A proton therapy system ambient radiation influence early warning system

Abstract

This invention relates to the field of radiation early warning technology, specifically to an early warning system for the radiation impact on the environment surrounding a proton therapy system. The system includes a radiation monitoring data acquisition module, a radiation spatial distribution generation module, a radiation risk level determination module, a radiation leakage analysis module, a dynamic risk information notification module, and a treatment optimization suggestion module. In this invention, by real-time monitoring and data integration of the radiation monitoring environment, the response speed and accuracy of radiation safety early warning are improved. By utilizing spatial data and radiation intensity information, a detailed radiation distribution map can be constructed, making risk assessment more intuitive and easier to understand. Accurate assessment of radiation risk allows for specific and targeted protective measures, and potential leakage points are classified according to radiation level deviations. Dynamic notification of risk information ensures that treatment personnel receive critical safety alerts in a timely manner, optimizing the treatment process and reducing the radiation risk to patients.

Description

Technical Field

[0001] This invention relates to the field of radiation early warning technology, and in particular to an early warning system for the environmental radiation impact around a proton therapy system. Background Technology

[0002] The field of radiation early warning technology focuses on developing systems and methods for detecting and issuing early warnings of harmful radiation levels. The aim is to monitor radiation intensity in the environment in real time to ensure the safety of personnel and equipment. The field encompasses a wide range of technologies, from radiation detectors to sophisticated network-based early warning systems, including sensors, software, and communication technologies for measuring, analyzing, and responding to radiation. Typically, these systems include threshold setting functionality, automatically issuing alarms when radiation levels exceed preset safety values, thereby prompting appropriate protective measures. Furthermore, these systems can be applied in fields such as nuclear power plants, medical radiotherapy, industrial monitoring, and scientific research, where the need for radiation safety management is particularly urgent.

[0003] One such system is an early warning system for the radiation impact around proton therapy systems. This system is specifically designed to monitor radiation levels in the environment surrounding proton therapy equipment. Its primary purpose is to ensure the safety of personnel and visitors within medical facilities, ensuring that radiation levels do not exceed legal and health safety standards. The system deploys radiation detection sensors at key locations to monitor changes in radiation levels in real time. When abnormally high radiation levels are detected, it alerts relevant personnel to take appropriate measures through audio and visual alarm mechanisms. Furthermore, the system also contributes to the safe operation and maintenance management of proton therapy equipment, making it an important safety enhancement tool in the field of medical radiotherapy.

[0004] Traditional early warning systems focus on general radiation monitoring and simple threshold warnings, lacking analysis of the spatial distribution and temporal changes in radiation intensity. This limits their ability to accurately pinpoint the dynamic changes and specific locations of radiation sources, and they lack detailed spatial distribution maps and precise risk level classifications. When sudden radiation events occur, they cannot provide sufficient information, leading to untimely or overly general protective responses, and failing to effectively address specific risks within a particular area. For example, without precise risk level classification, a radiation leak could trigger unnecessary large-scale evacuations, disrupt normal medical activities, affect patient treatment, and potentially cause adverse consequences. This demonstrates that current technologies are significantly inadequate in practical application for rapid and accurate risk assessment and response. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by proposing an early warning system for the environmental radiation impact of a proton therapy system.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] An early warning system for environmental radiation impact around a proton therapy system, the system comprising:

[0008] The radiation monitoring data acquisition module is based on the proton therapy environment and monitors the radiation intensity in real time. According to the radiation intensity of the monitor and the detector location data, the values ​​are sorted and grouped according to the order of the monitoring points to obtain the radiation detection set.

[0009] The radiation spatial distribution generation module extracts radiation intensity and spatial coordinate data from the radiation detection set based on the radiation detection set, constructs a radiation distribution map within a two-dimensional spatial range, and obtains radiation distribution information;

[0010] The radiation risk level determination module, based on the radiation distribution information, marks grid points exceeding the threshold as high-risk areas, and collects them according to the location and risk level classification of the risk points to obtain risk level labeling data.

[0011] The radiation leakage analysis module compares the intensity values ​​of high-risk points with normal radiation data point by point based on the risk level labeling data, determines the leakage category by combining the leakage point source location data, classifies and collects high-risk area data, and obtains radiation leakage classification results.

[0012] Based on the radiation leakage classification results, the risk information dynamic notification module combines the regional impact range and risk category to formulate corresponding early warning notification content, which is then sent to the target receiving end through communication equipment to notify the treatment personnel and obtain leakage risk notification information.

[0013] Based on the leakage risk information notification, the treatment optimization suggestion module assesses the patient's health risk, adjusts the subsequent proton therapy dose value, and plans the proton therapy interval to obtain optimized treatment suggestions.

[0014] Optionally, the radiation detection set includes monitoring point location information, radiation intensity values, and timestamps; the radiation distribution information includes grid coordinate points, grid intensity values, and two-dimensional spatial range; the risk level labeling data includes high-risk area coordinates, risk level classification, and the number of high-risk points; the radiation leakage classification results specifically include leakage source location, abnormal intensity values, and high-risk area categories; the leakage risk notification information includes risk area coordinates, leakage type classification, and regional impact range; and the optimized treatment recommendations include dose adjustment parameters, treatment interval values, and equipment operating status parameters.

[0015] Optionally, the radiation monitoring data acquisition module includes:

[0016] The radiation intensity extraction submodule is based on the proton therapy environment. It uses radiation detectors pre-installed at the monitoring points to collect radiation intensity data recorded by each detector, extract the intensity value of each detection point and the corresponding monitoring location, and obtain the radiation intensity information of the detection point.

[0017] The monitoring point collection submodule, based on the radiation intensity information of the detection points, calls the monitoring location and radiation intensity numerical data of each detection point, classifies each group of monitoring point locations and values ​​by region, and organizes them into a set to obtain the monitoring point location intensity set.

[0018] The timestamp grouping and sorting submodule extracts the timestamp information of the monitoring points based on the set of monitoring point locations and intensities, collects and sorts the monitoring point data within the same time period, and groups and sorts the intensity values ​​and location information corresponding to the monitoring points in chronological order to obtain the radiation detection set.

[0019] Optionally, the radiation spatial distribution generation module includes:

[0020] The spatial grid construction submodule extracts the spatial coordinate values ​​of the monitoring points based on the radiation detection set, divides the region into grids according to the coordinate range, and constructs the monitoring area into a spatial grid model by combining gridding rules.

[0021] The intensity value distribution calculation submodule, based on the spatial grid model, extracts the spatial coordinates of grid points and their corresponding radiation intensity values ​​according to the time series grouped intensity data, and calculates the radiation intensity value distribution relationship point by point according to the distribution between grid points to obtain the spatial distribution data of intensity values;

[0022] The two-dimensional image generation submodule extracts the radiation intensity values ​​and corresponding grid coordinate points based on the spatial distribution data of the intensity values, and constructs a visualized two-dimensional distribution map of the radiation intensity values ​​of the grid points according to the two-dimensional coordinate layout rules, thereby obtaining radiation distribution information.

[0023] Optionally, the radiation risk level determination module includes:

[0024] The risk threshold comparison submodule extracts the radiation intensity values ​​from the grid point data based on the radiation distribution information, compares them point by point with the preset risk level threshold, identifies grid point data that exceeds the threshold, and obtains grid point data with risk exceeding the threshold.

[0025] The high-risk point marking submodule extracts the coordinate and intensity values ​​of grid points that exceed the risk threshold based on the risk-exceeding-threshold grid point data, marks the grid points, defines them as high-risk points, and obtains high-risk point marking information;

[0026] The risk level collection submodule assesses the risk level of high-risk points based on the high-risk point marking information and the radiation intensity value of the high-risk points, and collects and classifies the high-risk points according to the preset risk level classification standard to obtain risk level labeling data.

[0027] Optionally, the formula for assessing the risk level of a high-risk point is:

[0028]

[0029] Among them, R i S represents the risk level value of the i-th grid point. i This represents the radiation intensity value at the i-th grid point. σ represents the average value of the radiation intensity at all grid points. S T represents the standard deviation of the radiation intensity values ​​at all grid points. i T represents the time dimension marker value of the i-th grid point. max w1 represents the maximum value of the time dimension marker among all grid points, and w2 are weighting coefficients.

[0030] Optionally, the radiation leakage analysis module includes:

[0031] The intensity deviation calculation submodule extracts the radiation intensity values ​​of grid points in high-risk areas and the corresponding leakage source location data based on the risk level labeling data. It then compares the radiation intensity values ​​of the grid points with the average value of normal radiation data point by point, calculates the deviation of the current radiation intensity value from the average value of normal radiation, and obtains the radiation intensity deviation data.

[0032] The leakage type classification submodule classifies the radiation intensity deviation values ​​of high-risk areas based on the radiation intensity deviation data and the spatial location of the leakage point source. By analyzing the deviation characteristics of multiple areas and the type of leakage point source, it determines the leakage category of each area and obtains leakage type judgment information.

[0033] The high-risk area labeling submodule extracts the radiation intensity value, spatial range, and corresponding leakage category information of the high-risk area based on the leakage type judgment information, and labels the information item by item into the high-risk area grid to obtain the radiation leakage classification result.

[0034] Optionally, the risk information dynamic notification module includes:

[0035] Based on the radiation leakage classification results, the leakage information extraction submodule extracts the location data, risk level data, and leakage point source data of multiple high-risk areas, and collects each extracted data item by item to obtain a high-risk area information set.

[0036] The dynamic notification content generation submodule extracts data on the location, risk level, and leakage source of the high-risk area based on the high-risk area information set. It matches and associates the data with the preset regional impact range and risk category analysis standards, generates the required content format for the notification according to preset rules, collects the notification information and adds regional location and risk classification descriptions to generate dynamic notification content for high-risk areas.

[0037] The regional risk data matching submodule matches the high-risk area data in the dynamic notification content with the preset target receiving end information based on the high-risk area dynamic notification content. It then sends the data to the target receiving end through communication devices, including mobile phones and computers, to notify the treatment personnel and generate leakage risk notification information.

[0038] Optionally, the treatment optimization suggestion module includes:

[0039] Based on the leakage risk notification information, the parameter joint adjustment submodule extracts radiation intensity data, area range data, and patient exposure duration data, and combines the patient exposure status with preset health risk assessment standards to assess the health risk of radiation to the patient and generate a health risk assessment result.

[0040] The dose update calculation submodule adjusts the dose value of subsequent proton therapy based on the health risk assessment results, the patient's exposure health risk level data, and the patient's current treatment dose parameters, to obtain the treatment dose update parameters.

[0041] The treatment interval optimization submodule, based on the treatment dose update parameters and combined with the patient's treatment time planning data, re-plans the proton therapy time interval according to the impact of radiation exposure and treatment effect, and obtains optimized treatment recommendations.

[0042] Optionally, the formula for estimating the health risk of radiation to the patient is:

[0043]

[0044] Among them, H r D represents the patient's health risk index, and D represents the cumulative radiation dose value within the leak area. safe T represents the set safe radiation dose threshold. e T represents the cumulative exposure time of patients in high-radiation areas. max R represents the maximum exposure time within the leak area. H R represents the health risk level of the radiation leak area. H,max V1 represents the preset maximum health risk level value, and V2 and V3 are the weighting coefficients for radiation dose deviation, exposure duration, and health risk level weight, respectively.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0046] In this invention, real-time monitoring and data integration of the radiation monitoring environment improve the response speed and accuracy of radiation safety early warning. Detectors deployed around proton therapy equipment can accurately capture radiation intensity and its changes, enabling rapid identification and response to any abnormal radiation levels. By utilizing spatial data and radiation intensity information, detailed radiation distribution maps can be constructed, making risk assessment more intuitive and easier to understand. Precise assessment of radiation risk allows for specific and targeted protective measures, improving the safety of personnel and equipment. High-risk areas can be identified, and potential leakage points can be classified based on radiation level deviations, promoting effective crisis management. Dynamically reporting risk information ensures that treatment personnel receive critical safety alerts in a timely manner, optimizing treatment processes and reducing radiation risks for patients. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a system flowchart of the present invention;

[0049] Figure 2 This is a schematic diagram of the system framework of the present invention;

[0050] Figure 3 This is a flowchart of the radiation monitoring data acquisition module of the present invention;

[0051] Figure 4 This is a flowchart of the radiation spatial distribution generation module of the present invention;

[0052] Figure 5 This is a flowchart of the radiation risk level determination module of the present invention;

[0053] Figure 6 This is a flowchart of the radiation leakage analysis module of the present invention;

[0054] Figure 7 This is a flowchart of the risk information dynamic notification module of the present invention;

[0055] Figure 8 This is a flowchart of the treatment optimization suggestion module of the present invention. Detailed Implementation

[0056] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0057] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0058] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, their intended meanings are consistent. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, their intended meanings are consistent.

