Particle dose determination method and device, electronic equipment and storage medium

Abstract

The invention provides a particle dose determination method and device, electronic equipment and a storage medium, and relates to the field of physics and computers, in particular to application of physics and computer technologies in the field of radiation medical treatment. The particle dose determination method comprises the following steps: respectively guiding a particle beam to move through M groups of scanning parameters to obtain a plurality of transverse radiation field dose distribution data; wherein each group of scanning parameters corresponds to a plurality of transverse radiation field dose distribution data, and M is a positive integer; according to the plurality of transverse radiation field dose distribution data, calculating to obtain a plurality of first radiation field dose distribution data corresponding to each group of scanning parameters; wherein the dimension of the first radiation field dose distribution data is higher than that of the transverse radiation field dose distribution data; based on scanning parameters and the first radiation field dose distribution data, obtaining a target model used for determining radiation field center dose distribution; and inputting the target scanning parameter into the target model, and determining the delivery dose according to the target radiation field center dose distribution output by the target model.

Description

Technical Field

[0001] The present disclosure relates to the fields of physics and computers, specifically to the application of physics and computer technology in the field of radiation medicine, and more specifically to a particle dose determination method, device, electronic device, and storage medium. Background Art

[0002] In radiotherapy, uniform scanning technology primarily uses magnets to control the beam's scanning motion, ensuring uniform dose distribution within the target area. To ensure beam accuracy and therapeutic efficacy, mathematical models are used to predict the dose distribution within the target area before actual treatment begins. Treatment plans (such as beam parameters and delivered dose) are then adjusted based on this dose distribution to ensure that the dose remains concentrated within the target area during treatment, avoiding damage to surrounding tissues.

[0003] Existing traditional modeling methods typically use Gaussian integrals to generate an S-shaped function to describe the beam dose distribution. During the modeling process, traditional methods often assume that dose fluctuations in the central region are negligible, that is, the central dose distribution of the beam is flat. However, in reality, the central dose of the beam can fluctuate significantly (often by more than 5%) due to factors such as scanning speed fluctuations. Therefore, the central dose distribution of the beam described by traditional modeling methods may deviate from the actual situation, thus affecting the ultimate treatment effect. Summary of the Invention

[0004] The present disclosure provides a particle dose determination method, device, electronic device, and storage medium, which are used to at least partially solve one of the above technical problems.

[0005] According to a first aspect of the present disclosure, a particle dose determination method is provided, comprising: guiding the movement of a particle beam through M groups of scanning parameters respectively to obtain a plurality of lateral field dose distribution data; wherein each group of scanning parameters corresponds to a plurality of lateral field dose distribution data, and M is a positive integer; based on the plurality of lateral field dose distribution data, a plurality of first field dose distribution data corresponding to each group of scanning parameters is calculated; wherein the dimension of the first field dose distribution data is higher than the dimension of the lateral field dose distribution data; based on the scanning parameters and the first field dose distribution data, a target model for determining the field center dose distribution is obtained; the target scanning parameters are input into the target model, and the delivered dose is determined according to the target field center dose distribution output by the target model.

[0006] According to an embodiment of the present disclosure, the particle beam is guided to move by M groups of scanning parameters to obtain N transverse field dose distribution data, including: guiding the particle beam to move within a preset depth range by M groups of scanning parameters, randomly measuring the transverse field dose distribution of the particle beam at N depth positions, and obtaining M*N transverse field dose distribution data; wherein each group of scanning parameters corresponds to N transverse field dose distributions, wherein N is a positive integer.

[0007] According to an embodiment of the present disclosure, based on multiple lateral field dose distribution data, multiple first field dose distribution data corresponding to each set of scanning parameters are calculated, including: obtaining a depth dose curve of the particle beam; wherein the depth dose curve is used to describe the energy deposition of the particle beam in the depth direction; the depth dose curve is calculated with the N lateral field dose distribution data under each set of scanning parameters, to obtain X first field dose distribution data corresponding to the multiple sets of scanning parameters, wherein X is a positive integer and X>N.

[0008] According to an embodiment of the present disclosure, the depth dose curve is calculated with the N lateral field dose distribution data under each set of scanning parameters to obtain X first field dose distribution data corresponding to the multiple sets of scanning parameters, including: performing the following operations on the lateral field dose distribution data under each set of scanning parameters: multiplying the depth dose curve and the multiple lateral field dose distribution data to obtain first field dose distribution data at multiple specific depths; based on the first field dose distribution data at the specific depth, determining the first field dose distribution data at other depths except the specific depth.

[0009] According to an embodiment of the present disclosure, a target model for determining the dose distribution at the center of the field is obtained based on the scanning parameters and the first field dose distribution data, including: training an initial model according to the scanning parameters and the first field dose distribution data to obtain a first model, wherein the first model is used to predict the dose mask corresponding to different scanning parameters; superimposing the first model with the objective function to obtain a target model for determining the dose distribution at the center of the field, wherein the objective function is used to determine the lateral field dose distribution under ideal conditions.

[0010] According to an embodiment of the present disclosure, an initial model is trained based on scanning parameters and first field dose distribution data to obtain a first model, including: determining multiple sets of scanning parameters as input data of the initial model, and determining multiple first field dose distribution data as output data of the initial model; using each distribution feature in the first field dose distribution data as prompt information; training the initial model based on the prompt information, input data and output data to obtain the first model.

[0011] According to an embodiment of the present disclosure, the scanning parameters include at least the energy of the particle beam, device performance parameters, and the range covered by the particle beam; and at least some of the scanning parameters in each set are different.

[0012] According to a second aspect of the present disclosure, a particle dose determination device is provided, comprising: a first acquisition module, configured to guide the movement of a particle beam based on M groups of scanning parameters to obtain a plurality of lateral field dose distribution data; wherein each group of scanning parameters corresponds to a plurality of lateral field dose distribution data, and M is a positive integer; a calculation module, configured to calculate, based on the plurality of lateral field dose distribution data, a plurality of first field dose distribution data corresponding to each group of scanning parameters; wherein the dimension of the first field dose distribution data is higher than the dimension of the lateral field dose distribution data; a second acquisition module, configured to obtain a target model for determining a field center dose distribution based on the scanning parameters and the first field dose distribution data; a determination module, configured to input the target scanning parameters into the target model, and determine the delivered dose according to the target field center dose distribution output by the target model. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other objects, features and advantages of the present disclosure will become more apparent through the following description of the embodiments of the present disclosure with reference to the accompanying drawings, in which:

[0014] Figure 1 Schematically illustrates a system architecture diagram of a particle dose determination method, apparatus, device, medium, and program product according to an embodiment of the present disclosure;

[0015] Figure 2 The flowchart of the particle dose determination method according to an embodiment of the present disclosure is schematically shown;

[0016] Figure 3 Schematically shows the lateral field dose distribution obtained under different scanning parameters according to an embodiment of the present disclosure;

[0017] Figure 4 Schematically illustrates multiple transverse field dose distributions obtained under the same scanning parameters according to the present disclosure;

[0018] Figure 5 A flowchart schematically illustrates a method for calculating a plurality of first field dose distribution data corresponding to each set of scanning parameters based on a plurality of lateral field dose distribution data according to an embodiment of the present disclosure;

[0019] Figure 6 A flowchart schematically illustrates calculating the depth dose curve with N lateral field dose distribution data under each set of scanning parameters to obtain X first field dose distribution data corresponding to multiple sets of scanning parameters according to an embodiment of the present disclosure;

[0020] Figure 7 Schematically illustrates a flow chart for obtaining a target model for determining a radiation field center dose distribution based on scanning parameters and first radiation field dose distribution data according to an embodiment of the present disclosure;

[0021] Figure 8 Schematically shows a flow chart of training an initial model according to the scanning parameters and the first field dose distribution data to obtain a first model according to an embodiment of the present disclosure;

[0022] Figure 9 A schematic diagram of obtaining a target model for determining a radiation field center dose distribution based on scanning parameters and first radiation field dose distribution data according to an embodiment of the present disclosure is schematically shown;

[0023] Figure 10 A diagram schematically illustrates a comparison between the dose calculation results corresponding to the target field center distribution determined by the target model obtained according to an embodiment of the present disclosure and the dose results of the traditional model;

[0024] Figure 11 The following schematically shows a structural block diagram of a particle dose determination device according to an embodiment of the present disclosure;

[0025] Figure 12 The figure schematically shows a block diagram of an electronic device suitable for implementing a particle dose determination method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0026] To make the objectives, technical solutions, and advantages of the present disclosure more clearly understood, the present disclosure is further described below in conjunction with specific embodiments and with reference to the accompanying drawings. It is apparent that the embodiments described are only a portion of the embodiments of the present disclosure, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present disclosure without inventive effort are intended to fall within the scope of protection of the present disclosure.

[0027] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise," "include," etc. used herein indicate the presence of the features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0028] In this disclosure, unless otherwise expressly specified or limited, terms such as "mounted," "connected," "connect," and "fixed" should be understood broadly. For example, they may refer to fixed connections, detachable connections, or integration; mechanical connections, electrical connections, or communication; direct connections or indirect connections through an intermediate medium; and internal communication between two components or interaction between two components. Those skilled in the art will understand the specific meanings of these terms in this disclosure based on specific circumstances.

[0029] In the description of the present disclosure, it should be understood that the terms "longitudinal", "length", "circumferential", "front", "rear", "left", "right", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present disclosure and simplifying the description, and do not indicate or imply that the subsystem or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present disclosure.

[0030] Throughout the drawings, identical elements are represented by identical or similar reference numerals. Conventional structures or configurations may be omitted when they may cause confusion in understanding the present disclosure. Furthermore, the shapes, sizes, and positional relationships of the components in the drawings do not reflect actual size, proportion, or actual positional relationships. Furthermore, any reference symbols placed between parentheses should not be construed as limiting.

[0031] Similarly, in order to streamline the present disclosure and aid in understanding one or more of the various disclosed aspects, in the above description of exemplary embodiments of the present disclosure, the various features of the present disclosure are sometimes grouped together into a single embodiment, figure, or description thereof. Descriptions with reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples" and the like mean that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in an appropriate manner.

[0032] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. Throughout the present disclosure, "plurality" means at least two, such as two or three, unless otherwise specifically defined.

[0033] An embodiment of the present disclosure provides a particle dose determination method, comprising: guiding the movement of a particle beam through multiple sets of scanning parameters to obtain multiple lateral field dose distribution data of the particle beam; wherein each set of scanning parameters corresponds to multiple lateral field dose distribution data; constructing an association model based on the multiple lateral field dose distribution data and the multiple sets of scanning parameters; wherein the association model is used to determine the fluctuation of the particle beam under specific conditions; based on the association model, determining the target field center dose distribution of the particle beam; simulating the spatial distribution of the particle beam in the tissue to be tested based on the target field center dose distribution, and determining the delivery dose of the particles according to the spatial distribution.

[0034] Figure 1 The system architecture diagram of the particle dose determination method, apparatus, device, medium and program product according to the embodiment of the present disclosure is schematically shown. Figure 1 As shown, the application scenario 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium for providing a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired or wireless communication links or optical fiber cables.

