A method and device for intelligent monitoring and evaluation of radiation protection performance of hospital proton area

Abstract

A method and device for intelligently monitoring and evaluating the radiation protection performance of a hospital's proton therapy area relates to the field of radiation monitoring. The method includes: performing a 3D scan of the actual building structure and equipment layout of a target proton therapy center to obtain 3D scan data, and then modifying a preset BIM model using the 3D scan data to obtain a 3D building model. After the detection equipment is turned on, the measured dose rate level of the target proton therapy center at a preset target measurement point is obtained. The measured dose rate level is curve-fitted to obtain a measured dose rate curve. The simulated dose rate level and the measured dose rate curve are then merged to obtain the actual dose rate level at each building structure location. The actual dose rate level is then mapped onto the 3D building model to obtain a 3D dose distribution map. Implementing this method can more intuitively demonstrate the radiation protection level of a hospital's proton therapy area.

Description

Technical Field

[0001] The present application relates to the field of radiation monitoring, and in particular to a method and device for intelligently monitoring and evaluating the radiation protection performance of a hospital proton area. Background Art

[0002] Currently, the radiation protection performance evaluation of hospitals with proton therapy areas is divided into two stages: the initial planning stage and the operation stage. Hospitals with proton therapy areas will conduct environmental assessments in the initial planning stage, especially the evaluation of the radiation protection performance of the proton area. Generally, the 3D BIM software Fluka based on the Monte Carlo method is used to evaluate the radiation protection performance of the proton area. During the operation stage, the 3D BIM model established using the construction unit's 3D BIM software Revit is used for construction. After the construction is completed, the radiation performance of the workplace needs to be evaluated in combination with the detection instruments and requirements. The evaluation method is a combination of instrument measurement and manual recording.

[0003] However, the data from these two periods are relatively independent, and the data measured by instruments during the operation period cannot intuitively show the radiation protection level of the hospital's proton therapy area. Summary of the Invention

[0004] The present application provides a method and device for intelligently monitoring and evaluating the radiation protection performance of a hospital's proton treatment area, which is used to more intuitively display the radiation protection level of the hospital's proton treatment area.

[0005] In a first aspect, the present application provides an intelligent monitoring and evaluation method for the radiation protection performance of a hospital proton area, which is applied to intelligent monitoring and evaluation equipment. The method includes: obtaining the actual building structure and actual equipment layout of a target proton therapy center, performing a three-dimensional scan of the actual building structure and the actual equipment layout to obtain three-dimensional scanning data, and correcting a preset BIM model based on the three-dimensional scanning data to obtain a three-dimensional building model; after the detection equipment is turned on, obtaining the measured dose rate level of the target proton therapy center at a preset target measurement point; performing curve fitting on the measured dose rate level to obtain a measured dose rate curve, fusing the simulated dose rate level with the measured dose rate curve to obtain the actual dose rate level of each building structure position, and the simulated dose rate level is simulated in a Monte Carlo program; mapping the actual dose rate level to the three-dimensional building model to obtain a three-dimensional dose distribution map, which includes a dose isosurface, a dose value at each building structure position, and a dose distribution slice map of any plane.

[0006] By adopting the above technical solution, three-dimensional scanning data of the actual building structure and equipment layout of the target proton therapy center is obtained, and the preset BIM model is modified according to the three-dimensional scanning data to obtain a three-dimensional building model. After the detection equipment is turned on, the measured dose rate level is obtained, and a curve fitting is performed on it to obtain a measured dose rate curve. The simulated dose rate level and the measured dose rate curve are then fused to obtain the actual dose rate level of each building structure location. Finally, the actual dose rate level is mapped to the three-dimensional building model to obtain a three-dimensional dose distribution map, including dose isosurfaces, dose values ​​at each building structure location, and dose distribution slices on any plane. This can intuitively and comprehensively display the radiation distribution of the proton therapy center and help to accurately evaluate the radiation protection performance in the entire proton area space.

[0007] In combination with some embodiments of the first aspect, in some embodiments, before the step of obtaining the actual building structure and actual equipment layout of the target proton therapy center and performing a three-dimensional scan on the actual building structure and the actual equipment layout to obtain three-dimensional scanning data, the method also includes: modeling the target proton therapy center in a Monte Carlo program based on a preset building structure and a preset equipment layout to obtain a three-dimensional grid model of the target proton therapy center; performing a dose rate level simulation in the Monte Carlo program based on the building material data of each building structure part in the three-dimensional grid model and the treatment parameters of the proton therapy equipment in the target proton therapy center to obtain a simulated dose rate level for each building structure position in the building structure part, the building material data including density, elemental composition and mass content, and the treatment parameters including target material and beam intensity.

[0008] By adopting the above technical solution, the target proton therapy center is modeled in the Monte Carlo program based on the preset building structure and equipment layout to obtain a three-dimensional grid model. In the Monte Carlo program, the dose rate level is simulated based on the building material data (including density, elemental composition, mass content, etc.) of each building structure part in the three-dimensional grid model and the treatment parameters of the proton therapy equipment in the target proton therapy center (including target material and beam intensity). The simulated dose rate level at each building structure position in the building structure is obtained, which can accurately reflect the actual situation of the proton therapy center and make the simulation results more reliable.

[0009] In combination with some embodiments of the first aspect, in some embodiments, the step of fusing the simulated dose rate level and the measured dose rate curve to obtain the actual dose rate level of each building structure position specifically includes: inputting each building structure position in the three-dimensional grid model into a preset credibility assessment model to obtain the simulated credibility corresponding to all building structure positions in the three-dimensional grid model, and normalizing the simulated credibility to obtain an initial fusion weight; calculating the distance attenuation coefficient of each building structure position based on the initial fusion weight and the distance from the building structure position to the nearest preset target measurement point; multiplying the initial fusion weight by the distance attenuation coefficient to obtain the final fusion weight of each building structure position; and based on the final fusion weight, weighted averaging the simulated dose rate level and the corresponding position dose rate obtained by interpolation according to the measured dose rate curve to obtain the actual dose rate level of each building structure part.

[0010] By adopting the above technical solution, each building structure position in the three-dimensional grid model is input into the preset credibility assessment model to obtain the simulation credibility corresponding to all building structure positions, and normalization is performed to obtain the initial fusion weight. The distance attenuation coefficient is calculated based on the initial fusion weight and the distance from the building structure position to the nearest preset target measurement point. The initial fusion weight is multiplied by the distance attenuation coefficient to obtain the final fusion weight of each building structure position. Based on the final fusion weight, the simulated dose rate level and the corresponding position dose rate obtained by interpolation according to the measured dose rate curve are weighted averaged to obtain the actual dose rate level of each building structure part, so that the calculation of the actual dose rate level is more accurate, thereby more accurately evaluating the radiation protection performance of concrete.

[0011] In combination with some embodiments of the first aspect, in some embodiments, the step of mapping the actual dose rate level to the three-dimensional building model to obtain a three-dimensional dose distribution map specifically includes: comparing the three-dimensional grid model with the three-dimensional building model, identifying the newly added structural part in the three-dimensional building model, and creating a new data point in the newly added structural part; assigning an initial dose value to the newly added data point based on the actual dose rate level; obtaining building material data of the newly added structural part in the three-dimensional building model, and calculating the attenuation coefficient corresponding to the initial dose value based on the building material data, the building material data including material parameters and geometric characteristics; multiplying the attenuation coefficient by the initial dose value to obtain a simulated dose level corresponding to the newly added data point; mapping the numerical value corresponding to the actual dose rate level to the three-dimensional building model, and mapping the numerical value corresponding to the simulated dose level to the newly added structural part to obtain a three-dimensional dose distribution map.

[0012] By adopting the above technical solution, the three-dimensional grid model is compared with the three-dimensional building model, and the newly added structural parts in the three-dimensional building model can be accurately identified. After creating new data points in the newly added structural parts, initial dose values ​​are assigned to the newly added data points based on the actual dose rate level, and the building material data of the newly added structural parts in the three-dimensional building model are obtained. The attenuation coefficient corresponding to the initial dose value is calculated based on the data, and the attenuation coefficient is multiplied by the initial dose value to obtain the simulated dose level corresponding to the newly added data point. The numerical value corresponding to the actual dose rate level is mapped to the three-dimensional building model, and the numerical value corresponding to the simulated dose level is mapped to the newly added structural parts to obtain a complete three-dimensional dose distribution map, which can accurately reflect the radiation dose distribution of the entire building and provide more accurate data support for the intelligent monitoring and evaluation of the radiation protection performance of concrete.

