Target point quantity determination method, electronic device, and storage medium

Abstract

The application provides a target point quantity determination method, an electronic device and a storage medium, relates to the technical field of medical treatment, and is used for reasonably and accurately determining the maximum target point quantity, and can support efficient and accurate optimization of a treatment plan. The method comprises the following steps: acquiring the volume and shape feature parameters of a target region to be treated; the shape feature parameters are used for reflecting the complexity of the shape of the target region to be treated; determining the initial target point quantity of the target region to be treated according to the volume of the target region to be treated; the initial target point quantity is the number of one or more collimators; the combination of one or more beam focal spot volumes corresponding to one or more collimators is combined with the target region to be treated; determining the target target point quantity of the target region to be treated based on the initial target point quantity and the shape feature parameters; the target target point quantity is positively correlated with the shape feature parameters; and the target target point quantity is used for representing the maximum number of target points allowed to be arranged in the target region to be treated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical treatment, and in particular to a target point quantity determination method, an electronic device, and a storage medium. BACKGROUND

[0002] Gamma stereotactic radiotherapy in radiotherapy is an effective method for treating tumors. A gamma stereotactic radiotherapy system (also referred to as a "gamma knife") can focus gamma rays so that a target region at a focal point receives a high dose of radiation, while surrounding healthy tissue receives a lower dose.

[0003] When treatment is performed by the gamma stereotactic radiotherapy system, different sizes of collimators are generally used to conform the rays reaching different positions in the target region to different diameter approximate "spheres" (also referred to as target points), the target region is filled with these target points, and by assigning different weights to these target points, a dose field formed by superimposing all the target points in the target region can cover the target region as much as possible while minimizing damage to normal tissue, so as to achieve radiotherapy for the patient.

[0004] Currently, an optimal target point quantity can be found by an automatic planning algorithm under a maximum target point quantity given based on human experience. If the maximum target point quantity given based on human experience is large, it can result in a large time consumption for generating a treatment plan of good quality, and can easily result in a large number of target points in the treatment plan generated by automatic planning, causing damage to normal tissue. If the maximum target point quantity given based on human experience is small, it can result in an inability to generate a qualified treatment plan, causing a small number of target points in the treatment plan generated by automatic planning, which cannot achieve effective radiotherapy for the target region. Therefore, it is necessary to reasonably and accurately determine the maximum target point quantity. SUMMARY

[0005] The present application provides a target point quantity determination method, an electronic device, and a storage medium, which can reasonably and accurately determine the maximum target point quantity, and can support efficient and accurate optimization of a treatment plan.

[0006] In a first aspect, the present application provides a target point quantity determination method, comprising: obtaining a volume of a target region to be treated and a shape feature parameter. The shape feature parameter is used to reflect a complexity of a shape of the target region to be treated. According to the volume of the target region to be treated, an initial target point quantity of the target region to be treated is determined. The initial target point quantity is a number of one or more collimators in a group. A combination of one or more beam focal spot volumes corresponding to the one or more collimators in the group matches the volume of the target region to be treated. Based on the initial target point quantity and the shape feature parameter, a target target point quantity of the target region to be treated is determined. The target target point quantity is positively correlated with the shape feature parameter. The target target point quantity is used to represent a maximum number of target points allowed to be deployed in the target region to be treated.

[0007] In some embodiments, the method for determining the initial target point number of the target region to be treated according to the volume of the target region to be treated specifically comprises: obtaining a plurality of beam focal spot volumes corresponding to collimators of different sizes. Based on the volume of the target region to be treated and the plurality of beam focal spot volumes, the initial target point number is determined.

[0008] In some embodiments, the method for determining the initial target point number based on the volume of the target region to be treated and the plurality of beam focal spot volumes specifically comprises: in the order of the plurality of beam focal spot volumes from large to small, the number of collimators that can accommodate the current beam focal spot volume in the current remaining volume of the target region to be treated is determined in sequence, to obtain the number of collimators of different sizes. The sum of the number of collimators of different sizes is determined as the initial target point number.

[0009] In some embodiments, the shape feature parameter comprises at least one of the following: a hole feature parameter of the target region to be treated, an intersection area feature parameter between the continuous multi-layer target region slices of the target region to be treated, and a relative position feature parameter between the continuous multi-layer target region slices. The hole feature parameter is positively correlated with the number of holes existing in the target region to be treated. The intersection area feature parameter is positively correlated with the number of times of direction transformation of the change trend of the intersection area between the continuous multi-layer target region slices. The change trend of the intersection area is the change trend of the size of the intersection area between each adjacent two layers of target region slices. The relative position feature parameter is the consistency degree of the area change trend corresponding to the continuous multi-layer target region slices. The area change trend consistency degree is used to indicate whether the change trend of the intersection area and the change trend of the slice area are consistent. The change trend of the slice area is the change trend of the size of the slice area between each adjacent two layers of target region slices.

[0010] In some embodiments, the method for obtaining the shape feature parameter of the target region to be treated specifically comprises: obtaining a slice image of each of the continuous multi-layer target region slices of the target region to be treated. Based on the slice image of each of the continuous multi-layer target region slices, the shape feature parameter is determined.

[0011] In some embodiments, in the case that the shape feature parameter comprises a hole feature parameter, the method for determining the shape feature parameter based on the slice images of the continuous multi-layer target region slices comprises: determining whether each target region slice has a hole based on the target region edge contour in each slice image. In the case that there is a target region slice having a hole in the continuous multi-layer target region slices, determining a target irregularity from the irregularities of the continuous multi-layer target region slices, as the hole feature parameter. The greater the irregularity of a target region slice, the greater the probability of being determined as the target irregularity. The irregularity of each target region slice is determined based on the effective rows, the effective columns, the target rows and the target columns in the slice image of each target region slice. The effective rows are used to represent the rows in which all the pixels in a row are located on the target region edge contour. The effective columns are used to represent the columns in which all the pixels in a column are located on the target region edge contour. The target rows are used to represent the rows in which the number of pixels located on the target region edge contour is greater than a preset number. The target columns are used to represent the columns in which the number of pixels located on the target region edge contour is greater than a preset number. In the case that there is no target region slice having a hole in the continuous multi-layer target region slices, determining a preset numerical value as the hole feature parameter.

[0012] In some embodiments, the method for determining whether each target region slice has a hole based on the target region edge contour in each slice image comprises: in the case that the proportion of the target rows in the effective rows is greater than a preset proportion, or the proportion of the target columns in the effective columns is greater than a preset proportion, determining that the target region slice has a hole. In the case that the proportion of the target rows in the effective rows is less than or equal to a preset proportion, and the proportion of the target columns in the effective columns is less than or equal to a preset proportion, determining that the target region slice does not have a hole.

[0013] In some embodiments, the irregularity of each target region slice is the ratio of the sum of the number of target rows and the number of target columns to the sum of the number of effective rows and the number of effective columns.

[0014] In some embodiments, in the case that the shape feature parameter comprises an intersection area feature parameter, the method for determining the shape feature parameter based on the slice images of the continuous multi-layer target region slices comprises: determining the intersection pixels between each pair of adjacent slice images in the continuous multi-layer slice images. The intersection pixels are used to represent the pixels that are located in the target region slice and have the same pixel position between the two slice images. Determining a first fitting result corresponding to the intersection area change trend based on the intersection pixels between each pair of adjacent slice images. Determining the number of continuous monotonic intervals in the first fitting result as the intersection area feature parameter.

[0015] In some embodiments, in a case where the shape feature parameter comprises the relative position feature parameter, the method for determining the shape feature parameter based on the slice images of the continuous multi-layer target region slices comprises: determining a second fitting result corresponding to a slice area change trend based on target region pixels in each slice image. In a case where a preset condition is met between the second fitting result and the first fitting result, determining that the first consistency degree is the relative position feature parameter. The first fitting result is determined based on intersection pixels between each two adjacent slice images. The intersection pixels are used to represent pixels that have the same pixel position and are located in the target region slice between the two slice images. The preset condition comprises that the number of continuous monotonic intervals is the same and the slice images corresponding to the continuous monotonic intervals are the same. The first consistency degree is used to indicate that the intersection area change trend and the slice area change trend are consistent. In a case where the preset condition is not met between the second fitting result and the first fitting result, determining that the second consistency degree is the relative position feature parameter. The second consistency degree is used to indicate that the intersection area change trend and the slice area change trend are inconsistent.

[0016] In some embodiments, the method for determining the target target point number of the target region to be treated based on the initial target point number and the shape feature parameter comprises: determining a feature target point number based on the initial target point number and the shape feature parameter. The feature target point number comprises at least one of the following: a first target point number determined according to the initial target point number, the hole feature parameter and a first coefficient, a second target point number determined according to the intersection area feature parameter and a second coefficient, and a third target point number determined according to the initial target point number, the relative position feature parameter and a third coefficient. The target target point number is determined according to the initial target point number and the feature target point number.

[0017] In a second aspect, the present application provides a target point number determination apparatus, comprising: an acquisition unit and a processing unit.

