CN109712186B - Method, computer device and storage medium for delineating a region of interest in an image - Google Patents
Method, computer device and storage medium for delineating a region of interest in an image Download PDFInfo
- Publication number
- CN109712186B CN109712186B CN201811510804.0A CN201811510804A CN109712186B CN 109712186 B CN109712186 B CN 109712186B CN 201811510804 A CN201811510804 A CN 201811510804A CN 109712186 B CN109712186 B CN 109712186B
- Authority
- CN
- China
- Prior art keywords
- region
- interest
- image
- current 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.)
- Active
Links
Images
Abstract
The present application relates to a method, computer device and storage medium for delineating a region of interest in an image. The method comprises the following steps: acquiring the position of an interested area in an original image in a current image; intercepting a region to be registered in the current image according to the position of the region of interest in the current image; registering the region of interest in the original image with the region to be registered to obtain a deformation matrix; and generating a corresponding basic sketch in the current image according to the deformation matrix and the basic sketch data of the region of interest in the original image. By adopting the method, the sketching in the current image can be quickly generated according to the sketching in the original image.
Description
Technical Field
The present application relates to the field of radiotherapy technology, and in particular, to a method, a computer device, and a storage medium for delineating a region of interest in an image.
Background
In adaptive radiotherapy systems, it is necessary to delineate the acquired CT (Computed Tomography) images to locate the organ or tumor to be treated. The basic delineation is obtained by manually drawing according to a CT image in a radiotherapy planning system by a doctor or a physicist, and is generally the delineation of important organs or tumors; the auxiliary delineation is generally based on the basic delineation, for example, a new delineation is obtained after the basic delineation is combined, intersected, subtracted or scaled, and the like, and is used for optimizing the planning of radiotherapy. The general process of making a radiotherapy plan is that a doctor gives a prescription and a treatment plan, the doctor and a physicist delineate a target area and an organ at risk, and the physicist makes the radiotherapy plan according to the prescription, the treatment plan and the delineation of a Region of Interest (ROI) of the doctor. Therefore, delineation of the region of interest is very important for radiation therapy planning.
At present, the original CT image and the newly acquired CT image acquired by the same patient need to be sketched, and if the newly acquired CT image is sketched again, the problems of low efficiency, low accuracy, resource waste and the like exist.
Disclosure of Invention
In view of the foregoing, there is a need to provide a method, a computer device and a storage medium for delineating a region of interest in an image, which can improve medical image delineation efficiency and accuracy.
A method of delineating a region of interest in an image, the method comprising:
acquiring the position of an interested area in an original image in a current image;
intercepting a region to be registered in the current image according to the position of the region of interest in the current image;
registering the region of interest in the original image with the region to be registered to obtain a deformation matrix;
and generating a corresponding basic sketch in the current image according to the deformation matrix and the basic sketch data of the region of interest in the original image.
A method of delineating a region of interest in an image, the method comprising:
acquiring the position of an interested area in an original image in a current image;
intercepting a second area in the current image according to the position of the region of interest in the current image;
and generating a corresponding basic sketch in the current image by an organ automatic segmentation method according to the second region.
A method of delineating a plurality of regions of interest in a medical image, the method comprising: and for each region of interest, generating a corresponding basic delineation in the current image according to the method for delineating the region of interest in the image.
A computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring the position of an interested area in an original image in a current image;
intercepting a region to be registered in the current image according to the position of the region of interest in the current image;
registering the region of interest in the original image with the region to be registered to obtain a deformation matrix;
and generating a corresponding basic sketch in the current image according to the deformation matrix and the basic sketch data of the region of interest in the original image.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring the position of an interested area in an original image in a current image;
intercepting a region to be registered in the current image according to the position of the region of interest in the current image;
registering the region of interest in the original image with the region to be registered to obtain a deformation matrix;
and generating a corresponding basic sketch in the current image according to the deformation matrix and the basic sketch data of the region of interest in the original image.
According to the method, the computer equipment and the storage medium for delineating the region of interest in the image, the region to be registered is intercepted from the image, and the region of interest is registered with the region to be registered, so that the accuracy of generating a new delineation is improved; when a plurality of interested areas are drawn, the whole image is divided into a plurality of organ areas, and then the basic drawing corresponding to the original image is generated in the current image independently according to the registration mode for the organ areas, so that the interference of similar gray values is reduced, and the accuracy of generating the basic drawing in the current image is improved; by delineating multiple regions of interest in parallel, efficiency may be improved.