[0013] In combination with some embodiments of the first aspect, in some embodiments, the step of performing a dose rate level simulation in a Monte Carlo program based on the building material data of each building structure part in the three-dimensional grid model and the treatment parameters of the proton therapy equipment in the target proton therapy center to obtain a simulated dose rate level for each building structure position in the building structure part specifically includes: obtaining the display accuracy requirements of each building structure part, and dividing the three-dimensional grid model into spatial units based on the display accuracy requirements to obtain grid units; matching the corresponding simulation parameters of the Monte Carlo program for each grid unit, and the simulation parameters include spatial resolution, statistical error threshold and number of iterations; inputting the building material data and the treatment parameters into the Monte Carlo program, performing a dose rate level simulation calculation for each grid unit, and obtaining a simulated dose rate level for each grid unit; mapping the simulated dose rate level to the corresponding building structure position in the three-dimensional grid model to obtain a simulated dose rate level for each building structure position in the building structure part.

[0014] By adopting the above technical solution, the display accuracy requirements of each building structure part are obtained, and the three-dimensional grid model is divided into spatial units based on this requirement to obtain appropriate grid units so that the model can meet the accuracy requirements of different structural parts. The simulation parameters of the corresponding Monte Carlo program are matched for each grid unit, including spatial resolution, statistical error threshold and number of iterations, to ensure the accuracy and efficiency of the simulation calculation. The building material data and treatment parameters are input into the Monte Carlo program, and the dose rate level simulation calculation is performed for each grid unit to obtain the simulated dose rate level of each grid unit. The simulated dose rate level is mapped to the corresponding building structure position in the three-dimensional grid model to obtain the simulated dose rate level of each building structure position in the building structure part, thereby achieving accurate simulation of the radiation dose level of the entire building structure.

[0015] In combination with some embodiments of the first aspect, in some embodiments, after the step of performing dose rate level simulation in the Monte Carlo program based on the building material data of each building structure part in the three-dimensional grid model and the treatment parameters of the proton therapy equipment in the target proton therapy center to obtain the simulated dose rate level of each building structure position in the building structure part, the method also includes: if the simulated dose rate level of a target building position exceeds a preset simulation threshold, performing a local correction on the target building position, the local correction including increasing the wall thickness and improving the wall material density; based on the locally corrected building material data, re-performing the dose rate level simulation in the Monte Carlo program to obtain a corrected dose rate level; repeating the local correction and the dose rate level simulation until the simulated dose rate level at the target building position does not exceed the preset simulation threshold.

[0016] By adopting the above technical solution, if the simulated dose rate level at the target building location exceeds the preset simulation threshold, the target building location is locally corrected, such as increasing the wall thickness and increasing the wall material density, which can effectively reduce the radiation dose level. Based on the locally corrected building material data, the dose rate level simulation is re-performed in the Monte Carlo program to obtain the corrected dose rate level to verify the effectiveness of the correction measures. The process of local correction and dose rate level simulation is repeated until the simulated dose rate level at the target building location does not exceed the preset simulation threshold, ensuring that the radiation protection performance of the building meets the safety standard. In this way, the problem of excessive radiation dose can be discovered and resolved in a timely manner, thereby improving the safety and reliability of the proton therapy center.

[0017] In combination with some embodiments of the first aspect, in some embodiments, after the step of mapping the actual dose rate level to a three-dimensional building model to obtain a three-dimensional dose distribution map, the method further includes: detecting whether there is a building location in the three-dimensional dose distribution map that exceeds a preset dose rate level threshold; if so, sending a prompt message to the target client, the prompt message including the location information and dose rate level data of the building location.

[0018] By adopting the above technical solution, after obtaining a three-dimensional dose distribution map, it is detected whether there are any building locations in the map that exceed the preset dose rate level threshold. If there are building locations that exceed the threshold, a prompt message is sent to the target client. The prompt message contains the location information and dose rate level data of the building location, so that relevant personnel can obtain key information in a timely and accurate manner so as to take corresponding measures.

[0019] In second aspect, an embodiment of the present application provides an intelligent monitoring and evaluation device, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the intelligent monitoring and evaluation device to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0020] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when run on an intelligent monitoring and evaluation device, enables the intelligent monitoring and evaluation device to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions. When the instructions are executed on an intelligent monitoring and evaluation device, the intelligent monitoring and evaluation device executes the method described in the first aspect and any possible implementation method of the first aspect.

[0022] It is understood that the intelligent monitoring and evaluation device provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the methods provided in the embodiments of the present application. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding methods and will not be repeated here.

[0023] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0024] 1. This application obtains three-dimensional scanning data of the actual building structure and equipment layout of the target proton therapy center, and modifies the preset BIM model based on the three-dimensional scanning data to obtain a three-dimensional building model. After the detection equipment is turned on, the measured dose rate level is obtained, and a curve fitting is performed on it to obtain a measured dose rate curve. The simulated dose rate level and the measured dose rate curve are then merged to obtain the actual dose rate level of each building structure location. Finally, the actual dose rate level is mapped to the three-dimensional building model to obtain a three-dimensional dose distribution map, including dose isosurfaces, dose values ​​at each building structure location, and dose distribution slices on any plane. This can intuitively and comprehensively display the radiation distribution of the proton therapy center, and help to accurately evaluate the radiation protection performance in the entire proton area space.

[0025] 2. This application models the target proton therapy center in a Monte Carlo program based on a preset building structure and equipment layout to obtain a three-dimensional grid model. In the Monte Carlo program, dose rate level simulation is performed based on the building material data (including density, elemental composition, mass content, etc.) of each building structure part in the three-dimensional grid model and the treatment parameters of the proton therapy equipment in the target proton therapy center (including target material and beam intensity). The simulated dose rate level at each building structure position in the building structure is obtained, which can accurately reflect the actual situation of the proton therapy center and make the simulation results more reliable.

[0026] 3. This application obtains the simulation credibility corresponding to all building structure positions by inputting each building structure position in the three-dimensional grid model into a preset credibility assessment model, and performs normalization processing to obtain the initial fusion weight. The distance attenuation coefficient is calculated based on the initial fusion weight and the distance from the building structure position to the nearest preset target measurement point. The initial fusion weight is multiplied by the distance attenuation coefficient to obtain the final fusion weight of each building structure position. Based on the final fusion weight, the simulated dose rate level and the corresponding position dose rate obtained by interpolation according to the measured dose rate curve are weighted averaged to obtain the actual dose rate level of each building structure part, so that the calculation of the actual dose rate level is more accurate and reasonable, thereby more accurately evaluating the radiation protection performance of concrete. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a flow chart of a method for intelligently monitoring and evaluating the radiation protection performance of a hospital proton area in an embodiment of the present application;

[0028] Figure 2 This is another flow chart of the method for intelligently monitoring and evaluating the radiation protection performance of a hospital proton area in an embodiment of the present application;

[0029] Figure 3 This is a schematic diagram of the physical device structure of the intelligent monitoring and evaluation equipment in the embodiment of the present application. DETAILED DESCRIPTION

[0030] The terms used in the following examples of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application, the singular expressions "a", "an", "above", "the", and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations of one or more of the listed items.

[0031] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0032] For ease of understanding, the application scenarios of the embodiments of the present application are introduced below.

[0033] Currently, hospitals with proton therapy areas conduct environmental assessments during the initial planning stages, specifically evaluating the area's radiation protection performance. This assessment is typically conducted using Fluka, a 3D BIM software based on the Monte Carlo method. During the construction of the proton therapy area, radiation protection requirements necessitate precise pre-embedding of equipment and pipelines. Furthermore, due to the large volume of radiation-resistant concrete, construction requires segmented construction. Construction companies use Revit to create 3D BIM models to guide the entire construction process. During the hospital's operational phase, radiation performance evaluations of the workplace are conducted as required, using a combination of instrumental measurements and manual documentation.

[0034] In this way, it is difficult to accurately assess the impact of these changes on the overall radiation protection effect. The lack of intuitive visualization tools makes it difficult for management to quickly understand and make decisions on potential radiation risk areas.

[0035] The intelligent monitoring and evaluation method proposed in this application is adopted. The treatment center is scanned using three-dimensional scanning technology in the early stage of planning to generate a three-dimensional building model. The scanned model in the early stage of planning is matched with the initial BIM design model to identify structural changes during the construction process. Radiation detectors are installed at key locations, and data is transmitted to the monitoring system in real time. The theoretical radiation distribution data of Monte Carlo simulation and real-time measurement data are combined for data fusion to generate a three-dimensional radiation distribution map of the treatment center, including dose isosurfaces and dose distribution slices of any plane, and the radiation level data of each location can be displayed through the interface.

[0036] For ease of understanding, the following describes the process of the method provided by this implementation in combination with the above scenario. Figure 1 , which is a flow chart of the intelligent monitoring and evaluation method of the radiation protection performance of the hospital proton area in the embodiment of this application.

[0037] S101. Obtain the actual building structure and actual equipment layout of the target proton therapy center, perform a three-dimensional scan on the actual building structure and the actual equipment layout to obtain three-dimensional scan data, and modify a preset BIM model based on the three-dimensional scan data to obtain a three-dimensional building model.

[0038] Among them, the target proton therapy center refers to a specific proton therapy center that requires intelligent monitoring and evaluation of concrete radiation protection performance. The actual building structure refers to the proton therapy center during its operation period, that is, the completed building structure, including walls, floors, ceilings, etc. The actual equipment layout is used to indicate the placement of proton therapy equipment in the treatment center during its operation period. The preset BIM model refers to the BIM model for construction established using Revit software. The three-dimensional building model refers to the final three-dimensional digital model containing the actual building structure and equipment layout information. This three-dimensional building model can accurately restore the physical project.

[0039] Specifically, before beginning a proton therapy center's radiation protection performance monitoring, the actual conditions of the center must be determined. Through on-site surveys or the use of surveying equipment, the actual building structure and equipment layout of the target proton therapy center must be captured. A comprehensive scan of the entire center is then performed using a 3D laser scanner or other 3D scanning device, generating 3D point cloud data encompassing the building structure and equipment layout. The resulting 3D scan data is then compared with a pre-prepared BIM model. If discrepancies are identified, the pre-prepared BIM model is modified and adjusted based on the 3D scan data. This data fusion and calibration process ultimately results in a 3D building model.

[0040] For example, during on-site scanning, the scanning can be divided into large-area overall scanning and special node precise scanning. The appropriate scanning radius is selected according to the actual situation of the scanning area. Large-area overall scanning means scanning the entire node to see the completion status of steel bars, pipelines, embedded parts and surrounding conditions. Special node precise scanning includes a certain treatment chamber, accelerator room or complex wall columns and pipelines. Three-dimensional scanning can generate three-dimensional coordinate information (XYZ), color value RGB, laser reflection intensity information and other data. The exported scanning data is compared with the relevant data of the BIM model. The BIM model is corrected based on the scanning data until the data in the BIM model conforms to the three-dimensional scanning data. After correction, a three-dimensional building model is obtained.

[0041] The specific method for modifying the preset BIM model based on 3D scanning data is to use a 3D laser scanner or other 3D scanning equipment to scan the target proton therapy center. The scanning is divided into large-area overall scanning and special node precision scanning. The large-area overall scanning covers the entire node's steel bars, pipelines, embedded parts completion and surrounding conditions. Special node precision scanning targets key areas such as a treatment chamber, accelerator room, or complex wall columns and pipelines. The appropriate scanning radius is selected according to the actual situation of the scanning area. The scanning can generate 3D coordinate information (XYZ), color value RGB, laser reflection intensity information and other data;

[0042] The scanned 3D point cloud data is preprocessed and compared with a pre-prepared BIM model created using Revit software. This comparison uses key structural features of the building as a benchmark, such as wall location, thickness, material type, and floor and ceiling structure. For each key feature, the difference between the 3D scan data and the BIM model data is calculated. For example, if the scan data indicates a deviation between the actual wall position and the BIM model position exceeding a certain threshold (e.g., 5 cm), the difference is recorded, and structural adjustments are made to the pre-prepared BIM model based on the comparison results. If a wall position deviation is detected, the wall is moved in the BIM model to align with the scan data. For structural components that exist but are missing from the BIM model, such as newly added small equipment support structures, corresponding structural elements are added to the BIM model. For structural dimensions that differ from those in the BIM model, such as actual wall thickness that is thicker or thinner than recorded in the BIM model, the wall thickness parameters in the BIM model are modified to align with the actual scan data. When the scan reveals that the actual building material differs from the material preset in the BIM model, the material property information in the BIM model is updated. For example, if the actual wall material is detected as a new type of radiation-proof concrete, but the BIM model records it as ordinary concrete, the relevant parameters of the wall material, such as density and elemental composition, are modified in the BIM model.