[0018] The acquisition unit is configured to acquire a volume of a target region to be treated and a shape feature parameter. The shape feature parameter is used to reflect a complexity of a shape of the target region to be treated. The processing unit is configured to determine an initial target point number of the target region to be treated according to the volume of the target region to be treated. The initial target point number is the number of one or more collimators. A combination of one or more beam focal spot volumes corresponding to the one or more collimators matches the volume of the target region to be treated. The processing unit is further configured to determine a target target point number of the target region to be treated based on the initial target point number and the shape feature parameter. The target target point number is positively correlated with the shape feature parameter. The target target point number is used to represent a maximum number of target points allowed to be deployed in the target region to be treated.

[0019] In some embodiments, the processing unit is specifically configured to: acquire a plurality of beam focal spot volumes corresponding to collimators of different sizes. The initial target point number is determined based on the volume of the target region to be treated and the plurality of beam focal spot volumes.

[0020] In some embodiments, the processing unit is specifically configured to: determine, in order of the plurality of beam focus spot volumes from large to small, the number of collimators corresponding to the current beam focus spot volume that can be accommodated in the current remaining volume of the target region to be treated, to obtain the number of collimators of different sizes; and determine the initial number of target points as the sum of the number of collimators of different sizes.

[0021] In some embodiments, the shape feature parameter comprises at least one of: a hole feature parameter of the target region to be treated, an intersection area feature parameter between the continuous multiple target region slices of the target region to be treated, and a relative position feature parameter between the continuous multiple target region slices. The hole feature parameter is positively correlated with the number of holes existing in the target region to be treated. The intersection area feature parameter is positively correlated with the number of times of direction transformation of the variation trend of the intersection area between the continuous multiple target region slices, and the variation trend of the intersection area is the variation trend of the size of the intersection area between each adjacent two target region slices. The relative position feature parameter is the consistency degree of the area variation trend corresponding to the continuous multiple target region slices. The area variation trend consistency degree is used to indicate whether the variation trend of the intersection area and the variation trend of the slice area are consistent. The variation trend of the slice area is the variation trend of the size of the slice area between each adjacent two target region slices.

[0022] In some embodiments, the acquisition unit is specifically configured to: acquire the slice images of the continuous multiple target region slices of the target region to be treated respectively; and determine the shape feature parameter based on the slice images of the continuous multiple target region slices respectively.

[0023] In some embodiments, the acquisition unit is specifically configured to: determine whether each target region slice has a hole based on the target region edge contour in each slice image. In the case that there is a target region slice having a hole in the continuous multiple target region slices, determine a target irregularity from the irregularities of the continuous multiple target region slices respectively as the hole feature parameter. The greater the irregularity of each target region slice, the greater the probability of being determined as the target irregularity. The irregularity of each target region slice is determined based on the effective row, the effective column, the target row, and the target column in the slice image of each target region slice. The effective row is used to represent the row in which the pixels located on the target region edge contour exist in the whole row of pixels. The effective column is used to represent the column in which the pixels located on the target region edge contour exist in the whole column of pixels. The target row is used to represent the row in which the number of pixels located on the target region edge contour is greater than a preset number in the whole row of pixels. The target column is used to represent the column in which the number of pixels located on the target region edge contour is greater than a preset number in the whole column of pixels. In the case that there is no target region slice having a hole in the continuous multiple target region slices, determine a preset numerical value as the hole feature parameter.

[0024] In some embodiments, the acquisition unit is specifically configured to: determine that the target region slice has the hole in a case where a proportion of the target rows in the effective rows is greater than a preset proportion or a proportion of the target columns in the effective columns is greater than the preset proportion. Determine that the target region slice does not have the hole in a case where the proportion of the target rows in the effective rows is less than or equal to the preset proportion and the proportion of the target columns in the effective columns is less than or equal to the preset proportion.

[0025] In some embodiments, the irregularity of each target region slice is a ratio of a sum of a number of target rows and a number of target columns to a sum of a number of effective rows and a number of effective columns.

[0026] In some embodiments, the acquisition unit is specifically configured to: determine intersection pixels between each two adjacent slice images in the continuous multi-layer slice images. The intersection pixels are used to represent pixels that have the same pixel position and are located in the target region slice between the two slice images. Determine a first fitting result corresponding to a change trend of the intersection area based on the intersection pixels between each two adjacent slice images. Determine a number of continuous monotonic intervals in the first fitting result as the intersection area feature parameter.

[0027] In some embodiments, the acquisition unit is specifically configured to: determine a second fitting result corresponding to a change trend of a slice area based on the target region pixels in each slice image. Determine the first consistency degree as the relative position feature parameter in a case where a preset condition is met between the second fitting result and the first fitting result. The first fitting result is determined based on the intersection pixels between each two adjacent slice images. The intersection pixels are used to represent pixels that have the same pixel position and are located in the target region slice between the two slice images. The preset condition includes that the number of continuous monotonic intervals is the same and the slice images corresponding to the continuous monotonic intervals are the same. The first consistency degree is used to indicate that the change trend of the intersection area and the change trend of the slice area are consistent. Determine the second consistency degree as the relative position feature parameter in a case where the preset condition is not met between the second fitting result and the first fitting result. The second consistency degree is used to indicate that the change trend of the intersection area and the change trend of the slice area are inconsistent.

[0028] In some embodiments, the processing unit is specifically configured to: determine a feature target point number based on the initial target point number and the shape feature parameter. The feature target point number includes at least one of the following: a first target point number determined according to the initial target point number, the hole feature parameter and a first coefficient, a second target point number determined according to the intersection area feature parameter and a second coefficient, and a third target point number determined according to the initial target point number, the relative position feature parameter and a third coefficient. Determine the target target point number according to the initial target point number and the feature target point number.

[0029] In a third aspect, the present application provides an electronic device, comprising: a processor configured to store a memory executable by the processor. Wherein the processor is configured to execute instructions to implement any one of the possible target point number determination methods in the first aspect.

[0030] In a fourth aspect, the present application provides a non-volatile storage medium, and the computer program is stored on the storage medium. When the computer program is read and executed, the method for determining the number of target points in any one of the first aspect is implemented.

[0031] In a fifth aspect, the present application provides a computer program product, comprising computer instructions, when the computer instructions are executed on an electronic device, the electronic device executes any one of the possible target point number determination methods in the first aspect.

[0032] These aspects or other aspects of the present application will be more apparent in the following description.

[0033] The technical solutions provided by the present application at least have the following beneficial effects:

[0034] In the present application, the electronic device can obtain the volume of the target region to be treated, and determine the initial target point number of the target region to be treated according to the volume of the target region to be treated. Since the initial target point number is the number of one or more collimators, and the combination of one or more beam focal spot volumes corresponding to one or more collimators matches the volume of the target region to be treated. Therefore, the initial target point number determined by the electronic device in the present application embodiment can accurately match the volume of the target region to be treated.

[0035] And the electronic device can obtain the shape feature parameter of the target region to be treated, and further determine the maximum number of target points allowed to be deployed in the target region to be treated based on the initial target point number and the shape feature parameter. Since the shape feature parameter is used to reflect the complexity of the shape of the target region to be treated, and the target target point number is positively correlated with the shape feature parameter. Therefore, the electronic device in the present application embodiment can determine the target target point number based on the initial target point number matching the volume of the target region to be treated, combined with the shape complexity of the target region to be treated, so that the target target point number can accurately match the volume and shape feature of the target region to be treated, can adapt to the target point uneven phenomenon caused by the shape complexity of the target region to be treated, and has higher rationality.

[0036] Therefore, compared with the manner of giving the maximum target point number based on artificial experience, the target point number determined by the present application can support the automatic planning to find the optimal treatment plan as much as possible based on a smaller maximum target point number without missing the optimal target point number, thereby improving the efficiency of finding the optimal target point number. In summary, the present application can be used to reasonably and accurately determine the maximum target point number, and can support the efficient and accurate optimization of the treatment plan. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced.

[0038] Figure 1 A structural schematic diagram of a radiotherapy system provided by an embodiment of the present application;

[0039] Figure 2 A hardware structural schematic diagram of an electronic device provided by an embodiment of the present application;

[0040] Figure 3 A flowchart of a target point number determination method provided by an embodiment of the present application;

[0041] Figure 4 A flowchart of another target point number determination method provided by an embodiment of the present application;

[0042] Figure 5 A flowchart of another target point number determination method provided by an embodiment of the present application;

[0043] Figure 6 A flowchart of another target point number determination method provided by an embodiment of the present application;

[0044] Figure 7 A structural schematic diagram of a target point number determination apparatus provided by an embodiment of the present application;

[0045] Figure 8 A structural schematic diagram of another target point number determination apparatus provided by an embodiment of the present application. DETAILED DESCRIPTION

[0046] The target point number determination method, the electronic device and the storage medium provided by the embodiments of the present application will be described in detail below with reference to the drawings.

[0047] Furthermore, the terms "comprise", "comprising", "have", "having", "include", "including", "contain", "containing", "provide", "providing", "offer", "offering", "specify", "specifying", "invent", "inventing" and any variations thereof in the description and in the claims shall not be construed as excluding other steps, elements or features. For example, use of the term "including" to describe one feature, structure, step, or element of an embodiment shall not be construed as excluding the presence of other features, structures, steps, or elements.

[0048] It should be noted that the terms "exemplary" and "for example" are used herein to mean "an example of" rather than "an ideal example" or "an idealic example." Any implementation described herein as "exemplary" or "for example" is not necessarily to be construed as preferred or advantageous over other implementations. The terms "exemplary" and "for example" are intended to be used only to illustrate the present disclosure and its potential applications.

[0049] The term "and / or" in the present application includes any one of the two methods or both methods.

[0050] The terms "first", "second", and "third" in the description of the present application and in the drawings are used to distinguish different objects, and are not used to describe a specific order of the objects, nor to indicate or imply relative importance or implicitly indicate the number of the indicated technical features.

[0051] In the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise specified.

[0052] Some concepts related to a target point quantity determination method, an electronic device and a storage medium provided by the embodiments of the present application are explained as follows.

[0053] With the development of radiotherapy technology, an automatic planning method based on reinforcement learning has been applied. The automatic planning can quickly generate qualified treatment plans, and can efficiently generate a large number of relatively accurate treatment plans. In the process of generating treatment plans by using the automatic planning method, the maximum number of target points in a target region needs to be given in advance, and then the automatic planning algorithm can find the optimal target point quantity, target point position, target point weight, and target point type within the given maximum target point quantity, so as to find a set of treatment plans with greater coverage (such as greater than or equal to 95%) and greater selection rate (such as greater than or equal to 80%) for the target region as possible.

[0054] It can be seen that the quality of the treatment plan generated by the automatic planning is strongly related to the maximum number of target points in the given target region. If the maximum number of target points in the given target region is small, it can lead to the failure to generate a qualified treatment plan, and easily lead to the number of target points in the treatment plan generated by the automatic planning being small, which cannot achieve effective radiotherapy of the target region. If the maximum number of target points in the given target region is large, it can lead to a large time consumption for generating a treatment plan of good quality, and easily lead to the number of target points in the treatment plan generated by the automatic planning being large, which causes damage to normal tissues. Therefore, it is necessary to reasonably and accurately determine the maximum number of target points.

[0055] Based on this, in order to reasonably and accurately determine the maximum number of target points, the embodiments of the present application provide a target point number determination method, an electronic device and a storage medium. In the present application, the electronic device can obtain the volume of the target region to be treated, and determine the initial number of target points of the target region to be treated according to the volume of the target region to be treated. Since the initial number of target points is the number of one or more collimators in a group, and the combination of one or more beam focal spot volumes corresponding to one or more collimators in a group matches the volume of the target region to be treated. Therefore, the initial number of target points determined by the electronic device in the embodiments of the present application can accurately match the volume of the target region to be treated.

[0056] Moreover, the electronic device can obtain the shape feature parameter of the target region to be treated, and further determine the maximum number of target points allowed to be deployed inside the target region to be treated based on the initial number of target points and the shape feature parameter. Since the shape feature parameter is used to reflect the complexity of the shape of the target region to be treated, and the target number of target points is positively related to the shape feature parameter. Therefore, the electronic device in the embodiments of the present application can determine the target number of target points based on the initial number of target points matching the volume of the target region to be treated, in combination with the complexity of the shape of the target region to be treated, so that the target number of target points can accurately match the volume and shape feature of the target region to be treated, can adapt to the uneven phenomenon of target points caused by the complexity of the shape of the target region to be treated, and has higher rationality.

[0057] Based on this, compared with the way of giving the maximum number of target points based on artificial experience, the target number of target points determined by the present application can support the automatic planning to perform optimization of the treatment plan based on a smaller maximum number of target points as much as possible on the premise of not missing the optimal number of target points, and improve the efficiency of finding the optimal number of target points. In summary, the present application can be used to reasonably and accurately determine the maximum number of target points, and can support efficient and accurate optimization of the treatment plan.

[0058] The target quantity determination method can be applied to an electronic device. The electronic device can be a device (for example, a treatment planning system (TPS), which can also exist as a standalone device) that has the functions of formulating, optimizing, and evaluating a radiotherapy plan. The present application does not limit the number of maximum targets provided to the treatment planning system.

[0059] As shown in Figure 1 , a structural schematic diagram of a radiotherapy system provided by an embodiment of the present application. The radiotherapy system 100 can include an electronic device 101, a control device 102, and a radiotherapy device 103. The control device 102 can be connected between the electronic device 101 and the radiotherapy device 103, respectively.

[0060] In some embodiments, the electronic device 101 can be a treatment planning system (TPS), including a TPS client and a TPS server.

[0061] The TPS client can be at least one of a smartphone, a smartwatch, a desktop computer, a laptop computer, a virtual reality terminal, an augmented reality terminal, a wireless terminal, and a laptop computer, etc. For example, in some embodiments, a user can trigger the TPS server to perform the target quantity determination and treatment plan optimization processes of the present application through the radiotherapy planning system running on the TPS server via the TPS client, and display the optimized treatment plan. In this way, the user's time can be effectively saved, and the optimized treatment plan can be more intuitively presented to the user for evaluation.

[0062] The TPS server can be at least one of a standalone physical server, or a server cluster or distributed file system composed of multiple physical servers, or a cloud server 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 distribution networks, and big data or artificial intelligence platforms, etc. The present application does not limit the number of TPS servers, which can be more or less in some embodiments. Of course, the TPS server can also include other functions to provide more comprehensive and diverse services. In some embodiments, the TPS server is used to provide background services for the TPS client, such as performing the target quantity determination and treatment plan optimization processes of the present application.

[0063] In some embodiments, the control device 102 is a device for controlling the radiotherapy device 103 to perform a treatment plan. In some embodiments, the control device 102 can include a host computer and a slave computer, the host computer is used for interaction with a user, and the slave computer is used for controlling the movement of each moving part in the radiotherapy device 103. The host computer can be at least one of a smart phone, a smart watch, a desktop computer, a laptop computer, a virtual reality terminal, an augmented reality terminal, a wireless terminal, a laptop computer, and the like, and / or a server device. The slave computer can be a programmable logic controller (PLC) or the like.

[0064] In some embodiments, the radiotherapy device 103 can be used to irradiate a treatment beam to a target region to be treated. For example, the radiotherapy device 103 can be a Gamma Knife or the like. Figure 1 The device form shown in FIG. 1 is only an example of a device form of the radiotherapy device 103. The embodiments of the present application do not limit this. In an embodiment of the present disclosure, the electronic device 101 can determine the volume and shape feature parameters of the target region to be treated based on the image information of the target region to be treated, and determine the initial target point number of the target region to be treated according to the volume of the target region to be treated, to further determine the target target point number of the target region to be treated based on the initial target point number and the shape feature parameters, i.e., to determine the maximum number of target points deployed in the target region to be treated, and then generate a treatment plan based on the maximum target point number. Moreover, the electronic device 101 can send the generated treatment plan to the control device 102. The control device 102 can receive the treatment plan from the electronic device 101, and control the radiotherapy device 103 to emit a beam to the target region to be treated based on the received treatment plan.

[0065] Figure 2 A hardware structure schematic diagram of an electronic device 101 provided by an embodiment of the present application is shown. The electronic device 101 can include a display screen 1011, a processor 1012, a memory 1013, and a communication interface 1014. The display screen 1011, the processor 1012, the memory 1013, and the communication interface 1014 can be connected to each other through a bus 1015.

[0066] The display screen 1011 can be a micro organic electroluminescence display (OLED) display, a liquid crystal on silicon (LCOS) display, or the like. The display screen 1011 can be used to display image information of a target region and the like.

[0067] The processor 1012 can be one or more central processing units (CPUs). When the processor 1012 is a CPU, it can be a single-core CPU or a multi-core CPU. The processor 1012 can be used to read data stored in the memory 1013 and perform processing such as image recognition and rendering.

[0068] The memory 1013 can be random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or compact disc read-only memory (CD-ROM).

[0069] The communication interface 1014 is used to receive / send data in response to instructions from the processor 1012 and the memory 1013.

[0070] Bus 1015 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. Bus 1015 can be divided into address bus, data bus, control bus, etc.

[0071] The embodiments of this application do not limit the number of these devices. For example, electronic device 101 may include one or more displays 1011. As another example, electronic device 101 may include one or more processors 1012. Or, electronic device 101 may include one or more memories 1013, etc.

[0072] The method for determining the number of target points provided in the embodiments of this application will be described below.

[0073] like Figure 3 The diagram shown is a flowchart illustrating a method for determining the number of target points according to an embodiment of this application. The execution entity of this method can be... Figure 1 or Figure 2 The method includes: S201-S203.

[0074] S201. Obtain the volume and shape feature parameters of the target area to be treated.

[0075] The target region to be treated can be a region requiring radiation irradiation to achieve tumor treatment. The region can include tumor tissue, or further include surrounding tissue of the tumor tissue, etc. It should be understood that the target region to be treated can also be referred to as a tumor target region or a planning target volume, etc., without limitation.

[0076] The volume of the target region to be treated is the size of the space occupied by the diseased tissue requiring radiotherapy.

[0077] The shape feature parameter of the target region to be treated is used to reflect the complexity of the shape of the target region to be treated.

[0078] In one possible manner, the electronic device can determine the volume and the shape feature parameter of the target region to be treated based on image information of the target region to be treated.

[0079] For example, the electronic device can segment an image containing the target region to be treated to determine the boundary of the target region to be treated. Further, the volume of the target region to be treated is determined. Optionally, the image of the target region to be treated can be a magnetic resonance (MR) image or a computed tomography (CT) image, etc. The image of the target region to be treated includes a plurality of target region slice images of the target region to be treated continuously acquired along a certain anatomical direction.

[0080] For another example, the electronic device can determine the shape feature parameter of the target region to be treated based on the plurality of target region slice images. The implementation manner of the process can refer to the specific description in S2011-S2012 below, which will not be repeated here.

[0081] The shape feature parameter of the target region to be treated can include at least one of a hole feature parameter of the target region to be treated, an intersection area feature parameter between the plurality of continuous target region slices of the target region to be treated, and a relative position feature parameter between the plurality of continuous target region slices.

[0082] The hole feature parameter of the target region to be treated is positively correlated with the number of holes existing in the target region to be treated.

[0083] The intersection area feature parameter between the plurality of continuous target region slices of the target region to be treated is positively correlated with the number of direction changes of the change trend of the intersection area between the plurality of continuous target region slices. The change trend of the intersection area is the change trend of the size of the intersection area between each adjacent two target region slices.

[0084] The relative position feature parameter between the plurality of continuous target region slices is the consistency degree of the area change trend corresponding to the plurality of continuous target region slices. The area change trend consistency degree is used to indicate whether the change trend of the intersection area and the change trend of the slice area are consistent. The change trend of the slice area is the change trend of the size of the slice area between each adjacent two target region slices.

[0085] S202, determine an initial target point quantity of the target region to be treated according to a volume of the target region to be treated.

[0086] wherein the initial target point quantity is a quantity of one or more collimators. A combination of one or more beam focal spot volumes corresponding to one or more collimators matches the volume of the target region to be treated.

[0087] wherein one beam focal spot corresponding to one collimator is formed by a beam emitted by a radiation source passing through a collimator with a same size as the one collimator at a focal point position. Further, the combination of one or more beam focal spot volumes corresponding to one or more collimators matches the volume of the target region to be treated, means that a sum of volumes of each beam focal spot in the one or more beam focal spots matches the volume of the target region to be treated in a case that each beam focal spot in the one or more beam focal spots does not overlap.

[0088] In a possible manner, the sum of volumes of each beam focal spot in the one or more beam focal spots matches the volume of the target region to be treated, which can be that a shape of a volume formed by the combination of each beam focal spot in the one or more beam focal spots is substantially the same as a shape of the volume of the target region to be treated, or that a difference value between the sum of volumes of each beam focal spot in the one or more beam focal spots and the volume of the target region to be treated meets a preset difference threshold. For example, the preset difference threshold can be one percent or three percent. In this way, the difference between the sum of volumes of the one or more beam focal spots corresponding to the one or more collimators and the volume of the target region to be treated is smaller, and the one or more beam focal spots can better cover the target region to be treated, and a better treatment effect can be generated.

[0089] In this way, the quantity of the one or more beam focal spots, that is, the maximum quantity of beam focal spots allowed to be accommodated in the target region to be treated, that is, the maximum quantity of target points allowed to be deployed, is the initial target point quantity. It should be understood that the volumes of different beam focal spots can be different or the same. That is, the sizes of different collimators in the one or more collimators can be the same or different.

[0090] It should be understood that the collimator is used to limit and adjust the shape and direction of the beam, and the beam passing through the collimator will form a beam focal spot in space. The size of the beam focal spot volume depends on the size of the collimator. For ease of understanding, embodiments of the present application take the example of different sizes of collimators producing different volumes of beam focal spots, and the same size of collimators producing the same volume of beam focal spots for description.

[0091] Optionally, when determining the initial target point quantity of the target region to be treated according to the volume of the target region to be treated, the electronic device can consider the shape of the target region to be treated, and fill the target region to be treated with collimators of different sizes. In this way, the electronic device can determine the number of one or more collimators in a group as the initial target point quantity when the beam focal spot corresponding to the one or more collimators in the group better covers the target region to be treated.

[0092] Alternatively, the electronic device can obtain a plurality of beam focal spot volumes corresponding to collimators of different sizes, and determine the initial target point quantity based on the volume of the target region to be treated and the plurality of beam focal spot volumes. The implementation of this process can refer to the specific description in S2021-S2022 below, which will not be repeated here.

[0093] S203, determining a target target point quantity of the target region to be treated based on the initial target point quantity and the shape feature parameter.

[0094] The target target point quantity is used to represent the maximum number of target points allowed to be deployed in the target region to be treated, to support the automatic planning algorithm to accurately find the optimal target point quantity.

[0095] The target target point quantity is positively correlated with the shape feature parameter. For example, the electronic device can multiply the initial target point quantity and the shape feature parameter to obtain the target target point quantity of the target region to be treated. For another example, the electronic device can perform weighted summation on the initial target point quantity and the shape feature parameter to obtain the target target point quantity of the target region to be treated. The present application embodiment is not limited thereto.

[0096] In one embodiment, in combination with the target point quantity determination method shown in Figure 3 , as shown in Figure 4 , a flowchart of another target point quantity determination method provided by the present application embodiment is shown. In the above S202, i.e., when the electronic device determines the initial target point quantity of the target region to be treated according to the volume of the target region to be treated, the present application embodiment provides an optional implementation, including: S2021-S2022.

[0097] S2021, obtaining a plurality of beam focal spot volumes corresponding to collimators of different sizes.

[0098] The collimators of different sizes correspond to different beam focal spot volumes.

[0099] S2022, determining the initial target point quantity based on the volume of the target region to be treated and the plurality of beam focal spot volumes.

[0100] For example, the electronic device can determine the average of the plurality of beam focal spot volumes as the average beam focal spot volume. Further, the electronic device can determine the quotient obtained by dividing the volume of the target region to be treated by the average beam focal spot volume as the initial target point quantity.

[0101] For example, the electronic device can determine the number of collimators corresponding to the current beam focal spot volume that can be accommodated in the current remaining volume of the target region to be treated in turn according to the order of the plurality of beam focal spot volumes from large to small, to obtain the number of collimators of different sizes. Further, the electronic device can determine the sum of the number of collimators of different sizes as the initial target point number. It should be understood that in the process of multiple calculations according to the order of the plurality of beam focal spot volumes from large to small, the current remaining volume of the target region to be treated is the volume of the target region to be treated when the calculation is performed for the first time, and the current beam focal spot volume is the beam focal spot volume with the largest median among the plurality of beam focal spot volumes.

[0102] For example, it is assumed that the beam focal spot volume corresponding to the collimator with size 1 is V18, the beam focal spot volume corresponding to the collimator with size 2 is V14, the beam focal spot volume corresponding to the collimator with size 3 is V8, and the beam focal spot volume corresponding to the collimator with size 3 is V4. Among them, V18 is greater than V14, V14 is greater than V8, and V8 is greater than V4.

[0103] Then the electronic device can determine the quotient of the volume of the target region to be treated divided by V18 as the first number, and obtain the remainder a. The first number is the number of collimators with size 1 corresponding to the beam focal spot volume V18. The remainder a is the current remaining volume of the target region to be treated. Next, the electronic device can determine the quotient of the remainder a divided by V14 as the second number, and obtain the remainder b. The second number is the number of collimators with size 2 corresponding to the beam focal spot volume V14. The remainder b is the current remaining volume of the target region to be treated. Next, the electronic device can determine the quotient of the remainder b divided by V8 as the third number, and obtain the remainder c. The third number is the number of collimators with size 3 corresponding to the beam focal spot volume V8. The remainder c is the current remaining volume of the target region to be treated. Next, the electronic device can determine the quotient of the remainder c divided by V4 as the fourth number. The fourth number is the number of collimators with size 4 corresponding to the beam focal spot volume V4. And the electronic device can determine the sum of the first number, the second number, the third number and the fourth number as the initial target point number in the case that there is no remainder when the remainder c is divided by V4, or there is no collimator with a smaller size.

[0104] Or further, the electronic device can determine the first number (such as 1 or 2) as the fifth number in the case that there is a remainder when the remainder c is divided by V4, and there is no collimator with a smaller size. Further, the electronic device can determine the sum of the first number, the second number, the third number, the fourth number and the fifth number as the initial target point number.

[0105] Alternatively, the electronic device can continue to select collimators with a beam focal spot volume less than V4 for calculation, if the remainder c divided by V4 has a remainder, and there is a collimator with a smaller size.

[0106] In an embodiment, in combination with the target quantity determination method shown in Figure 3 In an embodiment, in combination with the target quantity determination method shown in Figure 5 As shown in the flowchart of another target quantity determination method provided by the embodiments of the present application, in S201, i.e., when the electronic device acquires the shape feature parameter of the target region to be treated, the embodiments of the present application provide an optional implementation manner, including S2011-S2012.