Drawings
FIG. 1 is a schematic flow chart diagram illustrating a method for delineating a region of interest in an image, in accordance with one embodiment;
FIG. 2 is a schematic flowchart of the step of obtaining a deformation matrix by registration in one embodiment;
FIG. 3 is a schematic flow chart of a method for delineating a region of interest in an image in another embodiment;
FIG. 4 is a block diagram of an apparatus for delineating a region of interest in an image in one embodiment;
FIG. 5 is a block diagram of an apparatus for delineating a region of interest in an image in accordance with another embodiment;
FIG. 6 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In the existing adaptive radiotherapy system, the current image and the original image are registered according to the complete CT image to obtain the deformation matrix, i.e. the complete CT image includes information of all tissues or organs. During the registration process, the existence of similar information (such as similar gray values) between different tissues or organs may interfere with the accuracy of the registration result, and meanwhile, the complete CT image may cause too many variables to slow down the convergence rate of the registration. On the other hand, the original image includes a basic sketch and an auxiliary sketch, and if the auxiliary sketch in the original image directly generates the auxiliary sketch in the current image by using a deformation matrix, the generation rule of the original auxiliary sketch is likely to be damaged, for example, the auxiliary sketch is an annular region surrounding the basic sketch, and if the auxiliary sketch is generated in the current image by directly using deformation registration, the auxiliary sketch with an irregular shape is likely to be obtained, which is not desired by a person skilled in the art; for another example, an overlapping portion exists between a certain organ at risk and a target area, and in order to ensure that an optimization process for making a radiotherapy plan does not conflict, the optimization for making the radiotherapy plan is usually subtracted from the organ at risk from the overlapping portion of the organ at risk and the target area, and then an auxiliary delineation in the current image is directly generated by using a deformation matrix according to the auxiliary delineation in the original image, which may cause the organ at risk and the target area to overlap again.
In one embodiment, as shown in fig. 1, there is provided a method of delineating a region of interest in an image comprising the steps of:
step S110, acquiring a position of the region of interest in the original image in the current image.
Specifically, the original image includes at least one region of interest, and the current image includes a region of interest corresponding to the original image. The region of interest corresponds to a delineation region of an organ region. In some embodiments of the invention, the organ and region of interest domain names may be replaced.
Wherein, the acquiring the position of the region of interest in the original image in the current image comprises: rigidly registering the original image and the current image to obtain the position of the region of interest in the original image in the current image; or intercepting a first region containing the region of interest from an original image, and rigidly registering the first region with the current image to acquire the position of the region of interest in the current image; or the interested region in the original image is rigidly registered with the current image so as to acquire the position of the interested region in the current image.
The region of interest corresponding to the region of interest in the original image can be found in the current image, so that the approximate position of the region of interest in the current image is found.
And rigid registration is to find the approximate position of the region of interest in the current image by translating or rotating the region of interest in the original image up and down, left and right, and take the approximate position as the reference position of the region of interest in the current image.
The basic delineation is a delineation obtained by a doctor or a physicist through manual drawing according to a CT image in a self-adaptive radiotherapy planning system, or a delineation obtained through an automatic delineation algorithm and modified and confirmed by the doctor or the physicist, and is generally the delineation of important organs or tumors; the auxiliary delineation is generally based on basic delineation, and new delineations are obtained after the basic delineation is subjected to operations such as merging, intersection, subtraction or zooming and the like, and are used for optimizing the planning of radiotherapy. The position and the area of the organ in the original image can be found according to the basic delineation of the organ.
The first area may be a larger area in the original image comprising the region of interest, which is larger than the area covered by the region of interest and smaller than the original image.
And step S120, intercepting a region to be registered in the current image according to the position of the region of interest in the current image.
Specifically, according to the position of the region of interest in the current image, a certain area is cut out at the position by using a shape larger than the region of interest as a region to be registered, so that the region to be registered contains the region of interest.
Step S130, registering the region of interest in the original image with the region to be registered to obtain a deformation matrix.
