Method, device, equipment, medium and program product for setting radiotherapy plan parameters

Abstract

This application relates to a method, apparatus, device, medium, and program product for setting radiotherapy planning parameters. The method includes acquiring the delineation results of the target area and organs at risk in medical images for radiotherapy planning; acquiring a radiotherapy structure file based on the delineation results of the target area and organs at risk; and obtaining radiotherapy planning parameters based on the radiotherapy structure file and a preset neural network model. The radiotherapy planning parameters include field parameters and / or collimator angles, and the field parameters include at least one of the number of fields, field angle, and field energy. This method can automatically set radiotherapy planning parameters based on the received delineation results of the target area and organs at risk from the physician, eliminating the need for manual determination of radiotherapy planning parameters based on experience. This improves the accuracy of determining radiotherapy planning parameters and selects the optimal energy combination based on the relationship between the target area and organs at risk. It supports collimator angle prediction, improves target conformity, reduces the dose to organs at risk, and avoids harm to organs at risk.

Description

Technical Field

[0001] This application relates to the field of radiotherapy technology, and in particular to a method, apparatus, device, medium, and program product for setting radiotherapy planning parameters. Background Technology

[0002] The treatment planning system (TPS) is an indispensable core component of radiotherapy solutions. Treatment planning uses a specific TPS to inversely optimize the planning target volume (PTV) and organ at risk (OAR) by setting target limits. A crucial aspect of treatment planning is the setting of field parameters and collimator angles.

[0003] In traditional techniques, the settings for the firing field parameters and collimator angles are primarily determined manually by physicists based on experience. Therefore, this traditional method of setting firing field parameters and collimator angles suffers from low accuracy. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, device, equipment, medium, and procedure for setting radiotherapy planning parameters that can improve accuracy in addressing the aforementioned technical problems.

[0005] Firstly, this application provides a method for setting radiotherapy planning parameters. The method includes:

[0006] Obtain the delineation results of the target area and organs at risk in medical imaging for radiotherapy planning;

[0007] Obtain radiotherapy structural files based on the delineation results of the target area and organs at risk;

[0008] Based on the radiotherapy structure file and the preset neural network model, the radiotherapy planning parameters are obtained; the radiotherapy planning parameters include field parameters and / or collimator angles, and the field parameters include at least one of the following: number of fields, field angle, and field energy.

[0009] In one embodiment, the neural network model is obtained by training a preset initial neural network model based on a sample training set. The sample training set includes a first sample radiotherapy structure file and first sample radiotherapy plan parameters, a second sample radiotherapy structure file and second sample radiotherapy plan parameters; wherein, the first sample radiotherapy plan parameters are single-energy radiotherapy plan parameters; and the second sample radiotherapy plan parameters are mixed-energy radiotherapy plan parameters.

[0010] In one embodiment, radiotherapy planning parameters are obtained based on the radiotherapy structure file and a preset neural network model, including:

[0011] The radiotherapy structure file is input into the neural network model to obtain the radiation field parameters and collimator angle.

[0012] In one embodiment, the neural network model includes a first neural network model and a second neural network model; based on the radiotherapy structure file and the preset neural network model, radiotherapy planning parameters are obtained, including:

[0013] Input the radiotherapy structure file into the first neural network model to obtain the radiation field parameters;

[0014] The field angle from the field parameters is input into the second neural network model to obtain the collimator angle.

[0015] In one embodiment, obtaining the radiotherapy structure file based on the target area delineation results includes:

[0016] Based on the target area delineation results, determine the characteristic information of the target area;

[0017] Based on the target area delineation results, determine the characteristic information of organs at risk related to the target area;

[0018] The characteristic information of the target area and the characteristic information of the organs at risk are identified as the radiotherapy structure file.

[0019] In one embodiment, the feature information of the target region includes at least one of the target region's volume and the target region's geometric center coordinates.