[0107] S2011, acquire the slice image of each slice of the continuous multi-slice target region to be treated.

[0108] S2012, determine the shape feature parameter based on the slice image of each slice of the continuous multi-slice target region to be treated.

[0109] For example, in the case where the shape feature parameter of the target region to be treated is a hole feature parameter, the electronic device can identify whether there is a hole in the target region to be treated according to the slice image of each slice of the target region to be treated, and further determine the hole feature parameter of the target region to be treated. The hole feature parameter can be positively correlated with the number of holes existing in the target region to be treated. That is, the greater the number of holes existing in the target region to be treated, the greater the hole feature parameter. In other words, the hole feature parameter can be used to indicate the number of holes in the target region to be treated. The greater the hole feature parameter, the greater the number of holes in the target region to be treated, and the higher the complexity of the shape of the target region to be treated.

[0110] For another example, in the case where the shape feature parameter of the target region to be treated is an intersection area feature parameter, the electronic device can determine the intersection area between each two adjacent slices of the target region to be treated based on the slice image of each slice of the target region to be treated, and further determine the intersection area feature parameter between the continuous multi-slice target region to be treated. The intersection area feature parameter is positively correlated with the number of direction transformations of the change trend of the intersection area between the continuous multi-slice target region to be treated. The change trend of the intersection area is the change trend of the size of the intersection area between each two adjacent slices of the target region to be treated. That is, the greater the number of direction transformations of the change trend of the intersection area between the continuous multi-slice target region to be treated, the greater the intersection area feature parameter.

[0111] If the change trend of the intersection area between the continuous multi-slice target region to be treated changes from the intersection area becoming larger and larger to the intersection area becoming smaller and smaller, it can be indicated that the target region to be treated is approximately elliptical in shape. In this case, the number of direction transformations of the change trend of the intersection area between the continuous multi-slice target region to be treated is one, and the intersection area feature parameter can be smaller, which is used to indicate that the complexity of the shape of the target region to be treated is lower.

[0112] If the intersection area change trend between the continuous multi-layer target region slices changes from the intersection area becoming larger and larger to the intersection area becoming smaller and smaller, and then changes from the intersection area becoming smaller and smaller to the intersection area becoming larger and larger, it can be indicated that the target region to be treated is approximately in the shape of a gourd. In this case, the number of times of change in the direction of the intersection area change trend between the continuous multi-layer target region slices is three, and the intersection area characteristic parameter can be larger, which is used to indicate that the shape complexity of the target region to be treated is higher.

[0113] For example, in the case where the shape characteristic parameter of the target region to be treated is the relative position characteristic parameter, the electronic device can determine the area of each layer target region slice and the intersection area between each adjacent two layer target region slices based on the slice images of the layer target region slices, to further determine the relative position characteristic parameter between the continuous multi-layer target region slices of the target region to be treated. The relative position characteristic parameter is the consistency degree of the area change trend of the continuous multi-layer target region slices. The consistency degree of the area change trend is used to indicate whether the intersection area change trend and the slice area change trend are consistent. The slice area change trend is the size change trend of the slice area between each adjacent two layer target region slices.

[0114] If the intersection area change trend between the continuous multi-layer target region slices changes from the intersection area becoming larger and larger to the intersection area becoming smaller and smaller, and the slice area change trend of the continuous multi-layer target region slices changes from the slice area becoming larger and larger to the slice area becoming smaller and smaller, it can be indicated that the intersection area change trend and the slice area change trend are consistent, and it can be accurately indicated that the target region to be treated is approximately in the shape of an ellipse. In this case, the consistency degree of the area change trend is higher, and the relative position characteristic parameter can be larger, which is used to indicate that the shape complexity of the target region to be treated is lower.

[0115] If the intersection area change trend between the continuous multi-layer target region slices changes from the intersection area becoming larger and larger to the intersection area becoming smaller and smaller, and the slice area change trend of the continuous multi-layer target region slices changes from the slice area becoming larger and larger, it can be indicated that the intersection area change trend and the slice area change trend are inconsistent, and it can be accurately indicated that the target region to be treated is not approximately in the shape of an ellipse, but is in an irregular shape. In this case, the consistency degree of the area change trend is lower, and the relative position characteristic parameter can be smaller, which is used to indicate that the shape complexity of the target region to be treated is higher.

[0116] In an embodiment, in the above S2012, if the shape characteristic parameter is the hole characteristic parameter, an optional implementation manner provided by the embodiment of the present application includes: S20121-S20123.

[0117] S20121, based on the target region edge contour in each slice image, it is determined whether each layer target region slice has a hole.

[0118] In one possible implementation, the electronic device can identify the target region edge contour of the target region to be treated in each slice image based on the contour detection algorithm. If the target region to be treated does not have a hole in a slice, the target region edge contour in the slice image of the slice is one closed edge frame. If the target region to be treated has one or more holes in a slice, the target region edge contour in the slice image of the slice is a plurality of closed edge frames.

[0119] Based on this, the electronic device can determine whether each slice of the target region has a hole based on the number of edge frames included in the target region edge contour in each slice image. If the number of edge frames included in the target region edge contour in a slice image is equal to 1, the slice of the target region does not have a hole. If the number of edge frames included in the target region edge contour in a slice image is greater than 1, the slice of the target region has a hole.

[0120] In another possible implementation, after the electronic device identifies the target region edge contour of the target region to be treated in each slice image based on the contour detection algorithm, the electronic device can determine that a row of pixels in each slice image in which the pixels located on the target region edge contour exist is a valid row, and determine that a row of pixels in each slice image in which the number of pixels located on the target region edge contour is greater than a preset number is a target row. For example, the electronic device can assign a first pixel value (such as 1 or 2) to the pixels in each slice image in which the target region edge contour exists, and assign a second pixel value (such as 0) to the pixels in which the target region edge contour does not exist, to obtain a contour matrix of each slice image. Further, the electronic device can determine that a row of pixels in each slice image in which the pixels with the first pixel value exist is a valid row, and determine that a row of pixels in each slice image in which the number of pixels with the first pixel value is greater than the preset number is a target row based on the contour matrix of each slice image.

[0121] In addition, the electronic device can determine that a column of pixels in each slice image in which the pixels located on the target region edge contour exist is a valid column, and determine that a column of pixels in each slice image in which the number of pixels located on the target region edge contour is greater than a preset number is a target column. It should be understood that the implementation of the electronic device to determine the valid column and the target column can be understood with reference to the description of the electronic device to determine the valid row and the target row described above, and will not be described herein.

[0122] In this regard, considering that a row or column in which more than two contour lines exist is more likely to be a row or column in which a hole is located, the preset number can be 3, 4, or 5, so as to filter out the target row or target column in which the hole is located.

[0123] Further, if the proportion of the target rows in the effective rows of the slice image of the one layer of the target area slice is greater than a preset proportion, or the proportion of the target columns in the effective columns is greater than a preset proportion, it can be indicated that the one layer of the target area slice has obvious holes. The electronic device can determine that the one layer of the target area slice has holes. If the proportion of the target rows in the effective rows of the slice image of the one layer of the target area slice is less than or equal to a preset proportion, and the proportion of the target columns in the effective columns is less than or equal to a preset proportion, it can be indicated that the one layer of the target area slice can not have holes. The electronic device can determine that the one layer of the target area slice does not have holes. The preset proportion can be 0.25 or 0.3.

[0124] S20122. In a case where the target area slices in the continuous multiple layers of the target area slices have holes, determining a target irregularity from the irregularities of the continuous multiple layers of the target area slices as a hole characteristic parameter.

[0125] The greater the irregularity of the target area slice, the greater the probability of being determined as the target irregularity.

[0126] In a possible manner, in a case where the one layer of the target area slice has holes, the electronic device can determine the number of edge frames included in the target area edge contour in the slice image of the one layer of the target area slice as the irregularity of the one layer of the target area slice. In this way, the electronic device can determine the irregularities of the target area slices having holes. Further, the electronic device can determine a target irregularity in the irregularities of the target area slices as a hole characteristic parameter. For example, the electronic device can determine the irregularity with the maximum value in the irregularities of the target area slices as the target irregularity. For another example, the electronic device can determine the irregularity with the second maximum value in the irregularities of the target area slices as the target irregularity.

[0127] In another possible manner, in a case where the one layer of the target area slice has holes, the electronic device can determine the irregularity of the one layer of the target area slice based on the effective rows, the effective columns, the target rows and the target columns in the slice image of the one layer of the target area slice. For example, the electronic device can determine, as the irregularity of the one layer of the target area slice, a ratio of a sum of the number of the target rows and the number of the target columns to a sum of the number of the effective rows and the number of the effective columns in the slice image of the one layer of the target area slice. That is, the irregularity of each layer of the target area slice is a ratio of a sum of the number of the target rows and the number of the target columns to a sum of the number of the effective rows and the number of the effective columns. Further, the electronic device can determine a target irregularity in the irregularities of the target area slices as a hole characteristic parameter.

[0128] The effective row is used to represent a row of whole row pixels in which there is a pixel located on the edge profile of the target region. The effective column is used to represent a column of whole column pixels in which there is a pixel located on the edge profile of the target region. The target row is used to represent a row of whole row pixels in which the number of pixels located on the edge profile of the target region is greater than a preset number. The target column is used to represent a column of whole column pixels in which the number of pixels located on the edge profile of the target region is greater than a preset number.

[0129] S20123, in the case that there is no target region slice with a hole in the continuous multi-layer target region slices, determining a preset value as the hole feature parameter.

[0130] If there is no target region slice with a hole in the continuous multi-layer target region slices, it can be indicated that there is no hole in the target region to be treated. Then the electronic device can determine a preset value as the hole feature parameter. For example, the preset value can be 0. When the hole feature parameter is the preset value, it is used to indicate that the target region to be treated has no hole. In this case, it is not necessary to adjust the initial number of target points based on the hole feature parameter.

[0131] In one embodiment, in the above S2012, if the shape feature parameter is the intersection area feature parameter, the present embodiment provides an optional implementation manner, comprising: S20124-S20126.

[0132] S20124, determining the intersection pixels between each adjacent two slice images in the continuous multi-layer slice images.

[0133] The intersection pixels are used to represent the pixels that have the same pixel position and are located in the target region slice between the two slice images.

[0134] The electronic device can determine the pixels occupied by the target region to be treated in each slice image. Based on this, the electronic device can determine the same pixels between the pixels occupied by the target region to be treated in a slice image and the pixels occupied by the target region to be treated in the adjacent slice image of the slice image as the intersection pixels between the slice image and the adjacent slice image. In this way, the electronic device can determine the intersection pixels between each adjacent two slice images in the continuous multi-layer slice images.

[0135] S20125, determining a first fitting result corresponding to the intersection area change trend based on the intersection pixels between each adjacent two slice images.

[0136] The intersection pixels between the adjacent two slice images can represent the intersection area between the adjacent two target region slices corresponding to the adjacent two slice images. The intersection area between the adjacent two target region slices is the area of the overlapping part between the adjacent two target region slices.

[0137] In a possible manner, the electronic device can determine the first fitting result corresponding to the intersection area change trend based on the intersection pixels between each two adjacent slice images. For example, the electronic device can record the acquisition sequence of the continuous multiple slice images from early to late through the horizontal axis of a two-dimensional rectangular coordinate system, and record the intersection pixels between each two adjacent slice images through the vertical axis of the two-dimensional rectangular coordinate system, to obtain the first fitting result.

[0138] In another possible manner, the electronic device can determine a target slice image in which the number of pixels occupied by the target region to be treated is the largest in the i th slice image and the i+1 th slice image according to the acquisition sequence of the continuous multiple slice images from early to late, and divide the number of intersection pixels of the i th slice image and the i+1 th slice image by the number of pixels occupied by the target region to be treated in the target slice image to obtain a structural similarity value between the i th slice image and the i+1 th slice image. The structural similarity value between the two adjacent slice images is used to represent the structural similarity between the two adjacent slice images. In this way, the electronic device can determine the structural similarity value between each two adjacent slice images in the continuous multiple slice images. Further, the electronic device can subtract the (n+1) th structural similarity value from the n th structural similarity value to obtain the intersection area trend between the slice image corresponding to the n th structural similarity value and the adjacent slice image. In this way, the electronic device can determine the first fitting result corresponding to the intersection area change trend until the difference between each two adjacent structural similarity values is determined. Wherein, i and n are positive integers.

[0139] S20126, determine the number of continuous monotonic intervals in the first fitting result as the intersection area characteristic parameter.

[0140] The electronic device can identify the number of continuous monotonic intervals in the first fitting result, and determine the number of continuous monotonic intervals as the intersection area characteristic parameter. The continuous monotonic interval can be an interval in which the intersection pixels between each two adjacent slice images monotonically increase from small to large, or an interval in which the intersection pixels between each two adjacent slice images monotonically decrease from large to small.

[0141] It should be noted that the intersection area change trend of the target region to be treated with a regular external shape is generally first monotonically increasing from small to large, and then monotonically decreasing from large to small, that is, first increasing and then decreasing, and there are two continuous monotonic intervals in the first fitting result corresponding thereto. If the number of continuous monotonic intervals in the first fitting result is more, it can be indicated that the intersection area change trend is more complex, and the external shape of the target region to be treated is more irregular, and more target points need to be deployed to achieve a better irradiation treatment effect. Therefore, after the electronic device accurately determines the intersection area characteristic parameter in the embodiments of the present application, the initial target point number can be accurately adjusted based on the intersection area characteristic parameter to accurately determine the maximum target point number.

[0142] In one embodiment, in the S2012, if the shape feature parameter is a relative position feature parameter, an optional implementation of an embodiment of the present application is provided, comprising: S20127-S20129.

[0143] S20127, based on the target region pixels in each slice image, determine the second fitting result corresponding to the slice area change trend.

[0144] Wherein, the target region pixels in the slice image are the pixels occupied by the target region to be treated in the slice image. The number of target region pixels in the slice image corresponding to a target region slice can represent the target region area of the target region slice.

[0145] In one possible way, the electronic device can determine the second fitting result corresponding to the slice area change trend based on the number of target region pixels in each slice image in the continuous multiple slice images. For example, the electronic device can record the acquisition order of the continuous multiple target region slices from first to last through the horizontal axis of the two-dimensional rectangular coordinate system, and record the number of target region pixels of each slice image through the vertical axis of the two-dimensional rectangular coordinate system, thereby obtaining the second fitting result corresponding to the slice area change trend.

[0146] In another possible way, the electronic device can subtract the number of target region pixels of the (k+1)th slice image from the number of target region pixels of the kth slice image to obtain the difference value of the number of target region pixels between the kth slice image and the (k+1)th slice image, that is, the difference value of the target region area between the kth target region slice and the (k+1)th target region slice. In this way, the electronic device can obtain the second fitting result corresponding to the slice area change trend by determining the difference value of the number of target region pixels between each adjacent two slice images. Wherein, k is a positive integer.

[0147] S20128, in the case where the second fitting result and the first fitting result meet a preset condition, determine that the first consistency degree is a relative position feature parameter.

[0148] It should be understood that the determination method of the first fitting result can refer to the description in S20125 described above, and will not be repeated here.

[0149] Wherein, the preset condition includes that the number of continuous monotonic intervals is the same, and the slice images corresponding to the continuous monotonic intervals are the same. The first consistency degree is used to indicate that the intersection area change trend and the slice area change trend are consistent.

[0150] It should be noted that if the trends of the intersecting area and the slice area are consistent, it indicates that the interlayer differences in the target area are small and the shape of the target area is relatively regular. If the trends of the intersecting area and the slice area are inconsistent, it indicates that the interlayer differences in the target area are large and the shape of the target area is relatively irregular. If the trend of the intersecting area of ​​adjacent layers of the target area shows an initial increase followed by a decrease, but the area changes between the slices of the target area in each layer do not show an increasing trend, then the interlayer differences are relatively large, requiring the deployment of more target points to achieve a better irradiation treatment effect.

[0151] After determining the second fitting result corresponding to the trend of slice area change, the electronic device can identify the continuous monotonic intervals in the second fitting result. Further, the electronic device can compare the continuous monotonic intervals in the first fitting result and the second fitting result to obtain a comparison result. If the comparison result shows that the continuous monotonic intervals in the first fitting result and the second fitting result are consistent, it indicates that the shape of the target area to be treated is relatively regular. The electronic device then determines that the second fitting result and the first fitting result meet preset conditions and identifies the first consistency as a relative positional feature parameter.

[0152] In this case, the first consistency value can be small to avoid constituting an adjustment to the initial number of target points. For example, the first consistency value can be 0 or 0.1.

[0153] S20129. If the second fitting result and the first fitting result do not meet the preset conditions, the second consistency is determined as the relative position feature parameter.

[0154] The second consistency degree is used to indicate that the trend of change of intersection area and the trend of change of slice area are inconsistent.

[0155] If the continuous monotonic intervals in the first fitting result and the continuous monotonic intervals in the second fitting result are inconsistent, it indicates that the shape of the target area to be treated is relatively irregular. The electronic device then determines that the second fitting result and the first fitting result do not meet the preset conditions and determines the second consistency as a relative positional feature parameter.

[0156] In this case, the second consistency value can be relatively large to accurately adjust the initial number of target points. For example, the first consistency value can be 1 or 2.

[0157] Based on this, after the electronic device in the embodiments of this application accurately determines the relative position feature parameters, it can accurately adjust the initial number of target points based on the relative position feature parameters in order to accurately determine the maximum number of target points.

[0158] In one embodiment, combined with Figure 3The target point number determination method shown in FIG. 1A, as shown in Figure 6 As shown in FIG. 1C, it is a flowchart of another target point number determination method provided by an embodiment of the present application. In S203, that is, the electronic device determines the target point number of the target region to be treated based on the initial target point number and the shape feature parameter, an optional implementation manner provided by an embodiment of the present application includes S2031-S2032.

[0159] S2031, determine the feature target point number based on the initial target point number and the shape feature parameter.

