Tumor motion model establishment method and device and storage medium

Abstract

The invention provides a tumor motion model establishment method and device and a storage medium, and relates to the technical field of radiotherapy. The method comprises the following steps: acquiring a projection image sequence of a target object in a positioning stage, wherein the projection image sequence comprises a plurality of projection images containing tumors; for each projection image in the projection image sequence, determining a first position of a tumor in the projection image; and determining a motion model of the tumor based on the first position of the tumor in each projection image in the projection image sequence and the respiration signal of the target object. The tumor motion model can be constructed by using the projection image sequence in the positioning stage, so that additional projection images are prevented from being collected again before treatment is started, the treatment waiting time is effectively shortened, and the efficiency of the whole treatment process is improved.

Description

Technical Field

[0001] This application relates to the field of radiotherapy technology, and in particular, to a method, device, and storage medium for establishing a tumor motion model. Background Art

[0002] During radiotherapy, accurately focusing the radiation beam on the tumor is the key to achieving good treatment effects and reducing damage to surrounding healthy tissues. However, respiratory motion poses a significant challenge. When the patient breathes, the tissues of these body parts move accordingly, which in turn causes the tumor to displace. This displacement makes it difficult for the originally precisely set radiation beam to continuously and accurately irradiate the tumor. To solve the problems caused by respiratory motion, a respiratory motion model is introduced in tumor tracking technology to achieve real-time and precise positioning of tumor displacement caused by breathing.

[0003] Currently, when establishing a respiratory motion model, it is necessary to re-acquire additional projection images before the start of treatment to determine the moving position of the tumor, and then combine breathing for modeling, which additionally increases the treatment waiting time and reduces the efficiency of the entire treatment process. Summary of the Invention

[0004] This application provides a method, device, and storage medium for establishing a tumor motion model, which can utilize the sequence of projection images in the setup stage to construct a motion model of the tumor, thereby avoiding re-acquiring additional projection images before the start of treatment, effectively reducing the treatment waiting time, and improving the efficiency of the entire treatment process.

[0005] To achieve the above object, this application adopts the following technical solutions:

[0006] In a first aspect, this application provides a method for establishing a tumor motion model, the method including: obtaining a sequence of projection images of a target object in the setup stage, where the sequence of projection images includes multiple projection images containing a tumor; for each projection image in the sequence of projection images, determining a first position of the tumor in the projection image; based on the first position of the tumor in each projection image in the sequence of projection images and the respiratory signal of the target object, determining a motion model of the tumor.

[0007] In combination with the above first aspect, in a possible implementation manner, for each projection image in the sequence of projection images, determining a first position of the tumor in the projection image includes: during the process of continuously obtaining the sequence of projection images of the target object in the setup stage, for each obtained projection image, determining a first position of the tumor in the projection image.

[0008] Correspondingly, the above method for determining the motion model of the tumor based on the first position of the tumor in each projection image in the projection image sequence and the respiration signal of the target object includes: after acquiring the projection image sequence, determining the motion model of the tumor based on the first position of the tumor in each projection image in the projection image sequence and the respiration signal of the target object.

[0009] Combined with the above first aspect, in a possible implementation manner, when the positioning of the target object is completed in the positioning stage, the motion model of the tumor has been established.

[0010] Combined with the above first aspect, in a possible implementation manner, the above method for determining the first position of the tumor in the projection image includes: acquiring the initial position of the tumor; performing registration processing on two adjacent projection images in the projection image sequence in sequence to determine the displacement amount of the tumor in the two adjacent projection images; and determining the first position of the tumor in the projection image based on the initial position of the tumor and the displacement amount of the tumor in the two adjacent projection images in the projection image sequence.

[0011] Combined with the above first aspect, in a possible implementation manner, the above method for acquiring the initial position of the tumor includes: acquiring a first reference projection image of the target object, where the first reference projection image is an image generated by digitally projecting and reconstructing a reference image of the target object at the imaging angle of the first projection image in the projection image sequence; and registering the first projection image with the first reference projection image to obtain the initial position of the tumor.

[0012] Combined with the above first aspect, in a possible implementation manner, the above method for performing registration processing on two adjacent projection images in the projection image sequence in sequence to determine the displacement amount of the tumor in the two adjacent projection images includes: performing a first registration process on the two adjacent projection images; performing an expansion process on the tumor region after the first registration to generate a tumor region template; and based on the tumor region template, performing a second registration process on the two adjacent projection images to determine the displacement amount of the tumor in the two adjacent projection images.

[0013] Combined with the above first aspect, in a possible implementation manner, the above method for performing an expansion process on the tumor region after the first registration to generate a tumor region template includes: determining, based on the gray value of the tumor region after the first registration, that the region in the projection image with the gray value within a preset interval is the tumor region template; and the preset interval is determined based on the gray value of the tumor region.

[0014] Combined with the above first aspect, in a possible implementation manner, the method further includes: performing error correction processing on the displacement amount of the tumor in two adjacent projection images to obtain a corrected displacement amount.

[0015] Among them, error correction processing is performed on the displacement amount of the tumor in two adjacent projection images, including: determining the movement trend of the tumor based on the projection images before two adjacent projection images in the projection image sequence, and performing error correction processing on the displacement amount of the tumor when the displacement amount of the tumor does not conform to the movement trend of the tumor; and / or, performing noise filtering processing on the displacement amount of the tumor based on the noise filtering method corresponding to the system noise characteristics, where the system noise characteristics are signal characteristics that interfere with the displacement amount of the tumor generated during the determination of the displacement amount of the tumor.

[0016] Combined with the first aspect above, in a possible implementation manner, after determining the first position of the tumor in each projection image of the projection image sequence for each projection image in the projection image sequence, the method further includes: for the target projection image that is K projection images apart in the projection image sequence, obtaining the second reference projection image corresponding to the target projection image, where the second reference projection image is an image generated by digitally projecting and reconstructing the reference image of the target object at the imaging angle of the target projection image; K is a positive integer; performing registration processing on the target projection image and the second reference projection image to determine the second position of the tumor in the target projection image; and based on the deviation degree between the first position and the second position, using a correction method corresponding to the deviation degree to correct the first position to obtain the corrected first position of the tumor.

[0017] Combined with the first aspect above, in a possible implementation manner, the above-mentioned correction of the first position using a correction method corresponding to the deviation degree includes: corresponding to the deviation degree being less than the first threshold, the first position is not corrected; corresponding to the deviation degree being greater than the second threshold, the first position is replaced with the second position, and the first position corresponding to the projection image after the target projection image is corrected; the second threshold is greater than the first threshold; corresponding to the deviation degree being within the interval where the first threshold and the second threshold are located, the first position is replaced with the average value of the first position and the second position.

[0018] In a second aspect, the present application provides a tumor motion model establishment device, which includes: a communication unit and a processing unit; the communication unit is used to obtain a projection image sequence of the target object during the positioning stage, and the projection image sequence includes multiple projection images containing tumors; the processing unit is used to determine the first position of the tumor in each projection image of the projection image sequence for each projection image in the projection image sequence; the processing unit is further used to determine the motion model of the tumor based on the first position of the tumor in each projection image of the projection image sequence and the breathing signal of the target object.

[0019] Combined with the second aspect above, in a possible implementation, the processing unit is specifically configured to: during the process of continuously acquiring the projection image sequence of the target object in the positioning stage, for each acquired projection image, determine the first position of the tumor in the projection image; after completing the acquisition of the projection image sequence, based on the first position of the tumor in each projection image in the projection image sequence and the breathing signal of the target object, determine the motion model of the tumor.

[0020] Combined with the second aspect above, in a possible implementation, when the positioning of the target object is completed in the positioning stage, the motion model of the tumor has been established.

[0021] Combined with the second aspect above, in a possible implementation, the processing unit is specifically configured to: obtain the initial position of the tumor through the communication unit; perform registration processing on two adjacent projection images in the projection image sequence in sequence to determine the displacement amount of the tumor in the two adjacent projection images; based on the initial position of the tumor and the displacement amount of the tumor in the two adjacent projection images in the projection image sequence, determine the first position of the tumor in the projection image.

[0022] Combined with the second aspect above, in a possible implementation, the processing unit is specifically configured to: obtain the first reference projection image of the target object through the communication unit, where the first reference projection image is an image generated by digitally projecting and reconstructing the reference image of the target object at the imaging angle of the first projection image in the projection image sequence; register the first projection image with the first reference projection image to obtain the initial position of the tumor.

[0023] Combined with the second aspect above, in a possible implementation, the processing unit is specifically configured to: perform first registration processing on two adjacent projection images; perform outer expansion processing on the tumor region after the first registration to generate a tumor region template; based on the tumor region template, perform second registration processing on the two adjacent projection images to determine the displacement amount of the tumor in the two adjacent projection images.

[0024] Combined with the second aspect above, in a possible implementation, the processing unit is specifically configured to: based on the gray value of the tumor region after the first registration, determine that the region in the projection image with the gray value within the preset interval is the tumor region template; the preset interval is determined based on the gray value of the tumor region.

[0025] Combined with the second aspect above, in a possible implementation, the processing unit is further configured to: perform error correction processing on the displacement amount of the tumor in two adjacent projection images to obtain the corrected displacement amount; wherein, performing error correction processing on the displacement amount of the tumor in two adjacent projection images includes: determining the movement trend of the tumor based on the projection images before the two adjacent projection images in the projection image sequence, and performing error correction processing on the displacement amount of the tumor when the displacement amount of the tumor does not conform to the movement trend of the tumor; and / or, performing noise filtering processing on the displacement amount of the tumor based on the noise filtering method corresponding to the system noise characteristics; wherein the system noise characteristics are signal characteristics that cause interference to the displacement amount of the tumor during the determination of the displacement amount of the tumor.

[0026] Combined with the second aspect above, in a possible implementation, after determining the first position of the tumor in each projection image of the projection image sequence, the processing unit is further configured to: for the target projection image that is K projection images apart in the projection image sequence, obtain the second reference projection image corresponding to the target projection image, where the second reference projection image is an image generated by digitally projecting and reconstructing the reference image of the target object at the imaging angle of the target projection image; K is a positive integer; perform registration processing on the target projection image and the second reference projection image to determine the second position of the tumor in the target projection image; and based on the deviation degree between the first position and the second position, adopt a correction method corresponding to the deviation degree to correct the first position to obtain the corrected first position of the tumor.

[0027] Combined with the second aspect above, in a possible implementation, the processing unit is specifically configured to: corresponding to the deviation degree being less than the first threshold, not correct the first position; corresponding to the deviation degree being greater than the second threshold, replace the first position with the second position and correct the first position corresponding to the projection images after the target projection image; the second threshold is greater than the first threshold; corresponding to the deviation degree being within the interval where the first threshold and the second threshold are located, replace the first position with the average value of the first position and the second position.

[0028] In a third aspect, the present application provides an electronic device, which includes: a processor and a memory configured to store instructions executable by the processor; wherein, the processor is configured to execute the instructions to implement the tumor motion model establishment method described in the first aspect and any possible implementation manner of the first aspect.

[0029] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions are stored, and when the instructions are run on a terminal, the terminal is caused to execute the tumor motion model establishment method described in the first aspect and any possible implementation manner of the first aspect.

[0030] In a fifth aspect, the present application provides a computer program product containing instructions, which, when the computer program product runs on a computer, cause the computer to execute the method for establishing a tumor motion model described in the first aspect and any possible implementation manner of the first aspect.

[0031] In a sixth aspect, the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is configured to run a computer program or instructions to implement the method for establishing a tumor motion model described in the first aspect and any possible implementation manner of the first aspect.

[0032] Specifically, the chip provided in the present application further includes a memory for storing the computer program or instructions.

[0033] It should be noted that the above computer instructions may be stored in whole or in part on a computer-readable storage medium. Among them, the computer-readable storage medium may be packaged together with the processor of the device or separately packaged with the processor of the device, and the present application does not make any limitation in this regard.

[0034] In a seventh aspect, the present application provides a tumor motion model establishment system, including: an image acquisition device, a respiration detection device, and an image computer device, wherein the image computer device is configured to execute the method for establishing a tumor motion model described in the first aspect and any possible implementation manner of the first aspect.

[0035] The descriptions of the second to seventh aspects in the present application may refer to the detailed description of the first aspect; and, for the beneficial effects of the descriptions of the second to seventh aspects, reference may be made to the analysis of the beneficial effects of the first aspect, and details are not elaborated herein.

[0036] In the present application, the names of the above tumor motion model establishment devices do not constitute a limitation to the devices or functional modules themselves. In actual implementation, these devices or functional modules may appear under other names. As long as the functions of each device or functional module are similar to those of the present application and fall within the scope of the claims of the present application and equivalent technologies.

[0037] These aspects or other aspects of the present application will be more clearly understood in the following description.

[0038] The method for establishing a tumor motion model provided by this application first obtains a sequence of projection images of a target object in the positioning stage. The sequence of projection images includes multiple projection images containing tumors. Furthermore, for each projection image in the sequence of projection images, the first position of the tumor in the projection image is determined, and based on the first position of the tumor in each projection image in the sequence of projection images and the respiratory signal of the target object, the motion model of the tumor is determined. That is to say, when determining the motion model of the tumor in this application, the projection images in the positioning stage are effectively utilized, thereby avoiding re-acquiring additional projection images before the treatment starts, effectively reducing the treatment waiting time, and improving the efficiency of the entire treatment process. Brief Description of the Drawings

[0039] Figure 1 It is a schematic architecture diagram of a tumor motion model establishment system provided by an embodiment of this application;

[0040] Figure 2 It is a schematic architecture diagram of another tumor motion model establishment system provided by an embodiment of this application;

[0041] Figure 3 It is a flowchart of a method for establishing a tumor motion model provided by an embodiment of this application;

[0042] Figure 4 It is a flowchart of another method for establishing a tumor motion model provided by an embodiment of this application;

[0043] Figure 5 It is a schematic diagram of the coordinates of a projection image provided by an embodiment of this application;

[0044] Figure 6 It is a flowchart of another method for establishing a tumor motion model provided by an embodiment of this application;

[0045] Figure 7 It is a flowchart of another method for establishing a tumor motion model provided by an embodiment of this application;

[0046] Figure 8 It is a schematic structural diagram of a tumor motion model establishment device provided by an embodiment of this application;

[0047] Figure 9 It is a schematic hardware structure diagram of an electronic device provided by an embodiment of this application. Detailed Embodiments

[0048] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0049] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0050] The terms "first" and "second" in the specification and drawings of the present application are used to distinguish different objects or different treatments of the same object, rather than to describe the specific order of the objects.