[0020] Secondly, this application also provides a device for setting radiotherapy planning parameters. The device includes:

[0021] The first acquisition module is used to acquire the delineation results of the target area in the medical images of the radiotherapy plan;

[0022] The second acquisition module is used to obtain radiotherapy structure files based on the target area delineation results.

[0023] The third acquisition module is used to obtain radiotherapy planning parameters based on the radiotherapy structure file and the preset neural network model. The radiotherapy planning parameters include field parameters and collimator angle. The field parameters include at least one of the following: number of fields, field angle, and field energy.

[0024] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method in any of the embodiments of the first aspect described above.

[0025] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the method in any of the embodiments of the first aspect described above.

[0026] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the method in any of the embodiments of the first aspect described above.

[0027] The aforementioned method, apparatus, equipment, media, and program products for setting radiotherapy planning parameters obtain the delineation results of the target area and organs at risk in the radiotherapy planning medical images; obtain the radiotherapy structure file based on the delineation results of the target area and organs at risk; and obtain the radiotherapy planning parameters based on the radiotherapy structure file and a preset neural network model. The radiotherapy planning parameters include field parameters and / or collimator angles, with field parameters including at least one of the following: number of fields, field angle, and field energy. By using field energy, number, angle, and collimator angle as features in training, the system automatically sets the aforementioned radiotherapy planning parameters based on the received radiotherapy plan and the delineation results of the target area and organs at risk drawn by the physician. This eliminates the need for manual determination of radiotherapy planning parameters based on experience, improving the accuracy of determining radiotherapy planning parameters. Furthermore, it selects the optimal energy combination based on the relationship between the target area and organs at risk, supports collimator angle prediction, improves target conformity, reduces the dose to organs at risk, and avoids harm to organs at risk. Attached Figure Description

[0028] Figure 1 This is an application environment diagram of a method for setting radiotherapy planning parameters in one embodiment;

[0029] Figure 2 This is a flowchart illustrating a method for setting radiotherapy planning parameters in one embodiment;

[0030] Figure 3 This is a flowchart illustrating a method for setting radiotherapy planning parameters in another embodiment;

[0031] Figure 4 This is a flowchart illustrating a method for setting radiotherapy planning parameters in another embodiment;

[0032] Figure 5 This is a flowchart illustrating a method for setting radiotherapy planning parameters in another embodiment;

[0033] Figure 6 This is a flowchart illustrating a method for setting radiotherapy planning parameters in another embodiment;

[0034] Figure 7 This is a structural block diagram of a device for setting radiotherapy planning parameters in one embodiment. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0036] Intensity-modulated radiation therapy (IMRT) is characterized by high dose conformity, rapid dose drop outside the target area, and good protection of surrounding normal tissues. The treatment planning system (TPS) is an indispensable core component of radiotherapy solutions. IMRT planning uses a specific TPS to set target limits for the planning target volume (PTV) and organ at risk (OAR) for inverse optimization, resulting in a more rational treatment plan. This effectively reduces side effects during radiotherapy and improves treatment quality. A crucial aspect of IMRT planning is the setting of field parameters and collimator angles. Field parameters include: radiation type (X-ray, electron beam, or other radiation), radiation energy (6MV, 10MV, or other energies), field angle, and number of fields. Currently, these parameters need to be manually set by physicists based on experience. The manual planning process is extremely cumbersome. For inexperienced physicists, it requires repeatedly adjusting the field parameters based on the optimized results; for experienced physicists, it requires manually inputting the field parameters, both of which are time-consuming and inefficient. Furthermore, manually designed plans are often not optimal, merely meeting the doctor's requirements and being clinically acceptable, thus having relatively low accuracy.

[0037] Based on this, this application provides a method for setting radiotherapy planning parameters that can accurately set the field parameters and collimator angle. The method for setting radiotherapy planning parameters provided in this application can be applied to, for example... Figure 1 The computer device shown is a terminal, and its internal structure diagram can be as follows. Figure 1As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computational and control capabilities. Based on the delineation results of the target area and organs at risk in the acquired medical images of the radiotherapy plan and a preset neural network model, the processor can obtain radiotherapy plan parameters. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for wired or wireless communication with external terminals. Wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for setting radiotherapy plan parameters. The display screen of the computer device can be an LCD screen or an e-ink screen. The input devices of the computer device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device casing, or an external keyboard, touchpad, or mouse. The terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle systems. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0038] In one embodiment, such as Figure 2 As shown, a method for setting radiotherapy planning parameters is provided, which can be applied to... Figure 1 Taking a computer device as an example, the explanation includes the following steps:

[0039] S202, Obtain the delineation results of the target area and organs at risk in the medical images of the radiotherapy plan.

[0040] Generally, a radiotherapy plan can include three types of documents: medical images, structural files, and a planning document. Medical images can be CT or MRI images, used to provide operators with a basis for delineating the target area and organs at risk; this is not limited to these categories. Further, the target area refers to the location of the tumor; organs at risk refer to sensitive sites threatened by the tumor, such as the heart, brain, and kidneys, but not to tumor sites. The radiotherapy structural file is the result file obtained by the operator based on the medical images, reflecting the coordinate information, color information, and name of the target area. The radiotherapy planning document is the operator's planning document, containing the position and angle of the collimator blades, etc.

[0041] The delineation results of organs at risk are images of the target area and organs at risk marked by the operator in the medical images of the radiotherapy plan, and these delineation results can be stored in the database.

[0042] Optionally, the computer device can directly obtain the delineation results of the target area and organs at risk in the radiotherapy plan medical images from the database, or it can input the obtained radiotherapy plan medical images into a preset delineation model to obtain the delineation results of the target area and organs at risk in the radiotherapy plan medical images.

[0043] S204: Obtain radiotherapy structural files based on the delineation results of the target area and organs at risk.

[0044] The radiotherapy structure file may include: target volume and geometric center coordinates, volume and geometric center coordinates of each organ at risk, minimum distance from each organ at risk to the target, minimum and maximum distance between the skin and the target, projection shape of the target at different radiation field angles, color information of the target, and target name, etc.

[0045] Specifically, the computer equipment can calculate the feature information of the target area and the organ at risk based on the pixel coordinates of the delineation results, the pixel coordinates of the target area, and the pixel coordinates of the organ at risk. This feature information is then used as the radiotherapy result file. Alternatively, the delineation results can be input into a pre-defined segmentation network model to obtain the feature information of the target area and the organ at risk, which is then used as the radiotherapy result file. There is no limitation on this approach.

[0046] S206. Based on the radiotherapy structure file and the preset neural network model, obtain the radiotherapy planning parameters; the radiotherapy planning parameters include field parameters and / or collimator angles, and the field parameters include at least one of the following: number of fields, field angle, and field energy.

[0047] Specifically, the computer device can input the radiotherapy structure file into a preset neural network model and simultaneously output the field parameters and / or collimator angle. Alternatively, it can input the radiotherapy result file into a preset neural network model to output the field parameters, and then input the field parameters into another preset neural network model to obtain the collimator angle; there is no limitation on this. The preset neural network model is obtained by training an initial preset neural network model based on a sample training set. The sample training set used during the training process consists of a large number of clinical IMRT radiotherapy plan samples. The samples input into the sample training set can include radiotherapy result files determined based on the delineation results of target areas and organs at risk from medical images. Optionally, the samples output from the training set may include samples consisting entirely of single-energy radiotherapy planning parameters. For example, the output samples may consist entirely of radiotherapy planning parameters with normal radiotherapy energy, or entirely of mixed-energy radiotherapy planning parameters. Alternatively, the output sample set may include 50% mixed-energy radiotherapy planning parameters and 50% normal-energy radiotherapy planning parameters, or 30% normal-energy radiotherapy planning parameters and 70% mixed-energy radiotherapy planning parameters. Optionally, the neural network model of this application can perform feature extraction for tumors in different locations. Optionally, the neural network model can be any of the following: convolutional neural network, recurrent neural network, or adversarial network; this embodiment is not limited to any of these.

[0048] For example, taking a case of rectal cancer, the organs at risk include the bladder, left femoral head, and right femoral head. The features input to the neural network model include: target area (intestine) volume, target area geometric center coordinates, bladder geometric center coordinates and its minimum distance to the target area, left femoral head geometric center coordinates and its minimum distance to the target area, right femoral head geometric center coordinates and its minimum distance to the target area, and the projection of the target area at different radiation field angles. The output information includes at least one of the following: radiation field energy, number of radiation fields, radiation field angle, and collimator angle corresponding to each radiation field. In this embodiment, "radiation field" can also be called "irradiation field," which can be understood as: the radiation emitted by the radiotherapy machine passes through the skin to reach the patient's lesion site, and a range is defined on the human body surface by the simulator. Optionally, the radiation field can be located in the front, back, left, and right directions of the target.

[0049] The aforementioned method for setting radiotherapy planning parameters involves obtaining the delineation results of the target area and organs at risk in the radiotherapy plan medical images; obtaining a radiotherapy structure file based on the delineation results; and obtaining radiotherapy planning parameters based on the radiotherapy structure file and a pre-set neural network model. The radiotherapy planning parameters include field parameters and / or collimator angles. Field parameters include at least one of the following: number of fields, field angle, and field energy. This method can automatically set the aforementioned radiotherapy planning parameters by using field energy, number, angle, and collimator angle as features in training, based on the received radiotherapy plan and the delineation results of the target area and organs at risk drawn by the physician. This eliminates the need for manual determination of radiotherapy planning parameters based on experience, improving the accuracy of parameter determination. Furthermore, it selects the optimal energy combination based on the relationship between the target area and organs at risk, supports collimator angle prediction, improves target conformity, reduces the dose to organs at risk, and avoids harm to organs at risk.

[0050] The above embodiments have described the method for setting radiotherapy planning parameters. Now, an embodiment will be used to further illustrate the preset neural network model used in the above method. In one embodiment, the neural network model is obtained by training a preset initial neural network model based on a sample training set. The sample training set includes a first sample radiotherapy structure file and first sample radiotherapy planning parameters, a second sample radiotherapy structure file, and second sample radiotherapy planning parameters; wherein, the first sample radiotherapy planning parameters are single-energy radiotherapy planning parameters; and the second sample radiotherapy planning parameters are mixed-energy radiotherapy planning parameters.

[0051] Specifically, before training the neural network model, a first and a second structural radiotherapy file can be pre-extracted from the delineation results based on medical images. These files may include the target volume and geometric center coordinates, the volume and geometric center coordinates of each organ at risk, the minimum distance from each organ at risk to the target volume, the minimum and maximum distances between the skin and the target volume, and the projection shape of the target volume at different field angles. Simultaneously, first sample radiotherapy plan parameters corresponding to the first structural file and second sample radiotherapy plan parameters corresponding to the second structural file can be extracted. These first and second sample radiotherapy plan parameters include field energy, number of fields, field angle, and collimator angles corresponding to each field. Furthermore, the first sample radiotherapy plan parameters are single-energy radiotherapy plan parameters, while the second sample radiotherapy plan parameters are mixed-energy radiotherapy plan parameters. The proportion of the first and second sample radiotherapy plan parameters in the total sample can be equal or unequal. For example, a first sample radiotherapy plan parameter can be used with 50% energy for a normal energy plan, and a second sample radiotherapy plan parameter can be used with 50% energy for a mixed energy plan.

[0052] Once the training samples are determined, the first structure file can be input into the initial neural network model to output the predicted first radiotherapy plan parameters. A preset loss function is then used to calculate the loss value between the first radiotherapy plan parameters and the first sample radiotherapy plan parameters. The initial neural network model is adjusted until the loss value between the second radiotherapy plan parameters and the second sample radiotherapy plan parameters reaches a preset loss threshold. The second structure file is then input into the initial neural network model to output the predicted second radiotherapy plan parameters. A preset loss function is then used to calculate the loss value between the second radiotherapy plan parameters and the second sample radiotherapy plan parameters. The initial neural network model is adjusted until the loss value between the second radiotherapy plan parameters and the second sample radiotherapy plan parameters reaches a preset loss threshold. Training then ends, and the preset neural network model is obtained.

[0053] In this embodiment, the neural network model is obtained by training a preset initial neural network model based on a sample training set. The sample training set includes a first sample radiotherapy structure file and first sample radiotherapy plan parameters, a second sample radiotherapy structure file and second sample radiotherapy plan parameters. The first sample radiotherapy plan parameters are single-energy radiotherapy plan parameters, and the second sample radiotherapy plan parameters are mixed-energy radiotherapy plan parameters. Based on the mixed-energy radiotherapy plan, the optimal energy combination can be selected according to the relationship between the target area and organs at risk, thereby improving target conformity and reducing the dose to organs at risk.

[0054] The above embodiments illustrate how to obtain a preset neural network model. Now, an embodiment further illustrates how to obtain radiotherapy planning parameters using a preset neural network model. In one embodiment, radiotherapy planning parameters are obtained based on the radiotherapy structure file and the preset neural network model, including:

[0055] The radiotherapy structure file is input into the neural network model to obtain the radiation field parameters and collimator angle.

[0056] Specifically, the radiotherapy structure file can be input into a neural network model, which outputs the field parameters and collimator angle from the radiotherapy planning parameters. Alternatively, the radiotherapy structure file can be input into a neural network model, which outputs the field parameters from the radiotherapy planning parameters; then the field parameters can be input into another preset neural network model, which outputs the collimator angle.

[0057] Furthermore, in one embodiment, such as Figure 3 As shown, the neural network model includes a first neural network model and a second neural network model; based on the radiotherapy structure file and the preset neural network model, the radiotherapy plan parameters are obtained, including:

[0058] S302, input the radiotherapy structure file into the first neural network model to obtain the radiation field parameters;

[0059] S304. Input the field angle from the field parameters into the second neural network model to obtain the collimator angle.

[0060] Specifically, before inputting the radiotherapy structure file into the first neural network, feature information can be extracted from the radiotherapy structure file to obtain the target volume and geometric center coordinates, the volume and geometric center coordinates of each organ at risk, the minimum distance from each organ at risk to the target area, the minimum and maximum distances between the skin and the target area, and the projection shape of the target area under different radiation field angles. This feature information is then input into the first neural network model to obtain the radiation field parameters. The radiation field parameters may include radiation field energy, number of radiation fields, and radiation field angle.

[0061] The firing angle is retrieved from the firing field parameters and input into the second neural network model, which outputs the collimator angle. This second neural network model is used to determine the collimator angle. This model can be trained by using the firing angle as input and the collimator angle as output, and the final second neural network model is determined upon convergence.

[0062] In this embodiment, the radiation field parameters are obtained by inputting the radiotherapy structure file into the first neural network model; the radiation field angle from the radiation field parameters is then input into the second neural network model to obtain the collimator angle. This enables collimator angle prediction, improves target conformity, and reduces the dose received by organs at risk.

[0063] The above embodiments illustrate how to determine radiotherapy planning parameters. Now, one embodiment will be used to illustrate how to obtain radiotherapy structure files. In one embodiment, such as... Figure 4 As shown, the radiotherapy structure file is obtained based on the target area delineation results, including:

[0064] S402, Based on the target area delineation results, determine the feature information of the target area;

[0065] S404, Based on the target area delineation results, determine the characteristic information of organs at risk related to the target area;

[0066] S406 defines the characteristic information of the target area and the characteristic information of organs at risk as the radiotherapy structure file.

[0067] Optionally, the feature information of the target area includes at least one of the target area volume and the geometric center coordinates of the target area.

[0068] Optionally, the characteristic information of the organ at risk includes at least one of the following: the volume of the organ at risk, the geometric center coordinates of the organ at risk, the minimum distance between the organ at risk and the target area, and the projected shape of the target area under different field angles.

[0069] Specifically, since the delineation results distinguish between the target area and the organs at risk, and their positions and colors differ, the feature information of the target area and the organs at risk can be further determined based on the pixel information and pixel value information in the delineation results. This allows for the determination of the geometric coordinates and volume information of the target area and the organs at risk; it also allows for the determination of the minimum distance between the organs at risk and the target area, and the projection shape of the target area under different radiation field angles. Based on this, the feature information of the target area and the organs at risk is used as a medical structural file.

[0070] In this embodiment, by determining the feature information of the target area and the feature information of organs at risk related to the target area based on the target area delineation results, the feature information of the target area and the feature information of organs at risk are determined as the radiotherapy structure file. This method enables the determination of the radiotherapy structure file based on the delineation results, eliminating the need for manual multiple settings of radiation field parameters, repeated adjustments to the radiation field parameters after obtaining optimization results, and determination of the target radiation field parameters. This improves the efficiency of radiation field parameter determination and the accuracy of radiation field parameter settings.

[0071] To facilitate understanding by those skilled in the art, the method for setting radiotherapy planning parameters is further described below with reference to an embodiment. In one embodiment, as follows: Figure 5 As shown, the method for setting radiotherapy planning parameters includes:

[0072] S502, obtain the delineation results of the target area and organs at risk in the medical images of the radiotherapy plan;

[0073] S504, Based on the target area delineation results, determine the feature information of the target area;

[0074] S506, Based on the target area delineation results, determine the characteristic information of organs at risk related to the target area;

[0075] S508 defines the characteristic information of the target area and the characteristic information of the organs at risk as a radiotherapy structural file. The characteristic information of the target area includes at least one of the target area volume and the geometric center coordinates of the target area;

[0076] S510 inputs the radiotherapy structure file into the neural network model to obtain the radiation field parameters and collimator angle.

[0077] In this embodiment, the target area and organs at risk are delineated from medical images used in the radiotherapy plan. A radiotherapy structure file is then obtained based on these delineations. Radiotherapy plan parameters are derived from the radiotherapy structure file and a pre-defined neural network model. These parameters include field parameters and / or collimator angles. Field parameters include at least one of the following: number of fields, field angle, and field energy. By using field energy, number, angle, and collimator angle as features in the training process, the radiotherapy plan parameters are automatically set based on the received radiotherapy plan and the delineated target area and organs at risk. This eliminates the need for manual determination of radiotherapy plan parameters based on experience, improving the accuracy of parameter determination. Furthermore, the optimal energy combination is selected based on the relationship between the target area and organs at risk, supporting collimator angle prediction, improving target conformity, reducing the dose to organs at risk, and preventing harm to these organs.

[0078] To facilitate understanding by those skilled in the art, another embodiment will now be used to further illustrate the method for setting radiotherapy planning parameters. In one embodiment, as shown... Figure 6 As shown, the method for setting radiotherapy planning parameters includes:

[0079] S602, Obtain the delineation results of the target area and organs at risk in the medical images of the radiotherapy plan;

[0080] S604, Based on the target area delineation results, determine the feature information of the target area;

[0081] S606, Based on the target area delineation results, determine the characteristic information of organs at risk related to the target area;

[0082] S608, the characteristic information of the target area and the characteristic information of the organs at risk are determined as the radiotherapy structure file; the characteristic information of the target area includes at least one of the volume of the target area and the geometric center coordinates of the target area;

[0083] S610: Input the radiotherapy structure file into the first neural network model to obtain the radiation field parameters;

[0084] S612, input the field angle from the field parameters into the second neural network model to obtain the collimator angle.

[0085] In this embodiment, the target area and organs at risk are delineated from medical images used in the radiotherapy plan. A radiotherapy structure file is then obtained based on this delineation. Radiotherapy plan parameters are derived from the radiotherapy structure file and a pre-defined neural network model. These parameters include field parameters and / or collimator angles. Field parameters include the number of fields, field angle, and field energy. By using field energy, number, angle, and collimator angle as features in training, the system automatically sets these parameters based on the received radiotherapy plan and the delineated target area and organs at risk. This eliminates the need for manual determination of radiotherapy plan parameters based on experience, improving the accuracy of parameter determination. Furthermore, it selects the optimal energy combination based on the relationship between the target area and organs at risk, supports collimator angle prediction, improves target conformity, reduces the dose to organs at risk, and avoids harm to these organs.

[0086] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0087] Based on the same inventive concept, this application also provides a device for setting radiotherapy planning parameters to implement the method for setting radiotherapy planning parameters described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the device for setting radiotherapy planning parameters provided below can be found in the limitations of the method for setting radiotherapy planning parameters described above, and will not be repeated here.

[0088] In one embodiment, such as Figure 7 As shown, a device for setting radiotherapy planning parameters is provided, comprising:

[0089] The first acquisition module 702 is used to acquire the delineation results of the target area in the medical images of the radiotherapy plan;

[0090] The second acquisition module 704 is used to acquire radiotherapy structure files based on the target area delineation results.

[0091] The third acquisition module 706 is used to obtain radiotherapy planning parameters based on the radiotherapy structure file and the preset neural network model. The radiotherapy planning parameters include field parameters and collimator angle. The field parameters include at least one of the number of fields, field angle and field energy.

[0092] Optionally, the neural network model is obtained by training a preset initial neural network model based on a sample training set. The sample training set includes a first sample radiotherapy structure file and first sample radiotherapy plan parameters, a second sample radiotherapy structure file and second sample radiotherapy plan parameters; wherein, the first sample radiotherapy plan parameters are single-energy radiotherapy plan parameters; and the second sample radiotherapy plan parameters are mixed-energy radiotherapy plan parameters.

[0093] In this embodiment, the first acquisition module acquires the delineation results of the target area and organs at risk in the medical images of the radiotherapy plan; the second acquisition module acquires the radiotherapy structure file based on the delineation results of the target area and organs at risk; the third acquisition module obtains the radiotherapy plan parameters based on the radiotherapy structure file and a preset neural network model. The radiotherapy plan parameters include field parameters and / or collimator angles, and the field parameters include the number of fields, field angles, and field energy. By using field energy, number, angle, and collimator angle as features in training, the above-mentioned radiotherapy plan parameters can be automatically set based on the received radiotherapy plan and the delineation results of the target area and organs at risk drawn by the doctor. This eliminates the need for manual determination of radiotherapy plan parameters based on experience, improving the accuracy of determining radiotherapy plan parameters. Furthermore, it selects the optimal energy combination based on the relationship between the target area and organs at risk, supports collimator angle prediction, improves target conformity, reduces the dose to organs at risk, and avoids harm to organs at risk.

[0094] In one embodiment, the third acquisition module is specifically used to input the radiotherapy structure file into the neural network model to obtain the radiation field parameters and collimator angle.

[0095] In one embodiment, the neural network model includes a first neural network model and a second neural network model; the third acquisition module is specifically used to input the radiotherapy structure file into the first neural network model to obtain the radiation field parameters; and to input the radiation field angle from the radiation field parameters into the second neural network model to obtain the collimator angle.

[0096] In one embodiment, the second acquisition module includes:

[0097] The first determining unit is used to determine the feature information of the target area based on the target area delineation results;

[0098] The second determining unit is used to determine the characteristic information of organs at risk related to the target area based on the target area delineation results.

[0099] The third determining unit is used to determine the characteristic information of the target area and the characteristic information of the organs at risk as a radiotherapy structure file.

[0100] Optionally, the feature information of the target area includes at least one of the target area volume and the geometric center coordinates of the target area.

[0101] Each module in the aforementioned radiotherapy planning parameter setting device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the computer device's memory as software, so that the processor can call and execute the corresponding operations of each module.

[0102] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 1As shown. The computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for setting radiotherapy planning parameters. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0103] Those skilled in the art will understand that Figure 1 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0104] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0105] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0106] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0107] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0108] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this 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), magnetic 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. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0109] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0110] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A device for setting radiotherapy planning parameters, characterized in that, The device includes: The first acquisition module is used to acquire the delineation results of the target area in the medical images of the radiotherapy plan; The second acquisition module is used to acquire radiotherapy structure files based on the target area delineation results. The third acquisition module is used to obtain radiotherapy planning parameters based on the radiotherapy structure file and a preset neural network model. The radiotherapy planning parameters include field parameters and collimator angles. The field parameters include at least one of the number of fields, field angles, and field energy. The neural network model includes a first neural network model and a second neural network model. Specifically, the third acquisition module is used to extract feature information from the radiotherapy structure file, input the extracted feature information into the first neural network model to obtain the field parameters, and input the field angles from the field parameters into the second neural network model to obtain the collimator angles.

2. The apparatus according to claim 1, characterized in that, The neural network model is obtained by training a preset initial neural network model based on a sample training set. The sample training set includes a first sample radiotherapy structure file and a first sample radiotherapy plan parameter, a second sample radiotherapy structure file and a second sample radiotherapy plan parameter; wherein, the first sample radiotherapy plan parameter is a single-energy radiotherapy plan parameter; and the second sample radiotherapy plan parameter is a mixed-energy radiotherapy plan parameter.

3. The apparatus according to claim 2, characterized in that, The training process of the neural network model includes: The first sample radiotherapy structure file is input into the initial neural network model, which outputs the predicted first radiotherapy plan parameters. A preset loss function is used to calculate the loss value between the first radiotherapy plan parameters and the first sample radiotherapy plan parameters. The initial neural network model is adjusted until the loss value between the first radiotherapy plan parameters and the first sample radiotherapy plan parameters reaches a preset loss threshold. The second sample radiotherapy structure file is then input into the adjusted initial neural network model, which outputs the predicted second radiotherapy plan parameters. A preset loss function is used to calculate the loss value between the second radiotherapy plan parameters and the second sample radiotherapy plan parameters. The initial neural network model is adjusted until the loss value between the second radiotherapy plan parameters and the second sample radiotherapy plan parameters reaches a preset loss threshold, thus obtaining the neural network model.

4. The apparatus according to claim 1, characterized in that, The second acquisition module includes: a first determining unit, wherein: The first determining unit is used to determine the feature information of the target area based on the delineation result of the target area.

5. The apparatus according to claim 4, characterized in that, The second acquisition module further includes: a second determination unit, wherein: The second determining unit is used to determine the characteristic information of organs at risk related to the target area based on the delineation results of the target area.

6. The apparatus according to claim 5, characterized in that, The second acquisition module further includes: a third determining unit, wherein: The third determining unit is used to determine the feature information of the target area and the feature information of the organs at risk as the radiotherapy structure file.

7. The apparatus according to claim 4, characterized in that, The first determining unit is used to determine the feature information of the target area based on the pixel information and pixel value information in the delineation result of the target area.

8. The apparatus according to claim 7, characterized in that, The characteristic information of the target area includes at least one of the target area volume and the geometric center coordinates of the target area.

9. The apparatus according to claim 1, characterized in that, The characteristic information of the radiotherapy structure file includes the target volume and geometric center coordinates, the volume and geometric center coordinates of each organ at risk, the minimum distance from each organ at risk to the target, the minimum and maximum distance between the skin and the target, and the projection shape of the target under different radiation field angles.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, The processor includes a device for setting radiotherapy planning parameters as described in any one of claims 1 to 9.

Images