The registration process is usually performed based on the gray value of the pixel point of the image, and the purpose of the registration is to correspond the pixel point on the current image to the pixel point on the original image, so that the gray value of the corresponding pixel point is as close as possible. In this embodiment, a deformation matrix is obtained by performing deformation registration on the region of interest in the original image and the region to be registered in the current image. And the deformation matrix records the transformation relation between the pixel points in the region of interest and the pixel points in the region to be registered.
In one embodiment, when the region of interest in the original image is registered with the region to be registered, the region of interest in the original image may be directly registered with the region to be registered, or a larger region (e.g., the first region) in the original image may be registered with the region to be registered, where the larger region includes the region of interest.
And step S140, generating a corresponding basic sketch in the current image according to the deformation matrix and the basic sketch data of the region of interest in the original image.
The basic sketching data in the original image can be stored in a matrix mode independently, the deformation matrix is applied to the basic sketching data in the original image, so that the basic sketching data in the current image are converted into the basic sketching data in the current image, and the basic sketching can be formed in the current image according to the basic sketching data in the current image.
In one embodiment, the method for delineating the region of interest in the image further comprises the steps of:
and step S150, acquiring a generation rule for generating an auxiliary sketch according to the basic sketch in the original image.
The generating rule comprises the operations of merging, intersecting, deducting or zooming the basic sketches and the like.
And step S160, according to the generation rule, generating a corresponding auxiliary sketch according to the basic sketch in the current image.
In the method for delineating the region of interest in the image, the region to be registered is intercepted from the current image, and the region of interest of the original image is registered with the region to be registered of the current image, so that the interference of pixels outside the region to be registered on the registration is avoided, and the accuracy of the generation of the new delineation is improved.
In one embodiment, as shown in fig. 2, in step S130, the registering the region of interest in the original image with the region to be registered to obtain a deformation matrix includes:
step S131, acquiring a characteristic value of the region of interest from the original image to the current image, wherein the characteristic value represents the change trend.
The trend may be different for different organs within the test subject. In some embodiments, the trend of change of the region of interest includes at least one of a location trend, a volume trend, and a shape trend of the organ.
In general, the original image and the current image are images acquired by a detection object at different times, so that the same organ may have differences between the original image and the current image, such as changes in at least one of the position, shape, size, etc. of the organ, but the changes are limited by the characteristics of the organ. The characteristics of different organs may differ. Thus, in some embodiments, a feature value representing a trend of change of the organ may be acquired from the identification of the organ. Alternatively, the identifier of the organ may be a name, a type, and the like of the organ, and the change trend of the organ may be determined according to the name and/or the type of the organ, that is, a characteristic value representing the change trend of the organ is determined. For example, the head and neck organs may change in shape, but not in volume, and not in position relative to the skull, where the volume of the head and neck organs and/or the position of the head and neck organs relative to the skull may be used as constraints. For example, the position of an organ such as the stomach or the bladder is not changed, but the volume is changed because it is expanded or contracted, and in such a case, the position information thereof can be acquired as the constraint. For example, the shape and volume of an eyeball, a bone, a spinal cord, or the like are not changed, but the position may be changed, and thus the shape and/or volume information may be used as a constraint.
In some embodiments, a feature value representing a trend of change of the organ may be acquired from the neural network. Specifically, the basic delineation data (the same organ) of image samples of at least two time points of a plurality of patients are collected and input into a neural network model, the change characteristic values of the organ are obtained through training of the neural network model, the characteristic values can represent the change trend of the organ, and the characteristic values of the organ representing the change trend are recorded.
And S132, taking the characteristic value representing the change trend as a registration constraint condition, and registering the interest area in the original image and the area to be registered to obtain a deformation matrix.
Specifically, the trained feature value representing the change trend of the organ may be used as a registration constraint condition, and the region of interest in the original image and the region to be registered are registered to obtain a deformation matrix. The image registration needs to go through an iterative process, in the process, the change trend of the organ is considered, in the optimization process, the pixel points meet a specific characteristic equation, and parameters in the equation can be given according to a characteristic value determined by the organ identification or a characteristic value obtained by the neural network training, so that the registration accuracy can be improved. Deformation registration is a technique known in the art and will not be described in detail herein.
