A performance testing method for a radiotherapy laser positioning system

Abstract

The present application relates to the technical field of optical equipment testing, in particular to a radiotherapy laser positioning system performance testing method, first positioning data of a test optical positioning equipment under a load state is obtained, a body weight-optical response correlation model is constructed to analyze and obtain static optical equipment test data; a test personnel moves along a preset track, collects laser photosensitive sensor response signals and laser tracker space coordinates to generate second optical positioning data, a motion-optical response coupling model is constructed to analyze and obtain dynamic optical equipment test data; a multi-factor deviation prediction model is constructed to analyze optical interference signals, phase detection data and environmental temperature and humidity parameters to generate optical equipment compensation parameters, the static optical equipment test data, the dynamic optical equipment test data and the optical equipment compensation parameters are analyzed, and an optical calibration scene adaptability score, a positioning accuracy quantization matrix and an optical equipment acceptance benchmark value comprehensive evaluation report are calculated and generated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of optical equipment testing, in particular to a performance testing method of a radiotherapy laser positioning system. BACKGROUND

[0002] In the clinical performance testing of the laser positioning system, the optical property maintenance ability of the system under dynamic conditions directly affects the positioning accuracy of the medical equipment. The current optical property testing method is mainly aimed at the static working state, and the system performance is evaluated by analyzing the geometric parameters and intensity distribution of the optical marker. However, in the actual clinical environment, the dynamic motion of the subject's breathing rhythm and body position change will cause time-varying disturbance to the optical transmission path. This dynamic disturbance will cause changes in the transmission characteristics of the optical system, including but not limited to light intensity distribution distortion, marker projection offset, and optical imaging quality degradation, etc. However, the existing testing methods cannot effectively simulate and quantify the influence of dynamic disturbance on the optical performance of the system.

[0003] The current optical testing standard does not establish a testing method for dynamic working conditions, especially lacking quantitative detection methods for key performance indicators such as optical transmission stability and dynamic distortion suppression ability. Therefore, it is urgent to build a testing platform with multi-degree-of-freedom dynamic simulation function. The platform should integrate a motion parameter programmable control module and a synchronous optical property acquisition system to realize the transmission characteristic analysis of the optical system under dynamic conditions, real-time imaging resolution detection and marker projection stability evaluation.

[0004] Therefore, a performance testing method of a radiotherapy laser positioning system is proposed. SUMMARY

[0005] The present application relates to the technical field of optical equipment testing, in particular to a performance testing method of a radiotherapy laser positioning system.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0007] A performance testing method of a radiotherapy laser positioning system, comprising:

[0008] The test personnel are divided into different groups according to weight, first positioning data of the optical positioning device under load state is tested, a weight-optical response correlation model is constructed to analyze the first positioning data, and static optical device test data is obtained;

[0009] The test personnel are controlled to move along a preset trajectory, the photosensitive sensor response signal of the laser beam and the spatial coordinates of the laser tracker are synchronously collected, second optical positioning data is generated, a motion-optical response coupling model is constructed to analyze the second optical positioning data, and dynamic optical device test data is obtained;

[0010] A multi-factor deviation prediction model is constructed to analyze the optical interference signal, phase detection data and environmental temperature and humidity parameters of the laser beam synchronously collected, and optical device compensation parameters are generated;

[0011] The static optical device test data, dynamic optical device test data and optical device compensation parameters are analyzed, the interaction coefficients of the optical device influence factors are calculated, and a comprehensive evaluation report of optical calibration scene adaptability score, positioning accuracy quantization matrix and optical device acceptance reference value is generated.

[0012] Preferably, the first positioning data is static position information data collected under different load states, including coordinate data of the center position of the laser beam, laser beam slope data and deviation distance of the laser beam from the preset theoretical coordinate system;

[0013] The second optical positioning data is dynamic position information data continuously collected under the micro-motion trajectory of the test personnel's limbs, also including motion trajectory, displacement change, speed, acceleration data and continuous optical signal change data corresponding to the dynamic state of the test personnel and its timestamp; the micro-motion range of the limbs is within the threshold value set by the optical positioning device.

[0014] Preferably, the weight-optical response correlation model includes a first positioning data processing layer, an associated feature extraction layer, an associated feature analysis layer and a result verification layer;

[0015] The first positioning data processing layer performs preliminary processing on the first positioning data, including filtering, denoising and normalization operations;

[0016] The associated feature extraction layer performs correlation analysis on the processed first positioning data and weight data, generating weight-optical response correlation features;

[0017] The associated feature analysis layer analyzes the weight-optical response correlation features by statistical methods, obtains parameter data of weight change on the static performance of the optical device, including positioning error, response sensitivity and stability indicators;

[0018] The result verification layer obtains static optical equipment test data through statistical verification and error analysis on parameter data.

[0019] Preferably, the motion-optical response coupling model comprises a second optical positioning data processing layer, a dynamic feature extraction layer, a feature coupling layer and an analysis and prediction layer.

[0020] The second optical positioning data processing layer pre-processes the continuously collected second optical positioning data, including filtering, denoising and normalization operations.

[0021] The dynamic feature extraction layer processes the dynamic position information data and optical signal change data of limb micro-movement, extracts motion feature parameters and optical response feature parameters.

[0022] The feature coupling layer couples and analyzes the motion feature parameters and optical response feature parameters through machine learning, and generates motion and optical response joint features.

[0023] The analysis and prediction layer generates dynamic optical equipment test data by analyzing the motion and optical response joint features.

[0024] Preferably, the multi-factor deviation prediction model comprises a feature extraction layer, a parameter coupling and analysis layer, and a prediction and compensation layer.

[0025] The feature extraction layer extracts optical interference features, phase detection features and environmental features by extracting features from the optical interference signals, phase detection data and environmental temperature and humidity parameters of the laser beam; the optical interference features include interference fringe characteristics, phase information and signal intensity; the phase detection features include phase shift, change trend and related correction information; the environmental features include temperature change rate and humidity fluctuation.

[0026] The feature coupling and analysis layer couples the optical interference features, phase detection features and environmental features to obtain optical and environmental coupling features; analyzes the optical and environmental coupling features to obtain the deviation amount of the optical equipment in actual use due to environmental and signal fluctuations, and obtains key error indicators, including phase error, signal drift and positioning deviation caused by the environment.

[0027] The prediction and compensation layer calculates and generates optical equipment compensation parameters based on the key error indicators; the optical equipment compensation parameters include deviation correction coefficients and temperature and humidity compensation coefficients.

[0028] Preferably, the interaction coefficient of the calculation of the optical equipment influence factor comprises the following specific steps:

[0029] The static optical equipment test data, dynamic optical equipment test data and optical equipment compensation parameters are subjected to feature alignment and standardization processing to generate a multi-dimensional fusion data set;

[0030] A multi-factor coupling matrix is constructed, and the weight coefficients of the parameters in the multi-dimensional fusion data set are calculated by a partial least squares regression algorithm;

[0031] The weight coefficients are dynamically adjusted by using a particle swarm optimization algorithm, and the non-linear interaction effects between the factors are calculated by setting a fitness function;

[0032] The optimized weight coefficients are subjected to significance test to generate a composite interaction coefficient set containing linear coupling coefficients and non-linear interference coefficients;

[0033] The composite interaction coefficient set is verified by a leave-one-out method, and when the root mean square error is lower than a preset threshold, it is determined that the interaction coefficients are effective.

[0034] Compared with the prior art, the present application has the following advantages:

[0035] 1、The present application groups the test personnel according to body weight, pre-processes the static laser positioning data under different load conditions, and uses filtering, denoising and normalization methods to eliminate noise interference, so as to accurately extract core parameters such as laser beam center coordinates, slope and deviation distance. A body weight and optical response correlation model is constructed, and positioning error, response sensitivity and stability indicators are subjected to statistical analysis and result verification, realizing fine data processing and significantly improving test accuracy and reliability.

[0036] 2、The present application introduces test personnel limb micro-motion trajectory data in dynamic testing, continuously collects displacement, velocity and acceleration information during motion, and combines with optical signal timestamps to realize coupling analysis of motion and optical response. After filtering, denoising and normalization preprocessing, dynamic feature extraction and joint analysis are performed to effectively capture the laser positioning change law under motion state and quantitatively reflect system response delay and fluctuation. This method reveals the error generation mechanism under motion state, provides a scientific basis for fine testing of laser beam parameters, and improves the dynamic adaptability and practicality of the test results.

[0037] 3、The present application constructs a multi-factor deviation prediction model, combines laser beam optical interference signals, phase detection data and environmental temperature and humidity parameters to realize accurate extraction of error key indicators. By using feature extraction, parameter coupling and prediction compensation hierarchical structure, deviation correction coefficients and temperature and humidity compensation coefficients are calculated to effectively compensate for positioning deviations caused by environmental changes and signal drift. Fully considering the complex environmental factors, the error interference is significantly reduced, and the equipment positioning test precision and stability are improved.

[0038] 4, The application constructs a multi-dimensional fusion data set by aligning and standardizing the static test data, dynamic test data and optical equipment compensation parameters, and calculates the parameter weight and nonlinear interaction effect based on the partial least squares regression and particle swarm optimization algorithm, to generate a complex interaction coefficient set containing linear coupling coefficients and nonlinear interference coefficients. The method ensures the accuracy and scientificity of the evaluation model through significance test and leave-one-out validation, and finally forms a comprehensive evaluation report of scene adaptability score, quality control index quantization matrix and acceptance reference value, which provides multi-dimensional and systematic decision basis for equipment quality control, maintenance optimization and testing, and significantly improves the overall detection level and data reliability. BRIEF DESCRIPTION OF DRAWINGS

[0039] Figure 1 A radiotherapy laser positioning system performance test method flowchart is provided for the application;

[0040] Figure 2 A body weight-optical response correlation model structure diagram is provided for the embodiment of the application;

[0041] Figure 3 A motion-optical response coupling model structure diagram is provided for the embodiment of the application;

[0042] Figure 4 A multi-factor deviation prediction model structure diagram is provided for the embodiment of the application. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the application will be described in detail below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0044] Embodiment one:

[0045] Please refer to Figure 1 The application provides a radiotherapy laser positioning system performance test method, and the technical scheme is as follows:

[0046] The test personnel are divided into different groups according to body weight, the first positioning data of the optical positioning equipment under the load state is tested, the body weight-optical response correlation model is constructed to analyze the first positioning data, and the static optical equipment test data is obtained; the first positioning data is static position information data collected under different load states, including coordinate data of the center position of the laser beam, slope data of the laser beam and deviation distance of the laser beam from the preset theoretical coordinate system;

[0047] In the embodiment, the test personnel are divided into different groups according to weight, and the static positioning data of the laser positioning system is collected under different load conditions, so that the different load effects of the human body on the device in the actual use scene are effectively simulated.

[0048] The weight-optical response correlation model comprises a first positioning data processing layer, a correlation feature extraction layer, a correlation feature analysis layer and a result verification layer, and specific reference is made to Figure 2 ;

[0049] The first positioning data processing layer performs preliminary processing on the first positioning data, including filtering, denoising and normalization operations.

[0050] The correlation feature extraction layer performs correlation analysis on the processed first positioning data and the weight data, and generates weight-optical response correlation features.

[0051] The correlation feature analysis layer analyzes the weight-optical response correlation features by statistical methods, and obtains parameter data of the static performance of the optical device under the influence of weight changes, including positioning error, response sensitivity and stability indicators.

[0052] The result verification layer obtains static optical device test data by statistical verification and error analysis on the parameter data.

[0053] In the embodiment, by constructing the weight-optical response correlation model, the laser beam center position, slope and the deviation distance from the preset theoretical coordinate system are quantitatively analyzed, which can accurately reveal the influence of weight changes on the optical positioning performance, thereby providing accurate static test data. This method not only can find potential positioning errors and response instability problems, but also provides a scientific basis for device calibration, quality control and subsequent performance optimization, and ultimately helps to improve the reliability and accuracy of the optical positioning device in the radiotherapy process, and ensures the stability of the treatment effect and the safety of the patient.

[0054] The test personnel are controlled to move along a preset trajectory, and the photosensitive sensor response signal of the laser beam and the spatial coordinates of the laser tracker are synchronously collected to generate second optical positioning data. A motion-optical response coupling model is constructed to analyze the second optical positioning data, and dynamic optical device test data is obtained. The second optical positioning data is dynamic position information data continuously collected under the test personnel's limb micro-motion trajectory, including motion trajectory, displacement change, speed and acceleration data; continuous optical signal change data corresponding to the dynamic state of the test personnel and its timestamp; and the limb micro-motion range is within the threshold set by the optical positioning device.

[0055] The motion-optical response coupling model comprises a second optical positioning data processing layer, a dynamic feature extraction layer, a feature coupling layer and an analysis and prediction layer, and specific reference is made to Figure 3 ;

[0056] The second optical positioning data processing layer pre-processes the continuously collected second optical positioning data, including filtering, denoising and normalization operations;

[0057] The dynamic feature extraction layer processes the dynamic position information data and optical signal change data of limb micro-movement, extracts motion feature parameters and optical response feature parameters;

[0058] The feature coupling layer couples and analyzes the motion feature parameters and optical response feature parameters through machine learning to generate motion and optical response joint features; the analysis and prediction layer generates dynamic optical device test data by analyzing the motion and optical response joint features.

[0059] In this embodiment, by acquiring the dynamic optical positioning data continuously collected by the test personnel under the limb micro-movement trajectory, and constructing a motion-optical response coupling model for in-depth analysis, this method can truly reflect the response characteristics of the optical positioning device in the dynamic state. By using multi-level processing procedures such as data processing, dynamic feature extraction and machine learning coupling analysis, motion feature parameters and optical response feature parameters can be accurately extracted, and high-precision dynamic optical device test data can be generated. This method significantly improves the detection accuracy of the dynamic performance of the device, helps to discover the positioning deviation caused by human micro-movement in time, and provides a scientific basis for device testing and optimization. Dynamic testing relies on manual work and lacks a synchronization mechanism. The present application realizes millisecond-level dynamic error capture through high-frequency acquisition and LSTM model, as shown in Table 1.

[0060] Table 1 Dynamic test efficiency comparison table

[0061] Indicator Motion-optical response coupling model Manual trajectory recording Data acquisition frequency 1000 Hz (real-time synchronous optical signal) 100 Hz (manual marking) Trajectory analysis time < 5 ms (machine learning dimension reduction) > 50 ms (manual fitting) Dynamic positioning error ± 0.3 mm (LSTM prediction) ± 1.2 mm (linear interpolation) Motion-optical delay analysis Support time stamp matching (± 1 ms accuracy) No synchronization mechanism

[0062] An multi-factor deviation prediction model is constructed to analyze the optical interference signals, phase detection data and environmental temperature and humidity parameters of the synchronously collected laser beams, and to generate optical device compensation parameters;

[0063] The multi-factor deviation prediction model includes a feature extraction layer, a parameter coupling and analysis layer, and a prediction and compensation layer, as shown in Figure 4 ;

[0064] The feature extraction layer extracts features from the optical interference signals, phase detection data and environmental temperature and humidity parameters of the laser beams to obtain optical interference features, phase detection features and environmental features; the optical interference features include interference fringe characteristics, phase information and signal intensity; the phase detection features include phase shift, change trend and related correction information; the environmental features include temperature change rate and humidity fluctuation;

[0065] The feature coupling and analysis layer couples optical interference features, phase detection features and environmental features to obtain optical and environmental coupling features; the optical and environmental coupling features are analyzed to obtain deviation amounts of the optical device in actual use due to environmental and signal fluctuations, to obtain key error indicators, including phase error, signal drift and environmental positioning deviation;

[0066] The prediction and compensation layer calculates and generates optical device compensation parameters based on the key error indicators; the optical device compensation parameters include deviation correction coefficients and temperature and humidity compensation coefficients.

[0067] In this embodiment, after using the multi-factor deviation prediction model, various errors caused by environmental fluctuations and signal instability can be accurately identified and quantified before the device is running, so as to generate compensation parameters in advance and realize automatic correction of the optical device deviation. Through in-depth feature extraction and coupling analysis of the laser beam optical interference signal, phase detection data and environmental temperature and humidity parameters, key error indicators such as phase error, signal drift and environmental positioning deviation can be accurately obtained. This method significantly improves the positioning test precision and stability of the optical device in a complex environment.

[0068] The static optical device test data, dynamic optical device test data and optical device compensation parameters are analyzed, the interaction coefficients of the optical device influencing factors are calculated, and a comprehensive evaluation report of the optical calibration scene adaptability score, the positioning precision quantization matrix and the optical device acceptance benchmark value is generated.

[0069] The calculation of the interaction coefficients of the optical device influencing factors includes the following specific steps:

[0070] The static optical device test data, dynamic optical device test data and optical device compensation parameters are aligned and standardized to generate a multi-dimensional fusion data set;

[0071] A multi-factor coupling matrix is constructed, and the weight coefficients of each parameter in the multi-dimensional fusion data set are calculated by a partial least squares regression algorithm;

[0072] The particle swarm optimization algorithm is used to dynamically adjust the weight coefficients, and the non-linear interaction effects between factors are calculated by setting an adaptability function;

[0073] The optimized weight coefficients are subjected to significance test to generate a composite interaction coefficient set containing linear coupling coefficients and non-linear interference coefficients; the composite interaction coefficient set is verified by the leave-one-out method, and when the root mean square error is lower than a preset threshold, the interaction coefficients are determined to be effective.

[0074] In the embodiment, by deeply fusing and comprehensively analyzing static and dynamic optical equipment test data and compensation parameters, multi-dimensional data feature alignment and standardization processing are realized, a multi-factor coupling matrix is constructed, and a partial least squares regression and a particle swarm optimization algorithm are used to dynamically adjust weight coefficients, so that a complex interaction coefficient reflecting linear and nonlinear interaction effects between various influencing factors of the equipment is accurately calculated. After significance test and leave-out verification, the generated evaluation report not only includes optical calibration scene adaptability score, quality control index quantization matrix and acceptance benchmark value, but also provides scientific and quantitative basis for equipment calibration, performance optimization and clinical application, thereby significantly improving the detection accuracy and operation stability of the positioning system in the radiotherapy process.

[0075] The present application realizes all-round quantitative evaluation of the performance of the optical positioning equipment by comprehensively analyzing static and dynamic test data, environmental compensation parameters and multi-factor coupling. First, the test personnel are grouped according to weight, and data such as laser beam center position, slope and deviation distance are collected under different loads, and a weight-optical response correlation model is constructed to accurately reflect the influence of human load on the static performance of the equipment. Second, by obtaining dynamic data and optical signal changes under limb micro-motion trajectory, motion-optical response coupling model is used to extract motion and response characteristics, and high-precision capture of equipment performance under dynamic state is realized. In addition, a multi-factor deviation prediction model is used to extract key error indicators from laser interference, phase detection and environmental parameters, and to generate compensation parameters in advance, so as to realize automatic correction of equipment errors. By data alignment, regression analysis and particle swarm optimization of static and dynamic test data and compensation parameters, the complex interaction coefficient reflecting linear and nonlinear interaction effects is calculated, and the comprehensive evaluation report of scene adaptability score, quality control index matrix and acceptance benchmark value is generated, which significantly improves the test accuracy and stability of the equipment positioning. The traditional linear regression cannot handle the multi-factor nonlinear relationship, and the present application balances the complexity and accuracy through the optimization algorithm to realize high-precision prediction. For details, see Table 2.

[0076] Table 2 Algorithm complexity and accuracy balance

[0077] Algorithm type Invention (PLS + particle swarm optimization) Traditional method (ordinary least squares) Computational complexity O(n 2 )(parallelizable optimization) O (n) Prediction accuracy (RMSE) 0.12 mm 0.35 mm Nonlinear effect support Yes (interaction coefficient set) No Weight dynamic adjustment Particle swarm optimization iteration Fixed weight

[0078] Embodiment two:

[0079] The test personnel are divided into different groups according to weight, and the first positioning data of the optical positioning equipment under the load state is tested, a weight-optical response correlation model is constructed to analyze the first positioning data, and static optical equipment test data is obtained. The first positioning data is static position information data collected under different load states, including coordinate data of laser beam center position, laser beam slope data and deviation distance of laser beam from the preset theoretical coordinate system.

[0080] The body weight-optical response correlation model comprises a first positioning data processing layer, a correlation feature extraction layer, a correlation feature analysis layer, and a result verification layer.

[0081] The first positioning data processing layer performs preliminary processing on the first positioning data, including filtering, denoising, and normalization operations.

[0082] The correlation feature extraction layer performs correlation analysis on the processed first positioning data and the body weight data to generate body weight-optical response correlation features.

[0083] The Pearson correlation coefficient r1 between the body weight W and the positioning error △d is calculated by a correlation analysis method.

[0084]

[0085] where n is the number of test subjects, W i is the body weight of the i-th test subject, is the average body weight, △d i is the positioning error of the i-th test subject, is the average positioning error.

[0086] When r1>0.5, it is considered that there is a significant correlation.

[0087] For features with significant correlation, linear relationships are established for each body weight interval, and the specific formula is as follows:

[0088] △d=β0+β1W+β2W 2 +ε.

[0089] where β0, β1, and β2 are linear regression coefficients obtained by machine learning, and ε is an infinitesimal value.

[0090] Nonlinear relationships are captured by polynomial regression, and the optimal model is selected by F-test to generate correlation features.

[0091] The correlation feature analysis layer analyzes the body weight-optical response correlation features by statistical methods to obtain parameter data of the static performance of the optical device under the influence of body weight changes, including positioning error, response sensitivity, and stability index.

[0092] The response sensitivity is obtained by the error change rate S caused by unit body weight change, and the specific calculation formula is:

[0093]

[0094] The stability index is obtained by the variance of the error within the same body weight group.

[0095] The result verification layer obtains static optical equipment test data through statistical verification and error analysis on parameter data.

[0096] The statistical verification includes F detection and t detection, and the error analysis includes systematic error and random error.

[0097] The control test personnel are controlled to move along a preset track, and the photosensitive sensor response signal of the laser beam and the spatial coordinates of the laser tracker are synchronously collected to generate second optical positioning data, and a motion-optical response coupling model is constructed to analyze the second optical positioning data, and dynamic optical equipment test data is obtained; the second optical positioning data is dynamic position information data continuously collected under the micro-motion track of the test personnel's limbs, including motion track, displacement change, speed and acceleration data; continuous optical signal change data corresponding to the dynamic state of the test personnel and the time stamp thereof; the micro-motion range of the limbs is within the threshold value set by the optical positioning equipment.

[0098] The motion-optical response coupling model includes a second optical positioning data processing layer, a dynamic feature extraction layer, a feature coupling layer and an analysis and prediction layer; the second optical positioning data processing layer pre-processes the continuously collected second optical positioning data, including filtering, denoising and normalization operations; the dynamic feature extraction layer processes the dynamic position information data and the optical signal change data of the limb micro-motion to extract motion feature parameters and optical response feature parameters;

[0099] The motion feature parameters include trajectory curvature κ, displacement fluctuation amplitude A disp , average speed acceleration a v , acceleration standard deviation σ a and acceleration peak ratio R peak obtained by analyzing the bending degree of the limb micro-motion track;

[0100] The optical response feature parameters include signal delay time T d , signal intensity fluctuation ΔS, phase change rate k φ , spectral coherence C(f) and dynamic range compression ratio η.

[0101] The feature coupling layer couples and analyzes the motion feature parameters and the optical response feature parameters F optical =[T d , ΔS, k φ , C(f), η] through machine learning to generate joint features of motion and optical response;

[0102] The motion feature parameters and the optical response feature parameters F optical =[T d , ΔS, kφ The joint feature F is obtained by splicing the motion feature F and the optical response feature F joint ;

[0103] The joint feature F is obtained by splicing the motion feature F and the optical response feature F joint The joint feature F is obtained by splicing the motion feature F and the optical response feature F PCA , and the specific calculation formula is as follows:

[0104] F PCA = w T F joint ;

[0105] wherein w T is the transpose matrix of the PCA projection matrix;

[0106] The analysis and prediction layer generates dynamic optical equipment test data by analyzing the motion-optical response joint feature;

[0107] The motion-optical joint feature is input into the trained LSTM model, and dynamic optical equipment test data is output; the dynamic optical equipment test data includes dynamic positioning error, response delay, signal distortion degree, and dynamic stability coefficient.

[0108] A multi-factor deviation prediction model is constructed to analyze the optical interference signals, phase detection data, and environmental temperature and humidity parameters of the synchronously collected laser beams, and to generate optical equipment compensation parameters;

[0109] The multi-factor deviation prediction model includes a feature extraction layer, a parameter coupling and analysis layer, and a prediction and compensation layer;

[0110] The feature extraction layer extracts features from the optical interference signals, phase detection data, and environmental temperature and humidity parameters of the laser beams to obtain optical interference features, phase detection features, and environmental features; the optical interference features include interference fringe characteristics, phase information, and signal intensity; the phase detection features include phase shift, change trend, and related correction information; and the environmental features include temperature change rate and humidity fluctuation;

[0111] The feature coupling and analysis layer couples the optical interference features, phase detection features, and environmental features to obtain optical and environmental coupling features; the optical and environmental coupling features are analyzed to obtain the deviation amount of the optical equipment in actual use due to environmental and signal fluctuations, and key error indicators, including phase error, signal drift, and positioning deviation caused by the environment, are obtained;

[0112] The principal component direction is extracted through eigenvalue decomposition of the joint covariance matrix of the optical interference features Fop, the phase detection features Fph, and the environmental features Fenv, and the key coupling relationship is determined;

[0113] The phase error is obtained by the difference between the actual phase and the theoretical phase; the signal drift is detected by using the Hodrick-Prescott filter to separate the signal; and the positioning deviation caused by the environment is determined by linear regression.

[0114] The prediction and compensation layer calculates and generates optical equipment compensation parameters based on the key error indicators; the optical equipment compensation parameters include deviation correction coefficients and temperature and humidity compensation coefficients;

[0115] The specific calculation formula of the deviation correction coefficient is:

[0116] φcompensation=φoriginal-(△φ T +△φ H );

[0117] Wherein, φ 补偿 is the deviation correction compensation coefficient, φ 原始 is the original correction coefficient, △φ T is the temperature compensation coefficient, and △φ H is the humidity compensation coefficient;

[0118] The static optical equipment test data, dynamic optical equipment test data and optical equipment compensation parameters are analyzed, the interaction coefficient of the optical equipment influencing factor is calculated, and the comprehensive evaluation report of the optical calibration scene adaptability score, the positioning accuracy quantization matrix and the optical equipment acceptance benchmark value is generated.

[0119] The calculation of the interaction coefficient of the optical equipment influencing factor includes the following specific steps:

[0120] The static optical equipment test data, dynamic optical equipment test data and optical equipment compensation parameters are aligned and standardized to generate a multi-dimensional fusion data set; the feature alignment includes timestamp matching, data sampling rate synchronization and coordinate system unification; the standardization processing adopts z-score algorithm to normalize the static positioning error, dynamic displacement variance and compensation coefficient;

[0121] A multi-factor coupling matrix is constructed, and the weight coefficients of each parameter in the multi-dimensional fusion data set are calculated by the partial least squares regression algorithm; the dimensions of the multi-factor coupling matrix include:

[0122] Static factor dimension: including positioning error mean associated with body weight, response sensitivity decay rate; dynamic factor dimension: including maximum motion trajectory offset, phase jitter amplitude caused by acceleration; environmental compensation dimension: including temperature and humidity compensation coefficient, phase drift correction amount;

[0123] The partial least squares regression algorithm comprises a double feature extraction process, specifically including: performing covariance analysis on static factor dimensions and dynamic factor dimensions to extract principal component projection vectors; taking the environmental compensation dimension as a regulating variable, and calculating the regulating effect of the compensation factor on the principal component vectors by a ridge regression algorithm; and iteratively updating the weight coefficients until the model determination coefficient is determined.

[0124] The particle swarm optimization algorithm is used to dynamically adjust the weight coefficients, the non-linear interaction effects between the factors are calculated by setting a fitness function, the weight coefficients after optimization are subjected to a significance test, and a composite interaction coefficient set comprising linear coupling coefficients and non-linear interference coefficients is generated; the composite interaction coefficient set comprises three levels of influencing factors: a primary interaction coefficient: a synergistic influence coefficient of body weight and motion acceleration on positioning accuracy; a secondary interaction coefficient: a non-linear interference coefficient of environmental humidity and phase drift on dynamic trajectory; and a tertiary interaction coefficient: a time-varying coupling coefficient of compensation parameters and static positioning error;

[0125] The composite interaction coefficient set is verified by a hold-out validation method, and when the root mean square error is lower than a preset threshold, the interaction coefficients are determined to be effective; the verification method is to substitute the composite interaction coefficient set into a laser positioning simulation model, and the root mean square error is obtained by comparing the predicted positioning accuracy with the actual measured value;

[0126] The laser positioning simulation model comprises: a human tissue optical property database storing light scattering parameters corresponding to different BMI indexes; a motion interference simulation module generating random micro-motion patterns based on a finite state machine; and an environmental noise injection unit simulating electromagnetic interference and temperature and humidity fluctuations according to the IEEE 1159 standard.

[0127] The specific calculation formula of the optical calibration scene adaptability score A is:

[0128] A=α1A1+α2A2+α3A3;

[0129] Wherein, A1 is the static optical equipment test data score, α1 is the static optical equipment test data score weight, A2 is the dynamic optical equipment test data score, α2 is the dynamic optical equipment test data score weight, A3 is the optical equipment compensation parameter score, and α3 is the optical equipment compensation parameter score weight.

[0130] The static optical equipment test data score is obtained by a positioning error comprehensive factor P e , a response sensitivity R s and a stability factor S t , and the specific calculation formula is Wherein, k1 is an adjustment parameter, χ1, χ2, χ3 are corresponding weights; the positioning error comprehensive factor P eThe Nth positioning error is calculated by nonlinear weighting, and the specific calculation formula is △x i is the positioning error of the ith measurement, ω i is the corresponding body weight of the ith measurement; the response sensitivity R s is obtained by the optical response function f(ω) and the standard deviation σ ω of the body weight, and the specific calculation formula is ω is the body weight; the stability factor S t is obtained by the average error ε and the measurement period T, and the specific calculation formula is ε(t) is the error at time t.

[0131] The dynamic optical equipment test data score is obtained by the dynamic positioning error E d , the response delay L r , the signal distortion degree D s , the dynamic stability S d and the motion complexity V m , and the specific calculation formula is where μ1, μ2, μ3, μ4 are corresponding weights, and λ is the attenuation factor;

[0132] The dynamic positioning error E d is obtained by the predicted position and the actual position x(t), and the specific calculation formula is t d is the dynamic test duration; the response delay L r is obtained by the delay time t, the signal change amplitude △s i and the sampling point number M, and the specific calculation formula is The signal distortion degree D s is obtained by the frequency spectrum S(w) of the actual signal and the frequency spectrum of the ideal signal, and the specific calculation formula is w0 is the initial frequency, and w max is the maximum frequency; the dynamic stability S d is obtained by the trajectory speed and the variance, and the specific calculation formula is The motion complexity V m is obtained by the acceleration , and the specific calculation formula is

[0133] The optical equipment compensation parameter score is obtained by the temperature deviation factor η T , the humidity deviation factor η H and the compensation effect C e , and the specific calculation formula is ν is the enhancement factor; the temperature deviation factor is obtained by the temperature influence function and the temperature deviation; the humidity deviation factor is obtained by the humidity influence function and the humidity deviation; the compensation effect is obtained by the difference between the post-compensation and the actual output value;

[0134] The positioning accuracy quantification matrix is a 7-row 6-column matrix, in which:

[0135] Row: represents the main factors affecting positioning accuracy, covering static factors, dynamic factors and environmental compensation factors;

[0136] Column: represents the key indicators for evaluating the performance of optical equipment;

[0137] Matrix element: each element is a numerical value (usually ranging from 0 to 1), indicating the degree of influence of a specific influencing factor on a specific evaluation indicator; it is calculated by standardizing data, correlation coefficient or regression analysis, etc.

[0138] The behavior of the matrix is as follows:

[0139] Body weight related positioning error (static factor): derived from the linear or nonlinear relationship between body weight and positioning error in static testing;

[0140] Response sensitivity (static factor): calculated by the error change rate caused by unit weight change;

[0141] Stability (static factor): obtained by the variance of errors within the same body weight group;

[0142] Motion trajectory deviation (dynamic factor): derived from the displacement change of limb micro-motion trajectory in dynamic testing;

[0143] Acceleration induced phase jitter (dynamic factor): calculate the phase change by acceleration data in dynamic testing;

[0144] Temperature and humidity compensation coefficient (environmental compensation factor): derived from environmental feature analysis in multi-factor deviation prediction model;

[0145] Phase drift correction amount (environmental compensation factor): calculated by the deviation correction of optical interference signal and phase detection data;

[0146] The columns of the matrix are performance parameters, respectively:

[0147] Positioning error: the deviation distance of the laser beam center position from the theoretical coordinates in static and dynamic testing;

[0148] Response delay: response time in static testing or signal delay time in dynamic testing;

[0149] Signal distortion degree: the difference between the actual signal spectrum and the ideal signal spectrum in dynamic testing;

[0150] Dynamic stability: stability coefficient of trajectory speed and variance in dynamic test;

[0151] Motion complexity: motion complexity reflected by acceleration and trajectory curvature in dynamic test;

[0152] Compensation effect: improvement degree of positioning error after environmental compensation.

[0153] The numerical values of the matrix elements are quantified in the following way:

[0154] Static factor: correlation analysis (such as Pearson correlation coefficient) or regression coefficient based on the weight-optical response correlation model;

[0155] Dynamic factor: joint feature analysis (such as LSTM model output) based on the motion-optical response coupling model;

[0156] Environmental compensation factor: bias correction coefficient and temperature and humidity compensation coefficient data based on the multi-factor bias prediction model, see Table 3.

[0157] Table 3 Positioning accuracy quantification matrix

[0158]

[0159] The comprehensive evaluation report of the acceptance criteria of the optical equipment includes static test results, dynamic test results, environmental compensation parameters, comprehensive scores and quality control index matrix, and acceptance conclusion and suggestions.

[0160] The existing model ignores environmental interference, and the present application significantly improves the stability of the equipment in a complex environment through bias prediction and compensation parameter generation. See Table 4 for details.

[0161] Table 4 Environmental adaptability comparison table

[0162] Environmental conditions Temperature and humidity compensation model Uncompensated model Temperature fluctuation (± 5 °C) Positioning deviation ≤ 0.1 mm Deviation fluctuation ± 0.4 mm Humidity change (30% - 80%) Signal drift suppression rate 95% Drift amount increased by 120% Electromagnetic interference (IEEE 1159) Error correction coefficient adaptive Not detected, deviation accumulated Extreme environmental stability Acceptance score ≥ 85 points Score < 60 points (failure)

[0163] Although embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and alterations can be made thereto without departing from the principles and spirit of the present application, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method of testing the performance of a radiotherapy laser positioning system, characterized by, The method comprises the following steps: Divide the test personnel into different groups according to their body weight, test the first positioning data of the optical positioning device under the load state, build a body weight-optical response correlation model to analyze the first positioning data, and obtain static optical device test data; the first positioning data is static position information data collected under different load states, including coordinate data of the center position of the laser beam, laser beam slope data, and deviation distance of the laser beam from the preset theoretical coordinate system; Control the test personnel to move along the preset trajectory, synchronously collect the photosensitive sensor response signal of the laser beam and the spatial coordinates of the laser tracker, generate second optical positioning data, build a motion-optical response coupling model to analyze the second optical positioning data, and obtain dynamic optical device test data; the second optical positioning data is dynamic position information data continuously collected under the micro-motion trajectory of the test personnel's limbs, also including motion trajectory, displacement change, speed, acceleration data, and continuous optical signal change data corresponding to the dynamic state of the test personnel and its timestamp; the range of the limb micro-motion is within the threshold value set by the optical positioning device; Build a multi-factor deviation prediction model to analyze the optical interference signal, phase detection data and environmental temperature and humidity parameters of the laser beam synchronously collected, and generate optical device compensation parameters; Analyze the static optical device test data, dynamic optical device test data and optical device compensation parameters, calculate the interaction coefficient of the optical device influence factor, and generate a comprehensive evaluation report of the optical calibration scene adaptability score, positioning accuracy quantization matrix and optical device acceptance benchmark value.

2. The performance test method of the radiotherapy laser positioning system according to claim 1, characterized in that: The body weight-optical response correlation model comprises a first positioning data processing layer, an associated feature extraction layer, an associated feature analysis layer and a result verification layer; The first positioning data processing layer performs preliminary processing on the first positioning data, including filtering, denoising and normalization operations; The associated feature extraction layer performs associated analysis on the processed first positioning data and the body weight data, and generates body weight and optical response associated features; The associated feature analysis layer analyzes the body weight and optical response associated features by statistical methods, obtains parameter data of the body weight change on the static performance of the optical device, including positioning error, response sensitivity and stability indicators; The result verification layer obtains the static optical device test data by statistical verification and error analysis on the parameter data.

3. The performance test method of the radiotherapy laser positioning system according to claim 1, characterized in that: The motion-optical response coupling model comprises a second optical positioning data processing layer, a dynamic feature extraction layer, a feature coupling layer and an analysis and prediction layer; The second optical positioning data processing layer performs preprocessing on the continuously collected second optical positioning data, including filtering, denoising and normalization operations; The dynamic feature extraction layer processes the dynamic position information data and optical signal change data of the limb micro-motion, extracts motion feature parameters and optical response feature parameters; The feature coupling layer couples and analyzes the motion feature parameters and the optical response feature parameters through machine learning, to generate motion and optical response combined features; The analysis and prediction layer analyzes the motion and optical response combined features to generate dynamic optical equipment test data.

4. The performance test method of the radiotherapy laser positioning system according to claim 1, characterized in that: The multi-factor bias prediction model comprises a feature extraction layer, a parameter coupling and analysis layer, and a prediction and compensation layer; The feature extraction layer extracts features from the optical interference signals, phase detection data, and environmental temperature and humidity parameters of the laser beam to obtain optical interference features, phase detection features, and environmental features; the optical interference features include interference fringe characteristics, phase information, and signal strength; the phase detection features include phase shift, change trend, and related correction information; and the environmental features include temperature change rate and humidity fluctuation; The parameter coupling and analysis layer couples the optical interference features, phase detection features, and environmental features to obtain optical and environmental coupling features; analyzes the optical and environmental coupling features to obtain the bias amount of the optical equipment in actual use due to environmental and signal fluctuations, and obtains key error indicators, including phase error, signal drift, and positioning bias caused by the environment; The prediction and compensation layer calculates and generates optical equipment compensation parameters based on the key error indicators; the optical equipment compensation parameters include bias correction coefficients and temperature and humidity compensation coefficients.

5. The performance testing method for a radiotherapy laser positioning system according to claim 1, characterized in that: The interactive coefficient of the optical equipment influence factor includes the following specific steps: Align and standardize the static optical equipment test data, dynamic optical equipment test data, and optical equipment compensation parameters to generate a multi-dimensional fusion data set; Construct a multi-factor coupling matrix and calculate the weight coefficients of each parameter in the multi-dimensional fusion data set through a partial least squares regression algorithm; Use a particle swarm optimization algorithm to dynamically adjust the weight coefficients, calculate the nonlinear interaction effects between factors by setting a fitness function, and generate a composite interactive coefficient set containing linear coupling coefficients and nonlinear interference coefficients; Perform significance test on the optimized weight coefficients to generate a composite interactive coefficient set containing linear coupling coefficients and nonlinear interference coefficients; Verify the composite interactive coefficient set through a leave-one-out method, and determine that the interactive coefficient is valid when the root mean square error is lower than a preset threshold.

Images