A method and system for fusion of heterogeneous respiratory motion models based on fuzzy evaluation

Abstract

The present application provides a method and system for fusing heterogeneous respiratory motion models based on fuzzy evaluation, the method comprising the following steps: establishing a surface-tumor respiratory motion association model based on a chest and abdominal surface voxel model; obtaining a respiratory motion model by fitting parameters using a genetic algorithm; constructing a fuzzy weight evaluation matrix for the association model and the respiratory motion model based on a fuzzy evaluation method, the evaluation matrix being used to characterize the magnitude of the correlation between the two sets of models and tumor motion at different stages of a single-cycle respiration; and obtaining the weight distribution of the two sets of models at the same moment through the evaluation matrix and performing weighted averaging to obtain the fusion value at that moment. Compared with existing methods, the method proposed in the present application can effectively reduce the impact of respiratory disturbances on patients at the beginning and end of respiration, improve the correlation accuracy of the association model at the beginning and end of respiration, and contribute to improving the correlation accuracy of the surface-in-vivo respiratory motion association model.

Description

Technical Field

[0001] The present application relates to the technical field of precise radiotherapy robot respiratory tracking, and in particular to a heterogeneous respiratory motion model fusion method and system based on fuzzy evaluation. Background Art

[0002] During radiation therapy for lung tumors, a precision radiotherapy robot establishes a correlation model between the motion information of surface markers and the motion information of the tumor within the body, thereby predicting the tumor's position without the aid of X-rays. However, the limited number of markers placed on the chest and abdomen makes it difficult to characterize the respiratory characteristics of the chest and abdomen. Because the human body is prone to respiratory disturbances at the beginning and end of breathing, the correlation model's accuracy in these two phases is reduced. Therefore, research on improving the correlation model's accuracy at the beginning and end of breathing is key to improving the radiotherapy robot's radiotherapy accuracy.

[0003] Lung tumor motion is primarily influenced by the patient's free breathing, so the motion characteristics of the tumor are largely consistent with those of respiratory motion. The most significant characteristic of respiratory motion is its quasi-periodicity, meaning that respiratory motion can be roughly viewed as a periodic motion based on a time series. Therefore, tumor motion is influenced by respiratory motion and its motion characteristics also exhibit periodic characteristics. When establishing a correlation model for surface-to-body motion information, it is possible to consider combining the periodic respiratory motion model with the traditional correlation model, leveraging the respective strengths of each model to create an optimized correlation model.

[0004] After obtaining the two sets of models, how to effectively fuse them is also a key step. Common and simple data fusion methods such as weighted averaging can achieve data fusion by weighted averaging the two sets of data. Although this method can process data in real time, it cannot formulate the weight distribution of data at different times and scenarios, and is greatly affected by noise.

[0005] Therefore, studying the effective integration of the association model and the respiratory motion model is of great significance for improving the radiotherapy accuracy of the precision radiotherapy robot. Summary of the Invention

[0006] In view of this, the purpose of this application is to propose a heterogeneous respiratory motion model fusion method and system based on fuzzy evaluation. This application can specifically solve existing problems and improve the accuracy of tumor association models. This application chooses to use the principle of fuzzy reasoning to define the correlation between different data and tumor motion at different times and formulate a weight distribution scheme for data at different stages, giving the computer the same thinking ability as a human, which can achieve better fusion effect.

[0007] Based on the above objectives, this application proposes a heterogeneous respiratory motion model fusion method based on fuzzy evaluation, including:

[0008] Establish a body surface-tumor respiratory motion correlation model based on the chest and abdominal surface voxel model;

[0009] The respiratory motion model to be fused is obtained by fitting parameters using genetic algorithm;

[0010] Constructing a fuzzy weight evaluation matrix of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model, wherein the fuzzy weight evaluation matrix is used to characterize the correlation between the respiratory motion model to be fused and the body surface-tumor respiratory motion association model and tumor motion in different stages of a single respiratory cycle;

[0011] The weight distribution of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model at the same moment is obtained through the fuzzy weight evaluation matrix, and then the weighted average is performed to obtain the fusion value at the same moment.

[0012] Furthermore, the establishment of a body surface-tumor respiratory motion correlation model based on a chest and abdomen body surface voxel model includes:

[0013] Step 1: Use a depth camera to collect chest and abdomen point cloud information;

[0014] Step 2: Perform point cloud processing on the collected point cloud information, including point cloud registration, segmentation, filtering and smoothing, to obtain a voxel model of the chest and abdomen surface;

[0015] Step 3: Perform LLE dimensionality reduction on the chest and abdomen surface voxel model to obtain a one-dimensional feature vector of the body surface respiratory motion;

[0016] Step 4: Acquire the position of the simulated tumor through an electromagnetic tracker, and establish a body surface-tumor respiratory motion correlation model with the one-dimensional feature vector of the body surface respiratory motion obtained in step 3.

[0017] Furthermore, the obtaining of the respiratory motion model to be fused by fitting parameters through a genetic algorithm includes:

[0018] Step 5: Construct error functions by combining the three candidate respiratory motion models with the tumor motion information;

[0019] Step 6: Use the genetic algorithm to minimize the error functions in step 5 respectively, obtain the model parameters, and select the candidate respiratory motion model with the smallest error as the respiratory motion model to be fused.

[0020] Furthermore, the step of constructing a fuzzy weight evaluation matrix of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model includes:

[0021] Step 7: construct a fuzzy weight evaluation matrix of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model based on a fuzzy evaluation method.

[0022] Furthermore, the weight distribution of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model at the same time is obtained by using the fuzzy weight evaluation matrix, and then the weighted average is performed to obtain the fusion value at the same time, including:

[0023] Step 8: Obtain the weight distribution of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model in a certain frame through the fuzzy weight evaluation matrix, and perform weighted averaging to obtain the predicted tumor posture of the frame.

[0024] Furthermore, the three candidate respiratory motion models in step 4 are three classical models that represent information on quasi-periodic motion characteristics.

[0025] Furthermore, in step 7, weight distribution is determined by defining the correlation between the respiratory motion model to be fused and the body surface-tumor respiratory motion association model and tumor motion at different respiratory stages during the fusion process to form the fuzzy weight evaluation matrix.

[0026] Based on the above objectives, this application also proposes a heterogeneous respiratory motion model fusion system based on fuzzy evaluation, including:

[0027] The first modeling module is used to establish a body surface-tumor respiratory motion correlation model based on a chest and abdominal surface voxel model;

[0028] The second modeling module is used to obtain the respiratory motion model to be fused by fitting parameters through a genetic algorithm;

[0029] An evaluation matrix construction module is used to construct a fuzzy weight evaluation matrix of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model, wherein the fuzzy weight evaluation matrix is used to characterize the correlation between the respiratory motion model to be fused and the body surface-tumor respiratory motion association model and tumor motion in different stages of a single respiratory cycle;

[0030] The fusion module is used to obtain the weight distribution of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model at the same time through the weight evaluation matrix, and then perform weighted average to obtain the fusion value at the same time.

[0031] In general, the advantages of this application and the experience it brings to users are: this application uses a fuzzy weight evaluation matrix to fuse the association model and the periodic respiratory motion model. Compared with the traditional association model, it optimizes the association effect of the model at the beginning and end stages of breathing, and improves the association model's prediction accuracy for tumor posture. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar components or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed in this application and should not be construed as limiting the scope of this application.

[0033] Figure 1 This is a flow chart of the heterogeneous respiratory motion model fusion method based on fuzzy evaluation in this application.

[0034] Figure 2 This is the scene graph of the depth camera information collected by this application.

[0035] Figure 3 This is a schematic diagram of the process of extracting one-dimensional feature representation quantities of the chest and abdominal surface in this application.

[0036] Figure 4 This is a schematic diagram of the genetic algorithm used in this application.

[0037] Figure 5 The figure shows a structural diagram of a heterogeneous respiratory motion model fusion system based on fuzzy evaluation according to an embodiment of the present application.

[0038] Figure 6 A schematic structural diagram of an electronic device provided in one embodiment of the present application is shown.

[0039] Figure 7 A schematic diagram of a storage medium provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0040] The present application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are intended only to illustrate the relevant invention and are not intended to limit the invention. It should also be noted that, for ease of description, only portions relevant to the relevant invention are shown in the accompanying drawings.

[0041] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0042] In order to achieve the purpose of this application, in one embodiment of this application, a heterogeneous respiratory motion model fusion method based on fuzzy evaluation is provided, comprising the following steps:

[0043] Establish a body surface-tumor respiratory motion correlation model based on the chest and abdominal surface voxel model;

[0044] The respiratory motion model to be fused is obtained by fitting parameters using genetic algorithm;

[0045] Constructing a fuzzy weight evaluation matrix of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model, wherein the fuzzy weight evaluation matrix is used to characterize the correlation between the respiratory motion model to be fused and the body surface-tumor respiratory motion association model and tumor motion in different stages of a single respiratory cycle;

[0046] The weight distribution of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model at the same moment is obtained through the fuzzy weight evaluation matrix, and then the weighted average is performed to obtain the fusion value at the same moment.

[0047] Specifically, such as Figure 1 As shown, the specific implementation process of the above method is as follows:

[0048] Step 1: Use a depth camera to collect chest and abdomen point cloud information; the point cloud collection method is to use two Kinect v2 depth cameras to collect a set of point cloud information respectively. Figure 2 As shown, this is a point cloud information collection scenario using two depth cameras.

[0049] Step 2: Perform point cloud processing on the collected point cloud information to obtain a chest and abdomen voxel model; point cloud processing includes ICP registration of the two sets of point cloud information collected in step 1, followed by point cloud segmentation, filtering, and smoothing.

[0050] Step 3: Perform LLE dimensionality reduction on the voxel model to obtain a one-dimensional representation vector. The LLE dimensionality reduction process in step 3 is as follows: assign a minimum bounding box to the voxel model of each frame. The length, width and height of the bounding box should just accommodate the voxel of the largest frame. Then, the voxels are taken out in the same order and encoded as 0 and 1 to form a one-dimensional column vector x consisting of several sample points. i (i=1, 2, ..., n), find the k nearest neighbor points x of each sample point based on the Euclidean distance ij (j=1, 2, ..., k), find the local covariance matrix Z of the sample point and its neighboring points i =(x i -x ij )(x i -x ij ) T , and calculate the weight coefficient vector of the sample and its neighboring points:

[0051]

[0052] where Z i is the local covariance matrix of the sample point and its neighboring points, I k is a column vector with k rows and all elements are 1.

[0053] Merge W i, get the weight coefficient matrix W, calculate the matrix M = (IW)(IW) T , calculate the first d+1 eigenvalues of the matrix and calculate the eigenvectors; {ψ1, ψ2, ..., ψ d+1}, the one with the greatest correlation with tumor motion is selected from the feature vectors as the one-dimensional feature vector of body surface respiratory motion. Figure 3 As shown in FIG, this is the process of obtaining a one-dimensional representation vector.

[0054] Step 4: Acquire the position of the simulated tumor through an electromagnetic tracker, and establish a body surface-tumor respiratory motion correlation model with the one-dimensional feature vector of the body surface respiratory motion obtained in step 3.

[0055] Step 5: Construct error functions between the three candidate respiratory motion models and the tumor motion information, and select the best matching one from the three candidate respiratory motion models. The three candidate respiratory motion models are three classic models that represent information with quasi-periodic motion characteristics. Their mathematical expressions are as follows:

[0056]

[0057] Where c0 is the position of the tumor at the beginning of breathing, N is the order, a n and b n Represent the amplitudes of the sine function and cosine function respectively, and nω represents the respiratory period.

[0058]

[0059] Where c0 is the position of the tumor at the beginning of breathing, c1 reflects the degree of change of the tumor position at different times, N is the order, A is the amplitude range, and f i Represents the respiratory cycle, Indicates the phase offset.

[0060] z(t)=z0-bcos 2n (πt / τ-φ) (4)

[0061] Where Z0 is the position of the tumor at the beginning of breathing, b is the range of amplitude, τ is the breathing period, and n is the parameter that determines the steepness of the model shape. is the phase offset size.

[0062] To avoid overfitting of the model, the value of N in formula (2) and formula (3) should be less than or equal to 4, and the value of n in formula (4) should be less than or equal to 2.

[0063] Step 6: Use the genetic algorithm to minimize the error function in step 5, obtain the model parameters, and select the candidate respiratory motion model with the smallest error as the respiratory motion model to be fused. Figure 4The figure below shows the principle diagram of a genetic algorithm. A genetic algorithm is an optimization method used to minimize errors. By constructing an error function based on the error between the respiratory motion model and tumor motion, the motion model parameter values are obtained by minimizing the error. The algorithm first initializes the parameter values and re-encodes them. It then iterates through selection, crossover, and mutation of the encoded information, ultimately obtaining parameter values that meet the global optimal solution. The error function is shown below:

[0064]

[0065] Where F is the tumor respiratory motion model, y is the tumor motion information, and n is the data length.

[0066] Step 7: Construct a fuzzy weight evaluation matrix. The fuzzy weight evaluation matrix in step 7 is a method for implementing fuzzy processing for variables that are difficult to quantify in fuzzy mathematics. By defining the range of correlation between the two models and tumor movement at different respiratory stages during the fusion process (very small to very large), and using the training set data to obtain the weight distribution scheme of the two models in the corresponding range, a fuzzy weight evaluation matrix is finally formed. The evaluation matrix is shown in the following formula:

[0067]

[0068] The rows and columns of the matrix represent the correlation between the two groups of models and tumor motion from top to bottom and from left to right: very small, small, normal, large, very large, α ij Indicates the size of weight distribution, such as α 11 Represents the weight distribution when both groups of models have very little correlation with tumor motion.

[0069] Step 8: Obtain the weight distribution of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model in a certain frame through the fuzzy weight evaluation matrix (each frame corresponds to a time value), and perform weighted averaging to obtain the predicted tumor posture of the frame.

[0070] This application uses a fuzzy weight evaluation matrix to fuse the association model and the periodic respiratory motion model. Compared with the traditional association model, it optimizes the association effect of the model at the beginning and end stages of breathing and improves the prediction accuracy of the association model for tumor posture.

[0071] The embodiment of the application provides a heterogeneous respiratory motion model fusion system based on fuzzy evaluation, which is used to execute the heterogeneous respiratory motion model fusion method based on fuzzy evaluation described in the above embodiment, such as Figure 5 As shown, the system includes:

[0072] The first modeling module 501 is used to establish a body surface-tumor respiratory motion correlation model based on a chest and abdomen body surface voxel model;

[0073] The second modeling module 502 is used to obtain a respiratory motion model to be fused by fitting parameters through a genetic algorithm;

[0074] An evaluation matrix construction module 503 is used to construct a fuzzy weight evaluation matrix of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model, wherein the fuzzy weight evaluation matrix is used to characterize the correlation between the respiratory motion model to be fused and the body surface-tumor respiratory motion association model and tumor motion in different stages of a single respiratory cycle;

[0075] The fusion module 504 is used to obtain the weight distribution of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model at the same time through the fuzzy weight evaluation matrix, and then perform weighted average to obtain the fusion value at the same time.

[0076] The heterogeneous respiratory motion model fusion system based on fuzzy evaluation provided in the above-mentioned embodiments of the present application and the heterogeneous respiratory motion model fusion method based on fuzzy evaluation provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the applications they store.

[0077] The present application also provides an electronic device corresponding to the heterogeneous respiratory motion model fusion method based on fuzzy evaluation provided in the above embodiment, so as to execute the heterogeneous respiratory motion model fusion method based on fuzzy evaluation.

[0078] Please refer to Figure 6 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. Figure 6 As shown, the electronic device 20 includes: a processor 200, a memory 201, a bus 202 and a communication interface 203, and the processor 200, the communication interface 203 and the memory 201 are connected via the bus 202; the memory 201 stores a computer program that can be run on the processor 200, and when the processor 200 runs the computer program, it executes the heterogeneous respiratory motion model fusion method based on fuzzy evaluation provided in any of the aforementioned embodiments of the present application.

[0079] The memory 201 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage. The system network element communicates with at least one other network element via at least one communication interface 203 (which may be wired or wireless), and may utilize the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0080] The bus 202 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 201 is used to store programs, and the processor 200 executes the programs after receiving execution instructions. The heterogeneous respiratory motion model fusion method based on fuzzy evaluation disclosed in any of the aforementioned embodiments of the present application can be applied to the processor 200 or implemented by the processor 200.

[0081] The processor 200 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by hardware integrated logic circuits in the processor 200 or by software instructions. The above processor 200 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in conjunction with the embodiments of this application can be directly implemented and executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory 201 , and the processor 200 reads the information in the memory 201 and completes the steps of the above method in combination with its hardware.

[0082] The electronic device provided in the embodiment of the present application and the heterogeneous respiratory motion model fusion method based on fuzzy evaluation provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented by them.

[0083] The present application also provides a computer-readable storage medium corresponding to the heterogeneous respiratory motion model fusion method based on fuzzy evaluation provided in the above embodiment. Figure 7 The computer-readable storage medium shown is a CD 30, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will execute the heterogeneous respiratory motion model fusion method based on fuzzy evaluation provided by any of the aforementioned embodiments.

[0084] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0085] The computer-readable storage medium provided in the above-mentioned embodiment of the present application and the heterogeneous respiratory motion model fusion method based on fuzzy evaluation provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0086] It should be noted that:

[0087] The algorithms and displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems may also be used in conjunction with the teachings herein. Based on the above description, it is apparent that the structure required for constructing such systems is suitable. In addition, the present application is not directed to any specific programming language. It should be understood that various programming languages may be utilized to implement the present application described herein, and the description of specific languages above is provided for the purpose of disclosing the best mode of implementation of the present application.

[0088] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0089] Similarly, it should be understood that in order to streamline the present application and aid in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as reflected in the claims below, inventive aspects lie in fewer than all the features of the individual embodiments disclosed above. Accordingly, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim itself serving as a separate embodiment of the present application.

[0090] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition may be divided into multiple submodules or subunits or subcomponents. All features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed herein may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0091] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of this application and to form different embodiments. For example, in the claims below, any of the claimed embodiments may be used in any combination.

[0092] The various component embodiments of the present application can be implemented in hardware, or implemented in a software module running on one or more processors, or implemented in a combination thereof. Those skilled in the art will appreciate that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components in the creation system of the virtual machine according to an embodiment of the present application. The application can also be implemented as a device or system program (for example, a computer program and a computer program product) for performing a part or all of the methods described herein. Such a program realizing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0093] It should be noted that the above embodiments illustrate rather than limit the present application, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbols placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim enumerating several systems, several of these systems may be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

[0094] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various modifications or substitutions within the technical scope disclosed in this application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A heterogeneous respiratory motion model fusion method based on fuzzy evaluation, characterized in that: include: Establishing a body surface-tumor respiratory motion association model based on a chest and abdominal surface voxel model, comprising: step 1, using a depth camera to collect chest and abdominal point cloud information; step 2, performing point cloud processing on the collected point cloud information, including point cloud registration, segmentation, filtering, and smoothing, to obtain a chest and abdominal surface voxel model; step 3, performing LLE dimensionality reduction processing on the chest and abdominal surface voxel model to obtain a one-dimensional feature vector of body surface respiratory motion; step 4, obtaining the posture of the simulated tumor through an electromagnetic tracker, and establishing a body surface-tumor respiratory motion association model with the one-dimensional feature vector of body surface respiratory motion obtained in step 3; The method includes fitting parameters using a genetic algorithm to obtain a respiratory motion model to be fused, including: step 5, constructing an error function by respectively combining the three candidate respiratory motion models with the tumor motion information; step 6, minimizing the error functions in step 5 using a genetic algorithm to obtain model parameters and selecting the candidate respiratory motion model with the smallest error as the respiratory motion model to be fused; Constructing a fuzzy weight evaluation matrix of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model, wherein the fuzzy weight evaluation matrix is used to characterize the correlation between the respiratory motion model to be fused and the body surface-tumor respiratory motion association model and tumor motion in different stages of a single respiratory cycle; The weight distribution of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model at the same moment is obtained through the fuzzy weight evaluation matrix, and then the weighted average is performed to obtain the fusion value at the same moment.

2. The method according to claim 1, characterized in that The step of constructing a fuzzy weight evaluation matrix of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model includes: Step 7: construct a fuzzy weight evaluation matrix of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model based on a fuzzy evaluation method.

3. The method according to claim 2, characterized in that The method of obtaining the weight distribution of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model at the same time by using the fuzzy weight evaluation matrix and then performing weighted averaging to obtain the fusion value at the same time includes: Step 8: Obtain the weight distribution of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model in a certain frame through the fuzzy weight evaluation matrix, and perform weighted averaging to obtain the predicted tumor posture of the frame.

4. The method according to claim 1, wherein The three candidate respiratory motion models in step 4 are three classical models that represent quasi-periodic motion characteristic information.

5. The method according to claim 2, characterized in that In step 7, weight distribution is determined by defining the correlation between the respiratory motion model to be fused and the body surface-tumor respiratory motion association model and tumor motion at different respiratory stages during the fusion process to form the fuzzy weight evaluation matrix.

6. A heterogeneous respiratory motion model fusion system based on fuzzy evaluation, using the method according to any one of claims 1 to 5, characterized in that: include: The first modeling module is used to establish a body surface-tumor respiratory motion correlation model based on a chest and abdominal surface voxel model; The second modeling module is used to obtain the respiratory motion model to be fused by fitting parameters through a genetic algorithm; An evaluation matrix construction module is used to construct a fuzzy weight evaluation matrix of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model, wherein the fuzzy weight evaluation matrix is used to characterize the correlation between the respiratory motion model to be fused and the body surface-tumor respiratory motion association model and tumor motion in different stages of a single respiratory cycle; The fusion module is used to obtain the weight distribution of the respiratory motion model to be fused and the body surface-tumor respiratory motion association model at the same time through the fuzzy weight evaluation matrix, and then perform weighted average to obtain the fusion value at the same time.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor runs the computer program to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method according to any one of claims 1 to 5.

Images