[0035] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as physical simulation applications, shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (for example only).

[0036] The terminal devices 101 , 102 , and 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers.

[0037] Server 105 may be a server that provides various services, such as a background management server (for example only) that supports websites browsed by users using terminal devices 101, 102, and 103. The background management server may analyze and process received data such as user requests, and feed back processing results (e.g., web pages, information, or data obtained or generated based on user requests) to the terminal device.

[0038] It should be noted that the particle dose determination method provided in the embodiments of the present disclosure can generally be executed by the server 105. Accordingly, the particle dose determination apparatus provided in the embodiments of the present disclosure can generally be set in the server 105. The particle dose determination method provided in the embodiments of the present disclosure can also be executed by a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the particle dose determination apparatus provided in the embodiments of the present disclosure can also be set in a server or server cluster that is different from the server 105 and can communicate with the terminal devices 101, 102, 103 and / or the server 105.

[0039] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0040] The following will be based on Figure 1 The scene described by Figures 2 to 10 The particle dose determination method of the disclosed embodiment is described in detail.

[0041] Figure 2 The flowchart of the particle dose determination method according to an embodiment of the present disclosure is schematically shown.

[0042] like Figure 2 As shown, the particle dose determination method of this embodiment includes operations S210 to S240.

[0043] In operation S210 , the particle beam is guided to move using M groups of scanning parameters to obtain a plurality of transverse field dose distribution data; wherein each group of scanning parameters corresponds to a plurality of transverse field dose distribution data, and M is a positive integer.

[0044] In some embodiments, a particle beam is guided by a magnetron system to move along a predetermined path within the target area, and the lateral distribution of the particle beam within the target area is measured in real time to obtain multiple lateral field dose distribution data. The lateral field dose distribution data is used to describe the dose distribution within a plane (transverse cross section) perpendicular to the beam direction, such as how the dose diffuses or attenuates from the center outward in a certain transverse cross section. The uniformity of the lateral field dose distribution directly affects the accuracy of the dose coverage within the target area.

[0045] Scan parameter combinations include multiple different field parameters set based on treatment needs, with at least one field parameter varying across different scan parameter combinations. Examples of field parameters include beam energy (which determines penetration depth), device performance parameters (such as ridge filters), particle beam coverage, and scanning magnet speed (which influences dwell time).

[0046] For example, the transverse dose distribution can be measured in the transverse plane under each set of scanning parameters using tools such as a matrix ionization chamber and radiation film. The measured transverse dose distribution can effectively record the dynamic fluctuations in the actual operation of the equipment, including real effects such as uneven dwell time caused by magnet speed limitations and periodic fluctuations caused by scanning waveform distortion.

[0047] In operation S220 , first field dose distribution data corresponding to each set of scanning parameters is determined based on the plurality of lateral field dose distribution data.

[0048] In some embodiments, the transverse field dose distribution data is two-dimensional data. In addition to the scanning parameters affecting the transverse field dose distribution, changes in penetration depth will also affect the transverse field dose distribution. The corresponding first field dose distribution data is calculated based on the transverse field dose distribution data, wherein the first field dose distribution data is three-dimensional data.

[0049] During the initial stages of particle beam penetration (such as skin or superficial tissue), the energy is high, lateral scattering (caused by nuclear scattering and multiple Coulomb scattering) is minimal, and the lateral dose distribution is concentrated with sharp edges. As the particle beam gradually loses energy, the lateral scattering effect intensifies, and the beam broadens in the lateral direction (referred to as "beam broadening") becomes increasingly pronounced, causing the lateral dose distribution to widen and blur the edges. When the particle beam energy is nearly depleted, lateral scattering reaches its maximum, resulting in a significant broadening of the lateral dose distribution.

[0050] Therefore, in order to more accurately reflect the deposition process of the particle beam in the target tissue, the present disclosure proposes to convert the measured multiple lateral field dose distribution data into three-dimensional first field dose distribution data. The first field dose distribution data integrates the depth and lateral (X / Y) dose information, which can more realistically reflect the deposition process of the particle beam in the target tissue, thereby improving the accuracy of subsequent particle dose determination.

[0051] In operation S230 , a target model for determining a particle dose is obtained based on the scanning parameters and the first field dose distribution data.

[0052] In some embodiments, the target model is used to determine the field center dose distribution under target conditions.

[0053] The target model can be obtained, for example, by superimposing the first model with the traditional model. The first model is trained based on the scanning parameters and the first field dose distribution data. By analyzing the correlation between the scanning parameters and the actual field dose distribution, a two-dimensional correction coefficient matrix (i.e., a dose mask) is generated. This two-dimensional correction coefficient matrix can reflect dose fluctuations caused by the actual scanning parameters. The correction coefficient for each location can, for example, represent the ratio of the actual dose to the theoretical value at that location.

[0054] The first model can predict the dose fluctuation under the target scan parameters based on the input scan parameters and output a dose mask applicable to the current scan parameters. The dose mask can reflect the impact of the scan parameters on the dose distribution. For example, the dose mask can be a two-dimensional correction coefficient matrix composed of multiple two-dimensional correction coefficients, where each two-dimensional correction coefficient reflects the difference between the actual lateral field dose distribution and the ideal field dose distribution at a specific depth. Different masks correspond to different scan parameters to ensure that the target model can adapt to parameter changes. For example, during high-speed scanning, the mask automatically embeds the edge dose attenuation correction caused by the shortened dwell time.

[0055] The uniformity of the lateral distribution directly impacts the accuracy of target dose coverage. An inaccurate model can result in insufficient dose to the target edge or excessive dose to surrounding healthy tissue. The target model generates dose masks corresponding to different scanning parameters using actual measured lateral field dose distribution data. This effectively replaces the fixed assumptions of traditional models (such as Gaussian distribution), enabling the model to dynamically adapt to parameter changes.

[0056] Traditional models, based on the traditional S-shaped function, output an idealized central dose distribution for the field. These models assume a flat central dose (no fluctuations) and a fixed-gradient decay (e.g., Gaussian diffusion) at the edges, failing to reflect the dynamic errors experienced during actual scanning.

[0057] The ideal field center dose distribution output by the traditional S-type function is dynamically corrected by the dose mask output by the first model, so that a target field center dose distribution that is more in line with the actual situation can be obtained.

[0058] In operation S240 , the target scanning parameters are input into the target model, and the delivered dose is determined according to the target field center dose distribution output by the target model.

[0059] In some embodiments, the target scanning parameters are input into the target model to obtain the target field center dose distribution output by the target model, and the beam parameters and the delivered dose are determined according to the target field center dose distribution.

[0060] The target field center dose distribution can visually display the dose coverage of the target area, providing a basis for clinical decision-making. The beam parameters and delivery dose are adjusted according to the target field center dose to ensure the final

[0061] In this process, the dose distribution at the center of the target field is the benchmark for determining the beam parameters and the delivered dose. If the dose distribution at the center of the field cannot accurately reflect the actual dose deposition (such as the deviation between the planned value and the actual value is too large), the final delivered dose will be inaccurate, resulting in range deviation, destruction of dose uniformity, etc.

[0062] The particle dose delivery method provided by the disclosed embodiments constructs a target model for determining the field center dose distribution based on the actual measured lateral field dose distribution data. This target model is constructed by superimposing a first model trained based on the measured lateral field dose data with a traditional model. The resulting field center dose distribution is a field center dose distribution that is dynamically corrected based on a dose mask and includes dynamic fluctuations. Compared to the field center dose distribution determined based on the traditional model, the field center dose distribution determined based on the target model of the disclosed embodiments is more consistent with the dose fluctuations during actual treatment, thereby effectively improving the calculation accuracy of model parameters and delivery dose, and enhancing treatment efficacy.

[0063] In some embodiments, the multiple lateral field dose distribution data obtained by the present disclosure include, in addition to the lateral field dose distribution data corresponding to multiple groups of scanning parameters, each group of scanning parameters also corresponds to multiple lateral field dose distribution parameters at different depths.

[0064] Figure 3 The figure schematically shows the lateral field dose distribution obtained under different scanning parameters according to an embodiment of the present disclosure. Figure 4 The figure schematically shows multiple transverse field dose distributions obtained under the same scanning parameters according to the embodiment of the present disclosure.

[0065] In some embodiments, scanning parameters may include, for example, beam energy, scanning speed, and beam size. These parameters determine the beam's penetration and lateral spread. When charged particles (such as carbon ions) enter the target tissue, they interact with atomic nuclei and electrons in the tissue, resulting in energy loss (ionization loss) and path deflection (scattering). Scattering increases with decreasing particle energy, and energy loss determines the position of the Bragg peak. Therefore, as particle energy decreases with increasing depth, this may lead to increased lateral scattering, thereby affecting the lateral field dose distribution.

[0066] like Figure 3 As shown, the embodiments of the present disclosure guide the movement of the particle beam through multiple sets of scanning parameters to obtain multiple lateral field dose distribution data, including: guiding the movement of the particle beam based on M sets of different scanning parameters to obtain lateral field dose distribution data corresponding to the M sets of scanning parameters.

[0067] See also Figure 3 , Figure 3 a is the transverse dose distribution under the scanning parameters of energy 400 MeV / u, ridge filter RF100, and field size F20; Figure 3 b is the transverse dose distribution under the scanning parameters of energy 400 MeV / u, ridge filter RF90, and field size F10; Figure 3b is the transverse dose distribution under the scanning parameters of energy 330MeV / u, ridge filter RF40, and field size F20.

[0068] In some embodiments, operation S210, guiding the movement of the particle beam through multiple sets of scanning parameters to obtain multiple lateral field dose distribution data of the particle beam, also includes: guiding the particle beam to move within a preset depth range through M sets of scanning parameters, randomly measuring the lateral field dose distribution of the particle beam at N depth positions, and obtaining M*N lateral field dose distribution data; wherein each set of scanning parameters corresponds to N lateral field dose distributions, wherein N is a positive integer.

[0069] like Figure 4 As shown, for each set of scanning parameters, the dose distribution in the transverse plane is actually measured at multiple depths randomly to obtain N transverse field dose distributions at different depths corresponding to the set of scanning parameters.

[0070] Figure 5 The flowchart of calculating a plurality of first field dose distribution data corresponding to each set of scanning parameters based on a plurality of lateral field dose distribution data according to an embodiment of the present disclosure is schematically shown.

[0071] like Figure 5 As shown, the embodiment of the present invention calculates a plurality of first field dose distribution data corresponding to each set of scanning parameters based on a plurality of transverse field dose distribution data, including operations S510 to S520.

[0072] In operation S510 , a depth dose curve of a particle beam is acquired; wherein the depth dose curve is used to describe energy deposition of the particle beam in a depth direction.

[0073] In some embodiments, a depth dose curve is used to describe the variation of dose along the beam direction, which can determine the maximum energy deposition position and peak width of particles at a specific depth. For example, when the depth is z, the dose value of the particle beam is Ddepth(z).

[0074] In operation S520 , the depth dose curve is calculated with the N lateral field dose distribution data under each set of scanning parameters to obtain X first field dose distribution data corresponding to the multiple sets of scanning parameters, where X is a positive integer and X>N.

[0075] In some embodiments, the transverse field dose distribution is used to describe the dose diffusion morphology in the transverse plane (xy plane) at a certain depth z, and the transverse dose distribution is a two-dimensional distribution.

[0076] The depth dose curve is multiplied layer by layer with the lateral field dose distribution data to obtain a three-dimensional first field dose distribution. The first field dose distribution data can reflect the dose diffusion pattern at a certain location within the three-dimensional space of the particle beam. To further enrich the first field dose distribution data, in addition to calculating the corresponding first field dose distribution data based on the actually measured lateral field dose distribution data, it is also possible to perform difference calculations on multiple calculated field dose distribution data to obtain more first field dose distribution data. While reducing the measurement workload, enriching the first field dose distribution data improves the accuracy of the target model.

[0077] In some embodiments, the correlation model can determine the fluctuation of the particle beam and the correction coefficient according to the input scanning parameters.

[0078] For example, the correction coefficient corresponding to each spatial position under each set of scanning parameters can be determined by the ratio of the measured dose (i.e., the second field dose distribution data) to the theoretical dose, and the dose mask corresponding to the set of scanning parameters can be obtained based on the correction coefficient, wherein the dose mask can be, for example, a two-dimensional correction coefficient matrix, that is, each element in the dose mask is the correction coefficient of the corresponding spatial position.

[0079] The correction coefficient can be used to adjust the field center dose distribution calculated under ideal conditions, so that the fluctuation of the field center dose distribution under ideal conditions is more in line with the actual situation, thereby improving the accuracy of the target field dose distribution.

[0080] Figure 6 The flowchart schematically shows a method for calculating the depth dose curve and the N lateral field dose distribution data under each set of scanning parameters to obtain X first field dose distribution data corresponding to multiple sets of scanning parameters according to an embodiment of the present disclosure.

[0081] like Figure 6 As shown, this embodiment calculates the depth dose curve and the N lateral field dose distribution data under each set of scanning parameters to obtain X first field dose distribution data corresponding to multiple sets of scanning parameters, including operations S610 to S620, and performs the following operations on each set of scanning parameters to obtain X first field dose distribution data corresponding to the set of scanning parameters.

[0082] In operation S610 , a product calculation is performed on the depth dose curve and a plurality of lateral field dose distribution data to obtain first field dose distribution data at a plurality of specific depths.

[0083] In operation S620 , first field dose distribution data at other depths except the specific depth is determined based on the first field dose distribution data at the specific depth.

[0084] In some embodiments, for the measured depth z1 in each set of reference data, the detected lateral field dose distribution data is multiplied by the dose value of the corresponding depth in the depth dose curve to obtain a three-dimensional dose depth slice corresponding to the depth, i.e., the first field dose distribution data.

[0085] For any unmeasured depth z2 in the set of reference data, the upper and lower adjacent measurement points of the depth z2 are determined, and the first field dose distribution data corresponding to the unmeasured depth z2 is determined based on the first field dose distribution of the upper and lower adjacent measurement points.

[0086] For example, the measured depth z a The corresponding first field dose distribution data D a (x,y,z) is:

[0087] D a (x,y,z)=D a (z)×L a (x,y,z a )

[0088] Among them, D a (z) represents the depth z in the depth dose curve a The corresponding dose value, L a (x,y,z) represents the depth z a Measured lateral field dose distribution data.

[0089] For the unmeasured depth zc, determine the measurement points above and below the depth zc as z a and z b , (assuming z c =18cm, between z a =15cm and z b =18cm), then z c The corresponding first field dose distribution data D c (x,y,z) is:

[0090]

[0091] in, is the difference weight,

[0092] The disclosed embodiment combines the depth dose curve with the measured lateral field dose distribution through a multiplication calculation to generate three-dimensional dose data at discrete depths (i.e., first field dose distribution data). The dose distribution at unmeasured depths is then filled in using difference data, effectively reducing experimental complexity while ensuring accuracy. On the one hand, by combining the measured depth with the lateral dose characteristics, the true field dose distribution is restored. On the other hand, by using interpolation methods to fill in the unmeasured depth distribution, different treatment situations can be flexibly addressed, achieving dynamic adaptation to different scanning parameters and different equipment. Based on this, the amount of data can be expanded, data errors can be reduced, and uncertainty in the data can be improved, thereby optimizing the correlation between the two data in the data pair and improving the quality of the target model.

[0093] Figure 7 The flowchart of obtaining a target model for determining the central dose distribution of a field based on scanning parameters and first field dose distribution data according to an embodiment of the present disclosure is schematically shown.

[0094] like Figure 7 As shown, in this embodiment, obtaining a target model for determining a field center dose distribution based on scanning parameters and first field dose distribution data includes operations S710 to S720.

[0095] In operation S710 , an initial model is trained according to scanning parameters and first field dose distribution data to obtain a first model, wherein the first model is used to predict dose masks corresponding to different scanning parameters.

[0096] In operation S720 , the first model is superimposed on the objective function to obtain a target model for determining the particle dose, wherein the objective function is used to determine the lateral field dose distribution under ideal conditions.

[0097] In some embodiments, the target model includes a first module and a second module, wherein the first module is determined based on operation S610, and the first module is used to determine the dose mask corresponding to the scan parameter based on the input target scan parameter. The dose mask can be, for example, a two-dimensional correction coefficient matrix composed of multiple two-dimensional correction coefficients, wherein each two-dimensional correction coefficient reflects the difference between the actual lateral field dose distribution and the ideal field dose distribution at a certain specific depth.

[0098] The second module is used to determine the ideal lateral radiation dose distribution according to the objective function, wherein the objective function can be, for example, a traditional S-shaped function.

[0099] For example, when the target scanning parameters are input into the target model, the ideal lateral field dose distribution is first determined according to the objective function in the second module, and then the first module determines the dose template according to the target scanning parameters. The ideal lateral field dose distribution in the second module is dynamically adjusted by the correction coefficient in the dose mask to obtain a non-flat field center dose distribution (i.e., the target field center dose distribution).

[0100] The objective function, a long-proven function, accurately describes the basic form of the ideal lateral dose distribution (such as edge gradient attenuation) and offers high computational efficiency and strong stability. By superimposing the first model with the objective function, the target model, generated by integrating the first model with the objective function, can leverage the existing model framework and introduce dynamic corrections, improving the flexibility of the target model and the accuracy of the final output target field center dose distribution. The dose template output by the first model quantifies dose fluctuations caused by scanning parameters, directly correcting the idealized assumptions of the traditional function and improving the accuracy of the target field center dose distribution.

[0101] Compared to directly generating a new model, superimposing the objective function and the primary model allows for independent optimization and flexible adaptation of the target model. For example, the dose mask focuses on correcting dynamic errors (such as magnet velocity fluctuations), while the traditional model is responsible for the underlying morphology. Decoupling the two allows independent optimization of the primary model (e.g., updating the mask does not require modifying the sigmoid function). Furthermore, specific masks can be dynamically generated for different devices or parameter combinations, eliminating the need to rebuild a full model for each scenario. This effectively improves the flexible adaptation of the target model, allowing specific templates to be dynamically generated for different devices or parameter combinations, eliminating the need to rebuild a full model for each scenario.

[0102] Figure 8 The flowchart of training the initial model according to the scanning parameters and the first field dose distribution data to obtain the first model according to an embodiment of the present disclosure is schematically shown.

[0103] like Figure 8 As shown, in this embodiment, the initial model is trained according to the scanning parameters and the first field dose distribution data to obtain the first model, including operations S810 to S830.

[0104] In operation S810 , a plurality of sets of scanning parameters are determined as input data of an initial model, and a plurality of first field dose distribution data are determined as output data of the initial model.

[0105] In operation S820, each distribution feature in the first field dose distribution data is used as prompt information.

[0106] In operation S830 , an initial model is trained based on the prompt information, the input data, and the output data to obtain a first model.

[0107] In some embodiments, the initial model is trained using multiple sets of scanning parameters as input data of the model and the calculated first field dose distribution as output data of the model, so that the trained first model can calculate the corresponding particle beam correction coefficient based on the target scanning parameters.

[0108] The first model is obtained by training an initial model based on the scanning parameters and the first field dose distribution data. The initial model can be, for example, a convolutional neural network model or a fully connected model that can process spatial data. Taking the fully connected model as an example, the fully connected operation can be used to extract the correlation between the scanning parameters and the three-dimensional field dose distribution, so that the trained first model can determine the dose mask under the target conditions based on the target scanning parameters (such as energy, waveform, field size, etc.), wherein the dose mask can reflect the influence of the scanning parameters on the dose distribution. The dose mask can be, for example, a two-dimensional correction coefficient matrix, which is used to correct the ideal dose center distribution output by the second model to obtain the target dose center distribution.

[0109] Figure 9 A schematic diagram of obtaining a target model for determining the central dose distribution of a field based on scanning parameters and first field dose distribution data according to an embodiment of the present disclosure is schematically shown. Figure 10 A comparison diagram schematically shows the dose calculation results corresponding to the target field center distribution determined by the target model obtained according to an embodiment of the present disclosure and the dose results of the traditional model.

[0110] See also Figure 9 、 Figure 10 Compared with the traditional model, the target model based on the embodiment of the present disclosure (i.e. Figure 9 、 Figure 10 The dose calculation result determined by the new model in the present invention is more consistent with the actual measurement value, that is, the particle dose determined based on the embodiment of the present disclosure is more accurate.

[0111] Based on the above particle dose determination method, the present disclosure also provides a particle dose determination device. Figure 11 The device is described in detail.

[0112] Figure 11 The figure schematically shows a structural block diagram of a particle dose determination device according to an embodiment of the present disclosure.

[0113] like Figure 11 As shown, the particle dose determination device 1100 of this embodiment includes a first obtaining module 1110 , a calculation module 1120 , a second obtaining module 1130 and a determination module 1140 .

[0114] First acquisition module 1110 is configured to guide particle beam movement based on M sets of scanning parameters to obtain multiple transverse field dose distribution data. Each set of scanning parameters corresponds to multiple transverse field dose distribution data, and M is a positive integer. In one embodiment, first acquisition module 1110 can be configured to perform operation S210 described above and will not be further described here.

[0115] Calculation module 1120 is configured to calculate, based on the plurality of transverse field dose distribution data, a plurality of first field dose distribution data corresponding to each set of scanning parameters; wherein the first field dose distribution data has a higher dimension than the transverse field dose distribution data. In one embodiment, calculation module 1120 may be configured to perform operation S220 described above and will not be further described here.

[0116] The second obtaining module 1130 is used to obtain a target model for determining the field center dose distribution based on the scanning parameters and the first field dose distribution data. In one embodiment, the second obtaining module 1130 can be used to perform the operation S230 described above, which will not be repeated here.

[0117] The determination module 1140 is used to input the target scanning parameters into the target model and determine the delivered dose based on the target field center dose distribution output by the target model. In one embodiment, the determination module 1140 can be used to perform the operation S240 described above, which will not be repeated here.

[0118] According to an embodiment of the present disclosure, the first acquisition module 1110 guides the movement of the particle beam through M groups of scanning parameters to obtain N transverse field dose distribution data, including: guiding the particle beam to move within a preset depth range through M groups of scanning parameters, randomly measuring the transverse field dose distribution of the particle beam at N depth positions, and obtaining M*N transverse field dose distribution data; wherein each group of scanning parameters corresponds to N transverse field dose distributions, wherein N is a positive integer.

[0119] According to an embodiment of the present disclosure, the calculation module 1120 calculates multiple first field dose distribution data corresponding to each set of scanning parameters based on multiple lateral field dose distribution data, including: obtaining a depth dose curve of the particle beam; wherein the depth dose curve is used to describe the energy deposition of the particle beam in the depth direction; calculating the depth dose curve with the N lateral field dose distribution data under each set of scanning parameters, and obtaining X first field dose distribution data corresponding to the multiple sets of scanning parameters, wherein X is a positive integer, and X>N.

[0120] According to an embodiment of the present disclosure, the calculation module 1120 calculates the depth dose curve with the N lateral field dose distribution data under each set of scanning parameters to obtain X first field dose distribution data corresponding to the multiple sets of scanning parameters, including: performing the following operations on the lateral field dose distribution data under each set of scanning parameters: multiplying the depth dose curve and the multiple lateral field dose distribution data to obtain first field dose distribution data at multiple specific depths; based on the first field dose distribution data at the specific depth, determining the first field dose distribution data at other depths except the specific depth.

[0121] According to an embodiment of the present disclosure, the second acquisition module 1130 obtains a target model for determining the dose distribution at the center of the field based on the scanning parameters and the first field dose distribution data, including: training an initial model according to the scanning parameters and the first field dose distribution data to obtain a first model, wherein the first model is used to predict the dose mask corresponding to different scanning parameters; superimposing the first model with the objective function to obtain a target model for determining the dose distribution at the center of the field, wherein the objective function is used to determine the lateral field dose distribution under ideal conditions.

[0122] According to an embodiment of the present disclosure, the second acquisition module 1130 trains an initial model based on the scanning parameters and the first field dose distribution data to obtain a first model, including: determining multiple sets of scanning parameters as input data of the initial model, and determining multiple first field dose distribution data as output data of the initial model; using each distribution feature in the first field dose distribution data as prompt information; training the initial model based on the prompt information, input data and output data to obtain the first model.

[0123] According to embodiments of the present disclosure, any multiple modules among the first obtaining module 1110, the calculation module 1120, the second obtaining module 1130, and the determination module 1140 may be combined into a single module, or any one of these modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of other modules and implemented in a single module. According to embodiments of the present disclosure, at least one of the first obtaining module 1110, the calculation module 1120, the second obtaining module 1130, and the determination module 1140 may be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on a chip, a system on a substrate, a system on a package, an application-specific integrated circuit (ASIC), or may be implemented in hardware or firmware through any other reasonable means of circuit integration or packaging, or may be implemented in any one of the three implementation methods of software, hardware, and firmware, or any appropriate combination of any of these. Alternatively, at least one of the first obtaining module 1110 , the calculating module 1120 , the second obtaining module 1130 and the determining module 1140 may be at least partially implemented as a computer program module, which may perform corresponding functions when executed.

[0124] Figure 12 The figure schematically shows a block diagram of an electronic device suitable for implementing a particle dose determination method according to an embodiment of the present disclosure.

[0125] like Figure 12 As shown, the electronic device 1200 according to an embodiment of the present disclosure includes a processor 1201, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1202 or a program loaded from a storage portion 1208 into a random access memory (RAM) 1203. The processor 1201 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or a related chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1201 may also include onboard memory for caching purposes. The processor 1201 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0126] Various programs and data required for the operation of the electronic device 1200 are stored in the RAM 1203. The processor 1201, the ROM 1202, and the RAM 1203 are connected to each other via a bus 1204. The processor 1201 performs various operations of the method flow according to the embodiment of the present disclosure by executing the programs in the ROM 1202 and / or the RAM 1203. It should be noted that the programs may also be stored in one or more memories other than the ROM 1202 and the RAM 1203. The processor 1201 may also perform various operations of the method flow according to the embodiment of the present disclosure by executing the programs stored in the one or more memories.

[0127] According to an embodiment of the present disclosure, electronic device 1200 may further include an input / output (I / O) interface 1205, which is also connected to bus 1204. Electronic device 1200 may also include one or more of the following components connected to I / O interface 1205: an input section 1206 including a keyboard, mouse, etc.; an output section 1207 including devices such as a cathode ray tube (CRT), liquid crystal display (LCD), and speakers; a storage section 1208 including a hard disk; and a communication section 1209 including a network interface card such as a LAN card or modem. Communication section 1209 performs communication processing via a network such as the Internet. A drive 1210 is also connected to I / O interface 1205 as needed. Removable media 1211, such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed in drive 1210 as needed, so that computer programs read from the removable media can be installed into storage section 1208 as needed.

[0128] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments, or may exist independently and not be incorporated into the device / apparatus / system. The computer-readable storage medium carries one or more programs, and when executed, implements the method according to the embodiments of the present disclosure.

[0129] According to an embodiment of the present disclosure, a computer-readable storage medium may be a non-volatile computer-readable storage medium, and may include, for example, but not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, a computer-readable storage medium may include the ROM 1202 and / or RAM 1203 described above, and / or one or more memories other than ROM 1202 and RAM 1203.

[0130] Embodiments of the present disclosure also include a computer program product, which includes a computer program containing program code for executing the method shown in the flowchart. When the computer program product is executed in a computer system, the program code is used to cause the computer system to implement the particle dose determination method provided by the embodiments of the present disclosure.

