Method and device for determining radiation delivery plan, equipment, medium and product

Abstract

The invention relates to a method and device for determining a radiation delivery plan, equipment, a medium and a product. The method includes acquiring a predicted dose distribution of a target object, and determining a target dose distribution for a radiation delivery plan according to the predicted dose distribution and a plan quality control strategy. By using the method for determining the radiation delivery plan provided by the embodiment of the invention, high-quality target dose distribution for the radiation delivery plan can be obtained without consuming a lot of time and energy by workers.

Description

Technical Field

[0001] The present application relates to the field of radiation, and in particular to a method, device, equipment, medium and product for determining a radiation delivery plan. Background Art

[0002] For radiation delivery (e.g., radiotherapy, radiation processing, or radiation flaw detection), it is usually necessary to formulate a delivery plan before delivery to ensure that the appropriate radiation dose is used to deliver radiation to the area of ​​interest of the target object without harming the operator or other parts of the target object. How to formulate a suitable and optimal delivery plan has always been a hot issue in the industry.

[0003] As an example, the intensity-modulated radiotherapy plan in the radiation delivery plan is the most widely used treatment mode. The goal of the intensity-modulated radiotherapy plan is to ensure that the target area receives a sufficient dose of radiation while minimizing the dose to the endangered organs and surrounding normal tissues.

[0004] In traditional technology, intensity-modulated radiotherapy plans need to rely on manual setting of parameters such as target dose and weight factor, tolerance dose of organs at risk and weight factor. Staff need to adjust and optimize the parameters during the intensity-modulated radiotherapy plan making process, which consumes a lot of time and energy. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, equipment, medium and product for determining a radiation delivery plan without manually setting parameters to address the above technical problems.

[0006] In a first aspect, the present application provides a method for determining a radiation delivery plan, the method comprising:

[0007] determining a predicted dose distribution for a target object; and

[0008] Based on the predicted dose distribution and the plan quality control strategy, the target dose distribution for the radiation delivery plan is determined.

[0009] In one of the embodiments, the plan quality control strategy includes at least one of a priority control strategy, an off-target dose control strategy, a conformality control strategy, a hotspot control strategy, a target area dose control strategy, a uniformity control strategy, and an automatic normalization control strategy.

[0010] In one embodiment, if the plan quality control strategy includes multiple control strategies, determining a target dose distribution for the radiation delivery plan based on the predicted dose distribution and the plan quality control strategy includes:

[0011] Selecting any one control strategy from the plan quality control strategies as the current control strategy, and optimizing the predicted dose distribution according to the current control strategy to obtain an optimized dose distribution;

[0012] The optimized dose distribution is taken as the new predicted dose distribution, and any remaining control strategy in the plan quality control strategy is taken as the new current control strategy. The step of optimizing the predicted dose distribution according to the current control strategy is returned to execute until all control strategies in the plan quality control strategy are traversed, and the finally obtained optimized dose distribution is taken as the target dose distribution.

[0013] In one embodiment, determining a predicted dose distribution of a target object includes:

[0014] An image including the target object is input into a dose distribution prediction model to obtain a predicted dose distribution.

[0015] In one embodiment, inputting an image including a target object into a dose distribution prediction model to obtain a predicted dose distribution includes:

[0016] Input the image into the dose distribution prediction model to obtain the initial dose distribution;

[0017] The initial dose distribution is adjusted according to the dose distribution reference information to obtain a predicted dose distribution; the dose distribution reference information includes at least one of a target dose of a target area in a target image, a dose limit of an organ-at-risk area in a target image, and a priority of an organ-at-risk.

[0018] In one embodiment, the plan quality control strategy includes a priority control strategy, an off-target dose control strategy, a conformality control strategy, a hot spot control strategy, a target area dose control strategy, a uniformity control strategy, and an automatic normalization control strategy, and a target dose distribution for a radiation delivery plan is determined according to the predicted dose distribution and the plan quality control strategy, including:

[0019] The predicted dose is optimized according to the conformal control strategy and the off-target dose control strategy to obtain the first dose distribution;

[0020] The first dose distribution is optimized according to the target area dose control strategy to obtain a second dose distribution;

[0021] The second dose distribution is optimized according to the priority control strategy and the hot spot control strategy to obtain a third dose distribution;

[0022] The third dose distribution is optimized according to the uniformity control strategy and the automatic normalization control strategy to obtain the target dose distribution.

[0023] In a second aspect, the present application further provides a device for determining a radiation delivery plan, the device comprising:

[0024] A predicted dose distribution determination module, used to determine the predicted dose distribution of the target object;

[0025] The target dose distribution determination module is used to determine the target dose distribution for the radiation delivery plan based on the predicted dose distribution and the plan quality control strategy.

[0026] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores instructions, and when the processor executes the instructions, the steps of the determination method provided in the first aspect are implemented.

[0027] In a fourth aspect, the present application further provides a computer-readable storage medium having instructions stored thereon, and when the computer program is executed by a processor, the steps of the determination method provided in the first aspect above are implemented.

[0028] In a fifth aspect, the present application also provides a computer program product, comprising instructions, which, when executed by a processor, implement the steps of the determination method provided in the first aspect above.

