgical operation path search program and device therefor | |
| CN113705807B (en) | Neural network training device and method, ablation needle arrangement planning device and method | |
| JP7048760B2 (en) | Area modifiers, methods and programs | |
| US20200294253A1 (en) | Calibration of image-registration based tracking procedures | |
| CN112766258B (en) | Image segmentation method, system, electronic device and computer readable storage medium | |
| Wang et al. | Machine Learning-Based Techniques for Medical Image Registration and Segmentation and a Technique for Patient-Customized Placement of Cochlear Implant Electrode Arrays | |
| CN118057545A (en) | Method for managing virtual patient model and patient model management device | |
| CN115424720A (en) | Tubular structure fracture completion method and device and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant after: Shanghai Lianying Medical Technology Co., Ltd Address before: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |