阅读说明：本技术 一种智能型的离子束自适应放疗系统、存储介质及设备 (Intelligent ion beam self-adaptive radiotherapy system, storage medium and equipment ) 是由 张新阳 李强 贺鹏博 刘新国 戴中颖 马圆圆 申国盛 张晖 于 2021-09-10 设计创作，主要内容包括：本发明涉及一种智能型的离子束自适应放疗系统、存储介质及设备,其包括：采用通过DRR图像及与其对应的3D-CT图像构成数据集,对人工智能网络模型进行训练和验证,得到人工智能网络模型的权重参数；将每个分次的DR图像输入基于深度学习的二维图像翻译模型,生成对应的具有DRR风格的DR图像；将每个分次的具有DRR风格的DR图像输入人工智能网络模型构建模块,结合权重参数,得到每个分次的DR图像对应的虚拟3D-CT图像；将每个分次的虚拟3D-CT图像与带有勾画文件的参考3D-CT图像进行图像配准,生成虚拟3D-CT图像对应的勾画文件；将各个分次的虚拟3D-CT图像和各个分次的虚拟3D-CT图像对应的勾画文件输出至离子束放疗计划系统中,由离子束放疗计划系统制定每个分次的放疗计划。(The invention relates to an intelligent ion beam self-adaptive radiotherapy system, a storage medium and equipment, which comprise: adopting a data set formed by the DRR image and the 3D-CT image corresponding to the DRR image to train and verify the artificial intelligent network model to obtain a weight parameter of the artificial intelligent network model; inputting each classified DR image into a two-dimensional image translation model based on deep learning to generate a corresponding DR image with a DRR style; inputting each classified DR image with the DRR style into an artificial intelligent network model building module, and combining with the weight parameters to obtain a virtual 3D-CT image corresponding to each classified DR image; carrying out image registration on each divided virtual 3D-CT image and a reference 3D-CT image with a delineation file to generate a delineation file corresponding to the virtual 3D-CT image; and outputting each fractionated virtual 3D-CT image and a drawing file corresponding to each fractionated virtual 3D-CT image to an ion beam radiotherapy planning system, and making a radiotherapy plan of each fraction by the ion beam radiotherapy planning system.)

1. An intelligent ion beam adaptive radiotherapy system, comprising:

the artificial intelligence network model building module is used for training and verifying an artificial intelligence network model by adopting a data set formed by a DRR image and a 3D-CT image corresponding to the DRR image to obtain a weight parameter of the artificial intelligence network model;

the DR image generation module with the DRR style inputs each classified DR image into a two-dimensional image translation model based on deep learning to generate a corresponding DR image with the DRR style;

the virtual 3D-CT image generation module is used for inputting each classified DR image with the DRR style into the artificial intelligent network model construction module and obtaining a virtual 3D-CT image corresponding to each classified DR image by combining the weight parameters;

the image registration module is used for carrying out image registration on each divided virtual 3D-CT image and a reference 3D-CT image with a delineation file to generate a delineation file corresponding to the virtual 3D-CT image;

and the output module is used for outputting the virtual 3D-CT images of the respective fractions and the delineation files corresponding to the virtual 3D-CT images of the respective fractions to an ion beam radiotherapy planning system, and the ion beam radiotherapy planning system is used for making a radiotherapy plan of each fraction.

2. The intelligent ion beam adaptive radiotherapy system of claim 1, wherein in the artificial intelligence network model building module, the DRR image is generated by patient planning 3D-CT.

3. The intelligent ion beam adaptive radiotherapy system of claim 2, wherein said training and validating an artificial intelligence network model comprises: inputting N DRR images and S-layer 3D-CT images corresponding to the DRR images; the value of N is 1, and the value of S is the same as the number of layers of the patient plan 3D-CT.

4. The intelligent ion beam adaptive radiotherapy system of claim 1, wherein in said DR image generation module having a DRR style, said DR image is acquired by a DR imaging system device.

5. The system of claim 4, wherein the DR imaging system comprises only one set of X-ray emission sources and corresponding imaging panels for acquiring DR images of each fraction of the patient in real time.

6. The system of claim 5, wherein the X-ray emission source is installed on the floor of the treatment room, and the imaging plate is installed on the top of the treatment room and is rotated at a small angle with the center point of the treatment room as the origin.

7. The system of claim 5, wherein the X-ray emission source and the imaging plate are connected by a C-arm to perform small-angle motion as a whole with the center point of the treatment room as the origin.

8. The intelligent ion beam adaptive radiotherapy system of claim 1, wherein the image registration module comprises: and inputting each divided virtual 3D-CT image and the reference 3D-CT image with the delineation file into an image registration model based on a B spline, performing registration calculation, and outputting the delineation file corresponding to the virtual 3D-CT image.

9. A computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to implement the functions of the system of claims 1-8.

10. A computing device, comprising: one or more processors, memory, and one or more programs stored in the memory and configured to be executed by the one or more processors to implement the functions of any of the systems of claims 1-8.

Technical Field

The invention relates to the technical field of ion beam (proton and heavy ion) radiotherapy equipment, in particular to an intelligent ion beam self-adaptive radiotherapy system, a storage medium and equipment.

Background

In ion beam radiation therapy, it is common for a patient to receive multiple fractions of radiation during the weekly working days of the treatment session to complete the treatment. In the treatment process, due to the change of the anatomical structure caused by the change of the weight of the patient, the change of the tumor shape along with the treatment and the like, the target area of the tumor of the patient and the dose distribution nearby in the subsequent treatment process are deformed, and the problems are generally solved by adopting the ion beam adaptive radiotherapy. The ion beam adaptive radiotherapy is divided into ion beam online adaptive radiotherapy and ion beam offline adaptive radiotherapy. The method comprises the steps of selecting a corresponding adaptive radiotherapy mode according to the speed of change of an anatomical structure of a patient in the ion beam adaptive radiotherapy, carrying out ion beam online adaptive radiotherapy on the patient with daily change of the anatomical structure, and carrying out ion beam offline adaptive radiotherapy on the patient with peripheral change of the anatomical structure. The ion beam online adaptive radiotherapy is that CT images of a patient are acquired every day and are sketched, and then a new treatment plan is made online in an ion beam radiotherapy planning system to perform treatment. The ion beam off-line adaptive radiotherapy refers to that after a patient receives treatment for a plurality of times every week, a CT image of the patient is collected again and sketched, and then a treatment plan is re-formulated in an ion beam radiotherapy planning system to implement treatment of the next stage. Due to time and resource limitation and extremely high technical requirements of online adaptive radiotherapy on each link in radiotherapy, most of ion beam radiotherapy centers adopt offline adaptive radiotherapy at present. However, even in the online adaptive radiotherapy, the 3D-CT image of the patient needs to be acquired again and the radiotherapy plan needs to be re-made after the 3D-CT image is sketched, and although the defects and shortcomings of the offline adaptive therapy are solved to a certain extent theoretically, the online adaptive radiotherapy is still relatively complicated.

Computer technology, and in particular artificial intelligence technology, is gaining attention for its ability to learn complex relationships and incorporate prior knowledge into inference models, and exhibits superior performance in computer vision and medical image processing and multi-modal image generation. Therefore, it is feasible and necessary to develop an artificial intelligence based approach to achieve intelligent fast adaptive radiotherapy for ion beams using digital X-ray image (DR) guidance systems that are more common in ion beam radiotherapy centers.

Disclosure of Invention

In view of the above problems, an object of the present invention is to provide an intelligent ion beam adaptive radiotherapy system, a storage medium and a device, which solve the defects and shortcomings of a series of tedious tasks such as re-acquiring a 3D-CT image of a patient in conventional ion beam offline or online adaptive radiotherapy, and implement fast and intelligent ion beam adaptive radiotherapy.

In order to achieve the purpose, the invention adopts the following technical scheme:

an intelligent ion beam adaptive radiotherapy system, comprising: the artificial intelligence network model building module is used for training and verifying an artificial intelligence network model by adopting a data set formed by a DRR image and a 3D-CT image corresponding to the DRR image to obtain a weight parameter of the artificial intelligence network model; the DR image generation module with the DRR style inputs each classified DR image into a two-dimensional image translation model based on deep learning to generate a corresponding DR image with the DRR style; the virtual 3D-CT image generation module is used for inputting each classified DR image with the DRR style into the artificial intelligent network model construction module and obtaining a virtual 3D-CT image corresponding to each classified DR image by combining the weight parameters; the image registration module is used for carrying out image registration on each divided virtual 3D-CT image and a reference 3D-CT image with a delineation file to generate a delineation file corresponding to the virtual 3D-CT image; and the output module is used for outputting the virtual 3D-CT images of the respective fractions and the delineation files corresponding to the virtual 3D-CT images of the respective fractions to an ion beam radiotherapy planning system, and the ion beam radiotherapy planning system is used for making a radiotherapy plan of each fraction.

Preferably, in the artificial intelligence network model building module, the DRR image is generated by patient planning 3D-CT.

Preferably, the training and verifying the artificial intelligent network model includes: inputting N DRR images and S-layer 3D-CT images corresponding to the DRR images; the value of N is 1, and the value of S is the same as the number of layers of the patient plan 3D-CT.

Preferably, in the DR image generation module with DRR style, the DR image is acquired by a DR imaging system device.

Preferably, the DR imaging system only comprises a set of X-ray emission sources and imaging flat plates corresponding to the X-ray emission sources, and each time DR image of the patient is acquired in real time.

Preferably, the X-ray emission source is installed on the ground of the treatment room, and the imaging flat plate is installed on the top of the treatment room and rotates at a small angle respectively by taking the central point of the treatment room as the origin.

Preferably, the X-ray emission source and the imaging flat plate are connected together by a C-shaped arm, and perform small-angle motion as a whole by taking the central point of the treatment room as an origin.

Preferably, the image registration module includes: and inputting each divided virtual 3D-CT image and the reference 3D-CT image with the delineation file into an image registration model based on a B spline, performing registration calculation, and outputting the delineation file corresponding to the virtual 3D-CT image.

A computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to implement the functionality of the above-described system.

A computing device, comprising: one or more processors, memory, and one or more programs stored in the memory and configured to be executed by the one or more processors to implement any of the functions of the above-described system.

Due to the adoption of the technical scheme, the invention has the following advantages:

1. the invention solves the defects and shortcomings of a series of complicated work that the 3D-CT image of a patient needs to be acquired again in the conventional ion beam offline or online adaptive radiotherapy.

2. The invention adopts artificial intelligence technology, utilizes a DR image guide system generally configured by an ion beam radiotherapy center to generate 3D-CT images corresponding to each fraction from each 2D-DR image collected in real time, obtains a corresponding delineation file from each generated 3D-CT image according to an image registration model based on a B spline, and makes a new radiotherapy plan in an ion beam radiotherapy planning system according to each 3D-CT image and the corresponding delineation file, thereby overcoming the defects and shortcomings of the current ion beam self-adaptive radiotherapy caused by time, resource and technical limitations and realizing the rapid and intelligent ion beam self-adaptive radiotherapy.

3. The invention only needs a single DR imaging device and has low cost.

Drawings

Fig. 1 is a schematic structural diagram of an ion beam adaptive radiotherapy system in an embodiment of the present invention;

FIG. 2 is a cross-sectional difference diagram of a generated 3D-CT and its corresponding real 3D-CT in an embodiment of the present invention;

FIG. 3 is a schematic diagram of DR device coordinates in an embodiment of the present invention;

FIG. 4 is a system flow diagram in one embodiment of the invention;

FIG. 5 is a schematic diagram of a computing device in an embodiment of the invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the drawings of the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the described embodiments of the invention, are within the scope of the invention.

It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.

The invention provides an intelligent ion beam self-adaptive radiotherapy system, which is characterized in that a neural network model for reconstructing a three-dimensional CT image based on a two-dimensional view is established through a digital reconstruction ray image (DRR image) generated by a patient plan 3D-CT, a virtual 3D-CT image corresponding to a patient is generated according to each fractionated single DR image of the patient in ion beam radiotherapy, the virtual 3D-CT and the patient plan 3D-CT with a sketching file are subjected to image registration to obtain a sketching file of the virtual 3D-CT, and a new treatment plan is made in the ion beam radiotherapy plan system by using the generated virtual 3D-CT and the corresponding sketching file, so that the rapid and intelligent ion beam self-adaptive radiotherapy is realized.

In an embodiment of the present invention, as shown in fig. 1, an intelligent ion beam adaptive radiotherapy system is provided, and the intelligent ion beam adaptive radiotherapy system provided in this embodiment can be applied not only to an ion beam radiotherapy system, but also to a conventional radiation radiotherapy system such as photon radiotherapy, which is exemplified by the ion beam radiotherapy system in this embodiment. In this embodiment, the intelligent ion beam adaptive radiotherapy system includes:

the artificial intelligent network model building module is used for training and verifying the artificial intelligent network model by adopting a data set formed by the DRR image and the 3D-CT image corresponding to the DRR image to obtain a weight parameter of the artificial intelligent network model;

the DR image generation module with the DRR style inputs each classified DR image into a two-dimensional image translation model based on deep learning to generate a corresponding DR image with the DRR style;

the virtual 3D-CT image generation module is used for inputting each classified DR image with the DRR style into the artificial intelligent network model construction module and obtaining a virtual 3D-CT image corresponding to each classified DR image by combining the weight parameters;

the image registration module is used for carrying out image registration on each divided virtual 3D-CT image and a reference 3D-CT image with a delineation file to generate a delineation file corresponding to the virtual 3D-CT image;

and the output module is used for outputting the fractionated virtual 3D-CT images and the delineation files corresponding to the fractionated virtual 3D-CT images to an ion beam radiotherapy planning system, and the ion beam radiotherapy planning system is used for making radiotherapy plans of each fraction.

In the above embodiment, the DRR image is generated by the patient planning 3D-CT in the artificial intelligence network model building module. And further constructing a DRR image and a patient 3D-CT image data set corresponding to the DRR image, wherein the data set is used for training and verifying the artificial intelligent network model. The artificial intelligent network model can realize the functions of inputting a single DR image and outputting a virtual 3D-CT data set.

In the above embodiment, training and verifying the artificial intelligent network model includes: inputting N DRR images and S-layer 3D-CT images corresponding to the DRR images; the value of N is 1, and the value of S is the same as the number of layers of the patient plan 3D-CT.

The method specifically comprises the following steps: when the artificial intelligent network model performs D training verification, N DRR images and S-layer 3D-CT images corresponding to the N DRR images are input, where a value range of N is greater than or equal to 1, and imaging angles of each DRR generated by simulation are different, and theoretically, when a value of N is greater than 1, an effect of the model is the best, but the larger N is, the more complicated the preprocessing to be performed on a data set of the model is, the more DR images of each fraction to be subsequently photographed in a DR image generation module having a DRR style are, the more extra dose is brought to a patient, the more complicated the entire system is while the economic cost is increased, and therefore, in this embodiment, the value of N is preferably set to 1. The number of layers of S is consistent with the number of layers of the patient plan 3D-CT, and the layer thickness should also be consistent with or as close as possible to the patient plan 3D-CT, so that the obtained parameters of the artificial intelligence network model can play a role more accurately in the virtual 3D-CT image generation module, as shown in FIG. 2, a cross-sectional difference graph between the 3D-CT generated by the artificial intelligence network model according to 1 DRR image and the corresponding real 3D-CT is shown.

In the above-described embodiment, in the DR image generation module having the DRR style, the DR image is acquired by the DR imaging system apparatus.

As shown in fig. 3, the DR imaging system only includes a set of X-ray emission sources and corresponding imaging panels, and obtains DR images of each time of the patient in real time. The DR image of each fraction refers to a DR image taken by the patient before or during the current fraction treatment.

In the present embodiment, the X-ray emission source and the imaging plate are connected in two ways, one of them is selected; the first one is: the X-ray emission source can be arranged on the ground of the treatment room, the imaging flat plate is arranged at the top of the treatment room, and the central point of the treatment room is taken as the origin point to respectively rotate at a small angle. The second method is as follows: the X-ray emission source and the imaging flat plate are connected together by a C-shaped arm, and the X-ray emission source and the imaging flat plate perform small-angle motion as a whole by taking the central point of the treatment room as the origin.

Preferably, the small angular movement is a rotational movement with a rotational angle between-15 °, +15 °.

When the X-ray imaging system is used, the first connection mode is taken as an example, the DR imaging system acquires DR images of each time of a patient in real time, the X-ray emission source is installed on the ground of a treatment room, the imaging flat plate is installed at the top of the treatment room and rotates at a small angle by using a track respectively, and the movement mode is controlled by the existing control system so as to ensure the consistency of the movement direction and the accuracy of the position.

In the above embodiment, after the two-dimensional image translation model based on deep learning is trained and verified by using the DR image of the patient and the corresponding DRR image, the DR image with the DRR style can be automatically generated according to the DR image of the patient.

In the present embodiment, the two-dimensional image translation model based on deep learning is employed to solve the difference between the DRR image and the DR image, and the captured DR image is converted into a DR image having a DRR image style so as to successfully generate a corresponding 3D-CT image for each fraction using the captured DR image for each fraction.

In the above embodiment, in the image registration module, each of the divided virtual 3D-CT images and the reference 3D-CT image with the delineation file are input into the B-spline-based image registration model, registration calculation is performed, and the delineation file corresponding to the virtual 3D-CT image is output.

In this embodiment, a registration calculation may be performed by using a B-spline-based image registration model according to an input reference 3D-CT image with a delineation file and an individual virtual 3D-CT image to obtain a delineation file of the virtual 3D-CT image, so as to combine the 3D-CT corresponding to the fraction in the ion beam radiotherapy planning system to make a new treatment plan, and then perform each fraction of ion beam radiotherapy according to the made new treatment plan.

In summary, the invention uses an artificial intelligence technology to perform three-dimensional CT reconstruction on the two-dimensional DR image to obtain a real-time virtual 3D-CT image of the patient in each fraction, obtains a corresponding delineation file for each generated 3D-CT image in accordance with an image registration model based on a B-spline, and makes a new radiotherapy plan in an ion beam radiotherapy planning system in accordance with each 3D-CT image in each fraction and the corresponding delineation file, thereby realizing rapid and intelligent ion beam self-adaptive radiotherapy and improving the effect of ion beam radiotherapy.

Example (b):

the system of the present invention is further described by the following implementation, as shown in FIG. 4:

firstly, a set of DR imaging system capable of moving at small angle of-15 degrees and +15 degrees is arranged in a treatment room, and the equipment moves by taking the isocenter of the treatment room as an axis.

Second, a constructed artificial intelligence neural network is used, which can reconstruct a virtual 3D-CT image of the patient from a single DRR image. And carrying out training verification by using the marked DRR image and the corresponding 3D-CT image to obtain the weight parameters of the artificial intelligent neural network model.

Third, a constructed deep learning convolutional neural network is used, which can convert the photographed DR image into a DR image having a DRR image style. And carrying out training verification by using the DRR-DR image data set to obtain the weight parameters of the network model.

Fourthly, before or during each time division of the patient, the installed DR imaging system is used for shooting a real-time DR image, the DR image is guided into the deep learning convolution neural network constructed and trained in the third step, and the DR image of each time division with the DRR style is output.

And fifthly, importing each graded DR image with the DRR style in the fourth step into the artificial intelligent neural network constructed and trained in the second step, and outputting each graded virtual 3D-CT image.

Sixthly, a constructed CT image registration model is used, and the model can generate a delineation file corresponding to the virtual 3D-CT image by utilizing an input reference 3D-CT image with the delineation file and an independent virtual 3D-CT image;

seventhly, re-formulating a treatment plan in the ion beam radiotherapy planning system by using a delineation file corresponding to each fractionated 3D-CT image output in the sixth step and each fractionated virtual 3D-CT image output in the fifth step;

eighth, the irradiation treatment is carried out according to the new treatment plan obtained in the seventh step.

As shown in fig. 5, which is a schematic structural diagram of a computing device provided in an embodiment of the present invention, the computing device may be a terminal, and may include: a processor (processor), a communication Interface (communication Interface), a memory (memory), a display screen and an input device. The processor, the communication interface and the memory are communicated with each other through a communication bus. The processor is used to provide computing and control capabilities. The memory comprises a nonvolatile storage medium and an internal memory, wherein the nonvolatile storage medium stores an operating system and a computer program, and the computer program is executed by the processor to realize any function of the intelligent ion beam adaptive radiotherapy system in the embodiment; the internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, a manager network, NFC (near field communication) or other technologies. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on a shell of the computing equipment, an external keyboard, a touch pad or a mouse and the like. The processor may call logic instructions in the memory to implement the following functions:

adopting a data set formed by the DRR image and the 3D-CT image corresponding to the DRR image to train and verify the artificial intelligent network model to obtain a weight parameter of the artificial intelligent network model; inputting each classified DR image into a two-dimensional image translation model based on deep learning to generate a corresponding DR image with a DRR style; inputting each classified DR image with the DRR style into an artificial intelligent network model building module, and combining with the weight parameters to obtain a virtual 3D-CT image corresponding to each classified DR image; carrying out image registration on each divided virtual 3D-CT image and a reference 3D-CT image with a delineation file to generate a delineation file corresponding to the virtual 3D-CT image; and outputting each fractionated virtual 3D-CT image and a drawing file corresponding to each fractionated virtual 3D-CT image to an ion beam radiotherapy planning system, and making a radiotherapy plan of each fraction by the ion beam radiotherapy planning system.

In addition, the logic instructions in the memory may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

Those skilled in the art will appreciate that the architecture shown in fig. 5 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.

In one embodiment of the invention, there is provided a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the functions provided by the system of embodiments, including for example: adopting a data set formed by the DRR image and the 3D-CT image corresponding to the DRR image to train and verify the artificial intelligent network model to obtain a weight parameter of the artificial intelligent network model; inputting each classified DR image into a two-dimensional image translation model based on deep learning to generate a corresponding DR image with a DRR style; inputting each classified DR image with the DRR style into an artificial intelligent network model building module, and combining with the weight parameters to obtain a virtual 3D-CT image corresponding to each classified DR image; carrying out image registration on each divided virtual 3D-CT image and a reference 3D-CT image with a delineation file to generate a delineation file corresponding to the virtual 3D-CT image; and outputting each fractionated virtual 3D-CT image and a drawing file corresponding to each fractionated virtual 3D-CT image to an ion beam radiotherapy planning system, and making a radiotherapy plan of each fraction by the ion beam radiotherapy planning system.

In one embodiment of the present invention, a non-transitory computer-readable storage medium is provided, which stores server instructions, which when executed by a computer, implement the functions provided by the system in the above embodiments, for example, including: adopting a data set formed by the DRR image and the 3D-CT image corresponding to the DRR image to train and verify the artificial intelligent network model to obtain a weight parameter of the artificial intelligent network model; inputting each classified DR image into a two-dimensional image translation model based on deep learning to generate a corresponding DR image with a DRR style; inputting each classified DR image with the DRR style into an artificial intelligent network model building module, and combining with the weight parameters to obtain a virtual 3D-CT image corresponding to each classified DR image; carrying out image registration on each divided virtual 3D-CT image and a reference 3D-CT image with a delineation file to generate a delineation file corresponding to the virtual 3D-CT image; and outputting each fractionated virtual 3D-CT image and a drawing file corresponding to each fractionated virtual 3D-CT image to an ion beam radiotherapy planning system, and making a radiotherapy plan of each fraction by the ion beam radiotherapy planning system.

The implementation principle and technical effect of the computer-readable storage medium provided by the above embodiments are similar to those of the above method embodiments, and are not described herein again.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.