[0029] The above-mentioned radiation delivery plan determination method, device, equipment, medium and product, the method determines the predicted dose distribution of the target object; and determines the target dose distribution for the radiation delivery plan according to the predicted dose distribution and the plan quality control strategy. In this embodiment, the predicted dose distribution is optimized using the plan quality control strategy to obtain the target dose distribution for the radiation delivery plan, so that the target dose distribution can be determined directly according to the plan quality control strategy and the predicted dose distribution, without consuming a lot of time and energy of the staff, and a more accurate and higher quality target dose distribution can be determined. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is a schematic diagram of the structure of a computer device in one embodiment;

[0031] Figure 2 A schematic flow chart of the steps of a method for determining a radiation delivery plan in one embodiment;

[0032] Figure 3 A schematic flow chart of steps of a method for determining a radiation delivery plan in another embodiment;

[0033] Figure 4 A schematic flow chart of steps of a method for determining a radiation delivery plan in another embodiment;

[0034] Figure 5 is a schematic diagram of the structure of a dose distribution prediction model in one embodiment;

[0035] Figure 6 A schematic flow chart of steps of a method for determining a radiation delivery plan in another embodiment;

[0036] Figure 7 A schematic flow chart of steps of a method for determining a radiation delivery plan in another embodiment;

[0037] Figure 8 is a schematic diagram of a target area dose control strategy in one embodiment;

[0038] Fig. 9 A schematic flow chart of steps of a method for determining a radiation delivery plan in another embodiment;

[0039] Fig.10 FIG. 1 is a schematic diagram of the structure of a device for determining a radiation delivery plan in one embodiment. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0041] The serial numbers assigned to the components in this article, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning.

[0042] Before specifically introducing the technical solutions of the embodiments of the present application, the technical background and technical evolution context on which the embodiments of the present application are based are first introduced. Intensity modulated radiotherapy planning is the most widely used treatment mode at present. The goal of intensity modulated radiotherapy planning is to adjust the irradiation dose of the region of interest, that is, to irradiate the target area with a sufficient dose, and minimize the irradiation dose to the organs at risk and the surrounding normal tissue areas. In traditional technology, intensity modulated radiotherapy planning requires manual setting of parameters such as target area dose, weight factor, tolerance dose of organs at risk and weight factor. Staff members need to repeatedly adjust and optimize the parameters during the preparation of intensity modulated radiotherapy planning, which consumes a lot of time and energy. In addition, the staff members' own experience and the time invested in the preparation of intensity modulated radiotherapy planning have a direct impact on the intensity modulated radiotherapy planning. In this regard, the present application provides a method for determining a radiation delivery plan, which can be used to automatically formulate and / or optimize plans.

[0043] The following is an introduction to the technical solutions involved in the embodiments of the present application in combination with the scenarios in which the embodiments of the present application are applied.

[0044] The method for determining the radiation delivery plan provided in the present application can be applied to a computer device, and the internal structure of the computer device can be as follows: Figure 1As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected to a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for determining a radiation delivery plan is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0045] In one embodiment, Figure 2 As shown, a method for determining a radiation delivery plan is provided. This embodiment uses the method applied to a computer device as an example. In this embodiment, the steps of the method include:

[0046] Step 200: Determine a predicted dose distribution of a target object.

[0047] The target object may refer to any one of a human body or a part of a human body (e.g., a tissue, an organ, or other combination), a water film as a whole or a part of a water film, an object to be irradiated or a part of the object, an experimental body or a part of an experimental body, and a specific space (e.g., a region of interest or a volume of interest). This embodiment does not limit this.

[0048] The predicted dose distribution refers to the dose irradiated to each area of ​​the target object and the prediction of the dose distribution position. The predicted dose distribution can be in various forms, such as a fluence map, a specific value, a mathematical model, etc. The mathematical model can, for example, include one or more mathematical functions (e.g., a dose measurement function).

[0049] The predicted dose distribution of the target object may be determined in various ways, for example, by acquiring the predicted dose distribution of the target object from a storage device of a computer device or by calculating the predicted dose distribution using a computing device.

[0050] Step 210: Determine a target dose distribution for the radiation delivery plan based on the predicted dose distribution and the plan quality control strategy.

[0051] The plan quality control strategy may be a strategy preset by a user to optimize the predicted dose distribution. The plan quality control strategy may be pre-stored in a computer device by a user.

[0052] After obtaining the predicted dose distribution, the computer device can use the plan quality control strategy to adjust the machine parameters to optimize the predicted dose distribution and obtain the target dose distribution for the radiation delivery plan. The radiation delivery plan is used to characterize the target area of ​​the target object for sufficient irradiation dose, and the corresponding machine parameters when the irradiation dose outside the target area is minimized. Machine parameters may include blade shape, number of machine jumps, etc. In addition, other methods can also be used to optimize the predicted dose distribution using the plan quality control strategy. As a non-limiting example, for example, the plan quality control strategy can be used to optimize the fluence map corresponding to the predicted dose distribution, and the optimized fluence map can be used to determine various parameters related to radiation delivery (for example, pulse intensity, width, duration, etc.); for another example, the plan quality control strategy can be used to optimize the predicted dose distribution map, and the optimized predicted dose distribution map can be used to determine the machine parameters of the radiation delivery device to perform radiation delivery, and so on.

[0053] In this embodiment, the target radiation delivery plan can be obtained by optimizing the initial dose measurement function constructed according to the predicted dose distribution using the plan quality control strategy. In this way, the target radiation delivery plan can be determined directly based on the plan quality control strategy and the initial dose measurement function without consuming a lot of time and energy of the staff, and a more accurate and higher quality target dose distribution can be determined, thereby obtaining a more accurate radiation delivery plan.

[0054] In one embodiment, the plan quality control strategy may include a priority control strategy, an off-target dose control strategy, a conformality control strategy, a hotspot control strategy, a target area dose control strategy, a uniformity control strategy, an automatic normalization control strategy, and at least one of other strategies for controlling the quality of the plan. As an example, the plan quality control strategy may include one of the above-mentioned strategies. As another example, the plan quality control strategy may include multiple of the above-mentioned strategies. During the plan optimization process, the plan quality can be controlled by a combination of plan control strategies, so that the result obtained by one optimization can meet the plan requirements set by the user. The design of the plan quality control strategy can be an abstraction of the focus points in the manual plan design and / or evaluation process. The plan control strategy combination can be a strategy combination determined with a certain sequence and / or weight considerations during the optimization process, which can automatically optimize a high-quality plan that meets clinical requirements.

[0055] The plan quality control strategy may include one or more of a priority control strategy, an off-target dose control strategy, a conformality control strategy, a hotspot control strategy, a target area dose control strategy, a uniformity control strategy, and an automatic normalization control strategy. The priority control strategy is used to characterize the optimization of the predicted dose distribution according to the set priority. The off-target dose control strategy is used to characterize the optimization of the irradiation dose outside the target area in the predicted dose distribution. The conformality control strategy is used to characterize the optimization of the matching degree between the area of ​​the prescription dose line and the target area in the predicted dose distribution. The hotspot control strategy is used to characterize the control of the hotspot of the target area in the predicted dose distribution. The target area dose control strategy is used to characterize the optimization of the irradiation dose of the target area in the predicted dose distribution. The uniformity control strategy is used to characterize the optimization of the uniformization of the irradiation dose of the target area in the predicted dose distribution. The automatic normalization control strategy is used to characterize the normalization of the irradiation dose of the target area in the predicted dose distribution.

[0056] In this embodiment, a variety of plan quality control strategies are provided, and the user can select one or more of the various plan quality control strategies to optimize the predicted dose distribution according to actual needs, which can improve the practicality of the method for determining the radiation delivery plan.

[0057] In one embodiment, Figure 3 As shown, it is related to an implementation method of determining a target dose distribution according to a predicted dose distribution and a plan quality control strategy. The steps of the implementation method may include:

[0058] Step 300: construct an initial dose measurement function according to the predicted dose distribution.

[0059] After obtaining the predicted dose distribution of the target object, the computer device constructs an initial dose measurement function according to the predicted dose distribution. The initial dose measurement function represents the corresponding relationship between the predicted dose distribution and the target dose distribution to be optimized.

[0060] Step 310: Optimize the initial dose measurement function according to the plan quality control strategy to obtain the target dose measurement function.

[0061] After obtaining the initial dose measurement function, the computer device optimizes the initial dose measurement function according to the plan quality control strategy to obtain the target dose measurement function. The description of the plan quality control strategy can refer to the specific description in the above embodiment.

[0062] Step 320: Solve the target dose measurement function to obtain the target dose distribution.

[0063] After the computer equipment obtains the target dose measurement function, which is the correspondence between the optimized predicted dose distribution and the target dose distribution, the target dose distribution can be obtained after solving the target dose measurement function, and the radiation delivery plan can be determined based on the target dose distribution.

[0064] In an optional embodiment, solving the target dose measurement function refers to making the target dose measurement function as close to zero as possible through iterative calculation.

[0065] In an optional embodiment, the correspondence between the dose distribution and the radiation delivery plan is pre-stored in the computer device. After obtaining the target dose distribution, the computer device searches the computer device for a radiation delivery plan corresponding to the dose distribution that is the same as the target dose distribution, and determines it as the target radiation delivery plan.

[0066] In this embodiment, after optimizing the initial dose calculation function constructed according to the predicted dose distribution using the plan quality control strategy, a target dose calculation function is obtained, and the target dose distribution can be obtained by solving the target dose calculation function. In this way, the target dose distribution can be determined quickly, thereby quickly determining the radiation delivery plan, thereby improving the practicality and efficiency of the method for determining the radiation delivery plan.

[0067] In one embodiment, where the planned quality control strategy includes multiple control strategies, such as Figure 4 As shown, it is related to predicting dose distribution and planning quality control strategy, and an implementation method for determining a target dose distribution for a radiation delivery plan, the steps of which include:

[0068] Step 400: Select any control strategy from the planned quality control strategies as the current control strategy.

[0069] When the plan quality control strategy includes at least two of the priority control strategy, off-target dose control strategy, conformality control strategy, hotspot control strategy, target area dose control strategy, uniformity control strategy and automatic normalization control strategy, the computer device selects any one control strategy from the multiple plan quality control strategies as the current control strategy.

[0070] Step 410: Optimize the predicted dose distribution according to the current control strategy to obtain an optimized dose distribution.

