Radiotherapy plan generation method and device, terminal equipment and storage medium

Abstract

The invention discloses a radiotherapy plan generation method and apparatus, a terminal device and a storage medium. The method comprises the steps of obtaining CT image data and dose distribution data of a patient; inputting the CT image data and the dose distribution data into a trained radiotherapy machine parameter calculation model, so that the radiotherapy machine parameter calculation model calculates and outputs an MLC position, a Jaw position and an MU value of each control point of a radiotherapy machine according to the CT image data and the dose distribution data; generating a radiotherapy machine operation file according to the MLC positions, the Jaw positions and the MU values of all the control points; wherein the radiotherapy machine operation file is used for directly inputting the radiotherapy machine to control the radiotherapy machine to execute the radiotherapy plan. According to the method, the radiotherapy plan which can be directly input into a radiotherapy machine and can be executed can be completely and automatically generated according to the CT image data and the dose distribution data, the labor cost is saved, and the radiotherapy plan generation efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of radiotherapy technology, and in particular to a method, device, terminal equipment and storage medium for generating a radiotherapy plan. Background Art

[0002] At present, the most commonly used system in the design of radiotherapy plans is still the TPS treatment planning system. The obtained CT images or dose prediction plans are put into TPS. Taking the doctor's prescribed dose as the target, the physicist continuously modifies, tries and errors, and reversely optimizes to obtain radiotherapy plan parameters that can be directly used and meet clinical requirements, that is, the final usable treatment plan. In addition, due to the differences in the professional capabilities of physicists themselves and the different equipment used, the learning and training cycle of radiotherapy plan design is relatively long. It is difficult to improve the dosimetrist's treatment plan design level in a short period of time, and thus the design quality and consistency of the treatment plan are difficult to guarantee.

[0003] In the field of automated radiotherapy research, many dose prediction models have been developed, which can automate the dose prediction process of radiotherapy planning, which saves some time in the radiotherapy process to a certain extent. However, dose prediction alone is not enough because it cannot be directly delivered to the radiotherapy machine for use. The radiotherapy machine cannot directly recognize the dose prediction model or dose distribution map. Only by using specific parameters, such as arm position, collimator angle, treatment window angle, leaf position sequence, sub-field weight and other parameters, and inputting them into the radiotherapy machine in the form of corresponding files can it be delivered for clinical use. This process still requires the participation of physicists, which requires sufficient time and labor costs.

[0004] In summary, the existing technology has only automated the dose prediction part, but has failed to generate a radiotherapy plan that can be directly used in a radiotherapy machine. It requires human participation and is inefficient. Summary of the invention

[0005] The present invention provides a method, an apparatus, a terminal device and a storage medium for generating a radiotherapy plan, so as to solve the technical problem that the prior art cannot generate a radiotherapy plan that can be directly used in a radiotherapy machine, resulting in low efficiency.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a method for generating a radiotherapy plan, comprising:

[0007] Acquire CT image data and dose distribution data of the patient;

[0008] Inputting the CT image data and the dose distribution data into a trained radiotherapy machine parameter calculation model, so that the radiotherapy machine parameter calculation model calculates and outputs the MLC position, Jaw position and MU value of each control point of the radiotherapy machine according to the CT image data and the dose distribution data;

[0009] A radiotherapy machine operation file is generated according to the MLC position, Jaw position and MU value of all control points; wherein the radiotherapy machine operation file is used to directly input the radiotherapy machine to control the radiotherapy machine to execute the radiotherapy plan.

[0010] As a preferred solution, the radiotherapy machine parameter calculation model includes: a preprocessing module, an encoding module, a processing module and a decoding module;

[0011] The preprocessing module is used to preprocess the dose distribution data;

[0012] The encoding module is used to generate anatomical spatial dose distribution data according to the CT image data and the preprocessed dose distribution data; wherein the anatomical spatial dose distribution data is used to describe the spatial distribution of the dose in the patient's body;

[0013] The processing module is used to generate dose projection data of each control point according to the anatomical space dose distribution data;

[0014] The decoding module is used to decode the dose projection data of each control point to obtain the MLC position, Jaw position and MU value of each control point.

[0015] As a preferred solution, the preprocessing of the dose distribution data includes:

[0016] Matching the CT image data and the dose distribution data to determine the isocenter of the CT image data and the dose distribution data;

[0017] Taking the isocenter as the center of the cropping area, cropping the dose distribution data according to a preset size requirement;

[0018] The cropped dose distribution data is resampled according to a preset dimension to obtain preprocessed dose distribution data.

[0019] As a preferred solution, generating anatomical space dose distribution data according to the CT image data and the preprocessed dose distribution data includes:

[0020] Matching and fusing the CT image data and the dose distribution data to determine the anatomical spatial position information corresponding to each voxel in the dose distribution data in the CT image data and the dose information corresponding to each voxel in the dose distribution data;

[0021] The anatomical space dose distribution data is generated according to the anatomical space position information and dose distribution information corresponding to each voxel.

[0022] As a preferred solution, generating dose projection data of each control point according to the anatomical space dose distribution data includes:

[0023] For each control point, the radiation beam path of the radiotherapy machine at the control point is used as the projection direction, and all anatomical space dose distribution data in the projection direction are projected onto the control point to obtain the dose projection data of the control point.

[0024] As a preferred solution, the control point division process includes:

[0025] Obtain the anatomical spatial data of the patient under the radiotherapy machine;

[0026] Around the longitudinal axis of the patient, the patient body space corresponding to the anatomical space data is divided into a plurality of subspace regions, and a control point is set for each subspace region.

[0027] As a preferred solution, obtaining dose distribution data includes:

[0028] Acquire CT image data, OAR mask image data, and PTV image data of the patient;

[0029] The CT image data, OAR mask image data and PTV image data are input into a trained dose distribution prediction model, so that the dose distribution prediction model predicts the dose distribution according to the CT image data, OAR mask image data and PTV image data, and outputs the dose distribution data.

[0030] Based on the above embodiment, another embodiment of the present invention provides a radiotherapy plan generation device, including: a data acquisition module, a radiotherapy machine parameter calculation module and a radiotherapy machine operation file generation module;

[0031] The data acquisition module is used to acquire CT image data and dose distribution data of the patient;

[0032] The radiotherapy machine parameter calculation module is used to input the CT image data and the dose distribution data into the trained radiotherapy machine parameter calculation model, so that the radiotherapy machine parameter calculation model calculates and outputs the MLC position, Jaw position and MU value of each control point of the radiotherapy machine according to the CT image data and the dose distribution data;

[0033] The radiotherapy machine operation file generation module is used to generate a radiotherapy machine operation file according to the MLC position, Jaw position and MU value of all control points; wherein the radiotherapy machine operation file is used to directly input the radiotherapy machine to control the radiotherapy machine to execute the radiotherapy plan.

[0034] Based on the above embodiments, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the radiation therapy plan generation method described in the above invention embodiment is implemented.

[0035] Based on the above embodiment, another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the radiation therapy plan generation method described in the above invention embodiment.

[0036] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0037] The present invention obtains the patient's CT image data and dose distribution data; inputs the CT image data and dose distribution data into a trained radiotherapy machine parameter calculation model, so that the radiotherapy machine parameter calculation model calculates and outputs the MLC position, Jaw position and MU value of each control point of the radiotherapy machine according to the CT image data and dose distribution data; generates a radiotherapy machine operation file according to the MLC position, Jaw position and MU value of all control points; wherein the radiotherapy machine operation file is used to directly input the radiotherapy machine to control the radiotherapy machine to execute the radiotherapy plan. The present invention can fully and automatically generate a radiotherapy plan that can be directly put into the radiotherapy machine and can be executed according to the CT image data and dose distribution data, realize the automation of the most time-consuming and labor-intensive process in the radiotherapy plan formulation, save labor costs, and improve the efficiency of radiotherapy plan generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 It is a flowchart of a method for generating a radiotherapy plan provided by an embodiment of the present invention;

[0039] Figure 2 It is an architecture diagram of the front module and the back module of the dose distribution prediction model provided by one embodiment of the present invention;

[0040] Figure 3 is a schematic diagram of a radiotherapy machine parameter calculation model provided by an embodiment of the present invention;

[0041] Figure 4 It is a schematic diagram of control point subspace region division provided by an embodiment of the present invention;

[0042] Figure 5 A schematic structural diagram of a radiotherapy plan generating device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] Embodiment 1

[0045] Please refer to Figure 1 , is a flow chart of a method for generating a radiotherapy plan provided by an embodiment of the present invention, comprising:

[0046] S1. Acquire CT image data and dose distribution data of the patient.