[0051] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the present application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes other steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0052] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, using words such as "exemplary" or "for example" is intended to present relevant concepts in a specific manner.

[0053] In the description of the present application, unless otherwise specified, the meaning of "a plurality" refers to two or more.

[0054] During radiotherapy, accurately focusing the radiation beam on the tumor is the key to achieving good treatment effects and reducing damage to surrounding healthy tissues. However, respiratory motion poses a great challenge. When the patient breathes, the tissues of these body parts will move accordingly, which in turn causes tumors in the upper abdomen such as the lungs, liver, and pancreas to also displace. This displacement makes it difficult for the originally precisely set radiation beam to continuously and accurately irradiate the tumor. To solve the problems caused by respiratory motion, a respiratory motion model is introduced in tumor tracking technology to compensate for or predict the tumor displacement caused by breathing, so as to achieve real-time precise positioning of the tumor displacement caused by breathing.

[0055] Currently, when establishing a respiratory motion model, it is necessary to re-acquire additional projection images (e.g., KV images) before the start of treatment to determine the moving position of the tumor, and then model it in combination with respiration. This additionally increases the treatment waiting time and exposure dose, and reduces the efficiency of the entire treatment process.

[0056] Alternatively, currently, a method of obtaining a motion model of a tumor by registering and deforming the setup CBCT and the planned CT is also used, but this method has the problem of large data calculation and time consumption.

[0057] In view of this, the method for establishing a tumor motion model provided in this application first obtains a sequence of projection images of a target object in the setup stage, and the sequence of projection images includes a plurality of projection images containing the tumor. Then, for each projection image in the sequence of projection images, the first position of the tumor in the projection image is determined, and based on the first position of the tumor in each projection image in the sequence of projection images and the respiratory signal of the target object, the motion model of the tumor is determined. That is to say, when determining the motion model of the tumor in this application, the projection images in the setup stage are effectively utilized, thereby avoiding re-acquiring additional projection images before the start of treatment, effectively reducing the treatment waiting time and exposure dose, and improving the efficiency of the entire treatment process.

[0058] Moreover, in this application, after every K projection images, the first position of the tumor is corrected by referring to the reference projection image, which can effectively improve the accuracy of the tumor motion model while reducing the calculation amount.

[0059] Next, the implementation manners of the embodiments of this application will be described in detail with reference to the accompanying drawings of the specification.

[0060] It should be noted that the embodiments of this application can learn from or refer to each other. For example, for the same or similar steps, the method embodiments, system embodiments, and device embodiments can all refer to each other without limitation.

[0061] Figure 1 It is a schematic diagram of the architecture of a tumor motion model establishment system provided by an embodiment of this application. The tumor motion model establishment system may include: an image acquisition device 101, a respiration detection device 102, and an image computer device 103.

[0062] Among them, the image acquisition device 101 is connected to the image computer device 103 through a communication link, and the respiration detection device 102 is connected to the image computer device 103 through a communication link. This communication link can be a wired communication link or a wireless communication link, and this application does not make any limitations in this regard.

[0063] In some embodiments, the image acquisition device 101 is a device for acquiring the tumor site and surrounding normal tissues of a target object (such as a patient to be treated, an experimental subject, a phantom, etc.). In some embodiments, the image acquisition device 101 can be at least one of a cone-beam computed tomography (CBCT) device, a computed tomography (CT) device, and a magnetic resonance (MR) device, that is: the image acquisition device 101 can be a CBCT device, a CT device, or an MR device, and can also include any two of a CBCT device, a CT device, and an MR device. The image acquisition device 101 can also include a CBCT device, a CT device, and an MR device. The embodiments of the present application do not specifically limit the form of the image acquisition device 101.

[0064] See Figure 2 , the image acquisition device 101 can include a gantry 1011, an X-ray tube 1012, a detector 1013, and a support device 1014. Among them, the detector 1013 is connected to the image computer device 103 through a communication link.

[0065] Among them, the gantry 1011 can be a rotatable gantry. The X-ray tube 1012 can emit imaging rays, such as kilovolt (KV)-level X-rays. The detector 1013 can be a detection plate facing the X-ray tube 1012, such as an X-ray detection plate. The support device 1014 is used to support and move the target object and can be a treatment couch.

[0066] In some embodiments, when the target object is on the support device 1014, the rotation of the gantry 1011 can drive the X-ray tube 1012 to project 360 degrees around the target object. After the imaging rays pass through the target object, they can be projected onto the detector 1013. At this time, the detector 1013 can collect the projection data after the projection of the X-ray tube 1012. Furthermore, after collecting a sequence of projection images (for example, projection data of multiple projections), a medical image (such as a CBCT image) of the target object can be obtained through data reconstruction.

[0067] In some embodiments, the respiration detection device 102 is used to detect the respiration signal of the target object.

[0068] Optionally, as Figure 2 shown, the respiration detection device 102 can include an optical camera 1021 and at least one optical marker 1022 disposed on the chest body surface of the target object. The optical camera 1021 is connected to the image computer device 103 through a communication link.

[0069] Exemplarily, the optical camera 1021 may be an infrared camera. Correspondingly, the optical marker 1022 may be an infrared marker, or may be other types of optical cameras and adapted optical markers. The embodiments of the present application do not specifically limit the form of the respiration detection device 102.

[0070] In some embodiments, the imaging computer device 103 is a computer device with a graphical user interface (GUI). The computer device includes: one or more processors, a memory, and one or more applications.

[0071] Exemplarily, the imaging computer device 103 may include an image guidance system (IGS) application. The processor of the imaging computer device 103 executes the IGS application to achieve: obtaining a sequence of projection images of the target object in the positioning stage, where the sequence of projection images includes multiple projection images containing tumors; for each projection image in the sequence of projection images, determining a first position of the tumor in the projection image; based on the first position of the tumor in each projection image in the sequence of projection images and the respiration signal of the target object, determining a motion model of the tumor.

[0072] In the embodiments of the present application, the imaging computer device 102 may be an independent physical server, or a server cluster or distributed file system composed of multiple physical servers, or at least one of cloud servers providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks, and big data or artificial intelligence platforms. The embodiments of the present application do not limit this.

[0073] In some embodiments, the number of the above imaging computer devices 102 may be more or less. The embodiments of the present application do not limit this. Of course, the imaging computer device 102 may also include other functions to provide more comprehensive and diverse services.

[0074] In other embodiments, the imaging computer device 102 may also be a general computer device or a special computer device. In specific implementations, the computer device may be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, an embedded device, etc. The embodiments of the present application do not limit the type of the computer device.

[0075] Above, the tumor motion model establishment system in the embodiments of the present application has been introduced.

[0076] The method for establishing a tumor motion model in the embodiments of the present application can be applied to the above-mentioned tumor motion model establishment system. Hereinafter, through Figures 3 - 7 , the method for establishing a tumor motion model will be described in detail.

[0077] Figure 3 FIG. is a flowchart of a method for establishing a tumor motion model provided by an embodiment of the present application. As Figure 3 shown, the method includes the following S301-S303.

[0078] S301. Obtain a sequence of projection images of the target object in the positioning stage.

[0079] Among them, the sequence of projection images includes a plurality of projection images containing tumors.

[0080] In a possible implementation manner, a sequence of projection images of the target object is continuously obtained in the positioning stage. In this way, it is convenient to construct a motion model of the tumor according to the continuously obtained sequence of projection images during the positioning stage, so as to improve the model construction efficiency and reduce the treatment waiting time.

[0081] S302. For each projection image in the sequence of projection images, determine the first position of the tumor in the projection image.

[0082] In a possible implementation manner, the implementation timing of S302 is: during the process of continuously obtaining a sequence of projection images of the target object in the positioning stage, for each obtained projection image, determine the first position of the tumor in the projection image. In this way, the time of the target object in the positioning stage can be effectively utilized, so as to quickly determine the first position of the tumor in the projection image, and then quickly construct a tumor motion model.

[0083] In another possible implementation manner, the implementation process of S302 includes: first obtain the initial position of the tumor, and perform registration processing on two adjacent projection images in the sequence of projection images in turn to determine the displacement amount of the tumor in the two adjacent projection images; then, according to the initial position of the tumor and the displacement amount of the tumor in the two adjacent projection images, determine the first position of the tumor in the projection image.

[0084] Specifically, for the specific implementation solution for determining the first position of the tumor in the projection image, refer to the embodiments shown in S401-S403, which will not be elaborated here.

[0085] S303. Based on the first position of the tumor in each projection image in the sequence of projection images and the respiratory signal of the target object, determine the motion model of the tumor.

[0086] In a possible implementation, corresponding to S302, during the process of continuously acquiring the projection image sequence of the target object in the positioning stage, for each acquired projection image, the first position of the tumor in the projection image is determined. Correspondingly, the implementation process of S303 can be: after completing the acquisition of the projection image sequence, based on the first position of the tumor in each projection image in the projection image sequence and the respiratory signal of the target object, the motion model of the tumor is determined.

[0087] It can be understood that in the above technical solution, since during the process of continuously acquiring the projection image sequence of the target object in the positioning stage, the positioning of the first position of the tumor in the projection image has been completed. That is to say, during the positioning stage, the positioning of the first position of the tumor in the last projection image in the projection image sequence has been completed. In this way, after completing the acquisition of the projection image sequence, that is, after completing the positioning of the first position of the tumor in the last projection image, combined with the first position of the tumor in each projection image in the projection image sequence and the respiratory signal of the target object, the motion model of the tumor is determined.

[0088] Further, when the positioning of the target object is completed in the positioning stage, the motion model of the tumor has been established.

[0089] Optionally, in some embodiments, the present application can also determine the periodic change information of the tumor position in the head-foot direction. For example, when the positioning of the target object is completed in the positioning stage, the first position of the tumor in each projection image in the projection image sequence is output, and the physical space tumor movement amount is converted according to the optical path geometry. Furthermore, combined with the acquisition time of each projection image in the projection image sequence, the periodic change information of the tumor position in the head-foot direction is determined.

[0090] Based on the above technical solution, for the tumor motion model establishment method provided by the present application, first, the projection image sequence of the target object in the positioning stage is acquired, and the projection image sequence includes multiple projection images containing tumors. Then, for each projection image in the projection image sequence, the first position of the tumor in the projection image is determined, and based on the first position of the tumor in each projection image in the projection image sequence and the respiratory signal of the target object, the motion model of the tumor is determined. That is to say, when the present application determines the motion model of the tumor, the projection images in the positioning stage are effectively utilized, thereby avoiding re-acquiring additional projection images before the treatment starts, effectively reducing the treatment waiting time and exposure dose, and improving the efficiency of the entire treatment process.

[0091] As a possible embodiment of the present application, in combination with Figure 3 , as Figure 4 shown, the implementation process of determining the first position of the tumor in the projection image in S302 above can be implemented through the following S401-S403.

[0092] S401. Obtain the initial position of the tumor.

[0093] In a possible implementation, the implementation process of S401 includes: obtaining the first reference projection image of the target object; furthermore, registering the first projection image with the first reference projection image to obtain the initial position of the tumor.

[0094] Among them, the first reference projection image is an image generated by digitally projecting and reconstructing the reference image of the target object at the imaging angle of the first projection image in the projection image sequence. For example, taking the imaging angle of the first projection image as 1 degree as an example, the first reference projection image is an image generated by digitally projecting and reconstructing the reference image of the target object at the imaging angle of 1 degree.

[0095] Optionally, the reference image of the target object can be a computed tomography (CT) image. The first reference projection image can also be called a digitally reconstructed radiograph (DRR), that is, the first reference projection image is the DRR projection image of the CT image.

[0096] In an example, taking the first projection image as the projection image with an imaging angle of 1 degree and the first reference projection image as the DRR projection image with an imaging angle of 1 degree as an example. Then register the projection image of 1 degree and the DRR projection image of 1 degree to determine the position (u0, v0) of the tumor in the projection image of 1 degree based on the position data of the tumor in the DRR projection image of 1 degree. Take the position (v0) of the tumor in the head-foot direction of the target object as the initial position of the tumor. Wherein, u0 is the position of the tumor in the left-right direction of the target object.

[0097] It should be noted that the difference between two adjacent projection images in the projection image sequence during the positioning stage is caused by the rotation of the gantry driving the X-ray tube around the target object and the respiratory movement of the tumor during the image acquisition process. As Figure 5 shown, the difference caused by the rotation movement to two adjacent projection images is mainly reflected in: there are changes in the left-right direction (corresponding to Figure 5 the U direction therein) of the target object between two adjacent projection images. Thus, it can be known that the displacement of the tumor caused by the rotation movement is the displacement of the tumor in the left-right direction of the target object (that is, Figure 5 δu therein). The difference caused by the respiratory movement to two adjacent projection images is mainly reflected in: there are changes in the head-foot direction (corresponding to Figure 5 the V direction therein) of the target object between two adjacent projection images. Thus, it can be known that the displacement of the tumor caused by the respiratory movement is the displacement of the tumor in the head-foot direction of the target object (that is,Figure 5 in δv).

[0098] Since the purpose of this application is to construct a respiratory motion model of a tumor, that is, what this application needs to determine is the position of the tumor with respiratory motion. Therefore, when determining the initial position of the tumor, the position data of the tumor in the head-foot direction is used as the initial data to reflect the displacement characteristics of the tumor with respiratory motion.

[0099] S402. Perform registration processing on two adjacent projection images in the projection image sequence in turn, and determine the displacement amount of the tumor in the two adjacent projection images.

[0100] In a possible implementation manner, the implementation process of S402 includes: taking the projection image sequence including projection image 1, projection image 2, projection image 3, and projection image 4 as an example. Perform registration processing on projection image 2 and projection image 1 to determine the displacement amount 1 of the tumor in projection image 2 relative to the tumor in projection image 1; perform registration processing on projection image 3 and projection image 2 to determine the displacement amount 2 of the tumor in projection image 3 relative to the tumor in projection image 2; perform registration processing on projection image 4 and projection image 3 to determine the displacement amount 3 of the tumor in projection image 4 relative to the tumor in projection image 3.

[0101] Optionally, since the acquisition conditions of two adjacent projection images in the projection image sequence are basically the same, that is to say, the difference between two adjacent projection images is small. Therefore, when performing registration processing on two adjacent projection images in turn, the mean squared error (MSE) algorithm can be used as the similarity measurement algorithm, that is, the MSE algorithm is used to determine the similarity between two adjacent projection images. Since the calculation process of the MSE algorithm is relatively simple and direct, mainly involving basic operations (such as difference, square, summation, average, etc.) of pixel gray values, it does not require complex image feature extraction, complex model construction, and a large number of iterative operations, etc. Compared with some other similarity measurement algorithms (such as methods based on feature point matching, complex texture feature comparison, etc.), the computational complexity of the MSE algorithm is significantly lower. Using the MSE algorithm can quickly obtain the measurement result, thereby reducing the time required for calculation and the consumption of computing resources. It greatly saves the computing cost.

[0102] Of course, the above only uses 4 projection images to illustrate the specific implementation manner of S402. In this application, the projection image sequence may include more projection images.

[0103] In another possible implementation, the implementation process of S402 includes: performing a first registration process on two adjacent projection images; performing an expansion process on the tumor region after the first registration to generate a tumor region template (e.g., a mask); and based on the tumor region template, performing a second registration process on the two adjacent projection images to determine the displacement amount of the tumor in the two adjacent projection images.

[0104] In one example, taking projection image 2 and projection image 1 as two adjacent projection images. A first registration process is performed on projection image 2 and projection image 1 to achieve the registration of regions with gray values greater than or equal to a preset threshold in projection image 2 and projection image 1 (e.g., the regions corresponding to bones). Furthermore, for the regions with gray values less than the preset threshold that are not accurately registered (i.e., the tumor regions), an expansion process is performed to expand the range of the second registration, ensuring the accuracy of the second registration process, and thus accurately obtaining the displacement amount of the tumor in the two adjacent projection images.

[0105] It can be understood that in medical images, since the boundary of the tumor is not absolutely clear. And also due to the resolution limitation of the imaging device and the influence of surrounding tissues, there is a certain ambiguity in the pixel recognition of the tumor edge. Therefore, by expanding the tumor region after the first registration, regions related to the tumor can be included in the consideration scope, providing more comprehensive information for the subsequent second registration process.

[0106] Optionally, the implementation process of performing an expansion process on the tumor region after the first registration to generate a tumor region template may include: based on the gray value of the tumor region after the first registration, determining the region in the projection image with gray values within a preset interval as the tumor region template.

[0107] Among them, the preset interval is determined based on the gray value of the tumor region. For example, the preset interval may be the interval including the gray value of the tumor region with a preset ratio a floating up and down, that is, [(1 - a)I t , (1 + a)I t . Another example, taking the gray value of the tumor region as I t , and the preset threshold as b, the preset interval may be the interval including b floating up and down with I t , that is, [I t + b, I t - b]. t

[0108] Optionally, in combination with the preset interval [(1 - a)I t , (1 + a)I t , the tumor region template (mask) satisfies the following formula 1:

[0109]

[0110] In the above example, the implementation process of the tumor region template can be understood as follows: The regions in the projection image with gray values in the interval [(1 - a)I t , (1 + a)I t are marked as 1; the regions outside the interval [(1 - a)I t , (1 + a)I t (i.e., others) in the projection image are marked as 0, thereby obtaining the tumor region template.

[0111] Furthermore, in some embodiments, after determining the displacement amount of the tumor in two adjacent projection images through S402, the present application may further include a process of performing error correction processing on the displacement amount of the tumor in two adjacent projection images.

[0112] In a possible implementation manner, the implementation process of performing error correction processing on the displacement amount of the tumor in two adjacent projection images can be achieved through the following Method 1 and / or Method 2.

[0113] Method 1: Based on the projection images before two adjacent projection images in the projection image sequence, determine the motion trend of the tumor, and perform error correction processing on the displacement amount of the tumor when the displacement amount of the tumor does not conform to the motion trend of the tumor.

[0114] In an example, taking two adjacent projection images as Projection Image 1 and Projection Image 2, and Projection Image 2 is the image acquired after Projection Image 1 as an example. The displacement amounts of the tumor in Projection Image 1 and Projection Image 2 are accumulated to the initial position of the tumor to obtain the position of the tumor in Projection Image 2. Then verify whether the position of the tumor in Projection Image 2 conforms to the motion trend of the tumor; in the case of non - conformity, it indicates that the "position of the tumor in Projection Image 2" obtained from the "displacement amounts of the tumor in Projection Image 1 and Projection Image 2" is incorrect data. At this time, the displacement amounts of the tumor in Projection Image 1 and Projection Image 2 (i.e., the position of the tumor in Projection Image 2) are removed / deleted to achieve error correction processing on the displacement amount of the tumor, reduce incorrect data, and improve the accuracy of the displacement amount of the tumor.

[0115] Method 2: Based on the noise filtering method corresponding to the system noise characteristics, perform noise filtering processing on the displacement amount of the tumor.

[0116] Among them, the system noise characteristics are signal characteristics that cause interference to the displacement amount of the tumor during the determination process of the displacement amount of the tumor.

[0117] It is understandable that different imaging systems have different noise characteristics, including the type of noise (such as Gaussian noise, salt-and-pepper noise, etc.), the distribution law of noise (such as the spatial distribution in the image, the variation law over time, etc.), and the intensity of noise (usually measured by indicators such as standard deviation). Understanding the noise characteristics of the system can help select appropriate filtering methods. For example, if the noise data generated by the imaging system is Gaussian noise, then based on the error correction method corresponding to Gaussian noise (for example, filtering algorithms (specifically, Wiener filtering, mean filtering, median filtering, Gaussian filtering)), the displacement of the tumor can be filtered to remove noise.

[0118] Among them, Wiener filtering is a linear filtering method based on the minimum mean square error criterion, which can perform an optimal estimate on the noisy signal (that is, the tumor displacement signal with error after registration) according to the statistical characteristics of the noise data (such as the power spectral density of the noise data), so as to filter out the noise, reduce the error, and improve the accuracy of the tumor displacement.

[0119] It should be noted that since the purpose of this application is to construct a respiratory motion model of the tumor, that is, this application needs to determine the position of the tumor with the respiratory motion. Therefore, the displacement of the tumor in two adjacent projection images in S402 is specifically the displacement of the tumor in the head-foot direction of the target object in two adjacent projection images. Then, based on the displacement of the tumor caused by the respiratory motion, a respiratory motion model of the tumor is constructed.

[0120] S403. Based on the initial position of the tumor and the displacement of the tumor in two adjacent projection images in the projection image sequence, determine the first position of the tumor in the projection image.

[0121] In a possible implementation manner, the implementation process of S403 includes: successively accumulating the displacements of the tumor in the head-foot direction in two adjacent projection images in the projection image sequence to the initial position of the tumor to obtain the first position of the tumor in the projection image. For example, the first position (d i ) of the tumor in the i-th projection image satisfies the following formula 2:

[0122] d i =v 0 +∑ i i＝0 δv i Formula 2

[0123] Among them, δv i is the displacement of the tumor in the head-foot direction in the i-th projection image, v 0 is the initial position of the tumor, and i is a positive integer.

[0124] In one example, taking the displacement amounts of the tumor in two adjacent projection images in the projection image sequence, including displacement amount 1, displacement amount 2, and displacement amount 3, as an example. And, displacement amount 1 is the displacement amount of the tumor in projection image 2 relative to the tumor in projection image 1 in the head-foot direction; displacement amount 2 is the displacement amount of the tumor in projection image 3 relative to the tumor in projection image 2 in the head-foot direction; displacement amount 3 is the displacement amount of the tumor in projection image 4 relative to the tumor in projection image 3 in the head-foot direction. Add displacement amount 1 to the initial position of the tumor in projection image 1 to obtain the position of the tumor in projection image 2; further, add displacement amount 2 to the position of the tumor in projection image 2 to obtain the position of the tumor in projection image 3; further, add displacement amount 3 to the position of the tumor in projection image 3 to obtain the position of the tumor in projection image 4.

[0125] Based on the above technical solution, obtain the initial position of the tumor, and perform registration processing on two adjacent projection images in the projection image sequence in turn to determine the displacement amount of the tumor in the two adjacent projection images. Further, based on the initial position of the tumor and the displacement amount of the tumor in two adjacent projection images in the projection image sequence, determine the first position of the tumor in the projection image, which is convenient for subsequently constructing a motion model of the tumor based on the first position of the tumor.

[0126] As a possible embodiment of the present application, in combination with Figure 3 , as Figure 6 shown, after S302, the present application further includes a process of correcting the first position of the tumor, specifically including the following S601 - S603.

[0127] S601. For the target projection image that is K projection images apart in the projection image sequence, obtain the second reference projection image corresponding to the target projection image.

[0128] Among them, the second reference projection image is an image generated by digitally projecting and reconstructing the reference image of the target object at the imaging angle of the target projection image (for example, the DRR image at the imaging angle of the target projection image); K is a positive integer.

[0129] In one example, taking the projection image sequence including 0 - 7 projection images and K being 2 as an example. Then, for the 3rd projection image in the projection image sequence (the 3rd projection image is the one that is 2 projection images apart after the 0th projection image sequence), obtain the second reference projection image corresponding to the 3rd projection image; for the 6th projection image (the 6th projection image is the one that is 2 projection images apart after the 3rd projection image sequence, that is, the 6th projection image), obtain the second reference projection image corresponding to the 6th projection image.

[0130] S602. Perform registration processing on the target projection image and the second reference projection image to determine the second position of the tumor in the target projection image.

[0131] S603. Based on the deviation degree between the first position and the second position, adopt a correction method corresponding to the deviation degree to correct the first position, and obtain the corrected first position of the tumor.

[0132] In a possible implementation manner, the implementation process of S603 includes: corresponding to the deviation degree being less than the first threshold, the first position is not corrected.

[0133] It should be noted that corresponding to the deviation degree being less than the first threshold, it indicates that the first position of the tumor in the target projection image is accurate and does not need to be corrected, saving resources.

[0134] In another possible implementation manner, the implementation process of S603 includes: corresponding to the deviation degree being greater than the second threshold, the first position is replaced with the second position, and the first position corresponding to the projection image after the target projection image is corrected. Wherein, the second threshold is greater than the first threshold.

[0135] After replacing the first position with the second position, based on the second position, accumulate with at least one displacement amount (the displacement amount of the tumor between two adjacent projection images after the target projection image) to determine the first position of the tumor in the projection image after the target projection image.

[0136] Optionally, the implementation process of correcting the first position corresponding to the projection image after the target projection image includes: correcting the first position of the tumors from the (i - K)-th to the i-th according to the deviation degree between the first position and the second position. Wherein, i > K.

[0137] In an example, correcting the first position of the j-th tumor can be achieved through the following formula 3. Wherein, j ∈ [i - K, i].

[0138] d(j) = e*(j - i + k) / k Formula 3

[0139] In another possible implementation manner, the implementation process of S603 includes: corresponding to the deviation degree being within the interval where the first threshold and the second threshold are located, the first position is replaced with the mean value of the first position and the second position.

[0140] Or, corresponding to the deviation degree being within the interval where the first threshold and the second threshold are located, perform a weighted sum of the first position and the second position based on a preset weight to obtain a third position, and replace the first position with the third position.

[0141] Compared with the current method of obtaining the motion model of a tumor by registering and deforming the positioning CBCT and the planned CT, although the accuracy of the tumor position determined by this method is relatively high, there is a problem of large amount of data calculation and time consumption.

[0142] Based on the above technical solution, for the target projection image that is K projection images apart in the projection image sequence, obtain the second reference projection image corresponding to the target projection image. Perform registration processing on the target projection image and the second reference projection image to determine the second position of the tumor in the target projection image. Based on the deviation degree between the first position and the second position, use a correction method corresponding to the deviation degree to correct the first position to obtain the corrected first position of the tumor. It can be seen that in this application, after every K projection images, the first position of the tumor is corrected by the reference projection image, which can effectively improve the accuracy of the tumor motion model while reducing the amount of calculation.

[0143] In some embodiments, as Figure 7 shown, the process of correcting the first position of the tumor is specifically implemented through the following steps 1 - 7.

[0144] Step 1: After registering the first projection image and the first reference projection image (DRR image) to obtain the initial position of the tumor, for the projection image sequence, determine whether the interval is full of K projection images.

[0145] Step 2: If the interval is less than K projection images, register the target projection image and the adjacent projection image of the target projection image to determine the first position of the tumor in the target projection image.

[0146] Optionally, the breathing signal of the target object can be externally connected so as to output the motion model of the tumor in combination with the breathing signal subsequently.

[0147] Step 3a: If the interval is full of K projection images, execute S601 to obtain the second reference projection image corresponding to the target projection image.