[0160] The feature target point number includes at least one of the following: a first target point number determined according to the initial target point number, the hole feature parameter and a first coefficient, a second target point number determined according to the intersection area feature parameter and a second coefficient, and a third target point number determined according to the initial target point number, the relative position feature parameter and a third coefficient.

[0161] In one possible manner, when the electronic device determines the first target point number according to the initial target point number, the hole feature parameter and the first coefficient, the electronic device can multiply the initial target point number, the hole feature parameter and the first coefficient to obtain the first target point number. Alternatively, the electronic device can divide the product of the initial target point number and the hole feature parameter by the first coefficient to obtain the first target point number. For example, the first coefficient can be 3 or 0.4.

[0162] In another possible manner, when the electronic device determines the second target point number according to the intersection area feature parameter and the second coefficient, the electronic device can divide the intersection area feature parameter by the second coefficient to obtain the second target point number. Alternatively, the electronic device can multiply the intersection area feature parameter and the second coefficient to obtain the second target point number. For example, the second coefficient can be 2 or 0.5.

[0163] In another possible manner, when the electronic device determines the third target point number according to the initial target point number, the relative position feature parameter and the third coefficient, the electronic device can determine the product of the relative position feature parameter, the initial target point number and the third coefficient as the third target point number. Alternatively, the electronic device can divide the initial target point number by the relative position feature parameter and then further divide the result by the third coefficient to obtain the third target point number. The third coefficient can be 0.25 or 4.

[0164] S2032, determine the target point number according to the initial target point number and the feature target point number.

[0165] In a possible manner, the electronic device can add the initial target point quantity and the feature target point quantity to obtain the target target point quantity. The feature target point quantity can be at least one of the first target point quantity, the second target point quantity, and the third target point quantity. For example, in the case where the feature target point quantity is the first target point quantity and the second target point quantity, the electronic device can add the initial target point quantity, the first target point quantity, and the second target point quantity to obtain the target target point quantity. For another example, in the case where the feature target point quantity is the first target point quantity, the second target point quantity, and the third target point quantity, the electronic device can add the initial target point quantity, the first target point quantity, the second target point quantity, and the third target point quantity to obtain the target target point quantity.

[0166] In the embodiments of the present application, the electronic device can obtain the volume of the target region to be treated, and determine the initial target point quantity of the target region to be treated according to the volume of the target region to be treated. Since the initial target point quantity is the number of one or more collimators, and the combination of one or more beam focal spot volumes corresponding to the one or more collimators matches the volume of the target region to be treated. Therefore, the initial target point quantity determined by the electronic device in the embodiments of the present application can accurately match the volume of the target region to be treated.

[0167] In addition, the electronic device can obtain the shape feature parameter of the target region to be treated, and further determine the maximum number of target points allowed to be deployed in the target region to be treated based on the initial target point quantity and the shape feature parameter. Since the shape feature parameter is used to reflect the complexity of the shape of the target region to be treated, and the target target point quantity is positively correlated with the shape feature parameter. Therefore, the electronic device in the embodiments of the present application can determine the target target point quantity based on the initial target point quantity matching the volume of the target region to be treated, and in combination with the shape complexity of the target region to be treated, so that the target target point quantity can accurately match the volume and shape feature of the target region to be treated, can adapt to the target point uneven phenomenon caused by the shape complexity of the target region to be treated, and has higher rationality.

[0168] Therefore, compared with the manner of giving the maximum target point quantity based on artificial experience, the target target point quantity determined by the present application can support automatic planning to find the optimal target point quantity as much as possible based on a smaller maximum target point quantity without missing the optimal target point quantity, and improve the efficiency of finding the optimal target point quantity. In summary, the present application can be used to reasonably and accurately determine the maximum target point quantity, and can support efficient and accurate optimization of the treatment plan.

[0169] The embodiments of the present application can divide the functional modules of the electronic device and the like according to the above method examples. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in the form of hardware or in the form of a software functional module. It should be noted that the division of the modules in the embodiments of the present application is illustrative, and is only a logical functional division. In actual implementation, another division manner can be used.

[0170] In the case of dividing each functional module according to each function, Figure 7 A structural schematic diagram of a target point number determination apparatus is shown. The target point number determination apparatus 30 can be applied to an electronic device to implement any possible method involved in the above embodiments. As shown in the figure, Figure 7 The target point number determination apparatus 30 can include an acquisition unit 301 and a processing unit 302.

[0171] The acquisition unit 301 is configured to acquire a volume of a target region to be treated and a shape feature parameter. The shape feature parameter is used to reflect a complexity of a shape of the target region to be treated. The processing unit 302 is configured to determine an initial target point number of the target region to be treated according to the volume of the target region to be treated. The initial target point number is the number of one or more collimators in a group. A combination of one or more beam focal spot volumes corresponding to one or more collimators in a group matches the volume of the target region to be treated. The processing unit 302 is further configured to determine a target target point number of the target region to be treated based on the initial target point number and the shape feature parameter. The target target point number is positively correlated with the shape feature parameter. The target target point number is used to represent a maximum number of target points allowed to be deployed in the target region to be treated.

[0172] In some embodiments, the processing unit 302 is specifically configured to acquire a plurality of beam focal spot volumes corresponding to collimators of different sizes. The initial target point number is determined based on the volume of the target region to be treated and the plurality of beam focal spot volumes.

[0173] In some embodiments, the processing unit 302 is specifically configured to sequentially determine, in order from large to small, the number of collimators corresponding to a current beam focal spot volume that can be accommodated in a current remaining volume of the target region to be treated according to the plurality of beam focal spot volumes, to obtain the number of collimators of different sizes. The sum of the number of collimators of different sizes is determined as the initial target point number.

[0174] In some embodiments, the shape feature parameter comprises at least one of a hole feature parameter of the target region to be treated, an intersection area feature parameter between the continuous multi-layer target region slices of the target region to be treated, and a relative position feature parameter between the continuous multi-layer target region slices. The hole feature parameter is positively correlated with the number of holes existing in the target region to be treated. The intersection area feature parameter is positively correlated with the number of times of direction transformation of a variation trend of the intersection area between the continuous multi-layer target region slices, the variation trend being a variation trend of the size of the intersection area between each two adjacent target region slices. The relative position feature parameter is a consistency degree of a variation trend of the area between the continuous multi-layer target region slices. The consistency degree of the variation trend of the area is used to indicate whether the variation trend of the intersection area and a variation trend of the slice area are consistent. The variation trend of the slice area is a variation trend of the size of the slice area between each two adjacent target region slices.

[0175] In some embodiments, the acquisition unit 301 is specifically configured to acquire a slice image of each of the continuous multi-layer target region slices of the target region to be treated. The shape feature parameter is determined based on the slice image of each of the continuous multi-layer target region slices.

[0176] In some embodiments, the acquisition unit 301 is specifically configured to determine whether each target region slice has a hole based on a target region edge contour in each slice image. In a case where there is a target region slice having a hole in the continuous multi-layer target region slices, a target irregularity is determined from the irregularities of the continuous multi-layer target region slices, and the hole feature parameter is the target irregularity. The greater the irregularity of each target region slice, the greater the probability of being determined as the target irregularity. The irregularity of each target region slice is determined based on an effective row, an effective column, a target row, and a target column in the slice image of each target region slice. The effective row is used to represent a row in which all the pixels in the row are located on the target region edge contour. The effective column is used to represent a column in which all the pixels in the column are located on the target region edge contour. The target row is used to represent a row in which the number of pixels located on the target region edge contour is greater than a preset number. The target column is used to represent a column in which the number of pixels located on the target region edge contour is greater than the preset number. In a case where there is no target region slice having a hole in the continuous multi-layer target region slices, a preset value is determined as the hole feature parameter.

[0177] In some embodiments, the acquisition unit 301 is specifically configured to determine that the target region slice has a hole in a case where the proportion of the target row in the effective row is greater than a preset proportion or the proportion of the target column in the effective column is greater than the preset proportion. In a case where the proportion of the target row in the effective row is less than or equal to the preset proportion and the proportion of the target column in the effective column is less than or equal to the preset proportion, it is determined that the target region slice does not have a hole.

[0178] In some embodiments, the irregularity of each target region slice is a ratio of a sum of the number of target rows and the number of target columns to a sum of the number of effective rows and the number of effective columns.

[0179] In some embodiments, the obtaining unit 301 is specifically configured to: determine intersection pixels between each two adjacent slice images in the continuous multi-slice images. The intersection pixels are used to represent pixels that have the same pixel position and are located in the target region slice between the two slice images. A first fitting result corresponding to the intersection area change trend is determined based on the intersection pixels between each two adjacent slice images. The number of continuous monotonic intervals in the first fitting result is determined as the intersection area feature parameter.

[0180] In some embodiments, the obtaining unit 301 is specifically configured to: determine a second fitting result corresponding to the slice area change trend based on the target region pixels in each slice image. In a case where a preset condition is met between the second fitting result and the first fitting result, the first consistency degree is determined as the relative position feature parameter. The first fitting result is determined based on the intersection pixels between each two adjacent slice images. The intersection pixels are used to represent pixels that have the same pixel position and are located in the target region slice between the two slice images. The preset condition includes that the number of continuous monotonic intervals is the same, and the slice images corresponding to the continuous monotonic intervals are the same. The first consistency degree is used to indicate that the intersection area change trend and the slice area change trend are consistent. In a case where the preset condition is not met between the second fitting result and the first fitting result, the second consistency degree is determined as the relative position feature parameter. The second consistency degree is used to indicate that the intersection area change trend and the slice area change trend are inconsistent.

[0181] In some embodiments, the processing unit 302 is specifically configured to: determine a feature target point number based on the initial target point number and the shape feature parameter. The feature target point number includes at least one of the following: a first target point number determined according to the initial target point number, the hole feature parameter and a first coefficient, a second target point number determined according to the intersection area feature parameter and a second coefficient, and a third target point number determined according to the initial target point number, the relative position feature parameter and a third coefficient. The target target point number is determined according to the initial target point number and the feature target point number.

[0182] In the case of using integrated units, Figure 8 A structural schematic diagram of still another target point number determination apparatus is shown. The target point number determination apparatus 40 can be applied to an electronic device to implement any possible method involved in the above embodiments. As shown in Figure 8 The target point number determination apparatus 40 can include a processing module 401 and a communication module 402. The processing module 401 can be used to control and manage the actions of the target point number determination apparatus 40. The communication module 402 can be used to support the communication of the target point number determination apparatus 40 with other entities. Optionally, as shown in Figure 8 The target point number determination apparatus 40 can further include a storage module 403 for storing the program code and data of the target point number determination apparatus 40.

[0183] The processing module 401 can be a processor or a controller. The communication module 402 can be a transceiver, a transceiver circuit, or a communication interface, etc. The storage module 403 can be a memory.

[0184] When the processing module 401 is a processor, the communication module 402 is a transceiver, and the storage module 403 is a memory, the processor, the transceiver, and the memory can be connected through a bus.

[0185] It should be understood that, in various embodiments of the present application, the size of the sequence number of each process described above does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0186] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0187] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0188] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed on multiple network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the present embodiment scheme.

[0189] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by using a software program, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be magnetic media (such as floppy disk, hard disk, magnetic tape), optical media (such as DVD), or semiconductor media (such as solid state disk (SSD)) and the like.

[0190] The above description is merely a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered within 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 target point number determination method, characterized by, The method comprises the following steps: acquiring a volume and a shape feature parameter of a target region to be treated; the shape feature parameter is used to reflect a complexity of a shape of the target region to be treated; determining an initial target point number of the target region to be treated according to the volume of the target region to be treated; the initial target point number is a number of one or more collimators; a combination of one or more beam focal spot volumes corresponding to the one or more collimators matches the volume of the target region to be treated; determining a target target point number of the target region to be treated based on the initial target point number and the shape feature parameter; the target target point number is positively correlated with the shape feature parameter; the target target point number is used to represent a maximum number of target points allowed to be deployed in the target region to be treated.

2. The method of claim 1, wherein, The step of determining the initial target point number of the target region to be treated according to the volume of the target region to be treated comprises the following steps: acquiring a plurality of beam focal spot volumes corresponding to collimators of different sizes; determining the initial target point number based on the volume of the target region to be treated and the plurality of beam focal spot volumes.

3. The method of claim 2, wherein, The step of determining the initial target point number based on the volume of the target region to be treated and the plurality of beam focal spot volumes comprises the following steps: determining, in order from large to small, a number of collimators that can accommodate a current beam focal spot volume in a current remaining volume of the target region to be treated, to obtain a number of collimators of different sizes; summing the number of collimators of different sizes to determine the initial target point number.

4. The method of claim 1, wherein, The shape feature parameter comprises at least one of the following: a hole feature parameter of the target region to be treated, an intersection area feature parameter between a plurality of continuous target region slices of the target region to be treated, and a relative position feature parameter between the plurality of continuous target region slices; the hole feature parameter is positively correlated with a number of holes in the target region to be treated; the intersection area feature parameter is positively correlated with a number of times of direction transformation of a variation trend of the intersection area between the plurality of continuous target region slices; the variation trend of the intersection area is a variation trend of a size of the intersection area between each two adjacent target region slices; the relative position feature parameter is a consistency degree of a variation trend of an area corresponding to the plurality of continuous target region slices; the consistency degree of the variation trend of the area is used to indicate whether the variation trend of the intersection area and a variation trend of a slice area are consistent; the variation trend of the slice area is a variation trend of a size of the slice area between each two adjacent target region slices.

5. The method of claim 4, wherein, The step of acquiring the shape feature parameter of the target region to be treated comprises the following steps: acquiring a slice image of each of a plurality of continuous target region slices of the target region to be treated; determining the shape feature parameter based on the slice image of each of the plurality of continuous target region slices.

6. The method of claim 5, wherein, In a case where the shape feature parameter comprises the hole feature parameter, the step of determining the shape feature parameter based on the slice image of each of the plurality of continuous target region slices comprises the following steps: determining, based on a target region edge contour in each slice image, whether each target region slice has a hole. In a case where the continuous multi-layer target area slice has a target area slice with a hole, a target irregularity is determined from irregularities of the continuous multi-layer target area slice, as the hole characteristic parameter; the greater the irregularity of the target area slice, the greater the probability of being determined as the target irregularity; the irregularity of each layer of target area slice is determined based on effective rows, effective columns, target rows and target columns in a slice image of each layer of target area slice; the effective row is used to represent a row in which all pixels in the row are located on the target area edge contour; the effective column is used to represent a column in which all pixels in the column are located on the target area edge contour; the target row is used to represent a row in which the number of pixels located on the target area edge contour is greater than a preset number; and the target column is used to represent a column in which the number of pixels located on the target area edge contour is greater than the preset number; In a case where the continuous multi-layer target area slice does not have a target area slice with a hole, a preset value is determined as the hole characteristic parameter.

7. The method of claim 6, wherein, The determination of whether each layer of target area slice has a hole based on the target area edge contour in each layer of slice image comprises: In a case where a proportion of the target rows in the effective rows is greater than a preset proportion, or a proportion of the target columns in the effective columns is greater than the preset proportion, it is determined that the target area slice has a hole; In a case where the proportion of the target rows in the effective rows is less than or equal to the preset proportion, and the proportion of the target columns in the effective columns is less than or equal to the preset proportion, it is determined that the target area slice does not have a hole.

8. The method of claim 6, wherein, The irregularity of each layer of target area slice is a ratio of a sum of the number of target rows and the number of target columns to a sum of the number of effective rows and the number of effective columns.

9. The method of claim 5, wherein, In a case where the shape characteristic parameter comprises the intersection area characteristic parameter, the determination of the shape characteristic parameter based on the slice images of the continuous multi-layer target area slice comprises: determining intersection pixels between each adjacent two layers of slice images in the continuous multi-layer slice images; the intersection pixels are used to represent pixels which are located in the target area slice and have the same pixel position between two layers of slice images; determining a first fitting result corresponding to the intersection area change trend based on the intersection pixels between each adjacent two layers of slice images; determining a number of continuous monotonic intervals in the first fitting result as the intersection area characteristic parameter.

10. The method of claim 5, wherein, In a case where the shape characteristic parameter comprises the relative position characteristic parameter, the determination of the shape characteristic parameter based on the slice images of the continuous multi-layer target area slice comprises: determining a second fitting result corresponding to the slice area change trend based on target area pixels in each layer of slice image; In a case where the second fitting result and the first fitting result meet a preset condition, determining that a first consistency degree is the relative position feature parameter; the first fitting result is determined based on intersection pixels between every two adjacent slice images; the intersection pixels are used to represent pixels having the same position and located in a target region slice; the preset condition includes that a number of continuous monotonic intervals is the same and slice images corresponding to the continuous monotonic intervals are the same; and the first consistency degree is used to indicate that the intersection area change trend and the slice area change trend are consistent. In a case where the second fitting result and the first fitting result do not meet the preset condition, determining that a second consistency degree is the relative position feature parameter; and the second consistency degree is used to indicate that the intersection area change trend and the slice area change trend are inconsistent.

11. The method of claim 4, wherein, The method further includes: determining a target number of target points of the target region to be treated based on the initial number of target points and the shape feature parameter, including: determining a feature number of target points based on the initial number of target points and the shape feature parameter; the feature number of target points includes at least one of the following: a first number of target points determined according to the initial number of target points, the hole feature parameter and a first coefficient, a second number of target points determined according to the intersection area feature parameter and a second coefficient, and a third number of target points determined according to the initial number of target points, the relative position feature parameter and a third coefficient; 12. An electronic device, comprising: determining the target number of target points according to the initial number of target points and the feature number of target points. The electronic device includes: a processor; a memory configured to store instructions executable by the processor; 13. A non-volatile storage medium, comprising: wherein the processor is configured to execute the instructions to implement the method of any one of claims 1-11. The storage medium has stored thereon a computer program, which, when read and executed, implements the method of any one of claims 1-11. The storage medium has stored thereon a computer program, which, when read and executed, implements the method of any one of claims 1-11.

Images