In one embodiment, in step S120, the intercepting a region to be registered in the current image according to the position of the region of interest in the current image includes: and intercepting a region enclosed according to a regular shape in the current image according to the position of the region of interest in the current image, wherein the region enclosed according to the regular shape comprises the region of interest. Specifically, the regular shape is sized to fit around the organ. Wherein the regular shapes include circles and rectangles.
In one embodiment, as shown in fig. 3, there is provided a method of delineating a region of interest in an image, comprising the steps of:
step S310, acquiring a position of the region of interest in the original image in the current image.
Specifically, the original image includes at least one region of interest, and the current image includes a region of interest corresponding to the original image. The region of interest corresponds to a delineation region of an organ region. In some embodiments of the invention, the names of the organ and the region of interest may be replaced.
Wherein, the acquiring the position of the region of interest in the original image in the current image comprises: rigidly registering the original image and the current image to obtain the position of the region of interest in the original image in the current image; or intercepting a first region containing the region of interest from an original image, and rigidly registering the first region with the current image to acquire the position of the region of interest in the current image; or the interested region in the original image is rigidly registered with the current image so as to acquire the position of the interested region in the current image.
The region of interest corresponding to the region of interest in the original image can be found in the current image, so that the approximate position of the region of interest in the current image is found.
And rigid registration is to find the approximate position of the region of interest in the current image by translating or rotating the region of interest in the original image up and down, left and right, and take the approximate position as the reference position of the region of interest in the current image.
The basic delineation is a delineation obtained by a doctor or a physicist through manual drawing according to a CT image in a self-adaptive radiotherapy planning system, and is generally a delineation of an important organ or a tumor; the auxiliary delineation is generally based on basic delineation, and new delineations are obtained after the basic delineation is subjected to operations such as merging, intersection, subtraction or zooming and the like, and are used for optimizing the planning of radiotherapy. The position and the area of the organ in the original image can be found according to the basic delineation of the organ.
The first area may be a larger area in the original image comprising the region of interest, which is larger than the area covered by the region of interest and smaller than the original image.
Step S320, intercepting a second region in the current image according to the position of the region of interest in the current image.
Specifically, according to the position of the region of interest in the current image, a certain area is cut out at the position by using a shape larger than the region of interest as a second area, so that the second area contains the region of interest.
And step S330, generating a corresponding basic sketch in the current image by an organ automatic segmentation method according to the second region.
Specifically, in the method for automatically segmenting the organ, the size of the image pixel can be known according to the attribute value of the CT image, and the CT image can be divided into a plurality of organ regions according to the gray value because the gray values of the organs in the CT image are different, and each organ region represents the corresponding organ. The base delineation may be automatically generated based on the edges of the organ region.
The method for automatically segmenting the organ can be realized by adopting a known automatic organ segmentation algorithm, and the automatic organ segmentation algorithm stores a Region of Interest (ROI) as self-defined internal data into a database to perform automatic segmentation of relevant organs such as skin. The automatic organ segmentation means that the positions of organs, such as the left lung, the heart, the spine and the like, are preliminarily positioned according to a human body model, and then the required organs are marked by applying algorithms such as edge extraction in image processing and the like according to the difference of different organ image values (such as CT values) in a three-dimensional volume data file. In an embodiment of the invention, this step may be implemented using known organ automatic segmentation algorithms, which are not expanded here.
In one embodiment, in step S320, the intercepting the second region in the current image according to the position of the region of interest in the current image includes: and intercepting a region enclosed according to a regular shape in the current image according to the position of the region of interest in the current image, wherein the region enclosed according to the regular shape comprises the region of interest. Specifically, the regular shape is sized to just wrap around the region of interest. Wherein the regular shapes include circles and rectangles.
In one embodiment, the method for delineating the region of interest in the image further includes:
and S340, acquiring a generation rule for generating the auxiliary sketch according to the basic sketch in the original image.
The generating rule comprises the operations of merging, intersecting, deducting or zooming the basic sketches and the like.
And S350, generating a corresponding auxiliary sketch according to the basic sketch in the current image according to the generation rule.
According to the method for delineating the region of interest in the image, the basic delineation corresponding to the original image is generated in the current image by automatically segmenting the organ region, so that the accuracy and efficiency of the basic delineation generation in the current image are improved.
In one embodiment, a method for delineating a plurality of regions of interest in a medical image, wherein for each region of interest a corresponding base delineation is generated in the current image separately according to the method of the above-described embodiment.