[0148] Step 3b: Perform registration processing on the target projection image and the second reference projection image to determine the second position of the tumor in the target projection image.

[0149] Step 4a: Through a preset fusion correction technique, perform fusion processing on the first position and the second position of the tumor in the target projection image.

[0150] Among them, the preset fusion correction technique includes at least one of the following: linear correction technique, weighted fusion correction technique, neural network technique, maximum likelihood estimation technique, and Kalman filtering technique.

[0151] Step 4b: Update the first position of the tumor.

[0152] Step 5: Determine whether the target projection image is the last image in the projection image sequence.

[0153] Step 6: If so, output the motion model of the tumor in combination with the breathing signal of the target object; if not, repeat Steps 1 - 5 until all the projection images in the projection image sequence are registered.

[0154] Above, the process of correcting the first position of the tumor through Steps 1 - 6 has been introduced.

[0155] In the embodiments of the present application, the electronic device can be divided into functional modules or functional units according to the above method examples. For example, each functional module or functional unit can be corresponding to each function, or two or more functions can be integrated into one processing module. The above - integrated module can be implemented in the form of hardware, or in the form of a software functional module or functional unit. Among them, the division of modules or units in the embodiments of the present application is illustrative, only a logical function division, and there can be other division methods in actual implementation.

[0156] As Figure 8 shown, it is a schematic structural diagram of a tumor motion model establishment device 80 provided by an embodiment of the present application. The tumor motion model establishment device 80 includes: a communication unit 801 and a processing unit 802.

[0157] The communication unit 801 is used to obtain a projection image sequence of the target object in the positioning stage, and the projection image sequence includes multiple projection images containing tumors; the processing unit 802 is used to determine the first position of the tumor in each projection image of the projection image sequence; the processing unit 802 is further used to determine the motion model of the tumor based on the first position of the tumor in each projection image of the projection image sequence and the breathing signal of the target object.

[0158] In a possible implementation manner, the processing unit 802 is specifically used for: during the process of continuously obtaining the projection image sequence of the target object in the positioning stage, for each obtained projection image, determine the first position of the tumor in the projection image; after completing the acquisition of the projection image sequence, determine the motion model of the tumor based on the first position of the tumor in each projection image of the projection image sequence and the breathing signal of the target object.

[0159] In a possible implementation manner, when the positioning of the target object is completed in the positioning stage, the motion model of the tumor has been established.

[0160] In a possible implementation, the processing unit 802 is specifically configured to: obtain the initial position of the tumor through the communication unit 801; perform registration processing on two adjacent projection images in the projection image sequence in sequence to determine the displacement amount of the tumor in the two adjacent projection images; and determine the first position of the tumor in the projection image based on the initial position of the tumor and the displacement amount of the tumor in the two adjacent projection images in the projection image sequence.

[0161] In a possible implementation, the processing unit 802 is specifically configured to: obtain the first reference projection image of the target object through the communication unit 801, where the first reference projection image is an image generated by digitally projecting and reconstructing the reference image of the target object at the imaging angle of the first projection image in the projection image sequence; and register the first projection image with the first reference projection image to obtain the initial position of the tumor.

[0162] In a possible implementation, the processing unit 802 is specifically configured to: perform first registration processing on two adjacent projection images; perform an expansion process on the tumor region after the first registration to generate a tumor region template; and perform second registration processing on the two adjacent projection images based on the tumor region template to determine the displacement amount of the tumor in the two adjacent projection images.

[0163] In a possible implementation, the processing unit 802 is specifically configured to: determine, based on the gray value of the tumor region after the first registration, that the region with the gray value within a preset interval in the projection image is the tumor region template; and the preset interval is determined based on the gray value of the tumor region.

[0164] In a possible implementation, the processing unit 802 is further configured to: perform error correction processing on the displacement amount of the tumor in two adjacent projection images to obtain a corrected displacement amount.

[0165] Among them, performing error correction processing on the displacement amount of the tumor in two adjacent projection images includes: determining the motion trend of the tumor based on the projection images before the two adjacent projection images in the projection image sequence, and performing error correction processing on the displacement amount of the tumor when the displacement amount of the tumor does not conform to the motion trend of the tumor.

[0166] And / or, perform noise filtering processing on the displacement amount of the tumor based on the noise filtering method corresponding to the system noise characteristics; where the system noise characteristics are signal characteristics that cause interference to the displacement amount of the tumor generated during the determination process of the displacement amount of the tumor.

[0167] In a possible implementation, after determining the first position of the tumor in each projection image of the projection image sequence, the processing unit 802 is further configured to: for a target projection image that is K projection images apart in the projection image sequence, obtain a second reference projection image corresponding to the target projection image, where the second reference projection image is an image generated by digitally projecting and reconstructing a reference image of the target object at the imaging angle of the target projection image; K is a positive integer; perform registration processing on the target projection image and the second reference projection image to determine the second position of the tumor in the target projection image; and based on the deviation degree between the first position and the second position, correct the first position using a correction method corresponding to the deviation degree to obtain the corrected first position of the tumor.

[0168] In a possible implementation, the processing unit 802 is specifically configured to: if the deviation degree is less than a first threshold, do not correct the first position; if the deviation degree is greater than a second threshold, replace the first position with the second position and correct the first position corresponding to the projection images after the target projection image; the second threshold is greater than the first threshold; if the deviation degree is within the interval between the first threshold and the second threshold, replace the first position with the average value of the first position and the second position.

[0169] In a possible implementation, the tumor motion model establishment device 80 may further include a storage unit 803 ( Figure 8 shown in a dashed box), and the storage unit 803 stores a program or instructions. When the processing unit 802 executes the program or instructions, the tumor motion model establishment device 80 can execute the tumor motion model establishment method described in the above method embodiments.

[0170] When implemented by hardware, the embodiments of the present application further provide an electronic device for executing the tumor motion model establishment method shown in the above method embodiments.

[0171] Specifically, Figure 9 is a schematic hardware structure diagram of an electronic device provided by the embodiments of the present application. As Figure 9 shown, the electronic device includes at least one processor 901, a communication line 902, at least one communication interface 904, and a memory 903 configured to store instructions executable by the processor. Among them, the processor 901, the memory 903, and the communication interface 904 can be connected through the communication line 902. The processor is configured to execute instructions to implement the tumor motion model establishment method provided by the method embodiments of the present application.

[0172] The processor 901 can be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application. For example, one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs).

[0173] The communication line 902 may include a path for transmitting information between the above components.

[0174] The communication interface 904, used for communicating with other devices or communication networks, may use any device such as a transceiver, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0175] The memory 903 can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to include or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0176] In a possible design, the memory 903 can exist independently of the processor 901, that is, the memory 903 can be an external memory of the processor 901. At this time, the memory 903 can be connected to the processor 901 through the communication line 902, used to store execution instructions or application program codes, and controlled by the processor 901 to execute, so as to implement the tumor motion model establishment method provided by the embodiments of the present application. In another possible design, the memory 903 can also be integrated with the processor 901, that is, the memory 903 can be an internal memory of the processor 901. For example, the memory 903 is a cache, which can be used to temporarily store some data and instruction information, etc.