[0047] In a preferred embodiment, obtaining dose distribution data includes:

[0048] Acquire CT image data, OAR mask image data, and PTV image data of the patient;

[0049] The CT image data, OAR mask image data and PTV image data are input into a trained dose distribution prediction model, so that the dose distribution prediction model predicts the dose distribution according to the CT image data, OAR mask image data and PTV image data, and outputs the dose distribution data.

[0050] It should be noted that the dose distribution data is used to describe the 3D dose distribution in the patient's body space. The dose distribution prediction model takes the patient's CT image data, OAR mask image data and PTV image data as input and takes the dose distribution data as output.

[0051] The dose distribution prediction model is a two-layer U-net architecture, consisting of a front module, a processing block, and a back module, where both the front module and the back module are U-net architectures.

[0052] The former module uses the patient's CT image, OAR mask image and multiple channels of PTV image as input to predict a rough 3D dose distribution.

[0053] The processing block combines the coarse 3D dose output from the front module as one channel with the input multi-channel stack as the input to the back module.

[0054] The latter module is used to further fine-tune the prediction results of the former module and output the final prediction results, namely the dose distribution data.

[0055] Please refer to Figure 2 , which is an architecture diagram of the front module and the back module of the dose distribution prediction model provided by an embodiment of the present invention. U-net is a fully convolutional neural network. U-net consists of a downsampling path and an upsampling path and a skipped concatenation to bring the features of the lower layer to the upsampling path to retain more details. 3D-U-net has a downsampling path and an upsampling path. Each path has 5 levels (dimensions are 128×128×128, 64×64×64, 32×32×32, 16×16×16, 8×8×8), and the number of channels in the downsampling path gradually increases from 16 to 256. The downsampling path consists of similar modules: 3×3×3 convolutional layers, instance normalization (IN) layers, and rectified linear units (RELU). Downsampling uses 3×3×3 convolutional layers with a stride of 2. After each downsampling operation, the resolution of the feature image is reduced by half. The number of feature maps is doubled. The upsampling path is used to gradually restore the resolution of the feature image to generate a high-resolution predicted dose image. The upsampling module mainly consists of repeated upsampling layers, skip cascades, 3×3×3 convolutional layers, IN layers, and RELU. In order to prevent the loss of feature acquisition during the downsampling process, the corresponding size of the downsampled encoding layer original image is passed to the upsampled decoding layer block through skip connections, because the earlier high-resolution feature images from the upsampling module can help refine the position information. These skip cascades are to supplement the details lost in the downsampling operation. We use trilinear interpolation scaling and 3×3×3 convolutional layers to upsample the feature images. Based on the decoding module, the feature images are gradually upsampled to the original resolution, and the predicted dose images are generated after 1×1×1 convolution layers. Since the dose value cannot be negative, the negative predicted value will be replaced by 0, and the final output is 3D dose distribution data with a dimension of 128x128x128.

[0056] In the process of training the dose distribution prediction model, CT image data, OAR mask image data and PTV image data of several patients are collected as sample data, and the corresponding dose distribution data is collected, from which the spatial dose information is extracted and preprocessed into NumPy arrays as sample labels. The CT image data is first cropped to between -1024 and 1500HU, and then normalized to 1000HU. The OAR images and PTV images are marked with binary masks, and the model outputs a dose image normalized to 70Gy.

[0057] The U-net architecture is deeper than most other 3D dose prediction models. Since the increase in network depth may bring additional optimization difficulties, we used deep supervision for model optimization. The mean absolute error (MAE) between the predicted dose and the ground truth dose is used as the loss function. The loss value between the predicted dose result and the label is calculated as:

[0058]

[0059] Where D Q (i) represents the dose value of the i-th voxel predicted by the previous module, D H (i) represents the dose value of the i-th voxel predicted by the post-module; GT(i) represents the true dose value of the i-th voxel; N represents the total number of voxels; a represents the weight factor, which is 0.5.

[0060] S2. Input the CT image data and dose distribution data into a trained radiotherapy machine parameter calculation model, so that the radiotherapy machine parameter calculation model calculates and outputs the MLC position, Jaw position and MU value of each control point of the radiotherapy machine according to the CT image data and dose distribution data.

[0061] In a preferred embodiment, the control point division process includes:

[0062] Obtain the anatomical spatial data of the patient under the radiotherapy machine;

[0063] Around the longitudinal axis of the patient, the patient body space corresponding to the anatomical space data is divided into a plurality of subspace regions, and a control point is set for each subspace region.

[0064] It should be noted that the control points are first divided around the patient's longitudinal axis, that is, the axis from the patient's head to the feet. According to the number of control points optimized by the double arc treatment, it is generally from the starting point 179° counterclockwise to 181°, and then from 181° clockwise back to 179°. Each single arc has 178 control points, a total of 2X178 control points, and the angle distribution between each control point is about 2°. However, the position of the control point is basically fixed, and then a control point is set for each subspace area. Please refer to Figure 4 , is a schematic diagram of a control point subspace region division provided by an embodiment of the present invention. In the figure, 180 subspace regions are divided with the patient lying in a supine position and the frame angle of 0 degree just above the treatment machine as the starting point, that is, each 2 degrees is a subspace region, and the schematic diagram only draws the control point part around 90° of the frame.

[0065] In the training process of the radiotherapy machine parameter calculation model, the CT image data and dose distribution data of several patients are collected as samples, and the MLC position, Jaw position and MU value of each control point of the corresponding radiotherapy machine are collected and converted into a three-dimensional numpy array as the sample label. The input data is normalized using the minimum-maximum normalization technique, which scales the value to a range of 0 to 1. Output normalization includes scaling MLC and Jaw to values ​​between -1 and 1, and scaling MU to values ​​between 0 and 1. The L1 loss of the MLC position, Jaw position and MU is calculated respectively. After weighting the MLC loss by a factor of 100, the losses are summed. When we study the model, we emphasize learning this property to protect the patient's organs at risk and ensure the patient's health after surgery. The learning rate is adjusted according to the single-cycle strategy, and the Lion optimization model is used, with an initial learning rate of 10-4 and a weight decay of 10-3.

[0066] Hyperparameter adjustment is used to determine the optimal value loss function of the model hyperparameters. The loss function calculation formula is:

[0067] F total =100F MLC +F Jaw +F MU .

[0068] In the formula, F total Represents the total loss function value; F MLC represents the loss function value of the MLC decoder head; F Jaw represents the loss function value of the Jaw decoder head; F MU Represents the loss function value of the MU decoder head.

[0069] In a preferred embodiment, the radiotherapy machine parameter calculation model includes: a pre-processing module, an encoding module, a processing module and a decoding module;

[0070] The preprocessing module is used to preprocess the dose distribution data;

[0071] The encoding module is used to generate anatomical spatial dose distribution data according to the CT image data and the preprocessed dose distribution data; wherein the anatomical spatial dose distribution data is used to describe the spatial distribution of the dose in the patient's body;

[0072] The processing module is used to generate dose projection data of each control point according to the anatomical space dose distribution data;

[0073] The decoding module is used to decode the dose projection data of each control point to obtain the MLC position, Jaw position and MU value of each control point.

[0074] Please refer to Figure 3 , which is an architectural diagram of a radiotherapy machine parameter calculation model provided in one embodiment of the present invention.

[0075] It should be noted that the input of the radiotherapy machine parameter calculation model is CT image data and dose distribution data. The original size of the dose distribution data is 512mm×512mm×512mm, the image dimension is (128,128,128), and the original size of the voxel is 4mm×4mm×4mm. The layer thickness of the CT image data is 3mm, and the in-plane resolution is 0.81mm.

[0076] In a preferred embodiment, the preprocessing of the dose distribution data includes:

[0077] Matching the CT image data and the dose distribution data to determine the isocenter of the CT image data and the dose distribution data;

[0078] Taking the isocenter as the center of the cropping area, cropping the dose distribution data according to a preset size requirement;

[0079] The cropped dose distribution data is resampled according to a preset dimension to obtain preprocessed dose distribution data.

[0080] In this embodiment, the CT image data and the dose distribution data are matched to determine the isocenter of the CT image data and the dose distribution data; then the dose distribution data is cropped according to the preset size requirements with the isocenter as the center of the cropping area, and the preset size is 400mm×400mm×400mm; then the cropped dose distribution data is resampled according to the preset dimension, the preset dimension is (128,128,320), and the resampled voxel size is 3.125mm×3.125mm×1.250mm. The number of voxels of the preprocessed dose distribution data is increased, and the dose information data contained in the increased voxels is obtained by three-dimensional linear interpolation.

[0081] In a preferred embodiment, generating anatomical space dose distribution data according to the CT image data and the preprocessed dose distribution data includes:

[0082] Matching and fusing the CT image data and the dose distribution data to determine the anatomical spatial position information corresponding to each voxel in the dose distribution data in the CT image data and the dose information corresponding to each voxel in the dose distribution data;

[0083] The anatomical space dose distribution data is generated according to the anatomical space position information and dose distribution information corresponding to each voxel.

[0084] It should be noted that the encoding module is mainly composed of 3D convolution layer, BatchNorm3D, 3DMax pooling layer and activation function Relu layer, which is used to extract spatial dose information, namely anatomical spatial dose distribution data.

[0085] In a preferred embodiment, generating dose projection data of each control point according to the anatomical space dose distribution data includes:

[0086] For each control point, the radiation beam path of the radiotherapy machine at the control point is used as the projection direction, and all anatomical space dose distribution data in the projection direction are projected onto the control point to obtain the dose projection data of the control point.

[0087] In this embodiment, a projection operation is performed at each control point. The projection direction is along the ray beam path (the direction in which the accelerator generates the treatment beam during treatment) with a field of view. The projection operation is performed along the corresponding direction at each control point to reconstruct the 3D dose distribution data into 2D dose distribution data at each control point.

[0088] To prevent relative control points (rotated by 1π) from being represented identically, such as directly in front of and behind the patient (0 degrees and 180 degrees), the present invention introduces a three-dimensional tensor gradient field to simulate the absorption of the beam as it passes through the patient. At each control point, it decreases from 1 to 0 along the axis parallel to the beam path in the same direction as the projection. By multiplying the dose with the gradient field tensor, the ipsilateral voxels are given a larger weight than the contralateral voxels. The 2D images generated by each control point are stacked in the order of the control points to form the final input array of the decoder.

[0089] S3. Generate a radiotherapy machine operation file according to the MLC position, Jaw position and MU value of all control points; wherein the radiotherapy machine operation file is used to directly input the radiotherapy machine to control the radiotherapy machine to execute the radiotherapy plan.

[0090] The decoding module consists of three independent decoder heads, which are used to calculate the MLC position, Jaw position and MU value respectively.

[0091] Both MLC and Jaw decoder heads follow the same design principles: 8 convolutional blocks with residual connections to gradually reduce the data to the shape of the expected output: MLC 2X 178×60×2, Jaw 2X 178×2×1, using 3D convolutional layers, BatchNorm3D layers, and LeakyRelu activation functions to process the data.

[0092] The MU decoder head consists of six convolutional blocks, followed by an average pooling layer and an output convolutional layer. The tanh output activation function is used for the MLC and Jaw decoders. For the MU decoder, the output of the final convolutional layer is used directly, with dimensions of 2X 178 X1 X 1. A threshold is set for the MU decoder to prevent negative outputs.

[0093] Finally, the data output by the decoder is saved in DICOM format as a DICOM RT plan file for subsequent secondary dose review and plan quality confirmation, and then delivered to the treatment system equipment (such as LINAC) for use.

[0094] Embodiment 2

[0095] Please refer to Figure 2 , is a schematic diagram of the structure of a radiotherapy plan generating device provided by an embodiment of the present invention, comprising: a data acquisition module, a radiotherapy machine parameter calculation module and a radiotherapy machine operation file generating module;

[0096] The data acquisition module is used to acquire CT image data and dose distribution data of the patient;

[0097] The radiotherapy machine parameter calculation module is used to input the CT image data and the dose distribution data into the trained radiotherapy machine parameter calculation model, so that the radiotherapy machine parameter calculation model calculates and outputs the MLC position, Jaw position and MU value of each control point of the radiotherapy machine according to the CT image data and the dose distribution data;

[0098] The radiotherapy machine operation file generation module is used to generate a radiotherapy machine operation file according to the MLC position, Jaw position and MU value of all control points; wherein the radiotherapy machine operation file is used to directly input the radiotherapy machine to control the radiotherapy machine to execute the radiotherapy plan.

[0099] Embodiment 3

[0100] Accordingly, an embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the radiotherapy plan generation method described in the above embodiment of the invention is implemented.

[0101] Embodiment 4

[0102] Accordingly, an embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute the method for generating a radiotherapy plan described in the above embodiment of the invention.

[0103] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0104] Those skilled in the art can clearly understand that for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0105] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0106] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the device, and various interfaces and lines are used to connect various parts of the entire device.

[0107] The memory can be used to store the computer program, and the processor realizes various functions of the device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0108] The storage medium is a storage medium, and the computer program is stored in the storage medium. When the computer program is executed by the processor, the steps of each method embodiment described above can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer readable media do not include electric carrier signals and telecommunication signals.

[0109] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for generating a radiotherapy plan, characterized in that: include: Acquire CT image data and dose distribution data of the patient; Inputting the CT image data and the dose distribution data into a trained radiotherapy machine parameter calculation model, so that the radiotherapy machine parameter calculation model calculates and outputs the MLC position, Jaw position and MU value of each control point of the radiotherapy machine according to the CT image data and the dose distribution data; A radiotherapy machine operation file is generated according to the MLC position, Jaw position and MU value of all control points; wherein the radiotherapy machine operation file is used to directly input the radiotherapy machine to control the radiotherapy machine to execute the radiotherapy plan.

2. The method for generating a radiation therapy plan according to claim 1, wherein: The radiotherapy machine parameter calculation model includes: a preprocessing module, an encoding module, a processing module and a decoding module; The preprocessing module is used to preprocess the dose distribution data; The encoding module is used to generate anatomical spatial dose distribution data according to the CT image data and the preprocessed dose distribution data; wherein the anatomical spatial dose distribution data is used to describe the spatial distribution of the dose in the patient's body; The processing module is used to generate dose projection data of each control point according to the anatomical space dose distribution data; The decoding module is used to decode the dose projection data of each control point to obtain the MLC position, Jaw position and MU value of each control point.

3. The method for generating a radiation therapy plan according to claim 2, wherein: The preprocessing of the dose distribution data comprises: Matching the CT image data and the dose distribution data to determine the isocenter of the CT image data and the dose distribution data; Taking the isocenter as the center of the cropping area, cropping the dose distribution data according to a preset size requirement; The cropped dose distribution data is resampled according to a preset dimension to obtain preprocessed dose distribution data.

4. The method for generating a radiation therapy plan according to claim 3, wherein: Generating anatomical space dose distribution data according to the CT image data and the preprocessed dose distribution data includes: Matching and fusing the CT image data and the dose distribution data to determine the anatomical spatial position information corresponding to each voxel in the dose distribution data in the CT image data and the dose information corresponding to each voxel in the dose distribution data; The anatomical space dose distribution data is generated according to the anatomical space position information and dose distribution information corresponding to each voxel.

5. The method for generating a radiation therapy plan according to claim 2, wherein: Generating dose projection data of each control point according to the anatomical space dose distribution data includes: For each control point, the radiation beam path of the radiotherapy machine at the control point is used as the projection direction, and all anatomical space dose distribution data in the projection direction are projected onto the control point to obtain the dose projection data of the control point.

6. The method for generating a radiation therapy plan according to claim 1, wherein: The control point division process includes: Obtain the anatomical spatial data of the patient under the radiotherapy machine; Around the longitudinal axis of the patient, the patient body space corresponding to the anatomical space data is divided into a plurality of subspace regions, and a control point is set for each subspace region.

7. The method according to claim 1, wherein: Acquire dose distribution data, including: Acquire CT image data, OAR mask image data, and PTV image data of the patient; The CT image data, OAR mask image data and PTV image data are input into a trained dose distribution prediction model, so that the dose distribution prediction model predicts the dose distribution according to the CT image data, OAR mask image data and PTV image data, and outputs the dose distribution data.

8. A radiotherapy plan generating device, characterized in that: include: Data acquisition module, radiotherapy machine parameter calculation module and radiotherapy machine operation file generation module; The data acquisition module is used to acquire CT image data and dose distribution data of the patient; The radiotherapy machine parameter calculation module is used to input the CT image data and the dose distribution data into the trained radiotherapy machine parameter calculation model, so that the radiotherapy machine parameter calculation model calculates and outputs the MLC position, Jaw position and MU value of each control point of the radiotherapy machine according to the CT image data and the dose distribution data; The radiotherapy machine operation file generation module is used to generate a radiotherapy machine operation file according to the MLC position, Jaw position and MU value of all control points; wherein the radiotherapy machine operation file is used to directly input the radiotherapy machine to control the radiotherapy machine to execute the radiotherapy plan.

9. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method for generating a radiation therapy plan according to any one of claims 1 to 7 when executing the computer program.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute the method for generating a radiotherapy plan according to any one of claims 1 to 7.

Images