Tumor state prediction method, system, device, and medium

Abstract

This application relates to the field of medical image processing technology, and discloses a method, system, device, and medium for predicting tumor status, including: acquiring a set of CT images of the lungs of a target object during the current respiratory cycle; constructing a three-dimensional tumor model of the lung tumor based on the CT image set; the lung tumor has a real volume and real centroid coordinates; performing finite element analysis to obtain a finite element tumor model, calculating the simulated volume and simulated centroid coordinates of the lung tumor; comparing and obtaining the volume retention ratio and centroid offset; predicting the motion state of the lung tumor in the next respiratory cycle to obtain the initial motion state parameters of the lung tumor in the next respiratory cycle; if the motion state prediction quality of the lung tumor meets the preset motion state prediction quality based on the volume retention ratio and centroid offset, then the initial motion state parameters are used as the target motion state parameters to predict the motion state of the lung tumor, thereby improving the accuracy and correctness of radiotherapy.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and in particular to a method, system, device and medium for predicting tumor status. Background Technology

[0002] The mechanical properties of the lungs are spatially non-uniform, and the physiological structure of the thoracic cage also restricts lung movement. Therefore, the growth, expansion, or metastasis of lung tumors is actually anisotropic, exhibiting different characteristics in different directions. However, in clinical practice, uniformly distributed outward-expanding boundaries are often used to describe the movement of lung tumors, making the prediction of lung tumor movement status inaccurate. Consequently, it is difficult for physicians to accurately conform to the actual tumor area when developing radiotherapy plans, necessitating the development of a new method for predicting tumor status. Summary of the Invention

[0003] This application provides a method, system, device, and medium for predicting the state of a lung tumor. By modeling and simulating a lung tumor, the motion state of the lung tumor is predicted. This solves the technical problem of insufficient accuracy in predicting the motion state of lung tumors in related technologies, and achieves the technical effect of accurately predicting the motion state of lung tumors to improve the accuracy and correctness of radiotherapy.

[0004] To achieve the above objectives, the main technical solutions adopted in this application include:

[0005] In a first aspect, embodiments of this application provide a method for predicting tumor status, including:

[0006] A set of CT images of the lungs of the target object during the current respiratory cycle is obtained, and a three-dimensional tumor model of the lung tumor is constructed based on the CT image set; wherein the lung tumor has a real volume and a real centroid coordinate;

[0007] Finite element analysis is performed on the three-dimensional tumor model to obtain a finite element tumor model. Based on the finite element tumor model, the simulated volume and simulated centroid coordinates of the lung tumor are calculated.

[0008] The actual volume and the simulated volume are compared to obtain the volume retention ratio; and the actual centroid coordinates and the simulated centroid coordinates are compared to obtain the centroid offset.

[0009] The finite element tumor model is used to predict the motion state of the lung tumor in the next respiratory cycle, so as to obtain the initial motion state parameters of the lung tumor in the next respiratory cycle.

[0010] If the predicted motion state quality of the lung tumor meets the preset motion state prediction quality based on the volume retention ratio and the center of gravity offset, then the initial motion state parameters are used as the target motion state parameters of the lung tumor in the next respiratory cycle.

[0011] This application utilizes biophysical modeling and simulation to transform two-dimensional 4D-CT images of a patient's lungs into a three-dimensional tumor model with spatial awareness and multi-angle observation and measurement capabilities. Finite element analysis is then performed to simulate the state of the lung tumor under respiratory motion, thereby predicting the tumor's motion state. By ensuring that the motion state prediction quality meets the preset quality standards, the accuracy of the target motion state parameters is guaranteed.

[0012] Personalized radiotherapy plans are designed based on the specific circumstances of different target patients. The movement trajectory and extent of lung tumors in different target patients are predicted, and the boundaries of the radiotherapy target area are reduced in a timely manner to protect normal tissues. This ensures that the lung tumor receives sufficient radiation while reducing damage to normal lung tissues, thus improving the accuracy and correctness of radiotherapy.

[0013] This application omits the complex rib movements in the thoracic cavity, eliminates the complex segmentation of the diaphragm, and does not consider the influence of posture and gravitational loads, thereby reducing the modeling difficulty and modeling time cost, ensuring the timeliness of radiotherapy treatment, and overcoming the problems of high modeling difficulty and low simulation accuracy caused by simulating lung breathing movements to extract lung tumors in related technologies.

[0014] Optionally, constructing a three-dimensional tumor model of the lung tumor based on the CT image set includes:

[0015] A three-dimensional lung model containing the lung tumor is constructed based on the CT image set;

[0016] The three-dimensional lung model is segmented to obtain a three-dimensional tumor model of the lung tumor.

[0017] Optionally, the true volume and true centroid coordinates of the lung tumor are determined by the following methods:

[0018] Based on the three-dimensional tumor model, the relative position and size of the lung tumor in the lung are obtained, and the true volume and true centroid coordinates of the lung tumor are calculated based on the relative position and the relative size.

[0019] The actual volume and centroid coordinates of the lung tumor are calculated using tools provided by 3D Slicer as the true values ​​of the tumor data. The simulated volume and centroid coordinates of the lung tumor are then calculated using a subsequent finite element tumor model for comparative evaluation of the simulation effect and state prediction effect.

[0020] Optionally, the step of performing finite element analysis on the three-dimensional tumor model to obtain a finite element tumor model includes:

[0021] The three-dimensional tumor model is optimized to obtain a three-dimensional solid tumor model; the optimization process includes at least one of mesh generation, defect repair, error repair and precise surface processing.

[0022] Finite element analysis was performed on the three-dimensional solid tumor model to obtain a finite element tumor model.

[0023] In this way, the network of the 3D tumor model is re-divided, and its density or topology is changed to optimize the 3D tumor model. Defect and error repair are performed on the 3D tumor model to ensure its quality and accuracy. Precise surface processing of the 3D tumor model is carried out through four steps: contour detection, surface patch construction, grid construction, and surface fitting, to further adjust and optimize the 3D solid tumor model.

[0024] Optionally, the three-dimensional tumor model can be meshed in the following way:

[0025] Mesh parameters are set for the three-dimensional tumor model, including mesh density parameters and edge smoothness parameters. The three-dimensional tumor model is meshed based on the mesh density parameters and the edge smoothness parameters to improve the detail and smoothness of the three-dimensional tumor model.

[0026] Optionally, calculating the simulated volume and centroid coordinates of the lung tumor based on the finite element tumor model includes:

[0027] Based on the finite element tumor model, the elastic modulus and Poisson's ratio of the lung tumor are set, and the elastic modulus and Poisson's ratio are used to characterize the material properties of the lung tumor.

[0028] The simulated volume and centroid coordinates of the lung tumor are calculated based on the elastic modulus and Poisson's ratio.

[0029] Optionally, the initial motion state parameters include stress parameters, strain parameters, and displacement parameters;

[0030] The method of using the finite element tumor model to predict the motion state of the lung tumor in the next respiratory cycle includes:

[0031] The analysis duration and step size for motion state prediction are set, and the motion state of the lung tumor in the next respiratory cycle is predicted using the finite element tumor model based on the analysis duration and step size.

[0032] Secondly, embodiments of this application provide a tumor status prediction system, including an acquisition module, an analysis module, a comparison module, a status prediction module, and a quality judgment module;

[0033] The acquisition module is configured to acquire a set of CT images of the lungs of the target object during the current respiratory cycle, and construct a three-dimensional tumor model of the lung tumor based on the CT image set; wherein the lung tumor has a real volume and a real centroid coordinate.

[0034] The analysis module is configured to perform finite element analysis on the three-dimensional tumor model to obtain a finite element tumor model, and calculate the simulated volume and simulated centroid coordinates of the lung tumor based on the finite element tumor model.

[0035] The comparison module is configured to compare the actual volume and the simulated volume to obtain a volume retention ratio; and to compare the actual centroid coordinates and the simulated centroid coordinates to obtain a centroid offset.

[0036] The state prediction module is configured to use the finite element tumor model to predict the motion state of the lung tumor in the next respiratory cycle, so as to obtain the initial motion state parameters of the lung tumor in the next respiratory cycle.

[0037] The quality determination module is configured to, if the predicted motion state quality of the lung tumor meets the preset predicted motion state quality based on the volume retention ratio and the center of gravity offset, then use the initial motion state parameters as the target motion state parameters of the lung tumor in the next respiratory cycle.

[0038] Thirdly, embodiments of this application provide a computer device, including:

[0039] The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes these computer instructions to perform any of the aforementioned tumor state prediction methods.

[0040] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer instructions, which are used to cause a computer to execute any of the above-described tumor state prediction methods. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0042] Figure 1 This is a schematic diagram illustrating the steps of a tumor status prediction method provided in an embodiment of the present invention;

[0043] Figure 2 This is a flowchart of 3D Slimmer processing CT image groups in an embodiment of the present invention;

[0044] Figure 3a This is a schematic diagram of a slice image in the transverse direction displayed by 3D Slicer software in an embodiment of the present invention;

[0045] Figure 3b This is a schematic diagram of a slice image in the coronal direction displayed by 3D Slicer software in an embodiment of the present invention;

[0046] Figure 3c This is a schematic diagram of a sagittal slice image displayed by 3D Slicer software in an embodiment of the present invention;

[0047] Figure 3d This is a schematic diagram of a three-dimensional tumor model displayed by 3D Slicer software in an embodiment of the present invention;

[0048] Figure 4 This is a schematic diagram of the STL format files of the tumor-side lung and the tumor of two target objects in an embodiment of the present invention;

[0049] Figure 5 This is a flowchart illustrating the optimization process of STL format files using the Geomagic Wrap software in an embodiment of the present invention. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0051] The mechanical properties of the lungs are spatially non-uniform, and the physiological structure of the thoracic cage also restricts lung movement. Therefore, the growth, expansion, or metastasis of lung tumors is actually anisotropic, exhibiting different characteristics in different directions. However, in clinical practice, a uniformly distributed outward-expanding boundary is often used to describe the movement of lung tumors, making the prediction of lung tumor movement insufficiently accurate. Consequently, when doctors develop radiotherapy plans, they often fail to conform to the actual tumor area, resulting in poor radiotherapy efficacy.

[0052] In related technologies, there are two main methods for simulating the respiratory motion state of lung tumors. One is image registration, which directly extracts the motion field from 4D images to simulate the motion field, using a similarity metric that maximizes the number of individual 3D frames in the image sequence for registration. However, image registration is affected by artifacts in 4D-CT images, such as blurring, repetitive structures, overlapping structures, and incomplete structures, which can impact the extraction of motion data. Furthermore, respiratory physiological processes and the physical characteristics of organs are usually not considered, resulting in artifact errors and making the simulation less accurate.

[0053] The second method is biophysical modeling, which models the lungs and lung tumors, analyzes the physiological and physical factors of lung respiratory movements, and describes the motion using physics-based mathematical formulas. This process is more complex, and handling irregularly shaped lungs and lung tumors requires significant time. While there is no completely linear relationship between the volume changes of the lungs and tumors, most related techniques indirectly determine tumor motion by applying forces to the lungs. This method is difficult to model, time-consuming, and lacks accurate simulations.

[0054] Reference Figure 1 This application provides a method for predicting tumor status, including:

[0055] S100. Obtain a set of CT images of the lungs of the target object during the current respiratory cycle, and construct a three-dimensional tumor model of the lung tumor based on the CT image set; wherein the lung tumor has a real volume and a real centroid coordinate.

[0056] The CT images of the target lungs during the current respiratory cycle can be 4D-CT lung images. 4D-CT lung images are CT images scanned using four-dimensional imaging technology. In this embodiment, ten consecutive three-dimensional anatomical images are selected to form a complete respiratory cycle. Each 4D-CT data set consists of 10 phases spanning one respiratory cycle. The scanner tube potential and current are 140kVp and 120mAs / slicer, respectively, and the slice thickness for all scans is 3mm. This data is used to describe the positional changes of lung organs or lung tumors during respiration. Different phases can represent different stages in the respiratory cycle, such as the inspiratory and expiratory phases.

[0057] Specifically, 4D-CT lung images, through specific scanning conditions, ensure data from at least one respiratory cycle at each location. The collected data includes synchronously acquired patient respiratory signals and anatomical images, allowing observation of lung organ translation and deformation caused by respiratory motion. Using 4D-CT lung images to establish motion models of lung tumors, visualizing the morphological and positional changes of lung tumors, and individually determining the radiotherapy margin for each patient's lung tumor helps reduce the radiation exposure area and decrease the radiation dose to normal tissues.

[0058] CT scans in related technologies are static, typically acquiring a cross-sectional image of the body at a single moment, while 4D-CT lung images utilize continuous time to acquire images of multiple different respiratory stages, in order to better simulate and analyze the dynamic movement of lung tumors or lung organs.

[0059] Reference Figure 2 , Figure 2 The flowchart shows how 3D Slicer processes CT image sets. 3D Slicer is an open-source, cross-platform medical image processing software. In this embodiment, 3D Slicer is used to process CT image sets and construct a three-dimensional tumor model of lung tumors based on the CT image sets.

[0060] S110. Import 4D-CT lung images into 3D Slicer software to construct a three-dimensional tumor model.

[0061] Reference Figures 3a to 3d The 3D Slicer software interface displays slice images in three orthogonal directions: transverse, coronal, and sagittal. In 3D Slicer, the direction of the slice view can be controlled by dragging the mouse or using the keyboard. Figure 3a This is a schematic diagram of a slice image displayed in the transverse direction by 3D Slicer software. Figure 3b This is a schematic diagram of a slice image in the coronal direction displayed by 3DSlicer software. Figure 3c This is a schematic diagram of a sagittal slice image displayed by 3D Slicer software. Figure 3d This is a schematic diagram of a three-dimensional tumor model displayed by 3D Slicer software. The green part is the left lung, the yellow part is the right lung, and the red part is the lung tumor.

[0062] S130. Based on a three-dimensional tumor model of the lung tumor, calculate the true volume and true centroid coordinates of the lung tumor.

[0063] S150. After calculating the true volume and true centroid coordinates of the lung tumor, save the three-dimensional tumor model of the lung tumor as an STL format file.

[0064] STL files are a 3D printing file format that describes the surface geometry of a 3D model. They are typically composed of a series of triangular facets and can be used to describe anatomical structures such as bones, organs, or tissues for 3D reconstruction, visualization, and analysis of medical images.

[0065] S200. Perform finite element analysis on the three-dimensional tumor model to obtain the finite element tumor model. Calculate the simulated volume and centroid coordinates of the lung tumor based on the finite element tumor model.

[0066] Finite element analysis (FEM) can be performed using HyperMesh software. FEM is used to create geometric models of biological tissues, transforming the shape, size, and structure of a lung tumor into a finite element tumor model. The material properties of the lung tumor (such as elastic modulus and Young's modulus) are key parameters in FEM. These material properties can be obtained through experimental measurements, literature reports, or calculations and used in the FEM simulation. When simulating the mechanical behavior of a lung tumor, appropriate boundary conditions need to be defined. Boundary conditions include loads or constraints applied to the surface of the lung tumor, such as external forces, pressures, displacements, or other fixed boundary conditions.

[0067] Furthermore, before conducting finite element analysis, it is necessary to define the physical and mechanical properties of lung tumors, including material properties such as elastic modulus and Poisson's ratio. The specific elastic modulus and Poisson's ratio have individual differences; for example, the Poisson's ratio can dynamically change between 0.3 and 0.4.

[0068] S300: Compare the actual volume and the simulated volume to obtain the volume retention ratio; and compare the actual centroid coordinates and the simulated centroid coordinates to obtain the centroid offset.

[0069] The volume retention ratio, which is the ratio of the actual volume to the simulated volume, is used to assess how much realistic geometric information the 3D tumor model retains during finite element analysis. A volume retention ratio close to 100% indicates that the finite element tumor model accurately reflects the true size of the lung tumor. A ratio below 100% suggests that the finite element tumor model may contain errors in the size or shape of the tumor.

[0070] The centroid offset can be the difference between the actual centroid coordinates and the simulated centroid coordinates. It can be calculated using the Euclidean distance formula and reflects the accuracy of the finite element tumor model in spatial position. If the centroid offset is close to zero, it indicates that the finite element tumor model is very close to the actual tumor position, and the model can reproduce the tumor's position in three-dimensional space well. Conversely, a large centroid offset indicates a significant deviation in the finite element tumor model's position.

[0071] S400. Use the finite element tumor model to predict the motion state of the lung tumor in the next respiratory cycle, so as to obtain the initial motion state parameters of the lung tumor in the next respiratory cycle.

[0072] Finite element tumor models can be dynamically simulated using time steps to model the deformation and movement of lung tissue, tumors, and other related structures during the respiratory cycle. Based on the current state of the lungs and tumor (such as displacement, stress, strain, etc.), the initial state of the tumor in the next respiratory cycle can be predicted. Alternatively, historical data (such as the frequency and amplitude of the respiratory cycle) can be used to estimate the initial motion state of the tumor in the next cycle.

[0073] S500. If the predicted motion state quality of the lung tumor meets the preset motion state prediction quality based on the volume retention ratio and the center of gravity offset, then the initial motion state parameters are used as the target motion state parameters of the lung tumor in the next respiratory cycle.

[0074] Furthermore, if the predicted motion state quality of the lung tumor does not meet the preset predicted motion state quality based on the volume retention ratio and the center of gravity offset, the parameters of the finite element tumor model are adjusted to adjust the obtained initial motion state parameters. The judgment is then made again until the predicted motion state quality of the lung tumor meets the preset predicted motion state quality.

[0075] This application utilizes biophysical modeling and simulation to transform two-dimensional 4D-CT images of a patient's lungs into a three-dimensional tumor model with spatial awareness and multi-angle observation and measurement capabilities. Finite element analysis is then performed to simulate the state of the lung tumor under respiratory motion, thereby predicting the tumor's motion state. By ensuring that the motion state prediction quality meets the preset quality standards, the accuracy of the target motion state parameters is guaranteed.

[0076] Personalized radiotherapy plans are designed based on the specific circumstances of different target patients. The movement trajectory and extent of lung tumors in different target patients are predicted, and the boundaries of the radiotherapy target area are reduced in a timely manner to protect normal tissues. This ensures that the lung tumor receives sufficient radiation while reducing damage to normal lung tissues, thus improving the accuracy and correctness of radiotherapy.

[0077] This application omits the complex rib movements within the thoracic cavity, eliminates the intricate segmentation of the diaphragm, and disregards the influence of posture and gravitational loads, thereby reducing modeling difficulty and time costs. This ensures the timeliness of radiotherapy treatment and overcomes the problems of high modeling difficulty and low simulation accuracy caused by simulating lung respiratory movements to extract lung tumors in related technologies. Simultaneously, it also reduces the occurrence of insufficient simulation accuracy due to artifacts such as blurring, repetitive structures, overlapping structures, and incomplete structures in 4D-CT images.

[0078] As one implementation method, a three-dimensional tumor model of a lung tumor is constructed based on a set of CT images, including:

[0079] S112. Import 4D-CT lung images into 3D Slicer software to construct a three-dimensional lung model containing lung tumors.

[0080] S114. Segment the three-dimensional lung model to obtain a three-dimensional tumor model of the lung tumor.

[0081] S152. After calculating the true volume and true centroid coordinates of the lung tumor, save the segmented three-dimensional tumor model as an STL format file.

[0082] Specifically, please refer to Figure 4 , Figure 4 This is a schematic diagram of the STL format files of the tumor-side lung and the tumor of two target subjects.

[0083] As one implementation method, the true volume and true centroid coordinates of a lung tumor are determined by the following means:

[0084] S132. Obtain the relative position and size of the lung tumor in the lung based on the three-dimensional tumor model, and calculate the true volume and true centroid coordinates of the lung tumor based on the relative position and size.

[0085] Specifically, the actual volume and centroid coordinates of the lung tumor are calculated using tools provided by 3D Slicer as the true values ​​of the tumor data. The simulated volume and centroid coordinates of the lung tumor are then calculated using a subsequent finite element tumor model for comparative evaluation of the simulation effect and state prediction effect.

[0086] As one implementation method, finite element analysis is performed on a three-dimensional tumor model to obtain a finite element tumor model, including:

[0087] S210. Optimize the three-dimensional tumor model to obtain a three-dimensional solid tumor model; the optimization process includes at least one of mesh generation, defect repair, error repair and precise surface processing.

[0088] Specifically, STL format files are relatively coarse. Geomagic Wrap software is used to optimize coarse STL format files, that is, to optimize three-dimensional tumor models in order to obtain high-quality three-dimensional solid tumor models.

[0089] In this embodiment, refer to Figure 5 , Figure 5 This is a flowchart illustrating the optimization process of STL format files using the Geomagic Wrap software in an embodiment of the present invention.

[0090] S211. Import the STL format file into the Geomagic Wrap software.

[0091] S212. Re-divide the network of the three-dimensional tumor model, and change the density or topology of the three-dimensional tumor model to optimize the three-dimensional tumor model.

[0092] S213. Perform defect and error repair processing on the three-dimensional tumor model. Defect and error repair processing may include identifying and filling holes, detecting and repairing discontinuities, removing other unnecessary details, performing smoothing and trimming operations, or automatically adjusting the topology and vertex distribution of the three-dimensional tumor model to ensure the quality and accuracy of the three-dimensional tumor model.

[0093] S214. The three-dimensional tumor model is precisely surface-processed through four steps: probing the contour line, constructing surface patches, constructing a grid, and fitting the surface.

[0094] S215. Save the optimized 3D solid tumor model as an IGS format file. Accurate geometric descriptions are typically required in numerical simulations for finite element analysis (FEA). IGS files are a file format that allows for the exchange of geometric data between different CAD software programs, providing the necessary geometric data.

[0095] First, the contour of the surface is drawn on the surface of the 3D tumor model by probing the outline, determining the approximate shape and size of the surface. Next, surface patches are constructed to connect the drawn contour lines, ensuring continuity and smoothness between the patches to obtain a high-quality surface model. Then, a grid is constructed to decompose the surface patches into smaller regions for finer control over the shape and curvature of the surface model. Finally, the surface is fitted for further adjustments and optimization.

[0096] S230. Perform finite element analysis on the three-dimensional solid tumor model to obtain the finite element tumor model. Calculate the simulated volume and simulated centroid coordinates of the lung tumor based on the finite element tumor model.

[0097] Specifically, through analysis using Geomagic Wrap software, the simulated volume and centroid coordinates of the lung tumor were calculated based on the finite element tumor model. After comparing these with the actual volume and centroid coordinates of the lung tumor, the volume retention ratio and centroid offset were obtained to evaluate the simulation effect and state prediction effect.

[0098] As one implementation method, the three-dimensional tumor model is meshed in the following way:

[0099] Mesh parameters are set for the 3D tumor model, including mesh density parameters and edge smoothness parameters. The 3D tumor model is then meshed based on the mesh density parameters and edge smoothness parameters to improve the detail and smoothness of the 3D tumor model.

[0100] As one implementation method, the simulated volume and centroid coordinates of a lung tumor are calculated based on a finite element tumor model, including:

[0101] The elastic modulus and Poisson's ratio of lung tumors were set based on the finite element tumor model. The elastic modulus and Poisson's ratio are used to characterize the material properties of lung tumors.

[0102] The simulated volume and centroid coordinates of lung tumors were calculated based on elastic modulus and Poisson's ratio.

[0103] As one implementation method, HyperMesh is a finite element modeling and mesh generation software. This software generates the mesh required for finite element analysis and obtains the boundary conditions for lung tumor motion to be imported into the finite element software for simulation.

[0104] S401. Select Surface Elements: In HyperMesh, select appropriate surface elements to represent the surface of the lung tumor, and select triangles (TRIA) to construct the finite element tumor model.

[0105] S402. Create Surface Mesh: Using the meshing tool, create a surface mesh for the lung tumor based on the selected surface elements, ensuring that the mesh covers the entire surface of the lung tumor.

[0106] S403. Extract Nodes: After creating the surface mesh, use HyperMesh's node query tool to extract the surface nodes, query the location of the surface nodes, and import the coordinates of some selected nodes into Excel for summary, which will facilitate subsequent coordinate value comparison and calculation of node displacement.

[0107] S404. Save Results: After extracting surface nodes, save the results as an INP format file for import into Abaqus finite element analysis software for subsequent analysis or post-processing.

[0108] As one implementation method, S410, finite element analysis can be performed using Abaqus software. Determining the geometric characteristics of lung tumors is crucial, as lung tumors can cause changes in the elasticity, stiffness, and other mechanical properties of soft tissues. A key parameter in biomechanical modeling is simulating the elastic distribution of soft tissues, applying mechanical parameters to finite element simulations, such as those exhibiting nonlinearity, incompressibility, viscoelasticity, plasticity, and anisotropy.

[0109] S420. Determine the loads and boundary conditions. Set the nodal displacements calculated from HyperMesh as displacement loads. Use the Boundary command to define the displacement boundary conditions. Apply the displacement loads by specifying the nodes, displacement direction, and magnitude. type indicates the displacement boundary conditions, node set specifies the node set, and DOF1, DOF2, and DOF3 represent the displacements in the X, Y, and Z directions, respectively.

[0110] S430. After completing the settings, submit the "job" file. You can view warnings and other serious error messages in the Task Manager. Resolve these warnings until the finite element tumor model calculation converges. The solver performs numerical calculations on the finite element tumor model and generates initial motion state parameters. After the analysis is complete, check the initial motion state parameters, including stress, strain, and displacement parameters, and generate various charts, animations, and cross-sectional views to better understand and interpret the initial motion state parameters.

[0111] S500. If the predicted motion state quality of the lung tumor meets the preset motion state prediction quality based on the volume retention ratio and the center of gravity offset, then the initial motion state parameters are used as the target motion state parameters of the lung tumor in the next respiratory cycle.

[0112] As one implementation method, the initial motion state parameters include stress parameters, strain parameters, and displacement parameters.

[0113] Predicting the motion state of lung tumors in the next respiratory cycle using a finite element tumor model, including:

[0114] The analysis duration and step size for motion state prediction are set, and the motion state of lung tumors in the next respiratory cycle is predicted using a finite element tumor model based on the analysis duration and step size.

[0115] Specifically, the finite element analysis in this application is a static analysis, and the analysis duration and step size for predicting the motion state are set. The time step determines the degree of time discretization during the analysis process.

[0116] This application provides a tumor status prediction system, including an acquisition module, an analysis module, a comparison module, a status prediction module, and a quality judgment module;

[0117] The acquisition module is configured to acquire a set of CT images of the lungs of the target object during the current respiratory cycle, and construct a three-dimensional tumor model of the lung tumor based on the CT image set; wherein the lung tumor has a real volume and real centroid coordinates;

[0118] The analysis module is configured to perform finite element analysis on a three-dimensional tumor model to obtain a finite element tumor model, and calculate the simulated volume and simulated centroid coordinates of the lung tumor based on the finite element tumor model.

[0119] The comparison module is configured to compare the real volume and the simulated volume to obtain the volume retention ratio; and to compare the real centroid coordinates and the simulated centroid coordinates to obtain the centroid offset.

[0120] The state prediction module is configured to use a finite element tumor model to predict the motion state of the lung tumor in the next respiratory cycle, so as to obtain the initial motion state parameters of the lung tumor in the next respiratory cycle.

[0121] The quality assessment module is configured to use the initial motion state parameters as the target motion state parameters of the lung tumor in the next respiratory cycle if the motion state prediction quality of the lung tumor is determined to meet the preset motion state prediction quality based on the volume retention ratio and the center of gravity offset.

[0122] As one implementation method, the acquisition module is also configured to

[0123] A three-dimensional lung model containing lung tumors was constructed based on CT images;

[0124] The three-dimensional lung model is segmented to obtain a three-dimensional tumor model of the lung tumor.

[0125] As one implementation method, in the acquisition module, the true volume and true centroid coordinates of the lung tumor are determined by the following methods:

[0126] The relative position and size of the lung tumor in the lung are obtained based on a three-dimensional tumor model, and the true volume and true centroid coordinates of the lung tumor are calculated based on the relative position and size.

[0127] As one implementation method, the analysis module is also configured as follows:

[0128] The three-dimensional tumor model is optimized to obtain a three-dimensional solid tumor model; the optimization process includes at least one of defect repair, error repair, mesh generation, and precise surface processing.

[0129] Finite element analysis was performed on a three-dimensional solid tumor model to obtain a finite element tumor model.

[0130] As one implementation method, the analysis module performs mesh generation on the three-dimensional tumor model in the following way:

[0131] Mesh parameters are set for the three-dimensional tumor model, including mesh density parameters and edge smoothness parameters. The three-dimensional tumor model is then meshed based on the mesh density parameters and edge smoothness parameters.

[0132] As one implementation method, the analysis module is also configured as follows:

[0133] The elastic modulus and Poisson's ratio of lung tumors were set based on the finite element tumor model. The elastic modulus and Poisson's ratio are used to characterize the material properties of lung tumors.

[0134] The simulated volume and centroid coordinates of lung tumors were calculated based on elastic modulus and Poisson's ratio.

[0135] As one implementation method, the initial motion state parameters include stress parameters, strain parameters, and displacement parameters;

[0136] The state prediction module is also configured to: set the analysis duration and step size for motion state prediction, and use the finite element tumor model to predict the motion state of lung tumors in the next respiratory cycle based on the analysis duration and step size.

[0137] This application provides a computer device, including: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform a tumor status prediction method as provided in the above embodiments.

[0138] The computer device includes one or more processors, memory, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other using different buses and can be mounted on a common motherboard or otherwise installed as needed. The processor processes instructions that execute within the computer device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system).

[0139] The processor can be a central processing unit, a network processor, or a combination thereof. The processor may further include hardware chips. These hardware chips can be application-specific integrated circuits (ASICs), programmable logic devices (PLDs), or combinations thereof. The programmable logic devices can be complex programmable logic devices (CLPs), field-programmable gate arrays (FPGAs), general-purpose array logic (GDAs), or any combination thereof.

[0140] The memory stores instructions executable by at least one processor to cause the at least one processor to perform the method shown in the above embodiments.

[0141] The memory may include a stored program area and a stored data area, wherein the stored program area may store the operating system and application programs required for at least one function; the stored data area may store data created based on the use of the computer device, etc. Furthermore, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory may include memory remotely located relative to the processor, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0142] The memory may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory may also include a combination of the above types of memory.

[0143] The computer device also includes a communication interface for communicating with other devices or communication networks.

[0144] This application provides a computer-readable storage medium storing computer instructions for causing a computer to execute a tumor state prediction method as provided in the above embodiments.

[0145] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the methods shown in the above embodiments are implemented.

[0146] This application provides a computer program product including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the method of any embodiment of this application.

[0147] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

[0148] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0149] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0150] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0151] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can 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, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0152] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0153] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0154] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0155] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0156] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

[0157] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for predicting tumor status, characterized in that, include: A set of CT images of the lungs of the target object during the current respiratory cycle is obtained, and a three-dimensional tumor model of the lung tumor is constructed based on the CT image set; wherein the lung tumor has a real volume and a real centroid coordinate; Finite element analysis is performed on the three-dimensional tumor model to obtain a finite element tumor model. Based on the finite element tumor model, the simulated volume and simulated centroid coordinates of the lung tumor are calculated. The actual volume and the simulated volume are compared to obtain the volume retention ratio; and the actual centroid coordinates and the simulated centroid coordinates are compared to obtain the centroid offset. The finite element tumor model is used to predict the motion state of the lung tumor in the next respiratory cycle, so as to obtain the initial motion state parameters of the lung tumor in the next respiratory cycle. If the predicted motion state quality of the lung tumor meets the preset predicted motion state quality based on the volume retention ratio and the center of gravity offset, then the initial motion state parameters are used as the target motion state parameters of the lung tumor in the next respiratory cycle. If the predicted motion state quality of the lung tumor does not meet the preset predicted motion state quality based on the volume retention ratio and the center of gravity offset, then the parameters of the finite element tumor model are adjusted to adjust the obtained initial motion state parameters, and the judgment is made again until the predicted motion state quality of the lung tumor meets the preset predicted motion state quality.

2. The method as described in claim 1, characterized in that, The construction of a three-dimensional tumor model of the lung tumor based on the CT image set includes: A three-dimensional lung model containing the lung tumor is constructed based on the CT image set; The three-dimensional lung model is segmented to obtain a three-dimensional tumor model of the lung tumor.

3. The method as described in claim 2, characterized in that, The true volume and true centroid coordinates of the lung tumor are determined by the following methods: Based on the three-dimensional tumor model, the relative position and size of the lung tumor in the lung are obtained, and the true volume and true centroid coordinates of the lung tumor are calculated based on the relative position and the relative size.

4. The method as described in claim 1, characterized in that, The step of performing finite element analysis on the three-dimensional tumor model to obtain a finite element tumor model includes: The three-dimensional tumor model is optimized to obtain a three-dimensional solid tumor model; the optimization process includes at least one of mesh generation, defect repair, error repair and precise surface processing. Finite element analysis was performed on the three-dimensional solid tumor model to obtain a finite element tumor model.

5. The method as described in claim 4, characterized in that, The three-dimensional tumor model is meshed using the following method: Mesh parameters are set for the three-dimensional tumor model, including mesh density parameters and edge smoothness parameters. The three-dimensional tumor model is then meshed based on the mesh density parameters and the edge smoothness parameters.

6. The method as described in claim 1, characterized in that, The calculation of the simulated volume and centroid coordinates of the lung tumor based on the finite element tumor model includes: Based on the finite element tumor model, the elastic modulus and Poisson's ratio of the lung tumor are set, and the elastic modulus and Poisson's ratio are used to characterize the material properties of the lung tumor. The simulated volume and centroid coordinates of the lung tumor are calculated based on the elastic modulus and Poisson's ratio.

7. The method as described in claim 1 or 6, characterized in that, The initial motion state parameters include stress parameters, strain parameters, and displacement parameters; The method of using the finite element tumor model to predict the motion state of the lung tumor in the next respiratory cycle includes: The analysis duration and step size for motion state prediction are set, and the motion state of the lung tumor in the next respiratory cycle is predicted using the finite element tumor model based on the analysis duration and step size.

8. A tumor status prediction system, characterized in that, It includes an acquisition module, an analysis module, a comparison module, a status prediction module, and a quality judgment module; The acquisition module is configured to acquire a set of CT images of the lungs of the target object during the current respiratory cycle, and construct a three-dimensional tumor model of the lung tumor based on the CT image set; wherein the lung tumor has a real volume and a real centroid coordinate. The analysis module is configured to perform finite element analysis on the three-dimensional tumor model to obtain a finite element tumor model, and calculate the simulated volume and simulated centroid coordinates of the lung tumor based on the finite element tumor model. The comparison module is configured to compare the actual volume and the simulated volume to obtain a volume retention ratio; and to compare the actual centroid coordinates and the simulated centroid coordinates to obtain a centroid offset. The state prediction module is configured to use the finite element tumor model to predict the motion state of the lung tumor in the next respiratory cycle, so as to obtain the initial motion state parameters of the lung tumor in the next respiratory cycle. The quality determination module is configured to, if the predicted motion state quality of the lung tumor meets the preset predicted motion state quality based on the volume retention ratio and the center of gravity offset, then use the initial motion state parameters as the target motion state parameters of the lung tumor in the next respiratory cycle.

9. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform a tumor state prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform a tumor state prediction method according to any one of claims 1 to 7.

Images