Method and system for monitoring and correcting body surface contour of radiotherapy patient

Abstract

The invention relates to the technical field of medical image processing, and discloses a radiotherapy patient body surface contour monitoring and correction method and system, and the method comprises the steps: obtaining original point cloud data from the body surface of a patient through combining a three-dimensional scanning device, a stereoscopic microscope and an infrared sensor, and generating a high-resolution body surface contour model, dividing the body surface into a plurality of monitoring blocks based on a preset anatomical region division rule; local dynamic change features are extracted through time sequence analysis, correction guidance parameters are generated in combination with positioning information of an offset area, and a correction model is constructed to obtain a collaborative correction instruction set. And finally, correction is carried out based on the collaborative correction instruction set, whether correction succeeds or not is judged through a non-rigid registration technology, and if not, adjustment is carried out until correction succeeds. According to the method, the dynamic change of the body surface contour of the patient can be monitored and corrected in real time, accurate treatment positioning in the radiotherapy process is ensured, and the treatment effect and safety are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical image processing, in particular to a radiotherapy patient body surface contour monitoring and correction method and system. BACKGROUND

[0002] During radiotherapy, the geometric shape of the patient's body surface will change dynamically due to breathing, body position changes and other physiological factors, especially in the chest and abdomen regions. Since the treatment area of radiotherapy is usually closely related to the geometric shape of the patient's body surface, any change in the body surface may cause deviation in the positioning of the treatment area, thereby affecting the treatment effect and even causing side effects.

[0003] Traditional radiotherapy positioning methods rely mainly on static image data or manual adjustment of the positioning system, but these methods cannot track the dynamic changes in the patient's body surface in real time, so they cannot effectively deal with changes in the body surface shape caused by physiological movements.

[0004] In order to solve this problem, researchers have proposed a variety of dynamic monitoring and correction methods in recent years, including using three-dimensional imaging technology and sensors to monitor changes in the patient's body surface in real time.

[0005] However, most of the existing methods are limited to a single device and technology, or are difficult to achieve high precision and high efficiency in real-time correction, and there are still many technical challenges in dynamic change monitoring and physiological motion compensation. For example, how to capture the small changes in the body surface in real time during the patient's breathing cycle, and how to dynamically adjust the treatment parameters according to the changes in the body surface to ensure the accuracy of radiotherapy and treatment effect, are still difficult problems to be solved in the current radiotherapy field.

[0006] In addition, traditional methods also have the problems of insufficient accuracy and slow processing speed, and cannot provide timely and effective correction schemes in a rapidly changing treatment environment. To solve these problems, the present application provides a method combining three-dimensional scanning, stereomicroscopy and infrared sensors to monitor and correct the changes in the patient's body surface contour in real time, and uses dynamic change characteristics for accurate correction, thereby ensuring the accurate execution of the radiotherapy process and improving the treatment effect and safety of the patient. SUMMARY

[0007] The present application provides a radiotherapy patient body surface contour monitoring and correction method, which mainly includes: S1, obtaining original point cloud data from the patient's body surface, generating a high-resolution body surface contour model based on the point cloud data, dividing the body surface into multiple monitoring blocks using a preset anatomical region division rule, and determining the geometric boundary features of each monitoring block; S2, for each of the monitoring blocks, obtain the corresponding anatomical structure characteristics and motion mode data, extract the local dynamic change characteristics of the local area in the respiratory cycle, if the local dynamic change characteristics exceed the preset deviation threshold, use the offset region positioning method based on geometric matching to determine the positioning information of the offset region; S3, according to the positioning information of the offset region, obtain the deviation vector and the motion trajectory data, construct a weighted model to calculate the deviation data and obtain the correction guidance parameters, construct a correction model, input the correction guidance parameters, geometric boundary characteristics, anatomical structure characteristics and motion mode data into the correction model to obtain a collaborative correction instruction set; S4, based on the collaborative correction instruction set, the corrected point cloud data and the high-resolution body surface contour model are registered non-rigidly to obtain a registration result and determine whether the correction is successful, if not, analyze the factors of unsuccessful correction, and process different factors based on different factors until the correction is successful.

[0008] The technical scheme provided by the embodiment of the present application can include the following beneficial effects: The present application overcomes the technical bottlenecks of insufficient dynamic change monitoring accuracy and real-time correction difficulty in traditional radiotherapy positioning methods by combining three-dimensional scanning, stereomicroscopy and infrared sensor technology. By obtaining the original point cloud data and generating a high-resolution body surface contour model, the geometric features of the patient's body surface can be accurately captured, especially during physiological processes such as breathing and body position changes. The dynamic changes of the body surface contour are effectively monitored and corrected. Specifically, the combination of three-dimensional scanning equipment and infrared sensors enables real-time acquisition of dynamic data of the patient's body surface during radiotherapy, greatly improving the accuracy and real-time performance of data acquisition. At the same time, through time series analysis and dynamic change feature extraction, the offset region of the body surface under the influence of physiological motion can be accurately identified, and the offset information can be located through geometric matching method to ensure the correction accuracy of the offset region. More importantly, by constructing a weighted model and correction guidance parameters, the present application can generate a collaborative correction instruction set for different monitoring blocks, ensuring that the motion mode and physiological characteristics of each monitoring block are accurately compensated, greatly improving the accuracy and stability of the radiotherapy process. In addition, the present application uses non-rigid registration technology, so that the patient's body surface can adapt to the deformation caused by physiological motion during correction, further optimizing the effect of radiotherapy. This method can real-time feedback the correction result, and evaluate whether the correction is successful according to the registration error, if not, the reason can be automatically analyzed and re-corrected to ensure the high-precision execution of the treatment. Through this accurate and intelligent monitoring and correction method, the body surface contour of the patient can always be consistent with the treatment plan, greatly improving the accuracy of radiotherapy and reducing the possibility of side effects. It provides a new technical solution for the field of radiotherapy, with wide application prospect and good market value. BRIEF DESCRIPTION OF DRAWINGS

[0009] Figure 1 a flow chart of the radiotherapy patient body surface contour monitoring and correction method of the present application; Figure 2 a schematic diagram of the specific process of determining the geometric boundary features of each block of the present application; Figure 3 a comparison chart of errors using traditional methods and using LSTM models of the present application; Figure 4 a structural schematic diagram of the radiotherapy patient body surface contour monitoring and correction system of the present application. DETAILED DESCRIPTION

[0010] The technical solutions in the embodiments of the present application will be described in detail below with reference to the accompanying drawings of the embodiments of the present application. The described embodiments are only a part of the embodiments of the present application.

[0011] For ease of understanding, the specific process of the embodiments of the present application will be described below. Please refer to Figure 1 One embodiment of the radiotherapy patient body surface contour monitoring and correction method in the embodiments of the present application includes: S1, obtaining original point cloud data from the patient's body surface, generating a high-resolution body surface contour model based on the point cloud data, dividing the body surface into multiple monitoring blocks using a preset anatomical region division rule, and determining the geometric boundary features of each monitoring block.

[0012] Specifically, during radiotherapy, the body surface contour of the patient changes dynamically with time, body position, respiration and other physiological processes, especially in the abdominal and chest regions, and such changes are particularly significant. In the radiotherapy space, a flexible pressure mattress is arranged on a hard carbon fiber bed, i.e., below the patient's body and in direct contact with the patient. The flexible pressure mattress is used to collect pressure signals of the patient's back in a supine position. The output line is directly connected to a data acquisition module. The data acquisition module is located on the side of the flexible pressure mattress and is used to collect signals of each row and column of pressure sensitive points on the flexible pressure mattress. After processing, the signals are sent to a data display module. The data acquisition module and the data display module are connected through a network cable. The data display module is located in a control room outside the radiotherapy room and is used to display a two-dimensional image of the patient's back pressure signals in real time. The position error is adjusted and corrected by combining the pressure sensing condition with the three-dimensional image. Since the treatment area of radiotherapy is usually highly related to the geometric shape of the patient's body surface, accurate monitoring and timely correction of the changes in the body surface contour are crucial to ensure the accuracy of radiotherapy and treatment effect. If the body surface contour deviates during radiotherapy, it may cause positioning errors of the treatment area, and even affect the treatment effect of the patient or cause side effects. Therefore, how to monitor and correct these changes in real time to ensure that the patient's body surface is consistent with the treatment plan during the treatment process has become a technical problem to be solved in the field of radiotherapy. Therefore, the present application provides a method for monitoring and correcting the body surface contour of a radiotherapy patient.

[0013] Firstly, the original point cloud data of the patient is obtained by using a three-dimensional scanning device, a stereomicroscope and an infrared sensor in combination. A high-resolution body surface contour model is generated based on the point cloud data. The specific method for generating the high-resolution body surface contour model will be explained in detail later. In order to facilitate subsequent monitoring and correction, the body surface is divided into a plurality of monitoring blocks according to the anatomical region division rule (for example, head and neck, chest and abdomen). The divided monitoring blocks can reflect the geometric features and motion patterns of each region in detail. In order to facilitate subsequent monitoring and correction, the geometric boundary features of each monitoring block are also determined. The specific method for determining the geometric boundary features of each monitoring block will be explained in detail later.

[0014] S2, for each monitoring block, the corresponding anatomical structure characteristics and motion pattern data are obtained, the local dynamic change characteristics of the local region in the respiratory cycle are extracted, and if the local dynamic change characteristics exceed a preset deviation threshold, a geometric matching-based offset region positioning method is used to determine the positioning information of the offset region.

[0015] Specifically, during radiotherapy, the patient's body surface contour changes dynamically with physiological activities such as breathing. In order to timely discover these changes and make corrections, first, the local dynamic changes of each monitoring block are detected through time series analysis. The dynamic change feature refers to the morphological changes of the patient's body surface during physiological processes such as the breathing cycle, especially the breathing-related motion characteristics. If the changes in a certain region exceed the preset deviation threshold, it means that the region has shifted, and the offset region is identified and further located. When the dynamic change feature exceeds the threshold, an offset region positioning method based on geometric matching is used to determine the location of the offset region by matching the model and the current data. The specific method of determining the positioning information of the offset region will be explained in detail later. The positioning information will provide key data for subsequent correction, ensuring that dynamic changes during radiotherapy do not affect the accuracy of treatment.

[0016] S3, based on the positioning information of the offset region, obtaining the deviation vector and the motion trajectory data, constructing a weighted model to calculate the deviation data and obtaining the correction guidance parameters, constructing a correction model, inputting the correction guidance parameters, geometric boundary features, anatomical structure characteristics, and motion pattern data into the correction model to obtain a set of collaborative correction instructions.

[0017] Specifically, according to the determined offset region positioning information, the deviation vector (a vector representing the relative position change of the offset region) and the motion trajectory data are extracted. These data are quantitative representations of the motion changes of the patient's body surface. Using these data, a weighted model is constructed to calculate the deviation data of each monitoring block based on the physiological characteristics and motion patterns of different monitoring blocks. Based on the deviation data calculated by the weighted model, correction guidance parameters are generated, including translation, rotation angle, deformation amount, etc., indicating how to correct the position, posture, etc. of the monitoring block. The correction guidance parameters, geometric boundary features, anatomical structure characteristics, and motion pattern data are input into the correction model to obtain a set of collaborative correction instructions. The collaborative correction instruction set includes rigid monitoring block and translation correction, rotation correction instructions, as well as deformable block deformation correction instructions.

[0018] S4, based on the collaborative correction instruction set, performing correction, and performing non-rigid registration on the corrected point cloud data and the high-resolution body surface contour model to obtain a registration result and determine whether the correction is successful. If not, analyze the factors that cause the correction to be unsuccessful, and perform different processing based on different factors until the correction is successful.

[0019] Specifically, based on the collaborative correction instruction set, the correction of the body surface contour is performed, and the corrected point cloud data is registered with the high-resolution body surface contour model using a non-rigid registration technique. Non-rigid registration allows the body surface to be properly deformed during correction to adapt to physiological motion and offset. The registration result is evaluated, and based on the registration error (such as residual vector and root mean square error), it is determined whether the correction is successful. If the correction is not successful, the factors for the failure of the correction are analyzed, and necessary measures are taken for re-correction until success.

[0020] The above method combines three-dimensional scanning, stereomicroscopy, and infrared sensors to obtain accurate point cloud data, generates a high-resolution body surface contour model, and divides it into multiple monitoring blocks. Through time series analysis and extraction of dynamic change characteristics, the physiological motion influence of the patient's body surface is monitored, and correction guidance parameters are generated. Based on the collaborative correction instruction set, the correction is performed and the result is evaluated to ensure accurate alignment of the treatment area during radiotherapy and improve treatment effectiveness.

[0021] In a specific embodiment, a high-resolution body surface contour model is generated based on point cloud data, specifically including the following steps: S11, aligning the initial point cloud data using a point cloud registration algorithm to obtain standard point cloud data in a unified coordinate system, and using a mean filter algorithm to denoise the standard point cloud data to obtain smooth point cloud data; S12, based on the high-resolution image data collected by the stereomicroscope, generate texture mapping data, and fuse the texture mapping data with the smooth point cloud data to obtain a high-resolution body surface contour model containing texture information; S13, if the high-resolution body surface contour model has local missing areas, an interpolation algorithm is used to fill the missing areas to obtain a complete body surface contour model.

[0022] Specifically, in order to obtain an accurate and complete body surface contour model, first, a point cloud registration algorithm is used to align the original point cloud data obtained from different angles or different devices. Common point cloud registration algorithms include the Iterative Closest Point (ICP) algorithm, rough alignment, fine alignment and other methods. This step converts all point cloud data to a unified coordinate system for further processing. The aligned point cloud data is denoised, usually using mean filtering algorithm (or other denoising techniques) to smooth the data and eliminate noise caused by device errors or external environmental interference, obtaining smoothed point cloud data. High-resolution image data of the patient's body surface is collected using a stereomicroscope (or other high-resolution imaging devices). These image data will provide detailed information about the body surface, such as skin texture, tumor markers, surgical areas, etc. Based on the collected high-resolution image data, a texture mapping algorithm is used to map the texture information of the image onto the smoothed point cloud data. Texture mapping technology can map the color information of image pixels to each point in the point cloud model, so that the point cloud model not only represents the geometry, but also contains specific texture details. The generated texture mapping data is fused with the smoothed point cloud data, and through the combination of color information and geometric information, the resulting body surface contour model not only accurately describes the shape, but also shows the real body surface texture. In the generated high-resolution body surface contour model, check whether there are local missing areas. Missing areas may be caused by scanning angle blind area, device precision limitation or patient posture, etc. Detect these areas and mark them as missing areas. For the detected missing areas, use interpolation algorithm to fill in these areas. Common interpolation methods include nearest neighbor interpolation, bilinear interpolation or high-order interpolation based on surface. The interpolation process estimates the shape of the missing area using the data of the surrounding known points to ensure the continuity and smoothness of the model. Through the interpolation algorithm, the missing areas are filled in, and a complete body surface contour model is generated. The complete body surface contour model has smooth boundaries and complete texture information, providing accurate data for subsequent body surface monitoring and correction.

[0023] In a specific embodiment, the geometric boundary features of each block are determined, specifically including the following steps: S21, based on the spatial distribution data of each monitoring block, determine the corresponding initial boundary range, if the initial boundary range exists overlap, then use grid segmentation algorithm to divide the space of the overlapping area, get the boundary data of the non-overlapping monitoring block; S22, according to the boundary data, extract the geometric boundary features of each monitoring block, generate the spatial geometric description of each monitoring block, the spatial geometric description is to use mathematical model to express the boundary of the monitoring block; S23, in combination with the spatial geometry description, the boundary of each monitoring block is smoothed by using a surface fitting algorithm to obtain the optimized boundary surface data, and the discontinuous areas in the boundary surface data are repaired by using an interpolation algorithm to obtain a continuous boundary surface model; S24, according to the boundary surface model, three-dimensional visualization data of each monitoring block is generated to determine the final block geometry feature.

[0024] Specifically, in order to ensure that the geometric boundaries of each monitoring block are accurately delineated and described, as Figure 2 The specific process of determining the geometric boundary features of each block is shown in the schematic diagram, based on the spatial distribution data of each monitoring block, the corresponding initial boundary range is determined, the spatial distribution data refers to the geometric information of the position and distribution of each monitoring block in three-dimensional space, for example, the spatial position and distribution of the surface area of the head and neck, chest and abdomen on the patient's body surface, the spatial distribution data is usually obtained by three-dimensional scanning or imaging technology, which contains the size, shape, position and relative relationship of each region, based on the spatial distribution data, the initial boundary range of each monitoring block (such as head and neck, chest, abdomen, etc.) is determined. The initial boundary range is roughly delineated based on anatomical structure and patient's surface scanning data, if the initial boundary range of multiple monitoring blocks overlaps, it needs to be processed by grid segmentation algorithm, the grid segmentation algorithm divides the overlapping area into multiple sub-regions, and assigns an independent monitoring block boundary to each sub-region, avoiding the inaccuracy caused by area overlap, the grid segmentation method divides the overlapping area into non-overlapping small areas by creating a grid model, and uses these small areas as the boundary data of the new monitoring block, ensuring that there is no overlap between each monitoring block and accurate positioning.

[0025] Based on the preliminary delineation of the monitoring block boundary data, the specific geometric boundary features of the monitoring block are extracted by the geometric feature extraction algorithm, the geometric boundary features include the edge line, surface or spatial distribution characteristics of the monitoring block, for example, the boundary of the head and neck can be a curved surface, while the boundary of the abdomen may present a certain geometric shape, such as an ellipse or a rectangle, etc., based on the geometric boundary features, the spatial geometry description of each monitoring block is generated, the spatial geometry description refers to using mathematical models to express the boundary of the monitoring block, this process expresses the geometric shape of the monitoring block through formulas, surfaces or mathematical curves, for example, if the boundary of the monitoring block is a curved surface, a parametric equation can be used to represent the curved surface, or a B-spline curve can be used to represent the boundary line.

[0026] The boundary of the monitoring block is smoothed by a curved surface fitting algorithm. The curved surface fitting algorithm fits a smooth curved surface based on known point data, ensuring the smoothness and continuity of the boundary. Common curved surface fitting algorithms include least squares method, spline curve fitting, B-spline fitting, etc. If there is a discontinuous area in the fitted boundary curved surface, it indicates that there may be cracks or gaps due to data noise or measurement error. At this time, these discontinuous areas can be repaired by interpolation algorithm. Based on the repaired boundary curved surface model, three-dimensional visualization data of the monitoring block is generated by computer graphics technology. The geometric shape of each monitoring block is converted into a three-dimensional image that can be presented on the computer screen, facilitating further monitoring and correction. By extracting the geometric features (such as area, volume, curvature, boundary smoothness, etc.) of each monitoring block, the spatial properties of each monitoring block are finally determined. These geometric features provide quantitative basis for subsequent radiotherapy monitoring and correction. For example, the curvature of the head and neck is larger, while the curvature of the abdominal region is smaller. These geometric features can help accurately position the radiotherapy area.

[0027] In a specific embodiment, the local dynamic change characteristics of the local region in the respiratory cycle are extracted, including the following steps: S31, the stereomicroscope and the motion capture system are used to obtain the corresponding anatomical structure characteristics and motion mode data; S32, the motion mode data collected is preprocessed by time series analysis method to remove noise and standardize, and the Fourier transform is used to analyze the frequency domain of the standardized motion mode data, and the frequency characteristics of the block in the respiratory cycle are extracted; S33, a low-pass filter is used to smooth the high-frequency noise in the frequency domain characteristics to obtain smooth time series data, and a long short-term memory network model is used to extract the local dynamic change characteristics under the influence of respiratory motion from the time series data to obtain a dynamic characteristic vector; S34, according to the dynamic characteristic vector, the principal component analysis method is used to reduce the high-dimensional characteristics to obtain low-dimensional dynamic change characteristics, and if the variance contribution rate of the low-dimensional dynamic change characteristics is lower than the preset threshold, the parameters of the principal component analysis are adjusted and recalculated to obtain optimized local dynamic change characteristics.

[0028] Specifically, in order to accurately extract the dynamic change characteristics of the patient's body surface in the respiratory cycle during radiotherapy, a stereomicroscope and a motion capture system are used to obtain the corresponding anatomical structure characteristics and motion pattern data. The stereomicroscope is used to capture high-resolution images of the monitoring block to obtain the anatomical structure characteristics of the region, including important parameters such as the geometry, size, relative position, etc. of the block. The motion capture system is used to collect real-time motion trajectory data of the monitoring block, and by tracking the movement of the monitoring block in the respiratory cycle, the motion pattern data of the block is obtained. The motion pattern data refers to the motion trajectory of the monitoring block in the respiratory cycle. The motion pattern data obtained from the motion capture system is preprocessed by time series analysis, and noise caused by device errors, environmental interference, etc. is removed by a denoising algorithm to ensure the smoothness and continuity of the data. The denoised data is standardized to eliminate differences between different data sources or different measurement scales, so that all motion pattern data is within the same dimension range. Fourier transform is applied to the standardized time series data to convert time domain data to frequency domain data. Fourier transform can extract the characteristics of different frequency components in the motion pattern data and identify the periodic change pattern in the respiratory cycle. The frequency characteristics are extracted from the frequency domain data, mainly focusing on frequency components that represent periodic fluctuations. These components can reflect the regular dynamic changes of the monitoring block in the respiratory cycle. High-frequency noise in the frequency domain characteristics is filtered, usually using a low-pass filter to smooth the signal. The low-pass filter can effectively remove high-frequency noise in the frequency domain and retain lower-frequency dynamic characteristics to ensure more stable data. The smoothed time series data is input into a long short-term memory network model (LSTM). LSTM is a special recurrent neural network that can effectively handle and predict long-term dependencies in time series data. It extracts local dynamic change characteristics of the block under the influence of respiratory motion, such as shape and position changes, and obtains a dynamic feature vector representing dynamic changes. Principal component analysis (PCA) maps high-dimensional data to low-dimensional space through linear transformation, retaining the main information in the data and removing redundant and unnecessary features. The reduced dynamic change characteristics better represent the local motion pattern of the block, reducing noise and computational burden. To ensure that the reduced features accurately reflect the main change pattern of the data and avoid information loss, it is also determined whether the variance contribution rate of the reduced low-dimensional dynamic change characteristics is lower than the preset threshold. If so, adjust the PCA parameters and perform dimensionality reduction calculation again to optimize the low-dimensional features to provide more accurate dynamic change description and ensure that the features play a role in subsequent correction and monitoring.

[0029] The traditional methods such as edge detection, motion estimation, optical flow method, etc. may have large errors in dynamic feature extraction, especially when dealing with complex or non-periodic changes. The dynamic features extracted by the method using the LSTM model have smaller errors, which can better track the trend of changes, especially under the influence of complex physiological movements, such as Figure 3 As shown in the error comparison chart using the traditional method and the LSTM model.

[0030] In a specific embodiment, the positioning information of the offset region is determined, specifically including the following steps: S41, obtaining the preliminary offset range of the target monitoring block, and preliminarily positioning the offset region as a curved surface fitting model according to the geometric characteristics of the offset range, and generating preliminary offset region positioning data; S42, using a shape matching algorithm based on curved surface fitting, comparing the geometric characteristics of the target monitoring block with the preset standard curved surface, judging the position of the offset region by calculating the curved surface similarity measure, and obtaining the preliminary positioning result; S43, combining the preliminary positioning result, using a space registration method based on geometric projection to calibrate the space of the offset region at different angles and positions, using a projection alignment algorithm to optimize the positioning error, and further improving the positioning accuracy; S44, according to the geometric characteristics of the offset region, using an adaptive weighted distance calculation method to assign a unique weight coefficient to each offset region, and obtaining accurate positioning information through weighted calculation.

[0031] Specifically, in order to ensure the accurate positioning of the offset region, and thus provide accurate basis for subsequent radiotherapy correction, in the monitoring process, through the aforementioned dynamic feature extraction method and monitoring result, first, the preliminary offset range of the target monitoring block (such as the head and neck, chest or abdomen) is determined, the offset range refers to the displacement area of the monitoring block in the respiratory cycle or other physiological activities, which can be estimated by comparing the initial state and the current state of the body surface contour model, or by analyzing the body surface motion trajectory of the patient, by analyzing the geometric features of the target monitoring block, especially the shape and curvature of its boundary, etc., more accurate positioning data is provided for the preliminary offset range, the offset range is usually represented as a region in three-dimensional space, covering the boundary region that may appear offset, and needs to be compared with the preset geometric model, a preliminary modeling of the target monitoring block is performed using a surface fitting algorithm to generate a preliminary surface fitting model. This model will represent the preliminary geometric features of the target block, the preliminary positioning of the offset region is determined based on this surface fitting model, the range of which is the offset region, involving the geometric deformation and spatial position of the region, using a shape matching algorithm based on surface fitting, the geometric features of the target monitoring block are compared with the standard surface, which is a standard anatomical model or reference model trained and optimized to represent the normal body surface contour, through the shape matching algorithm, the similarity between the surface of the target monitoring block and the standard surface is calculated, the similarity measure usually includes the distance between the surfaces, the angle error and other geometric indicators, the similarity calculated by the shape matching generates the preliminary offset region positioning result, which provides the spatial position and boundary of the offset region, according to the preliminary positioning result, the offset region of the target monitoring block is further optimized using a spatial registration method based on geometric projection, the spatial registration method adjusts the positioning of the target block by calculating the transformation relationship between the target monitoring block and the reference model (such as the standard anatomical model), to ensure that the two are accurately aligned, a projection alignment algorithm is used to optimize the positioning accuracy of the offset region at different angles and positions. The projection alignment algorithm further optimizes the positioning accuracy by projecting the target monitoring block into the geometric space of the reference model and comparing the projection differences between the two, through the optimized spatial registration result, the final accurate offset region positioning information is obtained, according to the geometric features of the offset region, an adaptive weighted distance calculation method is used to assign a unique weight coefficient to each offset region, the weight coefficient is usually calculated based on the importance, shape complexity and importance of each region in radiotherapy, the more critical the region, the greater the weight, the weight coefficient of each offset region is calculated to obtain the accurate positioning information of each region, through the weighted calculation, the most accurate offset region positioning information is obtained. This information is used to guide the subsequent radiotherapy correction process to ensure accurate treatment region.

[0032] In a specific embodiment, the correction guidance parameters are obtained based on the deviation data, specifically including the following steps: S51, extracting a deviation vector according to the positioning information of the offset region, and performing time series analysis on the deviation vector and the motion trajectory data collected by the infrared sensor and the motion capture system to obtain deviation data; S52, constructing a weighted model according to the influence degree of each monitoring block on the overall radiotherapy effect, the importance of the region, and the relevance to the physiological movement of the patient, and calculating the weighted results of the deviation vectors of each monitoring block based on the weighted model, the weighted results representing the weighted deviation data of each monitoring block at each time point; S53, using an optimization algorithm to optimize the weighted results of multiple time points of each monitoring block to obtain optimized deviation data, and generating correction guidance parameters based on the optimized deviation data.

[0033] Specifically, the deviation vector refers to the displacement vector of the offset region relative to the initial or standard position, which represents the displacement direction and magnitude of the region in space. The motion trajectory data of the patient's body surface at different time points is collected using infrared sensors and motion capture systems (such as optical motion capture, infrared sensors, or other motion tracking devices), and the motion trajectory data includes the position information of each point on the body surface. The motion patterns of each monitoring block can be extracted through time series analysis methods, and combined with the offset region positioning information to obtain the deviation data. The collected motion trajectory data is subjected to time series analysis to determine the deviation vector and dynamic changes of the offset region during the motion process. Techniques such as Fourier transform are used to process the time series data to identify periodic changes and possible high-frequency noise, and further extract effective data reflecting the deviation information. These deviation data reflect the degree of deviation of the patient's body surface relative to the initial state over different time periods. According to the physiological importance of each monitoring block, the influence of the monitoring block on the overall radiotherapy effect, and its relevance to the patient's physiological movement, a weighted model is constructed. For different monitoring blocks (such as the head and neck, chest, abdomen, etc.), the influence degree and physiological characteristics (such as breathing, motion amplitude, etc.) are weighted, for example, the head and neck may have higher requirements for radiotherapy accuracy, while the dynamic changes of the abdomen are more dramatic, so these regions may be assigned different weight values. Based on the weighted model, the deviation vector of each monitoring block is calculated to obtain the weighted deviation data of each monitoring block. Each weighted deviation result corresponds to the dynamic deviation information at each time point. These weighted deviation data comprehensively consider the physiological influence of the monitoring block and its contribution to the overall radiotherapy effect, providing accurate deviation data to guide the subsequent correction process. The weighted deviation data of each monitoring block is usually represented in the form of a matrix or vector, where each element represents the deviation degree of the monitoring block at a specific time point. For multiple time point weighted results of each monitoring block, an optimization algorithm is used for optimization processing. Common optimization algorithms include least squares method, genetic algorithm, particle swarm optimization (PSO), etc. The goal of the optimization algorithm is to eliminate redundant information or excessive errors by adjusting the weighted deviation data, and to minimize the deviation of the correction data from the target position as much as possible. The optimization algorithm dynamically adjusts the weighted results according to the deviation of different monitoring blocks to ensure accurate correction of each monitoring block during radiotherapy. With the help of the optimization algorithm, the weighted deviation data of each monitoring block is optimized to optimized deviation data, which accurately reflects the deviation of the patient's body surface during radiotherapy and provides guidance for subsequent correction operations. Based on the optimized deviation data, correction guidance parameters are generated, including specific adjustment amounts of each monitoring block such as translation, rotation, or deformation, to ensure accurate alignment of the target region with the radiotherapy plan.

[0034] In a specific embodiment, the local dynamic change characteristics of the local region in the respiratory cycle are extracted, specifically including the following steps: In a specific embodiment, the cooperative correction instruction set is obtained, specifically including the following steps: S61, for the rigid monitoring block, based on the corresponding deviation data, calculate the three-dimensional translation correction amount and the rotation correction angle; S62, for the deformable monitoring block, based on the corresponding deviation data and motion mode data, based on the biomechanical deformation model, the driving point displacement instruction set is generated by the inverse solving method; S63, the translation correction amount and the rotation correction angle of the rigid monitoring block are detected and weighted with the driving point displacement instruction set of the deformable monitoring block, and the cooperative correction instruction set is obtained.

[0035] Specifically, in order to ensure the accurate correction of each monitoring block during radiotherapy, for the rigid monitoring block (such as the head or other less deformed regions), first, based on the deviation data, the three-dimensional translation correction amount and the rotation correction angle of the block are calculated. The three-dimensional translation correction amount refers to the translation amount along the X, Y and Z axes calculated by analyzing the deviation vector of the target block. Usually, the translation correction amount is determined by analyzing the position of the patient's body surface in three-dimensional space. The rotation correction amount is usually calculated based on the angle offset in the deviation data. Matrix transformation method can be used to calculate the rotation angle of the monitoring block in space (for example, the rotation angle around X, Y and Z axes). When calculating the translation correction amount, the least square method or other optimization algorithm is used to obtain the translation amount that minimizes the deviation. The calculation of rotation angle can be carried out by geometric matching method, combining the initial position and current state of the target region, using angle conversion matrix or quaternion method to obtain accurate rotation amount. The calculated three-dimensional translation correction amount and rotation correction angle are used as the correction instruction of the rigid monitoring block, which is used for subsequent physical therapy equipment adjustment.

[0036] For deformable monitoring blocks (such as the abdomen and other areas that are greatly affected by physiological movements such as respiration), first, based on the corresponding deviation data and motion mode data (such as dynamic changes within the respiratory cycle), analysis is performed. The deformable monitoring block usually has a large geometric change, so relying solely on the deviation vector for correction may not be sufficient. It is necessary to combine the motion mode data to obtain more accurate deformation information, use biomechanical deformation models to model the deformable monitoring block, and help predict the deformation pattern of the block. Through the reverse solving method, based on the motion mode data and the deviation data, a suitable set of driving point displacement instructions is generated. These driving point displacement instructions can guide the dynamic adjustment of the radiotherapy equipment to the deformable block to compensate for the offset caused by respiration, tumors or other physiological movements. The generated driving point displacement instruction set will provide position correction instructions for the key points of each monitoring block. These instructions can guide the treatment equipment to accurately adjust the patient's surface area, ensuring that the target block is always in the correct position during treatment.

[0037] Conflict detection refers to ensuring that there is no contradiction between the correction instructions of the rigid and deformable monitoring blocks when correcting them simultaneously. The rigid block and the deformable block may overlap at certain boundaries, or due to physical device limitations, the correction instructions of the two may conflict. Through conflict detection of the correction instructions, it can be ensured that the translation or rotation of the rigid block does not affect the driving point displacement of the deformable block. Conflict detection can be performed through geometric constraints and optimization algorithms. For the correction instructions of the rigid and deformable blocks after conflict detection, they need to be weighted and fused to integrate them into the final collaborative correction instruction set. Weighted fusion takes into account the influence of the correction instructions of each block on the overall treatment effect. During the fusion process, different weights are assigned to the correction instructions of the rigid and deformable blocks. The weights are usually calculated based on the physiological importance of the block, its position in radiotherapy, and the degree of influence of physiological movement. After weighted fusion, the final collaborative correction instruction set will take into account the correction needs of the rigid and deformable monitoring blocks, ensuring accurate positioning of the patient's surface and improving radiotherapy precision. The final collaborative correction instruction set obtained contains the correction data of all monitoring blocks, including the translation correction amount, rotation correction angle of the rigid monitoring block, and driving point displacement instruction of the deformable monitoring block.

[0038] In a specific embodiment, it is determined whether the correction is successful based on the registration result, specifically including the following steps: S71, the registration result includes residual error vectors and root mean square errors of each monitoring block, real-time dynamic errors are obtained based on the residual error vectors, and feature similarity within the respiratory cycle is calculated based on the real-time dynamic errors and dynamic change characteristics. S72, if all the monitoring blocks satisfy the preset condition at the same time, the preset condition is that the root mean square error is less than or equal to the preset geometric accuracy threshold and the feature similarity is greater than or equal to the dynamic consistency threshold, it is judged that the correction is successful, otherwise it is judged that the correction fails.

[0039] Specifically, in order to ensure the accurate alignment of the body surface contour during radiotherapy, ensure the treatment effect and patient safety, the residual error vector represents the size and direction of the deviation of each monitoring block in the registration process, the root mean square error is a standard for measuring the accuracy of registration, which represents the average error between the target and the registration result, in the process of radiotherapy, the residual error vector represents the offset of the monitoring block on the body surface position, which is usually a vector indicating the difference between the target area and the actual position, the root mean square error is a standard method for quantifying the accuracy of the model, by calculating the average of the sum of squares of errors of all monitoring blocks, an index reflecting the correction accuracy is obtained, the smaller the root mean square error, the higher the accuracy of the correction, the dynamic change feature is mainly obtained by analyzing the motion trajectory of the patient's body surface in the respiratory cycle, these features reflect the dynamic change pattern of the body surface, such as the deformation or displacement of the monitoring block due to the respiratory cycle or other physiological movements, combined with the residual error vector and the dynamic change feature, the feature similarity in the respiratory cycle is calculated, the feature similarity is measured by comparing the similarity of the dynamic change pattern of the target area at different time points with the standard dynamic pattern, which can be calculated using the Euclidean distance or cosine similarity method, the higher the feature similarity, the better the dynamic change matching degree of the patient's body surface with the preset model during the entire radiotherapy process, the feature similarity can be calculated by comparing the dynamic response of the registration result with the preset standard model, in the correction process, the preset condition is set to determine whether the correction is successful, the preset condition includes that the root mean square error is less than or equal to the preset geometric accuracy threshold, and the feature similarity is greater than or equal to the dynamic consistency threshold, the first condition ensures that the registration error of each monitoring block is within an acceptable range during the correction process, ensuring that the geometric matching accuracy of the body surface contour is high enough, the second condition ensures that the motion of the monitoring block matches well with the preset model during the dynamic change of the patient's body surface, especially under the influence of the respiratory cycle and physiological movements, ensuring dynamic consistency, if all the monitoring blocks satisfy the preset condition, it is judged that the correction is successful, the successful correction means that the target area of radiotherapy has been accurately aligned, and the dynamic change of the patient's body surface has been effectively considered, ensuring the high-precision execution of treatment, if any monitoring block does not satisfy the preset condition, that is, the root mean square error exceeds the geometric accuracy threshold, or the feature similarity is lower than the dynamic consistency threshold, it is judged that the correction fails, if the correction fails, the failure reason is analyzed and further analysis is carried out according to the failure reason, it may be necessary to adjust the correction parameters, re-collect data, or consider other factors (such as patient posture change, equipment calibration problem, etc.), until the correction satisfies the preset condition.

[0040] In a specific embodiment, different processing is performed based on different factors, specifically including the following steps: If the root mean square error of all monitoring blocks is greater than the preset geometric accuracy threshold or all feature similarities are less than the dynamic consistency threshold, it is judged that there is a systematic deviation, the geometric accuracy threshold or the dynamic consistency threshold is adjusted according to the deviation direction, otherwise, the deviation data of the monitoring block that does not meet the preset condition is extracted, the elastic parameter of the biomechanical deformation model is adjusted based on the deviation data, and S3-S4 is re-executed based on the updated elastic parameter until it is judged that the correction is successful.

[0041] Specifically, in order to ensure accurate body surface monitoring and correction during radiotherapy, when correction fails, first check the root mean square error and feature similarity of all monitoring blocks. If the RMSE of all monitoring blocks is greater than the preset geometric accuracy threshold, or the feature similarity of all monitoring blocks is less than the dynamic consistency threshold, it indicates that there is a systematic deviation during radiotherapy. Systematic deviation may be caused by factors such as equipment problems, model errors, and patient posture changes, resulting in similar directions and sizes of correction deviations of all blocks. If it is confirmed that there is a systematic deviation, the geometric accuracy threshold or the dynamic consistency threshold will be adjusted according to the deviation direction. The deviation direction is usually determined by analyzing the residual vector and the dynamic change characteristics. The deviation direction indicates the spatial direction and trend of the deviation. It may be due to the position deviation of the radiotherapy equipment, posture error or other systematic factors. For example, if the systematic deviation shows uniform geometric changes, the geometric accuracy threshold will be relaxed to tolerate a certain degree of error until the correction is successful. If the systematic deviation occurs during dynamic changes (such as the influence of the breathing cycle), the dynamic consistency threshold will be adjusted accordingly to allow greater dynamic changes.

[0042] If a systematic shift is not detected, identify monitoring blocks that do not meet the preset conditions. These blocks may not meet the preset conditions of root mean square error and feature similarity due to local geometric errors or physiological motion abnormalities. Extract deviation data from the monitoring blocks that do not meet the conditions. Deviation data typically includes information such as position changes, shape deformations, and dynamic movements, which helps determine the cause of the correction failure. Analyze the extracted deviation data to determine if it is caused by biomechanical deformation. Biomechanical deformation usually involves local deformation of the patient's body surface or organs, such as deformation caused by physiological factors such as breathing and body posture changes. If local deformation is considered the cause of the correction failure, adjust the biomechanical deformation model. The elastic parameters of the biomechanical deformation model usually determine the degree of response of the human body or organs to external forces. By adjusting these parameters, the deformation caused by physiological motion (such as breathing) can be more accurately simulated and compensated. The adjusted elastic parameters will help better match the dynamic changes of the patient's body surface and improve the accuracy of the correction. Use the updated biomechanical deformation model and elastic parameters to re-execute steps S3 and S4, i.e., perform new correction based on the new deformation model and correction guidance parameters. Re-execute the registration and correction process, taking into account the new elastic parameters to ensure that the correction data of each monitoring block is more consistent with the actual dynamic changes.

[0043] Continue iterating until the correction results of all monitoring blocks meet the preset conditions, i.e., the root mean square error is less than or equal to the geometric precision threshold, and the feature similarity is greater than or equal to the dynamic consistency threshold. Finally, determine that the correction is successful. Through multiple adjustments and optimizations, the final accurate correction of the patient's body surface is ensured to facilitate high-precision radiotherapy.

[0044] The above describes a radiotherapy patient body surface contour monitoring and correction method in an embodiment of the present application. The following describes a radiotherapy patient body surface contour monitoring and correction system in an embodiment of the present application. Please refer to Figure 4 An embodiment of a radiotherapy patient body surface contour monitoring and correction system in the present application includes: A data acquisition module acquires original point cloud data from the patient's body surface, generates a high-resolution body surface contour model based on the point cloud data, divides the body surface into multiple monitoring blocks using a preset anatomical region division rule, and determines the geometric boundary features of each monitoring block. A dynamic monitoring module acquires the corresponding anatomical structure characteristics and motion pattern data for each monitoring block, extracts the local dynamic change features of the local region within the breathing cycle, and determines the positioning information of the offset region using a geometric matching-based offset region positioning method if the local dynamic change features exceed the preset deviation threshold. The correction calculation module obtains a deviation vector and motion trajectory data according to the positioning information of the offset region, constructs a weighted model to calculate deviation data and obtain correction guidance parameters, constructs a correction model, inputs the correction guidance parameters, geometric boundary features, anatomical structure characteristics and motion mode data into the correction model to obtain a cooperative correction instruction set; The correction execution module performs correction based on the cooperative correction instruction set, performs non-rigid registration on the corrected point cloud data and the high-resolution body surface contour model to obtain a registration result and determine whether the correction is successful, analyzes factors for unsuccessful correction in the case of unsuccessful correction, and performs different processing based on different factors until the correction is successful.

[0045] The above is only a specific embodiment of the present specification, and those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, module and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be described here. It should be understood that the protection scope of the present specification is not limited to this. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical range disclosed in the present specification, and these modifications or replacements should be covered within the protection scope of the present specification.

Claims

1. A method of radiotherapy patient body surface contour monitoring and correction, characterized by, The method comprises: S1, obtaining original point cloud data from the patient's body surface, generating a high-resolution body surface contour model based on the point cloud data, dividing the body surface into multiple monitoring blocks using a preset anatomical region division rule, and determining the geometric boundary features of each monitoring block; S2, for each monitoring block, obtain its corresponding anatomical structure characteristics and motion mode data, extract the local dynamic change characteristics of the local region in the respiratory cycle, if the local dynamic change characteristics exceed the preset deviation threshold, use a geometric matching-based offset region positioning method to determine the positioning information of the offset region; S3, according to the positioning information of the offset region, obtain the deviation vector and motion trajectory data, construct a weighted model to calculate the deviation data and obtain the correction guidance parameters, construct a correction model, input the correction guidance parameters, geometric boundary features, anatomical structure characteristics and motion mode data into the correction model to obtain a collaborative correction instruction set; S4, based on the collaborative correction instruction set, perform correction, perform non-rigid registration on the corrected point cloud data and the high-resolution body surface contour model, obtain the registration result and judge whether the correction is successful, if not, analyze the factors of unsuccessful correction, and perform different processing based on different factors until the correction is successful.

2. The method of radiotherapy patient body surface contour monitoring and correction of claim 1, wherein, Generating a high-resolution body surface contour model based on point cloud data comprises: S11, aligning the initial point cloud data using a point cloud registration algorithm to obtain standard point cloud data in a unified coordinate system, and denoising the standard point cloud data using a mean filtering algorithm to obtain smooth point cloud data; S12, based on the high-resolution image data collected by the stereomicroscope, generating texture mapping data, and fusing the texture mapping data with the smooth point cloud data to obtain a high-resolution body surface contour model containing texture information; S13, if the high-resolution body surface contour model has a local missing area, use an interpolation algorithm to fill the missing area to obtain a complete body surface contour model.

3. The method of radiotherapy patient body surface contour monitoring and correction of claim 1, wherein, Determining the geometric boundary features of each block comprises: S21, based on the spatial distribution data of each monitoring block, determining the corresponding initial boundary range, if the initial boundary range has overlap, using a grid segmentation algorithm to divide the overlapping region in space to obtain the boundary data of the monitoring block without overlap; S22, according to the boundary data, extracting the geometric boundary features of each monitoring block, generating a spatial geometric description of each monitoring block, the geometric boundary features include the edge line, surface or spatial distribution characteristics of the monitoring block, and the spatial geometric description refers to using a mathematical model to express the boundary of the monitoring block; S23, through the spatial geometric description, using a surface fitting algorithm to smooth the boundary of each monitoring block to obtain optimized boundary surface data, and using an interpolation algorithm to repair the discontinuous region of the boundary surface data to obtain a continuous boundary surface model; S24, according to the boundary surface model, generating three-dimensional visualization data of each monitoring block, and determining the final block geometric features.

4. The method of radiotherapy patient body surface contour monitoring and correction of claim 1, wherein, Extracting the local dynamic change characteristics of the local region in the respiratory cycle comprises: S31, adopt a stereomicroscope and a motion capture system to obtain corresponding anatomical structure characteristics and motion mode data, wherein the anatomical structure characteristics include the geometry, size and relative position of the block, and the motion mode data includes the motion trajectory of the block in the respiratory cycle; S32, by time series analysis method, the collected motion mode data is preprocessed, noise is removed and standardized, and the motion mode data after standardization is analyzed in frequency domain by Fourier transform, and the frequency characteristics of the block in the respiratory cycle are extracted; S33, using a low-pass filter to smooth the high-frequency noise in the frequency domain characteristics, obtaining smooth time series data, using a long short-term memory network model to extract the local dynamic change characteristics under the influence of respiratory motion, and obtaining a dynamic characteristic vector; S34, according to the dynamic characteristic vector, the high-dimensional feature is reduced by principal component analysis method, and low-dimensional dynamic change feature is obtained, if the variance contribution rate of low-dimensional dynamic change feature is lower than the preset threshold, the parameters of principal component analysis are adjusted and recalculated, and the optimized local dynamic change feature is obtained.

5. The method of radiotherapy patient body surface contour monitoring and correction of claim 1, wherein, The positioning information of the offset region is determined, including: S41, obtaining the preliminary offset range of the target monitoring block, according to the geometric characteristics of the offset range, the offset region is preliminarily positioned as a curved surface fitting model, and the preliminary offset region positioning data is generated; S42, using a shape matching algorithm based on curved surface fitting, comparing the geometric characteristics of the target monitoring block with the preset standard curved surface, judging the position of the offset region by calculating the curved surface similarity measure, and obtaining the preliminary positioning result; S43, combining the preliminary positioning result, using a space registration method based on geometric projection, the space of the offset region at different angles and positions is calibrated, the positioning error is optimized by projection alignment algorithm, and the positioning accuracy is further improved; S44, according to the geometric characteristics of the offset region, using an adaptive weighted distance calculation method, assigning a unique weight coefficient to each offset region, and obtaining accurate positioning information through weighted calculation.

6. The method of radiotherapy patient body surface contour monitoring and correction of claim 1, wherein, According to the positioning information of the offset region, the deviation vector and the motion trajectory data are obtained, the weighted model is constructed to calculate the deviation data and obtain the correction guidance parameter, including: S51, according to the positioning information of the offset region, extracting the deviation vector, using the motion trajectory data collected by the infrared sensor and the motion capture system, and performing time series analysis on the deviation vector and the motion trajectory data to obtain the deviation data; S52, constructing a weighted model according to the influence degree of each monitoring block on the overall radiotherapy effect, the importance of the region and its correlation with the physiological movement of the patient, calculating the weighted results of the deviation vector of each monitoring block based on the weighted model, and the weighted results represent the weighted deviation data of each monitoring block at each time point; S53, using an optimization algorithm to optimize the weighted results of each monitoring block at multiple time points to obtain optimized deviation data, and generating correction guidance parameters based on the optimized deviation data.

7. The method of radiotherapy patient body surface contour monitoring and correction of claim 1, wherein, The collaborative correction instruction set is obtained, including: S61, for rigid monitoring block, calculating three-dimensional translation correction amount and rotation correction angle based on corresponding deviation data; S62, based on the corresponding deviation data and motion mode data, a driving point displacement instruction set is generated for the deformable monitoring block based on a biomechanical deformation model through a reverse solving method; S63, the translation correction amount and the rotation correction angle of the rigid monitoring block are subjected to conflict detection and weighted fusion with the driving point displacement instruction set of the deformable monitoring block to obtain a collaborative correction instruction set.

8. The method of radiotherapy patient body surface contour monitoring and correction of claim 1, wherein, Based on the registration result, it is judged whether the correction is successful, including: S71, the registration result includes residual vectors and root mean square errors of each monitoring block, and a feature similarity in a respiratory cycle is calculated based on the residual vectors and dynamic change characteristics; S72, if all monitoring blocks simultaneously satisfy the preset conditions, the preset conditions are that the root mean square error is less than or equal to the preset geometric precision threshold and the feature similarity is greater than or equal to the dynamic consistency threshold, it is judged that the correction is successful, otherwise it is judged that the correction fails.

9. The method of monitoring and correcting patient body surface contours for radiotherapy treatment of claim 1, wherein, The factors for unsuccessful correction are analyzed, and different treatments are carried out based on different factors, including: If the root mean square errors of all monitoring blocks are all greater than the preset geometric precision threshold or all the feature similarities are less than the dynamic consistency threshold, it is judged as systematic deviation, the geometric precision threshold or the dynamic consistency threshold is adjusted according to the deviation direction, otherwise, the deviation data of the monitoring block that does not satisfy the preset condition is extracted, the elastic parameters of the biomechanical deformation model are adjusted based on the deviation data, and S3-S4 are re-executed based on the updated elastic parameters until it is judged that the correction is successful.

10. A radiotherapy patient body surface contour monitoring and correction system for implementing a radiotherapy patient body surface contour monitoring and correction method as claimed in any one of claims 1-9, characterized by, The system comprises: A data acquisition module acquires original point cloud data from the surface of a patient, generates a high-resolution body surface contour model based on the point cloud data, divides the body surface into multiple monitoring blocks using a preset anatomical region division rule, and determines the geometric boundary features of each monitoring block; A dynamic monitoring module acquires the corresponding anatomical structure characteristics and motion mode data for each monitoring block, extracts the local dynamic change characteristics of the local region in the respiratory cycle, and determines the positioning information of the offset region using a geometric matching-based offset region positioning method if the local dynamic change characteristics exceed the preset deviation threshold; A correction calculation module acquires deviation vectors and motion trajectory data according to the positioning information of the offset region, constructs a weighted model to calculate deviation data and obtain correction guidance parameters, constructs a correction model, inputs the correction guidance parameters, geometric boundary features, anatomical structure characteristics, and motion mode data into the correction model to obtain a collaborative correction instruction set; A correction execution module performs correction based on the collaborative correction instruction set, performs non-rigid registration on the corrected point cloud data and the high-resolution body surface contour model, obtains a registration result and judges whether the correction is successful, and in the case of unsuccessful correction, analyzes the factors for unsuccessful correction, and carries out different treatments based on different factors until the correction is successful.

Images