[0059] In this embodiment of the invention, sometimes a subscript such as W1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0060] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0061] Please see Figure 1 An early warning system for the impact of environmental radiation on a proton therapy system, the system comprising:

[0062] The radiation monitoring data acquisition module is based on the proton therapy environment. It uses radiation detectors pre-installed at the monitoring points to monitor radiation intensity in real time. Based on the radiation intensity and detector location data, the data of each monitoring point is collected according to the timestamp. Combining the timestamp, the location information and intensity value corresponding to each group of data are extracted. The data are sorted and grouped according to the order of the monitoring points to obtain the radiation detection set.

[0063] The radiation spatial distribution generation module is based on a radiation detection set. It extracts radiation intensity and spatial coordinate data from the set, performs gridded calculation of radiation intensity values ​​according to coordinate points, establishes the intensity value distribution relationship between grid points, and constructs a radiation distribution map within a two-dimensional spatial range based on the grid distribution to obtain radiation distribution information.

[0064] The radiation risk level determination module extracts radiation intensity values ​​from grid data based on radiation distribution information, compares each point with a preset risk level threshold, marks grid points that exceed the threshold as high-risk areas, and collects them according to the location and risk level classification of the risk points to obtain risk level labeling data.

[0065] The radiation leakage analysis module extracts the radiation intensity and leakage source location of high-risk grids from the risk level labeling data. It compares the intensity value of high-risk points with normal radiation data point by point, calculates the deviation of the current intensity value from the average normal radiation value, and determines the leakage category by combining the leakage source location data. It then classifies and collects high-risk area data and labels the corresponding leakage type to obtain the radiation leakage classification results.

[0066] The risk information dynamic notification module extracts the location, risk level, and leak point source data of high-risk areas from the radiation leakage classification results. Combined with the regional impact range and risk category, it formulates corresponding early warning notification content and sends it to the target receiving end through communication devices, including mobile phones and computers, to notify treatment personnel and obtain leakage risk notification information.

[0067] The treatment optimization recommendation module is based on leakage risk information reports. It assesses the patient's health risk according to radiation intensity, area range, and patient exposure time. Based on the health risk, it adjusts the subsequent proton therapy dose and plans the proton therapy interval to obtain optimized treatment recommendations.

[0068] The radiation detection dataset includes monitoring point location information, radiation intensity values, and timestamps. Radiation distribution information includes grid coordinates, grid intensity values, and two-dimensional spatial range. Risk level labeling data includes high-risk area coordinates, risk level classification, and the number of high-risk points. The radiation leakage classification results specifically include the leakage source location, abnormal intensity value, and high-risk area category. Leakage risk notification information includes risk area coordinates, leakage type classification, and regional impact range. Optimized treatment recommendations include dose adjustment parameters, treatment interval values, and equipment operating status parameters.

[0069] Please see Figure 2 and Figure 3 The radiation monitoring data acquisition module includes a radiation intensity extraction submodule, a monitoring point collection submodule, and a timestamp grouping and processing submodule.

[0070] The radiation intensity extraction submodule is based on the proton therapy environment. It uses radiation detectors pre-installed at the monitoring points to collect radiation intensity data recorded by each detector, extract the intensity value of each detection point and the corresponding monitoring location, and obtain the radiation intensity information of the detection point.

[0071] Based on the radiation detector records in the proton therapy environment, the radiation intensity data collected by the pre-installed detectors at each monitoring point is read item by item. The output data of the detectors is analyzed according to the time series. During the analysis, the real-time radiation intensity value of each monitoring point needs to be extracted and compared with the preset geographical location information of the detector to confirm the geographical location of the detector data. The analysis steps include data verification, noise reduction, and outlier removal. In the verification stage, the physical range of each data point needs to be judged. The validity of the data is determined by checking whether it is within the effective measurement range of the device (e.g., the common radiation intensity range is 0.1-10 mSv). After removing data that are out of range, the sliding window averaging method is used to remove random noise from the continuously recorded detection point data. The remaining data is combined with the calibration location information of the detector to generate radiation intensity data for each monitoring point. The output radiation intensity value matches the geographical location of each monitoring point. These intensity values ​​are summarized into the detection point radiation intensity information table based on the calibration results. The detection point radiation intensity information includes the real-time radiation intensity value of each detection point and its physical location.

[0072] The monitoring point collection submodule, based on the radiation intensity information of the detection points, calls the monitoring location and radiation intensity numerical data of each detection point, classifies each group of monitoring point locations and values ​​by region, and organizes them into a set to obtain the monitoring point location intensity set.

[0073] Based on the radiation intensity information of the monitoring points, the monitoring locations and radiation intensity values ​​of the monitoring points are classified by region. The geographical location information of all monitoring points is imported into the region division model. The region division model needs to divide all monitoring points into regions based on a preset grid division standard. Each region division is based on physical distance. By checking the coordinate range of the grid points, the monitoring points are divided into different regions according to their coordinates. At the same time, the intensity values ​​of the monitoring points in each region are extracted. After classification, the data is sorted according to the order of the monitoring points in the region. Finally, the data is output as a set in the form of a monitoring point location intensity set. The set contains the monitoring location and corresponding radiation intensity values ​​of all monitoring points in each region. Each set is stored as a region for subsequent data grouping, processing and analysis.

[0074] The timestamp grouping and sorting submodule extracts the timestamp information of the monitoring points based on the intensity set of the monitoring point locations, collects and sorts the monitoring point data within the same time period, and groups and sorts the intensity values ​​and location information of the monitoring points according to the time order to obtain the radiation detection set.

[0075] Based on the timestamp information in the intensity set of monitoring points, the monitoring point data within each time period needs to be grouped and organized. During the data organization process, the timestamp recorded by each monitoring point must first be extracted, and its recording interval must be checked to see if it meets the specified time range. For example, for real-time monitoring data, the time interval is usually set to within 1 minute. Timestamp data that exceeds the range needs to be grouped and categorized. For the categorized timestamp data, by comparing it with the monitoring point location and radiation intensity data of the corresponding area, all monitoring point data within the same time period are integrated into a single group. After grouping, the data is rearranged according to the time order to ensure that the data can completely present the trend of radiation intensity changing over time, and organized into a radiation detection set. The radiation detection set contains the intensity values ​​and location information of all monitoring points within each time period arranged in chronological order, which is used for subsequent spatial distribution analysis.