[0177] As a possible implementation manner, the processor 901 can include one or more CPUs, such as Figure 9 CPU0 and CPU1 in Figure 9 As another possible implementation manner, the electronic device can include multiple processors, such as

[0178] the processor 901 and the processor 907 in

[0179] Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and conciseness of description, only the above division of each functional module is used as an example for illustration. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0180] The embodiments of the present application provide a computer program product containing instructions. When the computer program product runs on a computer, it causes the computer to execute the tumor motion model establishment method in the foregoing method embodiments.

[0181] The embodiments of the present application also provide a computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on a computer, it causes the computer to execute the tumor motion model establishment method in the method flow shown in the foregoing method embodiments.

[0182] Among them, a computer-readable storage medium can be, for example, but not limited to, a system, device, or component of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a register, a hard disk, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above, or any other form of computer-readable storage medium well-known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). In the embodiments of the present application, the computer-readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or combined with an instruction execution system, device, or component.

[0183] Various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays, application specific integrated circuits, application specific standard parts (ASSPs), system on chip (SOC) systems, complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, where the programmable processor can be a dedicated or general programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0184] The program code for implementing the methods of the present application can be written in any combination of one or more programming languages. These program codes can be provided to the processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing devices, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program codes can be executed entirely on the machine, partially on the machine, executed partially on the machine as an independent software package and partially on a remote machine, or executed entirely on a remote machine or server.

[0185] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user, such as a cathode ray tube (CRT) or a liquid crystal display (LCD) monitor; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and the input received from the user can be in any form (including acoustic input, voice input, or tactile input).

[0186] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with the implementations of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area networks, wide area networks (WANs), and the Internet.

[0187] A computer system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, a server of a distributed system, or a server incorporating a blockchain.

[0188] Since the electronic device, computer-readable storage medium, and computer program product in the embodiments of the present application can be applied to the above method, the technical effects they can achieve can also refer to the method embodiments above, and will not be elaborated herein.

[0189] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be in electrical, mechanical, or other forms.

[0190] It should be understood that various forms of the processes shown above can be used, reordering, adding, or deleting steps. For example, the steps recorded in the present disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions of the present application can be achieved, and no limitations are imposed herein.

[0191] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0192] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0193] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0194] The above is only the specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for establishing a tumor motion model, characterized in that: The method comprises: Acquiring a projection image sequence of the target object in a positioning phase, wherein the projection image sequence includes a plurality of projection images containing the tumor; For each projection image in the sequence of projection images, determining a first position of the tumor in the projection image; A motion model of the tumor is determined based on a first position of the tumor in each projection image in the sequence of projection images and a breathing signal of the target object.

2. The method according to claim 1, characterized in that: The step of determining, for each projection image in the projection image sequence, a first position of the tumor in the projection image comprises: In the process of continuously acquiring a sequence of projection images of the target object in the positioning stage, for each acquired projection image, determining a first position of a tumor in the projection image; Accordingly, determining the motion model of the tumor based on the first position of the tumor in each projection image in the projection image sequence and the breathing signal of the target object includes: After the sequence of projection images is acquired, a motion model of the tumor is determined based on a first position of the tumor in each projection image in the sequence of projection images and a breathing signal of the target object.

3. The method according to claim 1, characterized in that When the target object is positioned in the positioning phase, the motion model of the tumor has been established.

4. The method according to claim 1, characterized in that The determining a first position of the tumor in the projection image comprises: obtaining an initial position of the tumor; performing registration processing on two adjacent projection images in the projection image sequence in sequence to determine the displacement of the tumor in the two adjacent projection images; Based on the initial position of the tumor and the displacement of the tumor in two adjacent projection images in the projection image sequence, a first position of the tumor in the projection image is determined.

5. The method according to claim 4, characterized in that The obtaining of the initial position of the tumor comprises: Acquire a first reference projection image of the target object, where the first reference projection image is an image generated by digitally projecting and reconstructing a reference image of the target object at an imaging angle of a first projection image in the projection image sequence; The first projection image is registered with the first reference projection image to obtain an initial position of the tumor.

6. The method according to claim 4, characterized in that The step of sequentially performing registration processing on two adjacent projection images in the projection image sequence to determine the displacement of the tumor in the two adjacent projection images includes: Performing a first registration process on the two adjacent projection images; Performing an outward expansion process on the tumor region after the first registration to generate a tumor region template; Based on the tumor region template, a second registration process is performed on the two adjacent projection images to determine the displacement of the tumor in the two adjacent projection images.

7. The method according to claim 6, characterized in that The step of performing an expansion process on the first registered tumor region to generate a tumor region template includes: Based on the grayscale value of the tumor region after the first registration, a region in the projection image whose grayscale value is within a preset interval is determined as the tumor region template; the preset interval is determined based on the grayscale value of the tumor region.

8. The method according to claim 6, characterized in that The method further comprises: performing error correction processing on the displacement of the tumor in the two adjacent projection images to obtain a corrected displacement; The error correction process for the displacement of the tumor in the two adjacent projection images includes: Determine the movement trend of the tumor based on the projection image before the two adjacent projection images in the projection image sequence, and perform error correction processing on the displacement of the tumor when the displacement of the tumor does not conform to the movement trend of the tumor; and / or, Based on a noise filtering method corresponding to a system noise feature, noise filtering is performed on the displacement of the tumor; wherein the system noise feature is a signal feature that is generated during the process of determining the displacement of the tumor and interferes with the displacement of the tumor.

9. The method according to claim 1, characterized in that: After determining the first position of the tumor in the projection image for each projection image in the sequence of projection images, the method further comprises: For a target projection image separated by K projection images in the projection image sequence, a second reference projection image corresponding to the target projection image is obtained, where the second reference projection image is an image generated by digitally projecting and reconstructing the reference image of the target object at an imaging angle of the target projection image; K is a positive integer; Performing registration processing on the target projection image and the second reference projection image to determine a second position of the tumor in the target projection image; Based on the degree of deviation between the first position and the second position, the first position is corrected using a correction method corresponding to the degree of deviation to obtain a corrected first position of the tumor.

10. The method according to claim 9, characterized in that The correcting the first position by adopting a correction method corresponding to the degree of deviation includes: Corresponding to the degree of deviation being less than a first threshold, no correction is performed on the first position; Corresponding to the deviation degree being greater than a second threshold, the first position is replaced by the second position, and the first position corresponding to the projection image after the target projection image is corrected; the second threshold is greater than the first threshold; Corresponding to the deviation degree being within the interval where the first threshold and the second threshold are located, the first position is replaced by the average of the first position and the second position.

11. An electronic device, characterized in that: The electronic device comprises: processor; a memory configured to store instructions executable by the processor; Wherein, the processor is configured to execute the instructions to implement the tumor motion model establishment method as described in any one of claims 1-10.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions. When a computer executes the instructions, the computer executes the method for establishing a tumor motion model according to any one of claims 1 to 10.

Images