[0071] After determining the current control strategy, the computer device uses the current control strategy to optimize the predicted dose distribution to obtain an optimized dose distribution. The process of optimizing the predicted dose distribution using the current control strategy is related to the type of target control strategy selected, and different optimization methods are different for different types.

[0072] Step 420, take the optimized dose distribution as the new predicted dose distribution, and take any remaining control strategy in the planned quality control strategy as the new current control strategy, return to execute the step of optimizing the predicted dose distribution according to the current control strategy, until all control strategies in the planned quality control strategy are traversed, and take the final optimized dose distribution as the target dose distribution.

[0073] After obtaining the optimized dose distribution, the computer device uses the optimized dose distribution as the new predicted dose distribution, reselects any one control strategy from the remaining control strategies in the plan quality control strategy as the new current control strategy, and returns to execute step 410 until all control strategies in the plan quality control strategy have been traversed, and uses the optimized dose distribution obtained in the last cycle as the target dose distribution.

[0074] In this embodiment, when the plan quality control strategy includes multiple control strategies, the predicted dose distribution is optimized using the multiple control strategies, so that a better target dose distribution can be obtained, thereby obtaining a radiation delivery plan with higher quality.

[0075] In one embodiment, an implementation involving determining a predicted dose distribution of a target object includes:

[0076] The image including the target object is input into the dose distribution prediction model to obtain the predicted dose distribution.

[0077] The image of the target object may be a computed tomography (CT) image, a magnetic resonance (MR) image, an X-ray image or an ultrasound image of the target object. The computer device may obtain the image of the target object from an image device post-processing workstation, or may obtain the image of the target object from a PACS (Picture Archiving and Communication Systems) server. The image of the target object is a three-dimensional image.

[0078] The target area, the organ at risk area and other tissue areas in the image of the target object are divided. Optionally, the computer device can input the original image of the target object into a pre-trained classification model to obtain the divided image of the target object.

[0079] The dose distribution prediction model can be pre-trained by the user and stored in the computer device, or can be obtained by on-site calculation or adjustment. After acquiring an image including the target object, the computer device inputs the image into the pre-trained dose distribution prediction model, and outputs the predicted dose distribution through the dose distribution prediction model.

[0080] In an optional embodiment, the training method of the dose distribution prediction model includes: obtaining a training sample image set, outlining the target area in the training sample set, and obtaining gold standard image information of the dose distribution in the target area and outside the target area; inputting the training sample set and the gold standard image information into the initial neural network, and performing iterative training according to a pre-designed loss function until a preset iteration condition is reached to obtain a dose distribution prediction model. The iteration condition can be a preset number of iterations, or a preset accuracy, etc. The initial neural network can be 3D-UNet, UNet, 3D-UNet, or VNet.

[0081] In an optional embodiment, the structure of the dose distribution prediction model is as follows: Figure 5 shown.

[0082] In this embodiment, the predicted dose distribution can be obtained by directly inputting the image including the target object into the pre-trained dose distribution prediction model. This method of obtaining the predicted dose distribution is simple and fast.

[0083] Without limitation thereto, the dose distribution prediction model may also be trained using other types of data in addition or in lieu thereof, such as fluence maps, radiation experiment data, machine parameters, environmental conditions, patient physical conditions, etc., which are not limited here. Accordingly, in addition to or in lieu of image information, other types of information (such as, but not limited to, a two-dimensional or three-dimensional model of the target area, patient disease data) may be input into the dose distribution prediction model to obtain a predicted dose distribution.

[0084] In one embodiment, Figure 6 As shown, an implementation method involves inputting an image including a target object into a dose distribution prediction model to obtain a predicted dose distribution, and the steps of the implementation method include:

[0085] Step 600: Input the image into the dose distribution prediction model to obtain the initial dose distribution.

[0086] The description of the dose distribution prediction model may refer to the specific description in the above embodiment. The computer device inputs the acquired image into the pre-trained dose distribution prediction model to obtain the initial dose distribution in the image.

[0087] Step 610, adjusting the initial dose distribution according to the dose distribution reference information to obtain a predicted dose distribution; the dose distribution reference information includes at least one of a target dose of the target area in the target image, a dose limit of the organ at risk area in the target image, and a priority of the organ at risk.

[0088] Since the initial radiation delivery plan corresponding to the initial dose distribution may not meet the clinical specific requirements based on the patient's condition, the user may need a way to express specific requirements for plan quality. The dose distribution reference information (such as the target table) provides a rich way for users to express their plan requirements, and users can express their specific requirements for the plan in a personalized way in the dose distribution reference information. As a non-limiting example, the dose distribution reference information can be set to include information such as the target area prescription dose, organ limit requirements, and priority settings, where the priority information can characterize the importance between the target area and the organ and between organs.

[0089] The dose distribution reference information may be information pre-set by the user according to the specificity of the target object. The dose distribution reference information includes one or more of the target dose of the target area in the image, the dose limit of the organ at risk area in the image, and the priority of the organ at risk. The target dose of the target area in the image refers to the prescription dose set by the user for the target area in the image according to the specificity corresponding to the image. The dose limit of the organ at risk area in the image refers to the unacceptable lower limit requirement set by the user for the organ at risk outside the target in the image. The priority of the organ at risk refers to the priority of the organ at risk relative to the target area. The priority of the organ at risk may include high priority, medium priority, and low priority. High priority means that the priority of the organ at risk is higher than the priority of the target area, that is, the dose limit requirement for the organ at risk area in the image must be met, that is, the dose distribution of the organ at risk area in the predicted dose distribution selects the minimum value of the dose limit of the organ at risk area and the initial dose distribution. Medium priority means that the organ at risk area is in a competitive relationship with the target area, and the irradiation dose of the organ at risk area is lowered while ensuring that the target area has sufficient dose irradiation, that is, the dose distribution of the organ at risk area in the predicted dose distribution is determined according to the initial dose distribution. Low priority means that the priority of the target area is higher than that of the organ at risk. It is necessary to ensure that the target area has sufficient dose irradiation. The dose distribution of the organ at risk area in the predicted dose distribution is still determined based on the initial dose distribution.

[0090] In an optional non-limiting embodiment, the dose distribution reference information may be as shown in the following table:

[0091]

[0092] In another optional non-limiting embodiment, the dose distribution reference information may be shown in the following table:

[0093]

[0094] After obtaining the initial dose distribution, the computer device uses at least one of the dose distribution reference information to adjust the initial dose distribution to obtain a predicted dose distribution.

[0095] In this embodiment, by using dose distribution reference information to adjust the initial dose distribution obtained according to the dose distribution prediction model, a better predicted dose distribution can be obtained, thereby obtaining a better target dose distribution for radiation delivery planning.

[0096] In one embodiment, when the plan quality control strategy includes a priority control strategy, an off-target dose control strategy, a conformality control strategy, a hotspot control strategy, a target area dose control strategy, a uniformity control strategy, and an automatic normalization control strategy, as Figure 7 As shown, it is related to an implementation method of determining a target dose distribution for a radiation delivery plan according to a predicted dose distribution and a plan quality control strategy, and the steps of the implementation method include:

[0097] Step 700: Optimize the predicted dose distribution according to the conformality control strategy and the off-target dose control strategy to obtain a first dose distribution.

[0098] When the computer equipment optimizes the predicted dose distribution, it can first use the conformality control strategy to optimize the predicted dose distribution, and then use the off-target dose control strategy to optimize the optimized predicted dose distribution to obtain the first dose distribution; it can also first use the off-target dose control strategy to optimize the predicted dose distribution, and then use the conformality control strategy to optimize the optimized predicted dose distribution to obtain the first dose distribution.

[0099] In an optional embodiment, the initial dose calculation function f constructed according to the predicted dose distribution can be expressed as: f = ω1*∑(D i -D pre ,0) 2 , where ω1 is a parameter set artificially, D i represents the dose corresponding to the i-th voxel to be optimized in the image, D pre represents the dose corresponding to the ith voxel in the predicted dose distribution. The conformality control strategy f1 can be expressed as f1=ω2*(f CI -C index ) 2 , where ω2 is a parameter set artificially, C index =1, indicating that the conformity between the desired prescription dose coverage area and the target area is 1, f CI =TV_RI*TV_RI / (V_RI*TV), TV_RI represents the volume of the intersection of the prescription dose coverage area and the target area; V_RI represents the volume of the prescription dose coverage area; TV represents the volume of the target area. The off-target dose control strategy f2 can be expressed as f2=ω3*∑(max(D i -D pre ,0)) 2, where ω3 is a manually set parameter. The first dose measurement function after optimizing the initial dose measurement function according to the conformality control strategy and the off-target dose control strategy can be expressed as F1=f+f1+f2; the first dose distribution is obtained by solving the first dose measurement function. The dose measurement functions, control strategies, etc. listed above can adopt other types of forms.

[0100] In another optional embodiment, the off-target dose control strategy can optimize the off-target dose according to a preset drop rule. The preset drop rule is as follows: Figure 8 shown. Figure 8 The X-axis represents the shortest distance from a point in the off-target region to the target boundary, and the Y-axis represents the dose.

[0101] Step 710: Optimize the first dose distribution according to the target area dose control strategy to obtain a second distribution.

[0102] After obtaining the first dose distribution, the computer device uses the target area dose control strategy to optimize the first dose distribution to obtain the second dose distribution.

[0103] In an optional embodiment, the target area dose control strategy f3 can be expressed as f3=ω4*∑(min(D i -D prescripion ,0)) 2 , where ω4 is a parameter set artificially, D prescription The second dose calculation function after optimizing the first dose calculation function using the target area dose control strategy can be expressed as F2=F1+f3, and the second dose distribution is obtained by solving the second dose calculation function.

[0104] Step 720: Optimize the second dose distribution according to the priority control strategy and the hot spot control strategy to obtain a third dose distribution.

[0105] When the computer device optimizes the second dose distribution, it can first use the priority control strategy to optimize the second dose distribution, and then use the hotspot control strategy to optimize the optimized second dose distribution to obtain a third dose distribution; it can also first use the hotspot control strategy to optimize the second dose distribution, and then use the priority control strategy to optimize the optimized second dose distribution to obtain a third dose distribution.

[0106] In an optional embodiment, the priority control strategy L can be expressed as: Among them, λ, α, β are all artificially set parameters, F jThe dose distribution of the high-priority organ-at-risk region in the dose distribution is represented by the Lagrange multiplier method, and the dose distribution of the high-priority organ-at-risk region in the second dose estimation function is optimized. The hotspot control strategy f4 can be expressed as: Among them, ω5 is a manually set parameter, N represents the total number of voxels in the target area and outside the target area in the image, D0 represents the maximum exposure dose of all voxels set by the user, and p represents a parameter factor for the dose volume effect of the target area and outside the target area. When the third dose estimation function is optimized using the priority control strategy and the hot spot control strategy, the obtained third dose estimation function can be expressed as: The third dose distribution is obtained by solving the third dose measurement function.

[0107] Step 730: Optimize the third dose distribution according to the uniformity control strategy and the automatic normalization control strategy to obtain a target dose distribution.

[0108] After obtaining the third dose distribution, the computer device optimizes the third dose distribution according to the automatic normalization control strategy to obtain the target dose distribution.

[0109] In an optional embodiment, the uniformity control strategy f5 can be expressed as: f5 = ω6*[(D2-D mean ) 2 +(D mean -D 98 ) 2 ], where ω6 is a parameter set artificially, D mean represents the average dose in the target area, D2 represents the order of the voxel doses in the target area from high to low, and the dose of the voxel points corresponding to the first 2% is D 98 Indicates that the voxel doses in the target area are sorted from high to low, and the doses of the voxel points corresponding to the first 98%. The average dose in the target area is updated according to the iteration of the target dose measurement function corresponding to the target dose distribution. In other words, after the third dose measurement function is optimized according to the uniformity control strategy, the measurement function is solved through iteration until the number of iterations reaches the preset number, and the average dose in the target area after each iteration will be updated. The automatic normalization control strategy normalizes the dose in the target area according to the preset proportional coefficient. The target dose measurement function can be expressed as F5=f5+γf t , where γ represents the preset proportional coefficient, f t Represents the dose distribution function in the target area. For example, assuming that the dose in the target area after the uniformity control strategy is 4980 cGy and the prescription dose is 5000 cGy, the proportionality coefficient can be expressed as 5000 cGy / 4980 cGy.

[0110] In this embodiment, the priority control strategy, off-target dose control strategy, conformal control strategy, hot spot control strategy, target area dose control strategy, uniformity control strategy and automatic normalization control strategy in the plan quality control strategy are used to optimize the predicted dose distribution, and the obtained target dose distribution is more accurate, and the target radiation delivery plan obtained using the target dose distribution is more accurate. In addition, the dose measurement function, control strategy, etc. listed in this embodiment can adopt other types of forms.

[0111] See also Fig. 9 One embodiment of the present application provides a method for determining a radiation delivery plan, the method comprising the steps of:

[0112] Step 900: input the acquired image including the target object into a dose distribution prediction model to obtain an initial dose distribution;

[0113] Step 910: adjusting the initial dose distribution according to the dose distribution reference information to obtain a predicted dose distribution; the dose distribution parameter information includes the target dose of the target area in the image, the dose limit of the organ at risk area in the image, and the priority of the organ at risk;

[0114] The dose distribution reference information may include a target table with priorities, and the predicted dose distribution obtained by adjusting the initial dose distribution according to the target table with priorities may be referred to as a clinical target. Alternatively or additionally, the dose distribution reference information may also include other types of information, such as other types of target tables, fluence maps, etc. After the clinical target is generated, the target area in the image of the target object is delineated (i.e., the auxiliary structure is preprocessed) according to the clinical target and the initial dose distribution to distinguish the target area from the area outside the target area in the image.

[0115] Step 920: construct an initial dose measurement function according to the predicted dose distribution;

[0116] Step 930: Optimize the initial dose calculation function according to the conformality control strategy and the off-target dose control strategy to obtain a first dose calculation function;

[0117] Step 940: Optimize the first dose calculation function according to the target area dose control strategy to obtain a second dose calculation function;

[0118] Step 950: Optimize the second dose measurement function according to the priority control strategy and the hot spot control strategy to obtain a third dose measurement function;

[0119] Step 960: Optimize the third dose measurement function according to the uniformity control strategy and the automatic normalization control strategy to obtain a target dose measurement function;

[0120] Step 970: Solve the target dose measurement function to obtain the target dose distribution for the radiation delivery plan.

[0121] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0122] Based on the same or similar inventive concept, the embodiment of the present application also provides a device for determining a radiation delivery plan for implementing the method for determining a radiation delivery plan involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more devices for determining a radiation delivery plan provided below can refer to the limitations of the method for determining a radiation delivery plan above, and will not be repeated here.

[0123] In one embodiment, Fig.10 As shown, a device 10 for determining a radiation delivery plan is provided, comprising: a predicted dose distribution determination module 11 and a target dose distribution determination module 12, wherein:

[0124] The predicted dose distribution determination module 11 is used to determine the predicted dose distribution of the target object.

[0125] The target dose distribution determination module 12 is used to determine the target dose distribution for the radiation delivery plan according to the predicted dose distribution and the plan quality control strategy.

[0126] In one embodiment, the plan quality control strategy includes at least one of a priority control strategy, an off-target dose control strategy, a conformality control strategy, a hotspot control strategy, a target area dose control strategy, a uniformity control strategy, and an automatic normalization control strategy.