The original image may include a plurality of organs and basic delineations of the organs, and each basic delineation may generate a corresponding basic delineation in the current image according to the method for delineating the region of interest in the image in the above embodiment.
In some embodiments, when the image includes a plurality of regions of interest, since there may be mutual influence between the regions of interest, when the plurality of regions of interest are delineated according to the method of any embodiment of the present invention (for example, fig. 1 and/or fig. 2 described above), priorities may be set for the plurality of regions of interest. Preferably, the higher the priority that is less susceptible to other regions of interest, the lower the priority that is more susceptible. For example, regions of interest that change spontaneously are the highest priority, and regions of interest that are affected by changes in other regions of interest are lower priority. For example, bone is generally a spontaneously changing organ first, and is easy to register, with highest priority; secondly, the bladder, the heart and the stomach belong to spontaneously changed organs, and the priority is higher; secondly, the large intestine and the small intestine belong to organs which are easily affected by other organs, and the priority is low; finally, the target region is set to have the lowest priority because it needs to be judged in combination with other organs. The plurality of regions of interest may be delineated in the order of priority as described above.
In the process of delineating the region of interest, the registration result of the region of interest with high priority can be used as a constraint of the region of interest with low priority. For example, the delineation result of the region of interest with high priority serves as a constraint of the region of interest with low priority. For example, the first region of interest affects the second region of interest, and a base delineation of the first region of interest is first generated in the current image using the method of any embodiment of the present invention. When the second region of interest is sketched, the range of the first region of interest in the current image is considered, and the second region of interest obtained by sketching is prevented from being overlapped with the sketched first region of interest. Or, since the relative position of the first region of interest and the second region of interest is fixed, when the second region of interest is delineated, the relative position of the delineated first region of interest needs to be kept fixed. As another example, the registration matrix of the region of interest with high priority may be used as a constraint of the region of interest with low priority. Illustratively, the first region of interest is attached to the boundary of the second region of interest, the boundary of the first region of interest changes from the original image to the current image according to the deformation matrix, and the boundary of the second region of interest from the original image to the current image should be processed correspondingly.
In the above embodiment, for an image including a plurality of regions of interest, each region of interest may be independently delineated according to the method described in any embodiment of the present invention, so as to avoid interference of similar gray values between different regions.
In some embodiments, the delineation of a plurality of different regions of interest can be processed in parallel, thereby saving delineation time and improving efficiency.
It should be understood that although the various steps in the flow charts of fig. 1-3 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-3 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 4, there is provided an apparatus for delineating a region of interest in an image, comprising: a location acquisition module 410, an interception module 420, a registration module 430, and a base delineation generation module 440, wherein:
and a position obtaining module 410, configured to obtain a position of the region of interest in the original image in the current image.
And the intercepting module 420 is configured to intercept the region to be registered in the current image according to the position of the region of interest in the current image.
And the registration module 430 is configured to register the region of interest in the original image with the region to be registered, so as to obtain a deformation matrix.
A basic sketch generating module 440, configured to generate a corresponding basic sketch in the region in the current image according to the deformation matrix and the basic sketch data of the region of interest in the original image.
In one embodiment, the apparatus for delineating a region of interest in the image further comprises: the auxiliary drawing generation rule acquisition module is used for acquiring a generation rule for generating an auxiliary drawing according to the basic drawing in the original image; and the auxiliary sketch generation module is used for generating a corresponding auxiliary sketch according to the basic sketch in the current image according to the generation rule.
In one embodiment, the registration module 430 includes: the change trend acquisition unit is used for acquiring a characteristic value of the interesting region from an original image to a current image, wherein the characteristic value represents the change trend; and the deformation matrix obtaining unit is used for taking the characteristic value representing the change trend as a registration constraint condition, and registering the interest area in the original image and the area to be registered to obtain a deformation matrix.
In one embodiment, the intercepting module 420 is specifically configured to intercept, in the current image, a region enclosed according to a regular shape according to a position of the region of interest in the current image, where the region enclosed according to the regular shape includes the region of interest. Specifically, the regular shape is sized to fit around the organ. Wherein the regular shapes include circles and rectangles.