[0076] Please see Figure 2 and Figure 4 The radiation spatial distribution generation module includes a spatial grid construction submodule, an intensity value distribution calculation submodule, and a two-dimensional image generation submodule;

[0077] The spatial grid construction submodule is based on the radiation detection set, extracts the spatial coordinate values ​​of the monitoring points, divides the area into grids according to the coordinate range, and constructs the monitoring area into a spatial grid model by combining gridding rules.

[0078] Based on the radiation detection set, the spatial coordinate values ​​of the monitoring points are extracted and used for grid division. The geographic spatial coordinate values ​​of each monitoring point are extracted. By verifying the consistency between the calibrated coordinates and the actual measured coordinates of the monitoring points, abnormal points with coordinate deviations exceeding the preset range are eliminated. Then, an equidistant division method is adopted. The total area of ​​the grid division is determined according to the maximum and minimum values ​​of the monitoring point coordinate range. The monitoring area is divided into several small areas according to the target standard unit grid. The unique identifier of each grid is composed of its lower left corner coordinates. The monitoring point data in each grid is classified and assigned according to its coordinate position. At the same time, it is checked whether there are empty grids or abnormal grids (i.e., grids without monitoring point data). Empty grids are marked and abnormal points are eliminated to obtain a complete spatial grid model. The spatial grid model contains the coordinate range of each grid unit and the list of monitoring point data it contains.

[0079] The intensity value distribution calculation submodule is based on a spatial grid model. It extracts the spatial coordinates of grid points and their corresponding radiation intensity values ​​according to the time series grouped intensity data. It calculates the radiation intensity value distribution relationship point by point according to the distribution between grid points to obtain the spatial distribution data of intensity values.

[0080] Based on the spatial grid model, it is necessary to calculate the distribution relationship of radiation intensity values ​​point by point according to the time series grouped intensity data, extract the spatial coordinates of each grid point and the radiation intensity data of the time series group, check the integrity of each time series data and remove missing values, and then classify the intensity data in each grid according to the time point, and distribute the radiation intensity data of the same time period to the grid points, calculate the average radiation intensity value of each grid point point by point, and at the same time, combine the spatial interpolation method to calculate the gradient of the spatial distribution based on the distance between adjacent grid points and the difference in radiation intensity, check whether there are any anomalies in the gradient data (i.e., the gradient exceeds the set safety threshold range), and for points that exceed the threshold, the intensity distribution value is readjusted using the distance weight algorithm, and the corrected intensity data is output as the spatial distribution data of intensity values, which includes the average intensity value and spatial gradient information of each grid point.

[0081] The two-dimensional image generation submodule extracts the radiation intensity values ​​and corresponding grid coordinate points based on the spatial distribution data of intensity values, and constructs a visual two-dimensional distribution map of the radiation intensity values ​​of the grid points according to the two-dimensional coordinate layout rules to obtain radiation distribution information;

[0082] Based on the spatial distribution data of intensity values, the radiation intensity value of each grid point and its corresponding grid coordinate point are extracted. By checking the integrity of the spatial distribution data, it is ensured that each grid point contains complete intensity value and coordinate information. For missing grid points, the intensity value is filled in by interpolation. According to the two-dimensional coordinate layout rules, the coordinate value of each grid point is mapped onto the two-dimensional plane. At the same time, the radiation intensity value is converted into a color gradient value through color mapping. The color range usually represents the increase of radiation intensity from blue to red. The generated two-dimensional distribution map is verified to ensure that the color distribution is consistent with the actual intensity data. Finally, the complete radiation distribution information is output through visualization tools. The radiation distribution information includes the spatial coordinates of each grid point and the visualized intensity value image.

[0083] Please see Figure 2 and Figure 5 The radiation risk level determination module includes a risk threshold comparison submodule, a high-risk point marking submodule, and a risk level aggregation submodule.

[0084] The risk threshold comparison submodule extracts the radiation intensity values ​​from the grid point data based on radiation distribution information, compares them point by point with the preset risk level threshold, identifies grid point data that exceeds the threshold, and obtains grid point data with risk exceeding the threshold.

[0085] Based on radiation distribution information, radiation intensity values ​​are extracted from grid point data and compared point-by-point with preset risk level thresholds. The radiation intensity value of each grid point is extracted, ensuring that the measurement data for each intensity value is complete and within a reasonable range (e.g., within the typical detection range of 0.1 mSv to 10 mSv). Outliers are marked and removed. Then, the preset risk level threshold is invoked, and the threshold standard for each grid point is retrieved from the database. The threshold standard is typically set according to the radiation safety requirements of the specific environment. By comparing the radiation intensity value of each grid point with the corresponding threshold point point by point, grid point data exceeding the threshold are filtered out. Grid point intensity values ​​exceeding the threshold are marked as high-risk intensity values, and their corresponding grid point coordinates are recorded. All grid point data exceeding the threshold are summarized to generate risk-critical grid point data containing grid point intensity values ​​and corresponding spatial coordinates. This risk-critical grid point data is used for subsequent high-risk point marking analysis.

[0086] The high-risk point marking submodule extracts the coordinate and intensity values ​​of grid points that exceed the risk threshold based on the grid point data, marks the grid points as high-risk points, and obtains high-risk point marking information.

[0087] Based on the grid point data exceeding the risk threshold, it is necessary to extract and mark the coordinates and intensity values ​​of grid points that exceed the risk threshold. This involves extracting the radiation intensity value and spatial coordinates of the grid points to ensure that each data point contains complete intensity and spatial coordinate information. For grid points with missing intensity values, the weighted average of adjacent grid point data within the region is used to fill in the gaps. For grid points with missing coordinates, the original records are consulted for correction. All grid point data exceeding the threshold are then verified to ensure that the intensity values ​​indeed exceed the threshold and the markings are correct. By comparing the radiation intensity values ​​of the grid points with the preset high-risk standard, grid points exceeding the high-risk threshold are marked as high-risk points, and their coordinates and radiation intensity values ​​are recorded. The marking information is then compiled and output, generating high-risk point marking information containing grid point intensity values, spatial coordinates, and high-risk markings. This high-risk point marking information provides the basic data for subsequent risk level aggregation.

[0088] The risk level collection submodule assesses the risk level of high-risk points based on the high-risk point marking information and the radiation intensity value of the high-risk points, and collects and classifies the high-risk points according to the preset risk level classification standards to obtain risk level labeling data.

[0089] The formula for assessing the risk level of a high-risk location is:

[0090]

[0091] Among them, R i S represents the risk level value of the i-th grid point.i This represents the radiation intensity value at the i-th grid point. σ represents the average value of the radiation intensity at all grid points. S T represents the standard deviation of the radiation intensity values ​​at all grid points. i T represents the time dimension marker value of the i-th grid point. max w1 represents the maximum value of the time dimension marker among all grid points, and w2 are weighting coefficients.

[0092] Parameter meanings and acquisition methods:

[0093] S i : The radiation intensity value at the i-th grid point. Obtained in real time by a radiation detector installed at this grid point, and the unit is millisieverts (mSv).

[0094] The average value of the radiation intensity values ​​of all grid points is calculated by summing the radiation intensity values ​​of all grid points and then dividing by the total number of grid points N. The unit is millisieverts (mSv).

[0095] σ S Standard deviation of radiant intensity values ​​across all grid points. This measure reflects the degree of dispersion of radiant intensity values, indicating how much the radiant intensity at each grid point deviates from the average value, expressed in millisieverts (mSv).

[0096] T i : Cumulative exposure duration at the i-th grid point. Obtained from time data recorded by a radiation detector, in hours (h).

[0097] T max : The maximum cumulative exposure time across all grid points. This is achieved by comparing the T values ​​of all grid points. i The value is selected as the maximum value, and the unit is hours (h).

[0098] w1 and w2: Weighting coefficients in the risk level aggregation algorithm. They are used to adjust the influence of radiation intensity deviation and time dimension on the risk level; the specific values ​​are set according to the actual situation.

[0099] Calculation example:

[0100] Given the following data: total number of grid points N: 5; radiation intensity value S at each grid point i (Unit: mSv): S1 = 2.5, S2 = 3.0, S3 = 2.8, S4 = 3.2, S5 = 2.9; Cumulative exposure time T at each grid point i (Unit: h): T1 = 10, T2 = 15, T3 = 12, T4 = 18, T5 = 14; Weighting coefficients: w1 = 0.6, w2 = 0.4;

[0101] Calculate the average radiation intensity value

[0102]

[0103] Calculate the standard deviation σ of the radiation intensity values S :

[0104]

[0105] Determine the maximum cumulative exposure time T max :

[0106] T max =max(T1,T2,T3,T4,T5)=18h;

[0107] Calculate the risk level value R1 for the first grid point (i=1):

[0108] Calculate the standardized value of the radiation intensity deviation:

[0109]

[0110] Calculate the logarithm of the time ratio:

[0111]

[0112] Apply weighted coefficients and sum:

[0113]

[0114] Rounding down yields the risk level value R1:

[0115]

[0116] The above calculations yielded a risk level of 2 for the first grid point. This indicates that the radiation risk at this grid point falls under the second level of the preset risk level classification standard, suggesting that appropriate protective measures need to be taken.

[0117] Please see Figure 2 and Figure 6 The radiation leakage analysis module includes an intensity deviation calculation submodule, a leakage type classification submodule, and a high-risk area labeling submodule;

[0118] The intensity deviation calculation submodule extracts the radiation intensity values ​​of grid points in high-risk areas and the corresponding leakage source location data based on the risk level labeling data. It then compares the radiation intensity values ​​of the grid points with the average value of normal radiation data point by point to calculate the deviation of the current radiation intensity value from the average value of normal radiation, thus obtaining the radiation intensity deviation data.

[0119] Based on risk level labeling data, radiation intensity values ​​and leak source location data of grid points in high-risk areas are extracted. Radiation intensity values ​​for each grid point are retrieved from the database and compared point-by-point with the spatial location data of the leak source. The completeness of the grid point radiation intensity data is verified, and missing or outlier values ​​are removed or supplemented. For supplementation, correction can be performed using interpolation methods of radiation intensity data from surrounding grid points, such as inverse distance weighted interpolation, assigning higher weights to grid points closer to the leak source. The effective intensity value of each grid point is calculated. Then, the radiation intensity value of each grid point is compared with the average value of normal radiation data. Normal radiation data can be calculated from uncontaminated reference point data within the monitoring area, and its average value is obtained according to the time series. The current radiation intensity value of each grid point is subtracted from the normal average value to calculate the deviation. All calculations are ensured to be performed in uniform units. Simultaneously, all grid point data are reordered according to spatial coordinates, and radiation intensity deviation data containing the radiation intensity deviations of each grid point is output. This radiation intensity deviation data is used for subsequent leak type classification analysis.

[0120] The leakage type classification submodule classifies the radiation intensity deviation values ​​of high-risk areas based on radiation intensity deviation data and the spatial location of leakage point sources. By analyzing the deviation characteristics of multiple areas and the type of leakage point sources, it determines the leakage category of each area and obtains leakage type judgment information.

[0121] Based on radiation intensity deviation data, it is necessary to classify and analyze the radiation intensity deviation values ​​of high-risk areas by combining the spatial location of the leak source. The radiation intensity deviation value and corresponding spatial coordinate information of each grid point within the high-risk area are extracted. The spatial coordinate information is then partitioned, dividing each high-risk area into multiple sub-regions. Within each sub-region, the grid point data is divided into three layers—near, middle, and far—based on their distance from the leak source. The distribution characteristics of the radiation intensity deviation values ​​of each layer are then analyzed. By calculating the average and standard deviation of the radiation intensity deviation values ​​for each layer, the attenuation law of radiation intensity with distance is determined. Combined with the type of leak source, such as equipment failure, natural attenuation, or pipeline rupture, each sub-region is classified. The classification method can be based on empirical rules. For example, if the radiation intensity deviation is significantly higher in the near region than in other regions and decays irregularly, it can be identified as a local equipment failure. If the radiation intensity decays exponentially with distance, it may be a natural leak. After confirming the accuracy of the classification, leak category information for each sub-region is generated, outputting leak type judgment information containing the radiation intensity deviation values ​​of each high-risk area and their corresponding leak categories.

[0122] The high-risk area labeling submodule extracts the radiation intensity value, spatial range and corresponding leakage category information of the high-risk area based on the leakage type judgment information, and labels the information item by item into the high-risk area grid to obtain the radiation leakage classification result.

[0123] Based on the leakage type assessment information, it is necessary to extract the radiation intensity value, spatial range, and corresponding leakage category information of high-risk areas. Each grid cell in the high-risk area is then labeled. Radiation intensity data within each high-risk area is extracted from the leakage type assessment information, and the intensity values ​​are assigned to the corresponding grid cells according to their spatial coordinates. The integrity of the spatial coordinates is checked to ensure that each grid cell matches the leakage category information. The high-risk areas are then regrouped according to their spatial range, with each group containing independent high-risk areas. Grid cells within each group are categorized based on the leakage category. The categorized grid cell data is then labeled, including the leakage category, radiation intensity value, and spatial coordinate range. After labeling, the data is output in the order of the grid cells, generating a radiation leakage classification result containing the grid cell radiation intensity value, spatial range, and leakage category. This classification result can be used for subsequent risk assessment and area management.

[0124] Please see Figure 2 and Figure 7 The risk information dynamic notification module includes a leakage information extraction submodule, a dynamic notification content generation submodule, and a regional risk data matching submodule;

[0125] The leakage information extraction submodule extracts location data, risk level data, and leakage point source data of multiple high-risk areas based on the radiation leakage classification results. It then aggregates each extracted data item to obtain a set of high-risk area information.

[0126] Based on the radiation leak classification results, location data, risk level data, and leak source data for multiple high-risk areas are extracted. The extracted data are then systematically aggregated. The specific location of each high-risk area, including its center point coordinates and boundary information, is extracted from the radiation leak classification results. Subsequently, the risk level data for each high-risk area is extracted. Based on the risk levels recorded in the classification results, all areas are uniformly numbered to ensure that each risk level is uniquely and clearly labeled. Next, the leak source data corresponding to the high-risk areas is extracted. Leak source information includes the leak type (e.g., equipment failure, natural leakage), the spatial location of the leak point, and the leak intensity. The data is then systematically aggregated according to the location of each area, and the correlation between leak points and high-risk areas is verified. The spatial distance from the leak point to the center point of the high-risk area is calculated to ensure accurate data correlation. A high-risk area information set containing the location, risk level, and leak source information of all high-risk areas is obtained, providing complete input for subsequent processing.

[0127] The dynamic notification content generation submodule is based on a high-risk area information set. It extracts data on area location, risk level and leakage source, and combines it with preset regional impact range and risk category analysis standards to match and associate the data. It generates the required content format for the notification according to preset rules, collects the notification information and adds regional location and risk classification descriptions to generate dynamic notification content for high-risk areas.

[0128] Based on a high-risk area information set, the system extracts data on area location, risk level, and leak source. Combining this with preset regional impact range and risk category analysis standards, the data is matched and correlated. The system generates the required notification content format according to preset rules. It then calls the regional impact range standard, calculating the radius of influence range for each high-risk area based on its center point and boundary information. The system maps the location coordinates of each high-risk area to its impact range to generate regional impact range data. Subsequently, it calls the risk category analysis standard to analyze the correspondence between the risk level of the high-risk area and the leak source data. For example, it matches the type of leak source (e.g., equipment failure, external pollution) with the pattern of radiation intensity distribution within the area to confirm the area's risk category. The matched data is then collected as the initial content for the notification information. The content is organized according to a preset notification format, including recording the area location in latitude and longitude format, converting the risk level into more readable descriptive text, and adding explanations of the risk category. This generates complete dynamic notification content for high-risk areas. The notification content includes detailed descriptions of the location, risk level, and leak source of each high-risk area, providing structured input data for subsequent notification operations.

[0129] The regional risk data matching submodule matches the high-risk area data in the dynamic notification content of high-risk areas with the preset target receiving end information based on the dynamic notification content of high-risk areas. It then sends the data to the target receiving end through communication devices, including mobile phones and computers, to notify the treatment personnel and generate leakage risk notification information.

[0130] Based on the dynamic notification content of high-risk areas, the high-risk area data in the notification content is matched with the preset target receiving end information, and sent to the target receiving end through communication devices to notify the treatment personnel. First, the key data of each high-risk area in the dynamic notification content is extracted, including the area location, risk level, and leakage category description. Then, the target receiving end information database is called to classify and match the receiving end information. For example, receiving ends with device operation permissions are matched to the corresponding leakage point source device failure notification, and high-risk area information related to patient health is matched to the treatment personnel. Customized notification content is generated according to the information type of each receiving end. The matched high-risk area data is generated into a notification message in the corresponding format according to the receiving end device type (such as mobile phone or computer). After verifying the integrity of the message, it is sent through the communication device. The sending status and receiving status of each message are recorded to generate leakage risk notification information containing all notification content and their sending status. The notification information provides a detailed basic record for subsequent tracking and processing.

[0131] Please see Figure 2 and Figure 8 The treatment optimization suggestion module includes a parameter joint adjustment submodule, a dose update calculation submodule, and a treatment interval optimization submodule;

[0132] The parameter joint adjustment submodule extracts radiation intensity data, area range data, and patient exposure duration data based on leakage risk notification information. It then combines the patient exposure information with preset health risk assessment standards to assess the health risks of radiation to patients and generate health risk assessment results.

[0133] The formula for estimating the health risks of radiation to patients is:

[0134]

[0135] Among them, H r D represents the patient's health risk index, and D represents the cumulative radiation dose value within the leak area. safe T represents the set safe radiation dose threshold. e T represents the cumulative exposure time of patients in high-radiation areas. max R represents the maximum exposure time within the leak area. H R represents the health risk level of the radiation leak area. H,max V1 represents the preset maximum health risk level value, and V2 and V3 are the weighting coefficients for radiation dose deviation, exposure duration, and health risk level weight, respectively.

[0136] The meaning and acquisition method of the parameters:

[0137] D: Cumulative radiation dose value, representing the cumulative radiation dose to the patient during exposure within the leak area, measured in millisieverts (mSv), and is derived from real-time dose data recorded by radiation detectors installed within the leak area.

[0138] D safe Safe radiation dose thresholds are safe radiation dose limits set according to international radiation protection standards (such as the International Atomic Energy Agency (IAEA) or the International Commission on Radiation Protection (ICRP). They are used to determine whether the safe range has been exceeded. The unit is millisieverts (mSv). They can be obtained directly from international or national standard documents. For example, the ICRP limits the annual dose to the general public to 1 mSv and to occupationally exposed individuals to 20 mSv.

[0139] T e Cumulative exposure time represents the total exposure time of a patient in a high-radiation area, expressed in hours (h). It is calculated by combining the patient's trajectory tracking record system with timestamp data to count and accumulate the time periods when the patient enters and leaves the high-radiation area.

[0140] T max Maximum exposure duration: The maximum exposure duration among all patients in the leak area, expressed in hours (h), and is determined by comparing the exposure duration data recorded from the trajectory of all patients.

[0141] R H Health risk level value: This value represents the health risk level of the radiation leak area. It is calculated based on a risk assessment model and is used to quantify the radiation risk level of the leak area. The unit is dimensionless and is extracted directly from the leak risk notification information. It is usually calculated based on the results of the grid-based risk assessment within the area.

[0142] R H,max Maximum health risk level value: The preset highest health risk level, used to normalize the risk levels of different regions. The unit is dimensionless and is set according to the risk level classification standard. For example, risk levels are usually divided into 1 to 5, with the maximum risk level being 5.

[0143] V1, V2, and V3: Weighting coefficients, used to adjust the weights of radiation dose deviation, exposure duration, and health risk level on the health risk index, respectively. They are set based on expert experience or statistical analysis, combined with specific scenario requirements, such as selecting the optimal weights through a weight optimization model.

[0144] Calculation example:

[0145] The following data is set: D = 15 mSv: the patient's cumulative radiation dose, calculated from the detector's cumulative data; D safe =10mSv: Safe radiation dose threshold, set according to international radiation protection standards; Te =8h: Patient exposure duration, calculated through trajectory recording statistics; T max =12h: Maximum exposure duration, calculated from data from all patients; R H =3: Health risk level value, derived from the risk assessment model of the leak area; R H,max =5: Maximum health risk level, preset to the highest level; weighting coefficients: V1=0.6, V2=0.3, V3=0.1.

[0146] Calculate the normalized value of radiation dose deviation:

[0147]

[0148] Calculate the normalized square root of the exposure duration:

[0149]

[0150] Calculate the normalized value of the health risk level:

[0151]

[0152] Apply weighted coefficients and sum:

[0153] Substitute the calculation result into the formula

[0154] 0.6·0.5+0.3·0.816+0.1·0.6=0.3+0.2448+0.06=0.6048;

[0155] Use the round-up operation

[0156] H r =1;

[0157] The calculated patient health risk index is H. r =1 indicates that the patient's health risk is at the lowest level and no additional measures are needed immediately.

[0158] The dose update calculation submodule adjusts the dose value of subsequent proton therapy based on the health risk assessment results, the patient's exposure health risk level data, and the patient's current treatment dose parameters, to obtain the treatment dose update parameters.

[0159] Based on the health risk assessment results, and according to the patient's exposure health risk level data, combined with the patient's current treatment dose parameters, the dose value of subsequent proton therapy is adjusted. First, the risk level information in the health risk assessment results is extracted, and the corresponding treatment dose adjustment range is matched according to the risk level as mild, moderate, and severe. For example, mild risk corresponds to 95%-100% of the current treatment dose, moderate risk corresponds to 90%-95%, and severe risk corresponds to 85%-90%. The patient's current treatment dose parameters are extracted, and the dose parameters are matched and calculated with the adjustment range corresponding to the risk level. For example, a weighted method is used to calculate the new treatment dose value. When weighting the calculation, the severity of the patient's condition and treatment tolerance are combined, with the condition weight set to 0.6 and the tolerance weight set to 0.4. The patient's current dose value is adjusted according to the risk level, and the updated treatment dose parameters are output. The updated treatment dose parameters provide input data for the subsequent optimization of treatment time intervals.

[0160] The treatment interval optimization submodule, based on the treatment dose update parameters and combined with the patient's treatment time planning data, re-plans the time interval of proton therapy according to the impact of radiation exposure and treatment effect, and obtains optimized treatment suggestions.

[0161] Based on the updated treatment dose parameters, it is necessary to combine the patient's treatment time planning data and re-plan the proton therapy interval according to the impact of radiation exposure and treatment effect. The latest dose value in the updated treatment dose parameters is extracted and compared with the patient's treatment time planning data to check whether the current treatment plan can meet the latest dose requirements. Then, the patient's radiation exposure data during the treatment interval is extracted, including exposure time, radiation intensity, and cumulative dose. The data is integrated into a single cumulative radiation dose curve according to the time series and analyzed in conjunction with the changing trend of the patient's treatment effect. During the analysis, the patient's treatment tolerance level and recovery rate are calculated. By comprehensively considering the changes in the patient's cumulative radiation dose, treatment tolerance level, and treatment effect, the treatment interval is dynamically adjusted, and the optimized treatment interval is output. The treatment interval data and the updated treatment dose parameters together constitute the optimized treatment suggestions, providing a basis for adjusting the subsequent proton therapy plan.

[0162] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0163] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0164] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0165] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0166] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0167] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0168] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0169] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0170] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0171] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A proton therapy system ambient radiation influence early warning system, characterized by, The system comprises: The radiation monitoring data acquisition module monitors the radiation intensity in real time based on the proton therapy environment, sorts and groups the values in sequence according to the radiation intensity of the detector and the detector position data, and obtains a radiation detection set; The radiation spatial distribution generation module extracts the radiation intensity and spatial coordinate data in the set based on the radiation detection set, constructs a radiation distribution map within a two-dimensional spatial range, and obtains radiation distribution information; The radiation risk level determination module marks the grid points exceeding the threshold as high-risk areas based on the radiation distribution information, classifies and collects the risk points according to their positions and risk levels, and obtains risk level labeling data; The radiation leakage analysis module compares the intensity values of high-risk points with normal radiation data point by point based on the risk level labeling data, determines the leakage category in combination with the leakage point source position data, classifies and collects high-risk area data, and obtains radiation leakage classification results; The risk information dynamic reporting module formulates corresponding early warning reporting contents based on the radiation leakage classification results in combination with the area influence range and risk category, sends the contents to the target receiving end through a communication device, notifies the treatment personnel, and obtains leakage risk reporting information; The treatment optimization suggestion module evaluates the health risk of the patient based on the leakage risk information reporting, adjusts the subsequent proton therapy dose value, and plans the proton therapy interval, and obtains an optimized treatment suggestion.

2. The proton therapy system ambient radiation influence early warning system of claim 1, wherein, The radiation detection set comprises monitoring point position information, radiation intensity values, and time stamps, the radiation distribution information comprises grid coordinate points, grid intensity values, and a two-dimensional spatial range, the risk level labeling data comprises high-risk area coordinates, risk level classification, and the number of high-risk points, the radiation leakage classification results specifically comprise leakage point source positions, abnormal intensity values, and high-risk area categories, the leakage risk reporting information comprises risk area coordinates, leakage type classification, and area influence range, and the optimized treatment suggestion comprises dose adjustment parameters, treatment interval values, and device operation state parameters.

3. The proton therapy system ambient radiation influence early warning system of claim 1, wherein, The radiation monitoring data acquisition module comprises: The radiation intensity extraction submodule extracts the intensity values of each detection point and the corresponding monitoring position based on the proton therapy environment and the radiation detector preinstalled at the monitoring point, and obtains detection point radiation intensity information; The monitoring point position collection submodule calls the monitoring position and radiation intensity value data of each detection point based on the detection point radiation intensity information, classifies each group of monitoring point positions and values by area, and arranges them in set form, and obtains a monitoring point position intensity set; The time stamp grouping and arrangement submodule extracts the time stamp information of the monitoring points based on the monitoring point position intensity set, collects and sorts the monitoring point data within the same time period, groups and arranges the intensity values and position information corresponding to the monitoring points in time sequence, and obtains a radiation detection set.

4. The proton therapy system ambient radiation influence early warning system of claim 1, wherein, The radiation spatial distribution generation module comprises: The spatial grid construction submodule extracts spatial coordinate values of the monitoring points based on the radiation detection set, performs regional grid division according to a coordinate range, constructs a grid for the monitoring region in combination with a grid rule, and obtains a spatial grid model; The intensity value distribution calculation submodule extracts spatial coordinates of the grid points and corresponding radiation intensity values based on the spatial grid model and time series grouping intensity data, point-by-point calculates a radiation intensity value distribution relationship according to a distribution between the grid points, and obtains intensity value spatial distribution data; The two-dimensional image generation submodule extracts radiation intensity values and corresponding grid coordinate points based on the intensity value spatial distribution data, constructs a visual two-dimensional distribution diagram of the grid point radiation intensity values according to a two-dimensional coordinate layout rule, and obtains radiation distribution information.

5. The proton therapy system ambient radiation influence early warning system of claim 1, wherein, The radiation risk level determination module includes: The risk threshold comparison submodule extracts radiation intensity values in the grid point data, compares the radiation intensity values with preset risk level threshold values point by point, identifies grid point data exceeding the threshold values, and obtains risk threshold-exceeding grid point data; The high-risk point marking submodule extracts grid point coordinate values and intensity values exceeding the risk threshold values based on the risk threshold-exceeding grid point data, marks the grid points, defines the grid points as high-risk points, and obtains high-risk point marking information; The risk level collection submodule evaluates risk levels of the high-risk points according to the radiation intensity values of the high-risk points based on the high-risk point marking information, collects and classifies the high-risk points according to a preset risk level classification standard, and obtains risk level annotation data.

6. The proton therapy system ambient radiation influence early warning system of claim 5, wherein, The formula for evaluating the risk levels of the high-risk points is: wherein R i represents the risk level value of the i-th grid point, S i represents the radiation intensity value of the i-th grid point, represents the average value of the radiation intensity values of all grid points, σ S represents the standard deviation of the radiation intensity values of all grid points, T i represents the time dimension marker value of the i-th grid point, T max represents the maximum value of the time dimension marker values among all grid points, w1 and w2 are weighting coefficients.

7. The proton therapy system ambient radiation influence early warning system of claim 1, wherein, The radiation leakage analysis module includes: The intensity deviation calculation submodule extracts radiation intensity values of the grid points in the high-risk region and corresponding leakage point source position data based on the risk level annotation data, compares the radiation intensity values of the grid points with an average value of normal radiation data point by point, calculates a deviation amplitude of the current radiation intensity values from the average value of the normal radiation, and obtains radiation intensity deviation data; The leakage type classification submodule classifies radiation intensity deviation values of the high-risk region based on the radiation intensity deviation data and in combination with spatial positions of the leakage point sources, determines a leakage category of each region by analyzing deviation characteristics of multiple regions and types of the leakage point sources, and obtains leakage type judgment information; The high-risk region annotation submodule extracts radiation intensity values, spatial ranges, and corresponding leakage category information of the high-risk region based on the leakage type judgment information, annotates the information to the high-risk region grid item by item, and obtains a radiation leakage classification result.

8. The proton therapy system ambient radiation influence early warning system of claim 1, wherein, The risk information dynamic reporting module includes: The leakage information extraction submodule extracts position data, risk level data, and leakage point source data of multiple high-risk regions based on the radiation leakage classification result, collects each item of the extracted data item by item, and obtains a high-risk region information set; The dynamic notification content generation submodule extracts region position, risk level and leakage point source data based on the high-risk area information set, matches and associates the data in combination with preset region influence range and risk category analysis standards, generates a notification required content format according to a preset rule, collects notification information and adds region position and risk classification descriptions, and generates high-risk area dynamic notification content; The region risk data matching submodule matches high-risk area data in the notification content with preset target receiving end information based on the high-risk area dynamic notification content, sends the notification content to the target receiving end through a communication device including a mobile phone and a computer, generates leakage risk notification information, and notifies treatment personnel.

9. The proton therapy system ambient radiation influence early warning system of claim 1, wherein, The treatment optimization suggestion module includes: The parameter joint adjustment submodule extracts radiation intensity data, region range data and patient exposure time length data based on the leakage risk notification information, evaluates the health risk of radiation to the patient in combination with patient exposure conditions and a preset health risk evaluation standard, and generates a health risk evaluation result; The dose update calculation submodule adjusts the dose value of subsequent proton therapy according to patient exposure health risk level data in combination with the current treatment dose parameters of the patient based on the health risk evaluation result, and obtains treatment dose update parameters; The treatment interval optimization submodule replans the time interval of proton therapy according to radiation exposure influence and treatment effect in combination with patient treatment time planning data based on the treatment dose update parameters, and obtains an optimized treatment suggestion.

10. The proton therapy system ambient radiation influence early warning system of claim 9, wherein, The formula for evaluating the health risk of radiation to the patient is: wherein H r represents the health risk index of the patient, D represents the cumulative radiation dose value in the leakage area, D safe represents the set safety radiation dose threshold, T e represents the cumulative exposure time length of the patient in the high radiation area, T max represents the maximum value of the exposure time length in the leakage area, R H represents the health risk level value of the radiation leakage area, R H,max represents the preset maximum health risk level value, V1, V2 and V3 are weighting coefficients of the radiation dose deviation, the exposure time length influence and the health risk level weight, respectively.

Images