[0131] The computer program executes the above functions defined in the system / device of the embodiment of the present disclosure when the processor 1201 executes the computer program. According to the embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by a computer program module.

[0132] In one embodiment, the computer program may be stored on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may be transmitted and distributed in the form of a signal on a network medium, downloaded and installed via the communication portion 1209, and / or installed from the removable medium 1211. The program code contained in the computer program may be transmitted using any appropriate network medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0133] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 1209 and / or installed from the removable medium 1211. When the computer program is executed by the processor 1201, the above-described functions defined in the system of the embodiment of the present disclosure are performed. According to the embodiment of the present disclosure, the systems, devices, means, modules, units, etc. described above can be implemented by computer program modules.

[0134] According to an embodiment of the present disclosure, the program code for executing the computer program provided by the embodiment of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computer programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect via the Internet).

[0135] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0136] Those skilled in the art will appreciate that the features described in the various embodiments of the present disclosure may be combined and / or coupled in various ways, even if such combinations or couplings are not explicitly described in the present disclosure. In particular, the features described in the various embodiments of the present disclosure may be combined and / or coupled in various ways without departing from the spirit and teachings of the present disclosure. All such combinations and / or couplings fall within the scope of the present disclosure.

[0137] The above describes the embodiments of the present disclosure. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although each embodiment has been described separately above, this does not mean that the measures in each embodiment cannot be advantageously used in combination. Without departing from the scope of the present disclosure, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A particle dose determination method, characterized in that: include: The particle beam is guided to move by M groups of scanning parameters to obtain a plurality of transverse field dose distribution data; wherein each group of scanning parameters corresponds to a plurality of transverse field dose distribution data, and M is a positive integer; Calculating a plurality of first field dose distribution data corresponding to each set of scanning parameters based on the plurality of transverse field dose distribution data; wherein the dimension of the first field dose distribution data is higher than the dimension of the transverse field dose distribution data; Based on the scanning parameters and the first field dose distribution data, a target model for determining the field center dose distribution is obtained; The target scanning parameters are input into the target model, and the delivered dose is determined according to the target field center dose distribution output by the target model.

2. The particle dose determination method according to claim 1, characterized in that: The particle beam movement is guided by M sets of scanning parameters to obtain N transverse field dose distribution data, including: The particle beam is guided to move within a preset depth range by M sets of scanning parameters, and the transverse field dose distribution of the particle beam is randomly measured at N depth positions to obtain M*N transverse field dose distribution data; wherein each set of scanning parameters corresponds to N transverse field dose distributions, wherein N is a positive integer.

3. The particle dose determination method according to claim 1, characterized in that: The step of calculating, based on the plurality of transverse field dose distribution data, a plurality of first field dose distribution data corresponding to each set of scanning parameters comprises: Obtaining a depth dose curve of the particle beam; wherein the depth dose curve is used to describe the energy deposition of the particle beam in the depth direction; The depth dose curve is calculated with the N transverse field dose distribution data under each set of scanning parameters to obtain X first field dose distribution data corresponding to the multiple sets of scanning parameters, where X is a positive integer and X>N.

4. The particle dose determination method according to claim 3, characterized in that: The depth dose curve is calculated with the N lateral field dose distribution data under each set of scanning parameters to obtain X first field dose distribution data corresponding to the multiple sets of scanning parameters, including: Perform the following operations on the lateral field dose distribution data under each set of scanning parameters: Perform product calculations on the depth dose curve and the plurality of lateral field dose distribution data to obtain first field dose distribution data at a plurality of specific depths; Based on the first field dose distribution data at the specific depth, first field dose distribution data at other depths except the specific depth are determined.

5. The particle dose determination method according to claim 4, characterized in that: The step of obtaining a target model for determining a radiation field center dose distribution based on the scanning parameters and the first radiation field dose distribution data comprises: Training an initial model according to the scanning parameters and the first field dose distribution data to obtain a first model, wherein the first model is used to predict dose masks corresponding to different scanning parameters; The first model is superimposed on the objective function to obtain a target model for determining the central dose distribution of the field, wherein the objective function is used to determine the lateral dose distribution of the field under an ideal state.

6. The particle dose determination method according to claim 1, characterized in that: The step of training an initial model according to the scanning parameters and the first field dose distribution data to obtain a first model includes: Determining the multiple sets of scanning parameters as input data of an initial model, and determining the multiple first field dose distribution data as output data of the initial model; using each distribution feature in the first radiation field dose distribution data as prompt information; The initial model is trained based on the prompt information, the input data, and the output data to obtain the first model.

7. The particle dose determination method according to claim 1, characterized in that: The scanning parameters include at least the energy of the particle beam, device performance parameters, and the range covered by the particle beam; and at least some of the scanning parameters in each group are different.

8. A particle dose determination device, characterized in that: include: A first acquisition module is configured to guide the movement of the particle beam based on M groups of scanning parameters to obtain a plurality of transverse field dose distribution data; wherein each group of scanning parameters corresponds to a plurality of transverse field dose distribution data, and M is a positive integer; a calculation module, configured to calculate, based on the plurality of transverse field dose distribution data, a plurality of first field dose distribution data corresponding to each set of scanning parameters; wherein the dimension of the first field dose distribution data is higher than the dimension of the transverse field dose distribution data; A second acquisition module is configured to obtain a target model for determining a radiation field center dose distribution based on the scanning parameters and the first radiation field dose distribution data; The determination module is used to input the target scanning parameters into the target model and determine the delivered dose according to the target field center dose distribution output by the target model.

9. An electronic device comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are enabled to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to perform the method according to any one of claims 1 to 7.

Images