In another embodiment, as shown in fig. 5, there is provided an apparatus for delineating a region of interest in an image, comprising: a location acquisition module 510, an interception module 520, and a base delineation generation module 530, wherein:
the position obtaining module 510 is configured to obtain a position of the region of interest in the original image in the current image.
A clipping module 520, configured to clip the second region in the current image according to the position of the region of interest in the current image.
A basic sketch generating module 530, configured to generate a corresponding basic sketch in the current image according to the second region by using an organ automatic segmentation method.
In one embodiment, the intercepting module 520 is specifically configured to intercept, in the current image, a region enclosed according to a regular shape according to a position of the region of interest in the current image, where the region enclosed according to the regular shape includes the region of interest. Specifically, the regular shape is sized to fit around the organ. Wherein the regular shapes include circles and rectangles.
In one embodiment, the apparatus for delineating a region of interest in the image further comprises: the auxiliary drawing generation rule acquisition module is used for acquiring a generation rule for generating an auxiliary drawing according to the basic drawing in the original image; and the auxiliary sketch generation module is used for generating a corresponding auxiliary sketch according to the basic sketch in the current image according to the generation rule.
For the specific definition of the device for delineating the region of interest in the image, reference may be made to the above definition of the method for delineating the region of interest in the image, and details are not described here. The modules in the apparatus for delineating the region of interest in the image can be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 6. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing the CT image data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of delineating a region of interest in an image.
Those skilled in the art will appreciate that the architecture shown in fig. 6 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
acquiring the position of an interested area in an original image in a current image;
intercepting a region to be registered in the current image according to the position of the region of interest in the current image;
registering the region of interest in the original image with the region to be registered to obtain a deformation matrix;
and generating a corresponding basic sketch in the current image according to the deformation matrix and the basic sketch data of the region of interest in the original image.
In one embodiment, the processor is a parallel processor, which can execute the method for delineating the region of interest in the image in the above embodiments in parallel for a plurality of regions of interest.
In one embodiment, the processor, when executing the computer program, further performs the steps of: acquiring a generation rule for generating an auxiliary sketch according to the basic sketch in the original image; and generating a corresponding auxiliary sketch according to the basic sketch in the current image according to the generation rule.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
acquiring the position of an interested area in an original image in a current image;
intercepting a region to be registered in the current image according to the position of the region of interest in the current image;
registering the region of interest in the original image with the region to be registered to obtain a deformation matrix;
and generating a corresponding basic sketch in the current image according to the deformation matrix and the basic sketch data of the region of interest in the original image.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring a generation rule for generating an auxiliary sketch according to the basic sketch in the original image; and generating a corresponding auxiliary sketch according to the basic sketch in the current image according to the generation rule.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (12)
1. A method of delineating a region of interest in an image, the method comprising:
acquiring the position of an interested area in an original image in a current image;
intercepting a region to be registered in the current image according to the position of the region of interest in the current image;
registering the region of interest in the original image with the region to be registered to obtain a deformation matrix;
generating a corresponding basic sketch in the current image according to the deformation matrix and basic sketch data of the region of interest in the original image;
registering the region of interest in the original image with the region to be registered to obtain a deformation matrix, including:
acquiring a characteristic value of the region of interest from an original image to a current image, wherein the characteristic value represents a change trend; the obtaining of the characteristic value representing the variation trend comprises the following steps: acquiring the characteristic value representing the change trend according to a neural network, or acquiring the characteristic value representing the change trend according to the identifier of the organ corresponding to the region of interest;
and taking the characteristic value representing the change trend as a registration constraint condition, and registering the region of interest in the original image and the region to be registered to obtain a deformation matrix.
2. The method of claim 1, wherein the acquiring the position of the region of interest in the original image at the current image comprises:
rigidly registering the original image and the current image to obtain the position of the region of interest in the original image in the current image; or
Intercepting a first region containing the region of interest from an original image, and rigidly registering the first region with a current image to acquire the position of the region of interest in the current image; or
And carrying out rigid registration on the region of interest in the original image and the current image so as to acquire the position of the region of interest in the current image.
3. The method of claim 1, further comprising:
acquiring a generation rule for generating an auxiliary sketch according to the basic sketch in the original image;
and generating a corresponding auxiliary sketch according to the basic sketch in the current image according to the generation rule.
