WO2022198553A1

WO2022198553A1 - Three-dimensional image-guided positioning method and system, and storage medium

Info

Publication number: WO2022198553A1
Application number: PCT/CN2021/082938
Authority: WO
Inventors: 申国盛; 李强; 刘新国; 戴中颖; 金晓东; 贺鹏博
Original assignee: 中国科学院近代物理研究所
Priority date: 2021-03-25
Filing date: 2021-03-25
Publication date: 2022-09-29

Abstract

A three-dimensional (3D) image-guided positioning method and system, and a storage medium. The method comprises: automatically segmenting a set of 3D-CT images of a patient by means of an automatic segmentation algorithm to obtain tissue organs and tumor target regions, and reconstructing, by means of a tissue organ model reconstruction algorithm, contour data of tissue organs and tumor target regions in a patient treatment plan; generating a set of virtual 3D-CT images of the patient by means of an artificial intelligence network algorithm on the basis of real-time DR images of the patient; automatically segmenting the set of virtual 3D-CT images of the patient by means of the automatic segmentation algorithm to obtain virtual tissue organs and tumor target regions, and reconstructing contour data of the virtual tissue organs and tumor target regions of the patient; registering the contour data of the tissue organs and tumor target regions in the patient treatment plan with the contour data of the virtual tissue organs and tumor target regions, outputting patient positioning offset parameters, and determining whether a radiotherapy condition is met: if not, guiding the patient to be re-positioned; and if yes, completing the positioning.

Description

Three-dimensional image-guided positioning method, system and storage medium

technical field

The invention relates to a method, a system and a storage medium for three-dimensional image-guided placement based on artificial intelligence technology and a DR system in radiotherapy, and relates to the field of image-guided placement of radiotherapy patients.

Background technique

The speed and accuracy of patient placement verification in radiotherapy are important factors that affect the efficiency and efficacy of patient treatment. Especially in particle precision radiotherapy technology, patient placement takes up a lot of treatment time, which greatly reduces the cost of radiotherapy. Efficiency increases the cost of treatment and affects the radiotherapy effect of patients. Therefore, how to quickly and effectively guide the patient to perform the positioning operation and verification is one of the keys to the image-guided radiotherapy technology. Current image guidance systems are often used as a stand-alone medical device, and most use digital X-ray imaging (DR) systems, cone beam CT (CBCT) imaging systems, and rail CT (CT-on-rail) systems to obtain patient positioning Position information to guide and verify patient positioning.

Conventional DR image-based guidance systems require the use of two intersecting DR imaging equipment at large angles (close to or equal to 90 degrees orthogonal) or C-arm-connected rotating DR equipment to generate two large-angle intersecting DR images, which are consistent with patient treatment planning CT. The digital reconstructed radiography (DRR) generated by the image is registered to obtain the offset of the patient's positioning position and guide the patient's positioning, but there is no real three-dimensional (3D) positioning guidance. In addition, CBCT and orbital CT imaging systems will add additional radiation dose to patients, increasing the risk of complications for patients, and CBCT and orbital CT imaging systems are expensive, and the obtained CBCT image density resolution is not high. Accuracy and speed are not high.

SUMMARY OF THE INVENTION

In view of the above problems, the purpose of the present invention is to provide a method, system and storage medium for 3D image guidance positioning based on artificial intelligence technology and DR system that can achieve accurate 3D image guidance and obtain patient positioning information.

To achieve the above object, the present invention adopts the following technical solutions:

In a first aspect, the present invention provides a three-dimensional image-guided positioning method, comprising:

The patient's 3D-CT image set is automatically segmented into tissues and organs and tumor target areas by automatic segmentation algorithm, and the contour data of the tissues and organs and tumor target areas of the patient's treatment plan are reconstructed through the tissue-organ model reconstruction algorithm;

Based on the patient's real-time DR images, the artificial intelligence network algorithm is used to generate the patient's virtual 3D-CT image set;

The patient's virtual 3D-CT image set is automatically segmented into virtual tissues and organs and tumor target areas by an automatic segmentation algorithm, and the patient's virtual tissues and organs and tumor target area contour data are reconstructed through the tissue-organ model reconstruction algorithm;

Register the contour data of the tissue and organ and tumor target volume of the patient's treatment plan with the virtual tissue and organ and the contour data of the tumor target volume, output the patient's positioning offset parameter, and determine whether the offset parameter meets the radiotherapy conditions: if not , the patient is guided to reposition; if the conditions are met, the position is completed.

Further, the real-time DR image of the patient is acquired by using a DR imaging device.

Further, the DR imaging device includes a set of X-ray sources and a corresponding imaging flat panel;

The X-ray source is installed on the top of the treatment room, and the imaging plate is installed on the floor portion of the treatment room, and each uses a small-angle track to move; or,

The X-ray source and the imaging plate are connected by a C-arm for small-angle movement.

Further, the artificial intelligence network algorithm is obtained through training and verification, including:

Use the DR imaging equipment to capture the DR image of the patient, and use the CT system to capture the 3D-CT image of the same part of the same patient, so that the DR image of the patient and the 3D-CT image are in one-to-one correspondence, and the DR image and the corresponding 3D-CT image are established. CT image data set; part of the data in the established data set is used as a training data set, and the other part is used as a verification data set, a neural network model is constructed for training and verification, and the weights and parameters of the artificial intelligence network are obtained through continuous iteration through operations, and then the trained artificial intelligence network model.

Further, the automatic segmentation algorithm adopts a deep learning-based convolutional neural network model, which can automatically segment tissues, organs and tumor target areas according to the input CT images.

Further, the tissue and organ reconstruction algorithm can reconstruct the 3D models of all or specified tissues and organs, and can render and display different tissues and organs in different colors and modes, which is convenient for users to observe and distinguish operations.

Further, the registration employs a tissue-organ registration algorithm for manual and/or automatic 3D model registration.

In a second aspect, the present invention also provides a three-dimensional image-guided positioning system, the system comprising:

The organ reconstruction unit is configured to automatically segment the patient's 3D-CT image set into tissues, organs and tumor target areas by using an automatic segmentation algorithm, and reconstruct the contours of the tissues, organs and tumor target areas of the patient's treatment plan through the tissue-organ model reconstruction algorithm data;

The virtual image generation unit, based on the real-time DR image of the patient, uses the artificial intelligence network algorithm to generate the virtual 3D-CT image set of the patient;

The virtual organ reconstruction unit uses an automatic segmentation algorithm to automatically segment the patient's virtual 3D-CT image set into virtual tissue organs and tumor target areas, and reconstructs the patient's virtual tissue organs and tumor target area contour data through the tissue-organ model reconstruction algorithm;

The positioning judgment unit registers the contour data of the tissue and organ and tumor target area of the patient's treatment plan with the virtual tissue and organ and the contour data of the tumor target area, outputs the patient's positioning offset parameter, and judges whether the offset parameter is in line with the radiation therapy. Conditions: If not, guide the patient to reposition; if eligible, complete the position.

In a third aspect, the present invention further provides a processing device, the processing device includes at least a processor and a memory, and a computer program is stored on the memory, and the processor executes the computer program when running the computer program to realize the first aspect of the present invention The three-dimensional image-guided positioning method of the aspect.

In a fourth aspect, the present invention further provides a computer storage medium having computer-readable instructions stored thereon, and the computer-readable instructions can be executed by a processor to implement the three-dimensional image-guided positioning method described in the first aspect of the present invention .

The present invention has the following advantages due to taking the above technical solutions:

1. The present invention generates a virtual 3D-CT image of patient placement based on a small number of DR images, performs 3D reconstruction and registration of the patient's treatment plan 3D-CT and virtual 3D-CT, obtains patient placement information, and realizes accurate 3D image-guided radiotherapy , to solve the defects and deficiencies in conventional DR images and CBCT image guidance;

2. The present invention uses artificial intelligence technology to convert real-time 2D-DR images into virtual 3D-CT images, and performs 3D reconstruction and registration of virtual 3D-CT images and treatment plan 3D-CT images to realize 3D guidance in the true sense;

3. The present invention only needs a single DR imaging device, and the cost is low; compared with the CBCT system, while reducing the cost of the device to achieve 3D positioning and guidance, the additional radiation dose to the patient during imaging is also low.

In conclusion, the present invention is suitable for patient positioning guidance of any radiotherapy system.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for the purpose of illustrating preferred embodiments only and are not to be considered limiting of the invention. The same reference numerals are used to refer to the same parts throughout the drawings. In the attached image:

1 is a flowchart of a method for 3D image-guided positioning provided by an embodiment of the present invention;

2 is a schematic diagram of the coordinates of a DR device according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of an artificial intelligence network algorithm according to an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present invention will be more thoroughly understood, and will fully convey the scope of the present invention to those skilled in the art.

It is to be understood that the terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting. As used herein, the singular forms "a," "an," and "the" can also be intended to include the plural forms unless the context clearly dictates otherwise. The terms "comprising", "comprising", "containing" and "having" are inclusive and thus indicate the presence of stated features, steps, operations, elements and/or components, but do not preclude the presence or addition of one or Various other features, steps, operations, elements, components, and/or combinations thereof. Method steps, procedures, and operations described herein are not to be construed as requiring that they be performed in the particular order described or illustrated, unless an order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

For ease of description, spatially relative terms may be used herein to describe the relationship of one element or feature to another element or feature as shown in the figures, such as "inner", "outer", "inner" ", "outside", "below", "above", etc. This spatially relative term is intended to include different orientations of the device in use or operation other than the orientation depicted in the figures.

Computer technology, especially artificial intelligence technology, has shown excellent performance in computer vision and medical image processing segmentation and multi-modal image generation. More and more multi-modal image generation and automatic segmentation technologies are realized. Therefore, it is feasible and necessary to develop a method based on artificial intelligence technology to achieve 3D high-precision patient positioning image guidance and verification while reducing the price of image-guided equipment.

Example 1

As shown in Figure 1, the 3D image-guided positioning method based on artificial intelligence technology and DR system provided by this embodiment includes the following contents:

S1: Setting up a single DR imaging system device

Specifically, according to the schematic diagram of the DR imaging device shown in FIG. 2 , the DR imaging device in this embodiment includes a set of X-ray emission sources 1 and an imaging flat panel 2 corresponding thereto, which are used to obtain real-time DR images of patients. The system equipment can install the X-ray source 1 on the top of the treatment room, and the imaging plate 2 is installed on the ground part of the treatment room, each of which uses a small-angle track to move, and the movement mode is controlled by the corresponding control system to ensure the consistency of the movement direction and position. Accuracy; of course, the X-ray source 1 and the imaging plate 2 can also be connected together using a C-shaped arm according to needs, so as to perform small-angle movements as a whole.

In some implementations, the DR imaging device of this embodiment can take the center point of the treatment room as the origin, perform small-angle rotation imaging, and generate DR images of different angles, wherein, in the treatment room coordinate axis XYZ, the coordinate origin is the beam of the treatment room The isocenter of the flow, the X axis is parallel to the floor of the treatment room and points to the zero degree direction of the treatment bed, the Y axis is parallel to the floor of the treatment room and points to the 90° direction of the treatment bed, and the Z axis is perpendicular to the floor of the treatment room and points to the top of the treatment room.

In other implementations, the small angle in this embodiment is defined between -15 degrees and +15 degrees.

S2: Build a DR image and a corresponding 3D-CT image data set for patient radiotherapy. The 3D-CT image data set is used for training and verification of an artificial intelligence network algorithm model.

Specifically, a DR imaging device is used to capture a DR image of a patient, and a CT system is used to capture a 3D-CT image of the same part of the same patient, so that the DR image of the patient and the 3D-CT image are in one-to-one correspondence to establish a data set. Take 80% of the data in the established dataset as the training dataset and 20% as the validation dataset, first build the model and then train and validate.

S3: Build an artificial intelligence network algorithm model. The principle of the algorithm model is shown in Figure 3. The algorithm is implemented using a neural network, which can input a small number of DR images and output a virtual 3D-CT data set;

S4: Use the DR image set in step S2 and the corresponding 3D-CT image to train and verify the artificial intelligence network algorithm model in step S3, and obtain the weight and parameters of the artificial intelligence network model, and the parameters include the weight of each neuron of the network model. and neuron parameters;

Specifically, when the artificial intelligence network algorithm model is trained and verified, N DR images and the corresponding M-layer 3D-CT images are input. The value range of N is greater than or equal to 1, and the shooting angle of each DR image is different. Although the larger the value of N is in theory, the better, but with the increase of the value of N, the DR image to be shot becomes more and more The more, the more additional radiation dose is added to the patient, and the greater the economic cost is, so the N value should not exceed 8. The number of layers of M is determined with reference to the number of layers of CT in the treatment plan. Generally, the number of layers in M is close to or equal to that of CT in the treatment plan. CT for registration.

S5: Obtain the real-time DR image of the patient, and use the artificial intelligence network algorithm and artificial intelligence network weights and parameters to generate the virtual 3D-CT image of the current patient with the real-time generated DR image, and the tissues and organs are generated according to the 3D-CT segmentation of the patient. ;

Specifically, the real-time DR image refers to a DR image taken by a patient before or during the current fractional treatment, and the DR image is used to guide and verify the current treatment setup of the patient.

S6: Build an automatic segmentation algorithm for tissues and organs based on deep learning. After training and verification by using CT images and the corresponding doctors to manually segment tissues and organs, the algorithm can automatically and accurately segment the tissues and organs on the CT images according to the CT images (such as , skin, bone, etc.) and tumor target areas;

Specifically, an automatic segmentation algorithm for tissues and organs based on deep learning. This algorithm uses a deep learning convolutional neural network model to automatically segment tissues and organs according to the input CT images. The training and verification data of the algorithm comes from experienced physicians. The quality of the manually delineated tissues and organs and the corresponding CT and training certificate datasets must be guaranteed. The algorithm can output all or specified tissue, organs and tumor target contour sets for the next step of 3D reconstruction and registration.

S7: Construct a 3D tissue-organ model reconstruction algorithm, which realizes the automatically generated tissue-organ contour set from the input 3D-CT image, and the current patient's treatment plan CT data and/or tissue-organ contour set can reconstruct the output 3D tissue and organ (such as skin, Bone, etc.) model, you can also choose to reconstruct all organs or specific organs in CT according to your needs;

Specifically, the 3D tissue and organ reconstruction algorithm can reconstruct all or specific tissues and organs specified, and render and display different tissues and organs in different colors and modes, which is convenient for users to observe and distinguish operations.

S8: Use a 3D tissue and organ reconstruction algorithm to perform 3D reconstruction according to the patient's virtual CT data and/or tissue and organ contour sets to obtain a patient's virtual 3D tissue and organ such as skin, bone and other models;

S9: Build a conventional 3D model registration algorithm, which can register multiple input 3D models and output the offset of the 3D models after registration;

Specifically, the 3D tissue-organ registration algorithm can perform manual and/or automatic 3D model registration according to the reconstructed 3D tissue-organ model, and accurately output the offset parameter between the two models.

S10: Use a 3D model registration algorithm to perform automatic and/or manual registration calculations using the patient's virtual 3D tissue organ and patient plan and real-time partial or full treatment 3D tissue organ and contour set as input. In the present invention, the positioning accuracy of the patient can be verified only by calculating once after the patient completes the positioning or before the treatment, and calculating the positioning accuracy of the patient at an interval of 3-10 minutes during the treatment, and outputting the current positioning offset data of the patient;

S11: Determine whether the offset data output in step S10 meets the set radiation therapy requirements: if it does not meet the patient's treatment requirements, guide the patient to re-setup according to the set-up offset data, and move to step after re-setting S5, start to continue the setup verification process; if the setup offset data meets the treatment requirements, end the setup validation and start the treatment. Among them, whether it meets the standard of treatment requirements, the standard is obtained by the joint research of doctors and engineering technicians according to the laws and regulations of radiotherapy and industry standards.

To sum up, the present invention uses artificial intelligence technology to perform 3D reconstruction on a simple 2D-DR image, obtains a real-time virtual 3D-CT image of the patient, and reconstructs and matches the reconstructed virtual 3D-CT and the 3D-CT image of the patient treatment plan in three dimensions. Accurate, obtain the patient's precise 3D positioning offset parameters, guide and verify the patient's positioning, and ensure the effect of radiation therapy.

Example 2

Based on the content of the above-mentioned Embodiment 1, this embodiment describes in detail the specific application process of the method for 3D image-guided positioning based on artificial intelligence technology and DR system, and the specific process is as follows:

First, a DR imaging system that can move at a small angle [-15°, +15°] is installed in the treatment room, and the equipment moves around the center of the treatment.

Second, using the constructed artificial intelligence neural network, the network can reconstruct the virtual 3D-CT image of the patient from N[1~8] DR images. The labeled DR images and corresponding 3D-CT images are used for training and verification, and the weight parameters of the artificial intelligence neural network model are obtained.

Third, using the constructed deep learning convolutional neural network, the network can automatically and accurately segment CT images, and obtain the tissues, organs and tumor target areas in the CT images. Using the CT images manually segmented by experienced doctors for training and validation, the weight parameters of the network model are obtained.

Fourth, when the patient starts this treatment or during the treatment, use the DR imaging system installed above to take N[1-8] real-time DR images, and import the images into the artificial intelligence constructed and trained in the second step. In the neural network, virtual 3D-CT images are output.

Fifth, perform automatic tissue and organ segmentation on the virtual 3D-CT and 3D-CT images of the patient treatment plan output in the fourth step to obtain contour data of the tissue, organ and tumor target area.

Sixth, perform three-dimensional reconstruction of the organizer tube and tumor target area output in the fifth step, perform three-dimensional registration calculation after reconstruction, and output the parameters of patient placement offset. Determine whether the radiotherapy conditions are met: if not, guide the patient to re-position according to the output parameters, and re-enter the fourth step; if the conditions are met, the position is completed and the treatment can be started.

Example 3

The above-mentioned Embodiment 1 provides a 3D image-guided positioning method. Correspondingly, this embodiment provides a 3D image-guided positioning system. The guidance system provided in this embodiment may implement the 3D image guidance placement method of Embodiment 1, and the guidance system may be implemented by software, hardware, or a combination of software and hardware. For example, the guidance system may include integrated or separate functional modules or functional units to perform corresponding steps in each method of Embodiment 1. Since the guidance system of this embodiment is basically similar to the method embodiment, the description process of this embodiment is relatively simple, and the relevant parts may refer to the partial description of Embodiment 1, and the embodiment of the guidance system of this embodiment is only illustrative of.

This embodiment provides a three-dimensional image-guided positioning system, which includes:

Example 4

This embodiment provides a processing device corresponding to the 3D image-guided positioning method provided in Embodiment 1, and the processing device may be an electronic device used for a client, such as a mobile phone, a notebook computer, a tablet computer, a desktop computer, etc. , to perform the method of Example 1.

The processing device includes a processor, a memory, a communication interface and a bus, and the processor, the memory and the communication interface are connected through the bus to complete mutual communication. The bus can be an industry standard architecture (ISA, Industry Standard Architecture) bus, a peripheral device interconnect (PCI, Peripheral Component) bus or an extended industry standard architecture (EISA, Extended Industry Standard Component) bus and so on. A computer program that can be run on the processor is stored in the memory, and the processor executes the 3D image-guided positioning method provided in Embodiment 1 when the processor runs the computer program.

In some implementations, the memory may be a high-speed random access memory (RAM: Random Access Memory), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

In other implementations, the processor may be various types of general-purpose processors such as a central processing unit (CPU) and a digital signal processor (DSP), which are not limited herein.

Example 5

The method for 3D image-guided positioning in Embodiment 1 may be embodied as a computer program product, and the computer program product may include a computer-readable storage medium on which a computer-readable storage medium for executing the method described in Embodiment 1 is uploaded. Read program instructions.

A computer-readable storage medium may be a tangible device that retains and stores instructions for use by the instruction execution device. The computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination of the above.

It should be noted that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing the specified logical function(s). Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: the present invention can still be Modifications or equivalent replacements are made to the specific embodiments of the present invention, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention shall be included within the protection scope of the claims of the present invention. The above contents are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the technical scope disclosed in the present application can easily think of changes or replacements, which should cover within the scope of protection of this application. Therefore, the protection scope of the present application should be the protection scope of the claims.

Claims

A three-dimensional image-guided positioning method, comprising:

The patient's 3D-CT image set is automatically segmented into tissues, organs and tumor target areas by an automatic segmentation algorithm, and the contour data of the tissues, organs and tumor target areas of the patient's treatment plan are reconstructed through the tissue-organ model reconstruction algorithm;

Based on the patient's real-time DR images, the artificial intelligence network algorithm is used to generate the patient's virtual 3D-CT image set;

The patient's virtual 3D-CT image set is automatically segmented into virtual tissues and organs and tumor target areas by an automatic segmentation algorithm, and the patient's virtual tissues and organs and tumor target area contour data are reconstructed through the tissue-organ model reconstruction algorithm;

Register the contour data of the tissue and organ and tumor target volume of the patient's treatment plan with the virtual tissue and organ and the contour data of the tumor target volume, output the patient's positioning offset parameter, and determine whether the offset parameter meets the radiotherapy conditions: if not , the patient is guided to reposition; if the conditions are met, the position is completed.
The method according to claim 1, wherein the real-time DR image of the patient is acquired by using a DR imaging device.
The three-dimensional image-guided positioning method according to claim 2, wherein the DR imaging device comprises a set of X-ray sources and an imaging flat panel corresponding thereto;

The X-ray source is installed on the top of the treatment room, and the imaging plate is installed on the floor portion of the treatment room, and each uses a small-angle track to move; or,

The X-ray source and the imaging plate are connected by a C-arm for small-angle movement.
The three-dimensional image-guided positioning method according to claim 1, wherein the artificial intelligence network algorithm is obtained through training and verification, comprising:

Use the DR imaging equipment to capture the DR image of the patient, and use the CT system to capture the 3D-CT image of the same part of the same patient, so that the DR image of the patient and the 3D-CT image are in one-to-one correspondence, and the DR image and the corresponding 3D-CT image are established. CT image data set; part of the data in the established data set is used as a training data set, and the other part is used as a verification data set, a neural network model is constructed for training and verification, and the weights and parameters of the artificial intelligence network are obtained through continuous iteration through operations, and then the trained artificial intelligence network model.
The method of three-dimensional image-guided placement according to claim 1, wherein the automatic segmentation algorithm adopts a deep learning convolutional neural network model, and can automatically segment tissues and organs and tumor target areas according to the input CT image.
The three-dimensional image-guided positioning method according to claim 1, wherein the tissue-organ reconstruction algorithm can reconstruct 3D models of all or specified tissues and organs, and can render different tissues and organs with different colors and modes. The display is convenient for users to observe and distinguish operations.
The three-dimensional image-guided positioning method according to claim 1, wherein the registration adopts a tissue-organ registration algorithm to perform manual and/or automatic 3D model registration.
A three-dimensional image guidance system, characterized in that the system includes:

The organ reconstruction unit is configured to automatically segment the patient's 3D-CT image set into tissues, organs and tumor target areas by using an automatic segmentation algorithm, and reconstruct the contours of the tissues, organs and tumor target areas of the patient's treatment plan through the tissue-organ model reconstruction algorithm data;

The virtual image generation unit, based on the real-time DR image of the patient, uses the artificial intelligence network algorithm to generate the virtual 3D-CT image set of the patient;

The virtual organ reconstruction unit uses an automatic segmentation algorithm to automatically segment the patient's virtual 3D-CT image set into virtual tissue organs and tumor target areas, and reconstructs the patient's virtual tissue organs and tumor target area contour data through the tissue-organ model reconstruction algorithm;

The positioning judgment unit registers the contour data of the tissue and organ and tumor target area of the patient's treatment plan with the virtual tissue and organ and the contour data of the tumor target area, outputs the patient's positioning offset parameter, and judges whether the offset parameter is in line with the radiation therapy. Conditions: If not, guide the patient to reposition; if eligible, complete the position.
A processing device, the processing device includes at least a processor and a memory, and a computer program is stored on the memory, wherein the processor executes the computer program when running the computer program to realize any one of claims 1 to 7 The three-dimensional image-guided positioning method described in item.
A computer storage medium, characterized in that computer-readable instructions are stored thereon, and the computer-readable instructions can be executed by a processor to implement the three-dimensional image-guided positioning method according to any one of claims 1 to 7.