[0127] In one embodiment, the determination unit 12 is specifically used to select any one control strategy from the planned quality control strategy as the current control strategy, and optimize the predicted dose distribution according to the current control strategy to obtain an optimized dose distribution; use the optimized dose distribution as the new predicted dose distribution, and use any remaining control strategy in the planned quality control strategy as the new current control strategy, return to execute the step of optimizing the predicted dose distribution according to the current control strategy, until all control strategies in the planned quality control strategy are traversed, and the finally obtained optimized dose distribution is used as the target dose distribution.

[0128] In one embodiment, the acquisition module 11 is specifically used to input the image including the target object into the dose distribution prediction model to obtain the predicted dose distribution.

[0129] In one embodiment, the acquisition module 11 is specifically used to input the image into a dose distribution prediction model to obtain an initial dose distribution; adjust the initial dose distribution according to the dose distribution reference information to obtain a predicted dose distribution; the dose distribution reference information includes at least one of the target dose of the target area in the target image, the dose limit of the organ at risk area in the target image, and the priority of the organ at risk.

[0130] In one embodiment, the determination unit is specifically used to optimize the predicted dose distribution according to the conformality control strategy and the off-target dose control strategy to obtain a first dose distribution; optimize the first dose distribution according to the target area dose control strategy to obtain a second dose distribution; optimize the second dose distribution according to the priority control strategy and the hot spot control strategy to obtain a third dose distribution; optimize the third dose distribution according to the uniformity control strategy and the automatic normalization control strategy to obtain a target dose distribution.

[0131] Each module in the above-mentioned radiation delivery plan determination device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0132] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 1 As shown. Those skilled in the art can understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0133] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0134] determining a predicted dose distribution for a target object; and

[0135] Based on the predicted dose distribution and the plan quality control strategy, the target dose distribution for the radiation delivery plan is determined.

[0136] In one embodiment, the plan quality control strategy includes at least one of a priority control strategy, an off-target dose control strategy, a conformality control strategy, a hotspot control strategy, a target area dose control strategy, a uniformity control strategy, and an automatic normalization control strategy.

[0137] In one embodiment, when the processor executes the computer program, the following steps are also implemented: any one control strategy is selected from the planned quality control strategy as the current control strategy, and the predicted dose distribution is optimized according to the current control strategy to obtain an optimized dose distribution; the optimized dose distribution is used as the new predicted dose distribution, and any one of the remaining control strategies in the planned quality control strategy is used as the new current control strategy, and the step of optimizing the predicted dose distribution according to the current control strategy is returned to execute until all the control strategies in the planned quality control strategy are traversed, and the finally obtained optimized dose distribution is used as the target dose distribution.

[0138] In one embodiment, when the processor executes the computer program, the following steps are further implemented: inputting an image including the target object into a dose distribution prediction model to obtain a predicted dose distribution.

[0139] In one embodiment, when the processor executes the computer program, the following steps are also implemented: inputting the image into the dose distribution prediction model to obtain an initial dose distribution; adjusting the initial dose distribution according to the dose distribution reference information to obtain a predicted dose distribution; the dose distribution reference information includes at least one of the target dose of the target area in the target image, the dose limit of the organ-at-risk area in the target image, and the priority of the organ-at-risk.

[0140] In one embodiment, when the processor executes the computer program, the following steps are also implemented: optimizing the predicted dose distribution according to the conformality control strategy and the off-target dose control strategy to obtain a first dose distribution; optimizing the first dose distribution according to the target area dose control strategy to obtain a second dose distribution; optimizing the second dose distribution according to the priority control strategy and the hot spot control strategy to obtain a third dose distribution; optimizing the third dose distribution according to the uniformity control strategy and the automatic normalization control strategy to obtain a target dose distribution.

[0141] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0142] determining a predicted dose distribution for a target object; and

[0143] Based on the predicted dose distribution and the plan quality control strategy, the target dose distribution for the radiation delivery plan is determined.

[0144] In one embodiment, the plan quality control strategy includes at least one of a priority control strategy, an off-target dose control strategy, a conformality control strategy, a hotspot control strategy, a target area dose control strategy, a uniformity control strategy, and an automatic normalization control strategy.

[0145] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: any one control strategy is selected from the planned quality control strategy as the current control strategy, and the predicted dose distribution is optimized according to the current control strategy to obtain an optimized dose distribution; the optimized dose distribution is used as the new predicted dose distribution, and any one of the remaining control strategies in the planned quality control strategy is used as the new current control strategy, and the step of optimizing the predicted dose distribution according to the current control strategy is returned to execute until all the control strategies in the planned quality control strategy are traversed, and the finally obtained optimized dose distribution is used as the target dose distribution.

[0146] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: inputting an image including the target object into a dose distribution prediction model to obtain a predicted dose distribution.

[0147] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: inputting the image into the dose distribution prediction model to obtain an initial dose distribution; adjusting the initial dose distribution according to the dose distribution reference information to obtain a predicted dose distribution; the dose distribution reference information includes at least one of the target dose of the target area in the target image, the dose limit of the organ-at-risk area in the target image, and the priority of the organ-at-risk.

[0148] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: optimizing the predicted dose distribution according to the conformality control strategy and the off-target dose control strategy to obtain a first dose distribution; optimizing the first dose distribution according to the target area dose control strategy to obtain a second dose distribution; optimizing the second dose distribution according to the priority control strategy and the hot spot control strategy to obtain a third dose distribution; optimizing the third dose distribution according to the uniformity control strategy and the automatic normalization control strategy to obtain a target dose distribution.

[0149] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0150] determining a predicted dose distribution for a target object; and

[0151] Based on the predicted dose distribution and the plan quality control strategy, the target dose distribution for the radiation delivery plan is determined.

[0152] In one embodiment, the plan quality control strategy includes at least one of a priority control strategy, an off-target dose control strategy, a conformality control strategy, a hotspot control strategy, a target area dose control strategy, a uniformity control strategy, and an automatic normalization control strategy.

[0153] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: any one control strategy is selected from the planned quality control strategy as the current control strategy, and the predicted dose distribution is optimized according to the current control strategy to obtain an optimized dose distribution; the optimized dose distribution is used as the new predicted dose distribution, and any one of the remaining control strategies in the planned quality control strategy is used as the new current control strategy, and the step of optimizing the predicted dose distribution according to the current control strategy is returned to execute until all the control strategies in the planned quality control strategy are traversed, and the finally obtained optimized dose distribution is used as the target dose distribution.

[0154] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: inputting an image including the target object into a dose distribution prediction model to obtain a predicted dose distribution.

[0155] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: inputting the target image into the dose distribution prediction model to obtain an initial dose distribution; adjusting the initial dose distribution according to the dose distribution reference information to obtain a predicted dose distribution; the dose distribution reference information includes at least one of the target dose of the target area in the target image, the dose limit of the organ-at-risk area in the target image, and the priority of the organ-at-risk.

[0156] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: optimizing the predicted dose distribution according to the conformality control strategy and the off-target dose control strategy to obtain a first dose distribution; optimizing the first dose distribution according to the target area dose control strategy to obtain a second dose distribution; optimizing the second dose distribution according to the priority control strategy and the hot spot control strategy to obtain a third dose distribution; optimizing the third dose distribution according to the uniformity control strategy and the automatic normalization control strategy to obtain a target dose distribution.

[0157] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0158] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0159] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining a radiation delivery plan, characterized in that: The determination method comprises: determining a predicted dose distribution for a target object; and Based on the predicted dose distribution and a plan quality control strategy, a target dose distribution for the radiation delivery plan is determined.

2. The determination method according to claim 1, characterized in that: The plan quality control strategy includes at least one of a priority control strategy, an off-target dose control strategy, a conformality control strategy, a hotspot control strategy, a target area dose control strategy, a uniformity control strategy and an automatic normalization control strategy.

3. The determination method according to claim 2, characterized in that: The plan quality control strategy includes the priority control strategy, the off-target dose control strategy, the conformality control strategy, the hotspot control strategy, the target area dose control strategy, the uniformity control strategy and the automatic normalization control strategy. The target dose distribution for the radiation delivery plan is determined according to the predicted dose distribution and the plan quality control strategy, including: Optimizing the predicted dose distribution according to the conformality control strategy and the off-target dose control strategy to obtain a first dose distribution; Optimizing the first dose distribution according to the target area dose control strategy to obtain a second dose distribution; Optimizing the second dose distribution according to the priority control strategy and the hot spot control strategy to obtain a third dose distribution; and The third dose distribution is optimized according to the uniformity control strategy and the automatic normalization control strategy to obtain the target dose distribution.

4. The determination method according to claim 1, characterized in that: In the case where the plan quality control strategy includes multiple control strategies, determining the target dose distribution for the radiation delivery plan according to the predicted dose distribution and the plan quality control strategy includes: selecting any one control strategy from the plan quality control strategies as the current control strategy, and optimizing the predicted dose distribution according to the current control strategy to obtain an optimized dose distribution; and The optimized dose distribution is taken as the new predicted dose distribution, and any remaining control strategy in the planned quality control strategy is taken as the new current control strategy, and the step of optimizing the predicted dose distribution according to the current control strategy is returned to execute until all control strategies in the planned quality control strategy are traversed, and the finally obtained optimized dose distribution is taken as the target dose distribution.

5. The determination method according to claim 1, characterized in that: The step of determining a predicted dose distribution of a target object comprises: An image including the target object is input into a dose distribution prediction model to obtain the predicted dose distribution.

6. The determination method according to claim 5, characterized in that: The step of inputting the image including the target object into a dose distribution prediction model to obtain the predicted dose distribution includes: Inputting the image into the dose distribution prediction model to obtain an initial dose distribution; and The initial dose distribution is adjusted according to dose distribution reference information to obtain the predicted dose distribution; the dose distribution reference information includes at least one of a target dose of a target area in the target image, a dose limit of an organ-at-risk area in the target image, and a priority of the organ-at-risk.

7. A device for determining a radiation delivery plan, characterized in that: The determining device comprises: a predicted dose distribution determination module, used to determine a predicted dose distribution of a target object; and The target dose distribution determination module is used to determine the target dose distribution for the radiation delivery plan according to the predicted dose distribution and a plan quality control strategy.

8. A computer device comprising a memory and a processor, wherein the memory stores instructions, characterized in that: When the processor executes the instructions, the steps of the determination method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by a processor, the steps of the determination method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising instructions, characterized in that When the instructions are executed by a processor, the steps of the determination method according to any one of claims 1 to 6 are implemented.

Images