4. The method of claim 1, wherein the trend of change comprises at least one of a trend of change in position of the region of interest, a trend of change in volume of the region of interest, and a trend of change in shape of the region of interest.
5. The method according to claim 1, wherein the intercepting a region to be registered in the current image according to the position of the region of interest in the current image comprises:
and intercepting a region enclosed according to a regular shape in the current image according to the position of the region of interest in the current image, wherein the region enclosed according to the regular shape comprises the region of interest.
6. The method according to claim 1, wherein the organ includes a stomach or a bladder, and the characteristic value indicating the trend of change includes position information of the organ;
alternatively, the organ includes an eyeball, a bone, or a spinal cord, and the characteristic value indicating the trend of change includes shape information and/or volume information of the organ.
7. The method of claim 1, wherein the obtaining the characteristic value representing the trend according to the neural network comprises:
acquiring more than two groups of image sample basic sketching data; the group of image sample basic delineation data comprises image sample basic delineation data of at least two time points of the same object;
and inputting the basic sketching data of the image sample into a neural network for training to obtain the characteristic value representing the change trend.
8. A method of delineating a plurality of regions of interest in a medical image, wherein for each of said regions of interest a corresponding base delineation is generated in the current image in accordance with the method of any one of claims 1-7 separately.
9. The method of claim 8, further comprising prioritizing the plurality of regions of interest, the registration result of a region of interest with a higher priority serving as a constraint for a region of interest with a lower priority.
10. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 9 when executing the computer program.
11. Computer device according to claim 10, wherein the processor is a parallel processor which can perform the method of any of claims 1 to 9 in parallel for a plurality of regions of interest.
12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 9.
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 CN109712186A (en) | 2019-05-03 |
| CN109712186B true 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) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN112419338B (en) * | 2020-12-08 | 2021-12-07 | 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109712186A (en) | 2019-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109872333B (en) | Medical image segmentation method, medical image segmentation device, computer equipment and storage medium | |
| JP7030050B2 (en) | Pseudo-CT generation from MR data using tissue parameter estimation | |
| JP6567179B2 (en) | Pseudo CT generation from MR data using feature regression model | |
| EP3123443B1 (en) | Method and device for generating one or more computer tomography images based on magnetic resonance images with the help of tissue class separation | |
| CN111161270A (en) | Blood vessel segmentation method for medical image, computer device and readable storage medium | |
| EP2715663B1 (en) | Apparatus for generating assignments between image regions of an image and element classes | |
| CN109472835B (en) | Method for processing medical image data and image processing system for medical image data | |
| CN106462974B (en) | Parameter optimization for segmenting images | |
| CN109712186B (en) | Method, computer device and storage medium for delineating a region of interest in an image | |
| CN111724389B (en) | Method, device, storage medium and computer equipment for segmenting CT image of hip joint | |
| CN110490841B (en) | Computer-aided image analysis method, computer device and storage medium | |
| CN112200780B (en) | Bone tissue positioning method, device, computer equipment and storage medium | |
| CN111192268A (en) | Medical image segmentation model construction method and CBCT image bone segmentation method | |
| CN111462139A (en) | Medical image display method, medical image display device, computer equipment and readable storage medium | |
| CN111568451A (en) | Exposure dose adjusting method and system | |
| CN113516624A (en) | Determination of puncture forbidden zone, path planning method, surgical system and computer equipment | |
| CN111899273A (en) | Image segmentation method, computer device and storage medium | |
| CN111160441B (en) | Classification method, computer device, and storage medium | |
| CN111161240A (en) | Blood vessel classification method, computer device and readable storage medium | |
| CN111179373A (en) | Medical image bone removal model construction method and bone information removal method | |
| CN114187320B (en) | Spine CT image segmentation method and spine imaging identification method and device | |
| CN116168097A (en) | Method, device, equipment and medium for constructing CBCT sketching model and sketching CBCT image | |
| CN113962957A (en) | Medical image processing method, bone image processing method, device and equipment | |
| CN113962938A (en) | Image segmentation method and device, computer equipment and readable storage medium | |
| CN110766652B (en) | Network training method, device, segmentation method, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant after: Shanghai Lianying Medical Technology Co., Ltd Address before: 201807 Shanghai City, north of the city of Jiading District Road No. 2258 Applicant before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |