Radiotherapy compensation film generation method and system based on point cloud data processing and Poisson reconstruction, and electronic equipment

Abstract

The invention discloses a radiotherapy compensation film generation method and system based on point cloud data processing and Poisson reconstruction, and electronic equipment. The method comprises the steps of performing data optimization processing based on acquired body surface point cloud data of a patient; calculating the point cloud data to obtain normal vector information of each point; based on the point cloud data and the normal vector information corresponding to the point cloud data, adopting a Poisson reconstruction method to construct a body surface grid and carrying out smoothing processing to obtain a smooth anatomical region body surface model; based on the smooth anatomical region body surface model, performing curved surface differentiation on the model to obtain a group of three-dimensional curves, and transforming the three-dimensional curves to obtain a two-dimensional compensation membrane plane model; and the two-dimensional compensation film model is guided into a compensation film pressing device, and the prefabricated moldable sheet-shaped compensation film is guided to be cut. According to the method, the point cloud data of the anatomical structure of the patient is efficiently processed through the Poisson reconstruction method, the three-dimensional anatomical structure is obtained and unfolded into the two-dimensional shape, and the convenient and accurate personalized compensation film production method is provided.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical materials, and specifically relates to a method, system and electronic equipment for generating a radiotherapy compensation film based on point cloud data processing and Poisson reconstruction. Background Art

[0002] Radiotherapy (abbreviated as radiotherapy) is one of the important means of treating tumors. It kills cancer cells by irradiating tumors with high-energy rays. In the process of radiotherapy for superficial tumors, there is a dose build-up effect in the photon beam, that is, the dose deposited in the superficial area increases with the increase of depth, thus causing superficial dose deficiency, thus affecting the treatment effect. In order to increase the dose of the superficial target area, a radiotherapy tissue compensation film is used to cover the surface of the superficial tissue to increase the incident thickness of the rays, thereby reducing the impact of the dose build-up effect.

[0003] At present, standardized, mass-produced sheet compensation films with fixed specifications are widely used in clinical practice. This type of compensation film is slightly hard in texture, and its shape is not adapted to the contour of the body, so it is difficult to fit the irregular outer contour of the human body tightly. In order to improve the fit between the compensation film and the patient's body surface, personalized 3D printed compensation films are used in clinical practice, but due to the long time-consuming 3D printing process and material limitations, this technology has not yet been promoted in clinical practice.

[0004] With the application of structured light-based optical body surface equipment in radiotherapy, the production of personalized compensation films can be guided by the optical body surface to collect the patient's three-dimensional body surface contour. The optical body surface system can collect the structured light point cloud data reflected by the patient's body surface in real time, and reconstruct the patient's three-dimensional body surface contour information based on this. Accurately converting the three-dimensional contour information into a two-dimensional shape and guiding the production of a two-dimensional personalized sheet compensation film that adapts to the patient's body surface contour can effectively improve the accuracy of radiotherapy for superficial tumors, thereby significantly improving the accuracy and safety of radiotherapy. This new technology can quickly produce personalized compensation films that meet the needs of patients and has important clinical application value.

[0005] In summary, the urgent need for radiotherapy compensation films is to quickly produce high-precision, personalized compensation films to meet the requirements of fitting complex anatomical structures and rapid positioning at the same time. The commercially available standard compensation films have poor fit on the body surface with large topological changes and are fixed in size, making it difficult to fully meet the high standards of modern precision radiotherapy. A method based on three-dimensional contour unfolding to quickly obtain a two-dimensional shape can guide automated cutting compensation film equipment to quickly cut out conformable compensation films. This unfolding can be assisted by UV unfolding technology, but the accuracy of UV unfolding is low, especially in places with large topological changes. Therefore, there is an urgent need for an algorithm that can accurately unfold three-dimensional contours into two-dimensional shapes. Summary of the invention

[0006] The main purpose of the present invention is to overcome the shortcomings and deficiencies of the prior art, and to provide a method, system and electronic device for generating radiotherapy compensation films based on point cloud data processing and Poisson reconstruction. The human body point cloud data is processed by the Poisson reconstruction method, and the patient's body surface point cloud data is efficiently processed, providing a convenient and accurate method for generating personalized compensation films.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] In a first aspect, the present invention provides a method for generating a radiotherapy compensation film based on point cloud data processing and Poisson reconstruction, comprising the following steps:

[0009] Perform data preprocessing on the collected patient surface point cloud data;

[0010] Calculate the normal vector of the point cloud data to obtain the local orientation information of each point;

[0011] Based on the point cloud data and its corresponding local orientation information, a body surface mesh is constructed using a Poisson reconstruction algorithm to obtain a rough anatomical region surface model, and the rough anatomical region surface model is smoothed to obtain a smooth anatomical region surface model;

[0012] Performing surface differentiation on the smooth anatomical region surface model to obtain a set of three-dimensional curves, and transforming the three-dimensional curves to obtain a two-dimensional compensation membrane plane model;

[0013] The two-dimensional compensation film model is introduced into the compensation film pressing device to guide the cutting of the pre-made plastic sheet compensation film.

[0014] As a preferred technical solution, the data preprocessing includes:

[0015] Based on the downsampling of high-precision point cloud data obtained from the anatomical area of ​​the body surface, the data volume is reduced and the main features of the point cloud data are retained;

[0016] Remove outliers and noise points from point cloud data.

[0017] As a preferred technical solution, the surface grid is constructed using the Poisson reconstruction algorithm based on the point cloud data and its corresponding local orientation information. Specifically, the normal vector of each point in the point cloud data is obtained, and the Poisson equation is calculated using the normal vector. The formula is as follows:

[0018] ▽ 2 φ(x)=▽·N(x)

[0019] Where N(x) is the normal vector field of point x, φ(x) is the solved scalar field of the point cloud, ▽ 2 represents the second-order derivative of the scalar field, ▽·N(x) is the divergence of the normal vector field;

[0020] The Poisson equation is discretely solved and isosurfaces are screened from the solution to obtain a reconstructed three-dimensional surface. The point cloud data is reconstructed into a body surface mesh according to the mesh topology of the reconstructed three-dimensional surface.

[0021] As a preferred technical solution, the surface differentiation of the smooth anatomical region surface model includes:

[0022] Calculate the covariance matrix of the mesh vertex coordinates to obtain the fixed-point distribution characteristics;

[0023] Determine the main axis direction of the three-dimensional grid according to the fixed point distribution characteristics, generate an OBB bounding box using the main axis direction, and align the side length of the OBB bounding box with the main axis direction;

[0024] In the OBB bounding box, select the edge perpendicular to the main axis as the direction of plane generation, and generate a series of planes at fixed intervals along the selected edge, and the planes are parallel to the main axis;

[0025] Calculate the intersection points between the plane and the mesh model, and connect the intersection points to obtain the mesh surface curve.

[0026] As a preferred technical solution, the three-dimensional curve is transformed, including the following steps: curve stretching and affine transformation.

[0027] As a preferred technical solution, the curve stretching is specifically:

[0028] Each mesh surface curve is divided into multiple segments, and adjacent points on each curve are connected in pairs to obtain several line segments. The Euclidean distance of each line segment is calculated, and all of them are accumulated to obtain the length of the curve; the midpoint of the curve on the object is used as the launch point, and the connection line is launched to both ends of the curve to obtain the same length as the curve.

[0029] As a preferred technical solution, the affine transformation is specifically:

[0030] The Euclidean distance between adjacent parallel curves is calculated, and all adjacent curves are stretched in a direction perpendicular to the adjacent curves on the same plane according to the distance to obtain an unfolded compensation film plane model;

[0031] The Euclidean distance between the adjacent parallel curves is as follows:

[0032]

[0033] Among them, d is the direction vector of the line, a i and a i+1 are two points on adjacent straight lines.

[0034] As a preferred technical solution, the rough anatomical region surface model is smoothed by adjusting the rough anatomical region surface model according to surface features, wherein the surface features include thickness, shape and defects.

[0035] In a second aspect, the present invention further provides a system, applied to the method described, comprising a first processing module, a second processing module, a third processing module and a task execution module;

[0036] The first processing module is used to pre-process the collected patient body surface point cloud data;

[0037] The second processing module is used to calculate the normal vector of the point cloud data and obtain the local orientation information of each point;

[0038] The third processing module is used to obtain the point cloud data and its corresponding local orientation information, and then use the Poisson reconstruction algorithm to construct the body surface mesh to obtain the rough anatomical region surface model. The rough anatomical region surface model is smoothed to obtain the smooth anatomical region surface model;

[0039] The fourth processing module is used to perform surface differentiation on the smooth anatomical region surface model to obtain a set of three-dimensional curves, and transform the three-dimensional curves to obtain a two-dimensional compensation membrane plane model;

[0040] The task execution module is used to import the smooth compensation film model into the compensation film pressing device and guide the cutting of the pre-made plastic sheet compensation film.

[0041] In a third aspect, the present invention provides an electronic device, the electronic device comprising:

[0042] at least one processor; and,

[0043] a memory communicatively connected to the at least one processor; wherein,

[0044] The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the medical radiotherapy compensation film generation method based on point cloud data processing and Poisson reconstruction.

[0045] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0046] (1) The present invention constructs a triangular mesh model based on point cloud data and its corresponding local direction information using the Poisson reconstruction method. It has the characteristics of global optimal decision-making and can create a smooth and continuous three-dimensional surface from point cloud data. Compared with other local processing methods, Poisson reconstruction solves the Poisson equation and utilizes the overall information of the entire point cloud, which not only ensures the smoothness and continuity of the surface, but also retains the detailed features of the model.

[0047] (2) The present invention uses the method of eigenvalue decomposition of the covariance matrix to calculate the main orientation and obtain the main axis direction of the grid. These main axis directions represent the main directions of vertex distribution and can accurately help determine the main direction and structure of the model, thereby effectively identifying the main trend or direction in the data set and improving the accuracy of model construction.

[0048] (3) The present invention simplifies the compensation membrane shape generation process through point cloud data gridding and three-dimensional surface planarization Poisson reconstruction technology, thereby reducing the cumbersome manual intervention and processing steps in traditional methods; compared with the three-dimensional surface of previous solutions, the compensation membrane can be automatically processed from data acquisition to model generation, and the compensation membrane can be produced more quickly, which has broad clinical application prospects.

[0049] (4) The two-dimensional plane model obtained by the present invention can guide the machine to cut out a compensation film for direct use. The technician only needs to spread the cut compensation film on the patient's body surface and adjust the appropriate body surface contour in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. The following drawings are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 This is a flow chart of a method for generating a radiotherapy compensation film based on point cloud data processing and Poisson reconstruction according to an embodiment of the present invention;

[0052] Figure 2 A schematic diagram of surface curve construction according to an embodiment of the present invention;

[0053] Figure 3 Schematic diagram of an OBB bounding box according to an embodiment of the present invention;

[0054] Figure 4 A schematic diagram of the effect of constructing a grid model using the Poisson reconstruction method according to an embodiment of the present invention;

[0055] Figure 5 It is a structural schematic diagram of a radiotherapy compensation film generation system based on point cloud data processing and Poisson reconstruction according to an embodiment of the present invention;

[0056] Figure 6 This is a structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiment of the present application will be clearly and completely described below in conjunction with the drawings in the embodiment of the present application. Obviously, the embodiment is only a part of the embodiment of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application.

[0058] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0059] See also Figure 1 This embodiment provides a method for generating a radiotherapy compensation film based on point cloud data processing and Poisson reconstruction, comprising the following steps:

[0060] Step 1: Point cloud data collection and preprocessing.

[0061] Point cloud data collection: Scan the patient's body surface anatomical area with a 3D scanning device to obtain high-resolution point cloud data. Downsample the collected point cloud data to reduce the amount of data while retaining the main features of the model to improve subsequent calculation efficiency.

[0062] Preprocessing: In order to efficiently process the patient's anatomical structure point cloud data and reduce the interference of noise and floating points on model generation, this embodiment performs discrete point denoising to remove outliers and noise points to ensure the cleanliness and accuracy of the point cloud data. The floating point data on the point cloud surface is corrected to further optimize the data quality.

[0063] Specifically, first, downsampling is performed on the point cloud data to reduce the amount of data while maintaining the main features of the model, which helps to speed up the subsequent processing and reduce the computational cost. Next, discrete point denoising is performed to remove outliers or noise points in the point cloud. These noise points are often caused by errors in the acquisition process or environmental factors. Denoising can significantly improve the cleanliness and smoothness of the model. In addition, reducing surface floating points can also help improve the refinement and visual effect of the model.

[0064] After preliminary cleaning of the point cloud data, the normal vector of the processed point cloud data is calculated to obtain the local direction information of each point as a prerequisite for point cloud meshing.

[0065] Step 2: Extract normal vector information.

[0066] Calculate the normal vector information of the preprocessed point cloud data. The calculation of the normal vector provides the necessary direction basis for the three-dimensional meshing of the point cloud, while ensuring the accuracy of the topological structure of the mesh model.

[0067] Step 3: Poisson reconstruction.

[0068] After the normal vector calculation is completed, this embodiment uses the Poisson reconstruction algorithm to generate a three-dimensional body surface mesh based on the point cloud data and its normal vector. Poisson reconstruction is a mesh reconstruction technology based on integral theory, which can generate a high-quality three-dimensional model while retaining the point cloud features. The generated mesh not only has high-precision geometric restoration capabilities, but also has excellent topological integrity.

[0069] Specifically, the acquisition of body surface grid includes the following steps:

[0070] S31. Obtain the normal vector of each point in the point cloud data, and use the normal vector to calculate the Poisson equation. The formula is as follows:

[0071] ▽ 2 φ(x)=▽·N(x)

[0072] Where N(x) is the normal vector field of point x, φ(x) is the solved scalar field of the point cloud, ▽ 2 represents the second-order derivative of the scalar field, ▽·N(x) is the divergence of the normal vector field;

[0073] S32, by solving the discrete Poisson equation and selecting isosurfaces from the solution, obtaining a reconstructed three-dimensional surface, and reconstructing the point cloud data into a body surface mesh according to the mesh topology structure obtained from the reconstructed three-dimensional surface. The selected isosurface is a complete topology structure, and the points of the point cloud are connected according to the indexes given by the isosurface to form the body surface mesh.

[0074] Then, for the details of small defects or irregularities that may exist on the rough anatomical area surface model, this embodiment needs to smooth the rough anatomical area surface model to further improve the appearance quality of the model. Smoothing eliminates small defects or irregularities that may exist on the mesh model by filtering, making the model surface smoother and more natural, thereby improving the visual effect and practicality of the final product.

[0075] Step 4: Grid processing.

[0076] In order to simplify the production process and improve the treatment efficiency, this embodiment will perform grid processing, which adopts a differential-based idea to gradually decompose the three-dimensional surface into a two-dimensional plane. That is, this embodiment needs to differentiate the surface into a series of curves, and then further differentiate these curves into straight line segments of equal length. In this way, the complex three-dimensional surface is effectively decomposed into a simple two-dimensional plane.

[0077] In particular, mesh processing includes surface curve construction and curve stretching, such as Figure 2 and Figure 3 shown.

[0078] Among them, (1) surface curve construction.

[0079] S41. Calculate the covariance matrix of the grid vertex coordinates to obtain fixed-point distribution features.

[0080] This embodiment obtains the distribution of vertices in different dimensions by calculating the covariance matrix, and obtains the overall distribution characteristics of the vertices.

[0081] S42. Determine the principal axis direction of the two-dimensional grid according to the vertex distribution characteristics, generate an OBB bounding box using the principal axis direction, and align the edge of the OBB bounding box with the long principal axis direction.

[0082] like Figure 3 As shown, this embodiment decomposes the eigenvalues ​​of the covariance matrix to obtain the main axis direction of the grid. These main axis directions represent the main directions of vertex distribution, which are usually called main orientations. The main orientation can determine the main direction and structure of the model. Next, this embodiment uses the main orientation information to generate an OBB rectangular bounding box with the main orientation aligned. The OBB bounding box can accurately analyze the boundary relationship and mechanical relationship between each point cloud data, determine the position and direction of the plane group generation, and thus improve the accuracy of the compensation film shape generation.

[0083] S43. In the OBB bounding box, select an edge perpendicular to the main axis direction as the direction for plane generation, and generate a series of planes at fixed intervals along the selected edge, and the planes are parallel to the main axis direction.

[0084] S44. Calculate the intersection points between the plane and the mesh model, and connect the intersection points to obtain the mesh surface curve.

[0085] At this point, the outline of the two-dimensional grid has basically appeared. Now we will start connecting the curves and expanding the two-dimensional grid.

[0086] (2) Curve stretching includes:

[0087] S45. Divide each mesh surface curve into multiple segments and calculate the length of the curve. Use the midpoint of the curve on the object as the launch point and launch toward both ends of the curve to obtain a connecting line, which is equal in length to the curve.

[0088] Each curve is composed of a series of points P 0 , P 1 , ..., P n Composition, the two adjacent points P i and P i+1 Connect two by two to obtain several line segments, calculate the Euclidean distance of each line segment, and add them all up to get the approximate length, as shown in the following formula:

[0089]

[0090] Where P(x, y, z) i represents the coordinate position of the i-th point, and L represents the approximate length of the curve.

[0091] Among the series of points that make up the curve, take the midpoint as the emission point Calculate the distance from the launch point to the two end points respectively, directly generate the two end points of the straight line according to the distance, and connect the two end points to get the straight line developed based on a certain point of the model.

[0092] The length of each curve is calculated by differentiation, and the Euclidean distance between adjacent curves in space is calculated to achieve two-dimensional tiling of the line segment group. However, these straight lines still have multidimensionality at this time. This embodiment also needs to consider the depth distance between the lines unfolded on the model in the Z-axis direction. It is necessary to calculate the parallel depth distance of adjacent parallel lines, stretch the adjacent line segments along the direction perpendicular to the line segments by the same distance, and finally obtain the unfolded plane, as shown below.

[0093] S46, calculating the Euclidean distances between adjacent parallel lines, and stretching all adjacent lines in a direction perpendicular to the lines on the same plane according to the Euclidean distances to obtain an unfolded compensation film plane model.

[0094] The Euclidean distance between adjacent expanded lines is calculated according to the formula:

[0095]

[0096] Among them, d is the direction vector of the line, a i and a i+1 are two points on adjacent straight lines. After obtaining the depth distance, the two-dimensional line segment group after tiling is meshed to obtain a two-dimensional plane. This process finally achieves the effect of decomposing the three-dimensional surface into a two-dimensional plane, such as Figure 4 As shown in the upper right picture.

[0097] Step 5: Compensation film manufacturing.

[0098] like Figure 4The two-dimensional model shown in the lower left figure is imported into the compensation film pressing device to guide the cutting of the pre-made plastic rectangular compensation film to obtain a two-dimensional compensation film that conforms to the patient's body surface. Finally, the radiotherapy technician presses the cut compensation film onto the patient's body surface. After the compensation film is formed, this compensation film that is highly fitted to the patient's body surface can be reused, thereby improving the accuracy and safety of radiotherapy.

[0099] It should be noted that, for the sake of convenience, the aforementioned method embodiments are all expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited to the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously.

[0100] Based on the same concept as the radiotherapy compensation film generation method based on point cloud data processing and Poisson reconstruction in the above-mentioned embodiment, the present invention also provides a radiotherapy compensation film generation system based on point cloud data processing and Poisson reconstruction, which can be used to execute the above-mentioned radiotherapy compensation film generation method based on point cloud data processing and Poisson reconstruction. For ease of explanation, the structural schematic diagram of the embodiment of the radiotherapy compensation film generation system based on point cloud data processing and Poisson reconstruction only shows the parts related to the embodiment of the present invention. Those skilled in the art can understand that the illustrated structure does not constitute a limitation on the device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0101] See also Figure 5 In another embodiment of the present application, a radiotherapy compensation film generation system 10 based on point cloud data processing and Poisson reconstruction is provided, the system comprising a first processing module 11, a second processing module 12, a third processing module 13, a fourth processing module 14 and a task execution module 15;

[0102] The first processing module 11 is used for preprocessing the collected patient body surface point cloud data;

[0103] The second processing module 12 is used to calculate the normal vector of the point cloud data and obtain the local orientation information of each point;

[0104] The third processing module 13 is used to obtain the point cloud data and its corresponding local orientation information, and then use the Poisson reconstruction algorithm to construct a body surface mesh to obtain a rough anatomical region surface model. The rough anatomical region surface model is smoothed to obtain a smooth anatomical region surface model.

[0105] The fourth processing module 14 is used to perform surface differentiation on the smooth anatomical region surface model to obtain a set of three-dimensional curves, and transform the three-dimensional curves to obtain a two-dimensional compensation membrane plane model;

[0106] The task execution module 15 is used to import the smooth compensation film model into the compensation film pressing device to guide the cutting of the pre-made plastic sheet compensation film.

[0107] It should be noted that the radiotherapy compensation film generation system based on point cloud data processing and Poisson reconstruction of the present invention corresponds one to one with the radiotherapy compensation film generation method based on point cloud data processing and Poisson reconstruction of the present invention. The technical features and beneficial effects described in the above-mentioned embodiment of the radiotherapy compensation film generation method based on point cloud data processing and Poisson reconstruction are applicable to the embodiment of the radiotherapy compensation film generation method based on point cloud data processing and Poisson reconstruction. For specific contents, please refer to the description in the embodiment of the method of the present invention, which will not be repeated here. This is hereby declared.

[0108] In addition, in the implementation of the medical radiotherapy compensation film generation system based on point cloud data processing and Poisson reconstruction in the above-mentioned embodiment, the logical division of each program module is only an example. In actual applications, the above-mentioned functions can be assigned to different program modules as needed, for example, for the configuration requirements of the corresponding hardware or the convenience of software implementation. That is, the internal structure of the medical radiotherapy compensation film generation system based on point cloud data processing and Poisson reconstruction is divided into different program modules to complete all or part of the functions described above.

[0109] See also Figure 6 In one embodiment, an electronic device is provided for implementing a method for generating a medical radiotherapy compensation film based on point cloud data processing and Poisson reconstruction. The electronic device 20 may include a first processor 21, a first memory 22, and a bus. It may also include a computer program stored in the first memory 22 and executable on the first processor 21, such as a medical radiotherapy compensation film generation program 23 based on point cloud data processing and Poisson reconstruction.

[0110] The first memory 22 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the first memory 22 can be an internal storage unit of the electronic device 20, such as a mobile hard disk of the electronic device 20. In other embodiments, the first memory 22 can also be an external storage device of the electronic device 20, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 20. Further, the first memory 22 can also include both an internal storage unit of the electronic device 20 and an external storage device. The first memory 22 can not only be used to store application software and various types of data installed in the electronic device 20, such as the code of the medical radiotherapy compensation film generation program 23 based on point cloud data processing and Poisson reconstruction, but also can be used to temporarily store data that has been output or is to be output.

[0111] In some embodiments, the first processor 21 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The first processor 21 is the control core (ControlUnit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes various functions and processes data of the electronic device 20 by running or executing programs or modules stored in the first memory 22, and calling data stored in the first memory 22.

[0112] Figure 6 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 6 The structure shown does not constitute a limitation on the electronic device 20 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0113] The medical radiotherapy compensation film generation program 23 based on point cloud data processing and Poisson reconstruction stored in the first memory 22 of the electronic device 20 is a combination of multiple instructions. When running in the first processor 21, it can achieve:

[0114] Perform data optimization processing based on the collected patient surface point cloud data;

[0115] Calculate the point cloud data to obtain the local direction information of each point;

[0116] Based on the point cloud data and its corresponding local direction information, a Poisson reconstruction method is used to construct a mesh model to obtain a rough anatomical region surface model, and the anatomical region surface model is smoothed to obtain a smooth anatomical region surface model;

[0117] Based on the smooth anatomical region surface model, the model is surface differentiated to obtain a set of three-dimensional curves, and the three-dimensional curves are transformed to obtain a two-dimensional compensation membrane plane model;

[0118] The two-dimensional compensation film model is introduced into the compensation film pressing device to guide the cutting of the pre-made plastic sheet compensation film.

[0119] Furthermore, if the module / unit integrated in the electronic device 20 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium. The computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0120] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0121] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0122] The above embodiments are preferred implementation modes of the present invention, but the implementation modes of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications that do not deviate from the spirit and principles of the present invention should be equivalent replacement methods and are included in the protection scope of the present invention.

Claims

1. A method for generating a radiotherapy compensation film based on point cloud data processing and Poisson reconstruction, characterized in that: The steps include: Perform data preprocessing on the collected patient surface point cloud data; Calculate the normal vector of the point cloud data to obtain the local orientation information of each point; Based on the point cloud data and its corresponding local orientation information, a body surface mesh is constructed using a Poisson reconstruction algorithm to obtain a rough anatomical region surface model, and the rough anatomical region surface model is smoothed to obtain a smooth anatomical region surface model; Performing surface differentiation on the smooth anatomical region surface model to obtain a set of three-dimensional curves, and transforming the three-dimensional curves to obtain a two-dimensional compensation membrane plane model; The two-dimensional compensation film model is introduced into the compensation film pressing device to guide the cutting of the pre-made plastic sheet compensation film.

2. The method for generating a radiotherapy compensation film based on point cloud data processing and Poisson reconstruction according to claim 1, characterized in that: The data preprocessing includes: Based on the downsampling of high-precision point cloud data obtained from the anatomical area of ​​the body surface, the data volume is reduced and the main features of the point cloud data are retained; Remove outliers and noise points from point cloud data.

3. The method for generating a radiotherapy compensation film based on point cloud data processing and Poisson reconstruction according to claim 1, characterized in that: The method described above is to construct a surface grid based on point cloud data and its corresponding local orientation information using the Poisson reconstruction algorithm. Specifically, the normal vector of each point in the point cloud data is obtained, and the discrete Poisson equation is calculated using the normal vector. The formula is as follows: ▽ 2 φ(x)=▽·N(x) Where N(x) is the normal vector field of point x, φ(x) is the solved scalar field of the point cloud, ▽ 2 represents the second-order derivative of the scalar field, ▽·N(x) is the divergence of the normal vector field; The Poisson equation is discretely solved and isosurfaces are screened from the solution to obtain a reconstructed three-dimensional surface. The point cloud data is reconstructed into a body surface mesh according to the mesh topology of the reconstructed three-dimensional surface.

4. The method for generating a radiotherapy compensation film based on point cloud data processing and Poisson reconstruction according to claim 1, characterized in that: The surface differentiation of the smooth anatomical region surface model comprises: Calculate the covariance matrix of the mesh vertex coordinates to obtain the fixed-point distribution characteristics; Determine the main axis direction of the three-dimensional grid according to the fixed point distribution characteristics, generate an OBB bounding box using the main axis direction, and align the side length of the OBB bounding box with the main axis direction; In the OBB bounding box, select the edge perpendicular to the main axis as the direction of plane generation, and generate a series of planes at fixed intervals along the selected edge, and the planes are parallel to the main axis; Calculate the intersection points between the plane and the mesh model, and connect the intersection points to obtain the mesh surface curve.

5. The method for generating a radiotherapy compensation film based on point cloud data processing and Poisson reconstruction according to claim 1, characterized in that: The three-dimensional curve is transformed, including the following steps: curve stretching and affine transformation.

6. The method for generating a radiotherapy compensation film based on point cloud data processing and Poisson reconstruction according to claim 5, characterized in that: The curve stretching is specifically: Each mesh surface curve is divided into multiple segments, and adjacent points on each curve are connected in pairs to obtain several line segments. The Euclidean distance of each line segment is calculated, and all of them are accumulated to obtain the length of the curve; the midpoint of the curve on the object is used as the launch point, and the connection line is launched to both ends of the curve to obtain the same length as the curve.

7. The method for generating a radiotherapy compensation film based on point cloud data processing and Poisson reconstruction according to claim 5, characterized in that: The affine transformation is specifically: The Euclidean distance between adjacent parallel curves is calculated, and all adjacent curves are stretched in a direction perpendicular to the adjacent curves on the same plane according to the distance to obtain an unfolded compensation film plane model; The Euclidean distance between the adjacent parallel curves is as follows: Among them, d is the direction vector of the line, a i and a i+1 are two points on adjacent straight lines.

8. The method for generating a radiotherapy compensation film based on point cloud data processing and Poisson reconstruction according to claim 1, characterized in that: The smoothing of the rough anatomical region surface model is specifically: adjusting the rough anatomical region surface model according to surface features, where the surface features include thickness, shape, and defects.

9. A radiotherapy compensation film generation system based on point cloud data processing and Poisson reconstruction, characterized in that: A method for generating a radiotherapy compensation film based on point cloud data processing and Poisson reconstruction, applied to any one of claims 1 to 8, comprising a first processing module, a second processing module, a third processing module and a task execution module; The first processing module is used to pre-process the collected patient body surface point cloud data; The second processing module is used to calculate the normal vector of the point cloud data and obtain the local orientation information of each point; The third processing module is used to obtain the point cloud data and its corresponding local orientation information, and then use the Poisson reconstruction algorithm to construct the body surface mesh to obtain the rough anatomical region surface model. The rough anatomical region surface model is smoothed to obtain the smooth anatomical region surface model; The fourth processing module is used to perform surface differentiation on the smooth anatomical region surface model to obtain a set of three-dimensional curves, and transform the three-dimensional curves to obtain a two-dimensional compensation membrane plane model; The task execution module is used to import the smooth compensation film model into the compensation film pressing device and guide the cutting of the pre-made plastic sheet compensation film.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores computer program instructions that can be executed by the at least one processor, and the computer program instructions are executed by the at least one processor so that the at least one processor can execute the medical radiotherapy compensation film generation method based on point cloud data processing and Poisson reconstruction as described in any one of claims 1-8.

Images