[0043] It should be noted that the 3D building model is generated by 3D scanning the actual building structure and equipment layout of the target proton therapy center to obtain 3D scan data. This data is then used to modify a pre-set BIM model (e.g., a model created using Revit software). Using the actual building geometry as the framework, the 3D building model includes precise information about building components such as walls, floors, and ceilings, as well as the actual equipment layout, including proton therapy equipment. The specific parameters of the 3D building model include geometric and material parameters. Geometric parameters include: wall thickness, accurate to the millimeter level. Wall thickness in different areas may vary due to different radiation protection requirements. For example, wall thickness in critical protection areas may be between 800-1200 mm, while that in non-critical areas may be between 200-600 mm. Room dimensions (length, width, and height) are based on actual measurements and are accurate to the centimeter level. For example, a proton accelerator room may be between 10-15 meters long, 8-12 meters wide, and 4-6 meters high. Equipment size and location: The size of proton therapy equipment is determined by the equipment model, and its location is based on the actual installation location, accurate to the centimeter level. For example, a proton accelerator of a certain model may be between 5 and 8 meters long and 3 and 5 meters wide. Its installation location within the treatment room may be within 3 and 5 meters of a corner. Material parameters include: wall material. For radiation-resistant walls, material properties include density, elemental composition, and mass content. For example, the density of radiation-resistant concrete may be between 2.2 and 2.8 g / cm³. The elemental composition may include elements such as lead and boron, with the mass content varying depending on the formulation. Floor and ceiling material properties also include density, elemental composition, and mass content, which are determined based on radiation protection and structural requirements. For example, a floor made of a composite material containing a certain proportion of heavy metals may have a density between 1.8 and 2.5 g / cm³.

[0044] The geometry and position of building components and equipment in the model must be identical to the actual building and equipment layout, with tolerances within acceptable limits. For example, wall position deviations must not exceed ±5 cm, and equipment position deviations must not exceed ±3 cm. Material properties recorded in the model must match the actual material properties, with tolerances within acceptable limits. For example, material density deviations must not exceed ±0.2 g / cm³. Errors in elemental composition and mass content are determined based on actual conditions and testing accuracy, but must not affect the assessment of radiation protection performance.

[0045] S102: After the detection device is turned on, a measured dose rate level of the target proton therapy center at a preset target measurement point is obtained.

[0046] Among them, the detection equipment refers to an instrument used to measure the radiation dose rate, such as a portable radiation detector. The preset target measurement point refers to a predetermined specific location where the radiation dose rate measurement is required. The measured dose rate level refers to the radiation dose rate value measured at the specific location, usually in μSv / h (microsievert / hour).

[0047] Specifically, the preset target measurement points are typically located in areas most exposed to radiation, or in locations that must be monitored according to relevant standards and regulations. For example, measurement points are set up in locations such as the proton accelerator room, the main control room, and the rotating therapy room. The detection equipment will obtain and record the dose rate level data at these measurement points in real time.

[0048] S103, curve fitting is performed on the measured dose rate level to obtain a measured dose rate curve, and the simulated dose rate level and the measured dose rate curve are merged to obtain the actual dose rate level at each building structure position, where the simulated dose rate level is simulated in a Monte Carlo program.

[0049] Among them, the measured dose rate level represents the actual radiation dose rate value measured at the preset target measurement point, curve fitting refers to fitting discrete measurement data points into a continuous function curve through mathematical methods, and the measured dose rate curve is used to represent the continuous dose rate distribution function obtained after fitting. The simulated dose rate level refers to the theoretical dose rate distribution obtained by Monte Carlo simulation calculation, and the Monte Carlo program refers to professional software used for Monte Carlo simulation calculations, such as MCNP or Geant4. The actual dose rate level refers to the more accurate dose rate distribution obtained by fusing the measured data and simulated data.

[0050] Specifically, first, the measured dose rate level is curve-fitted using the least squares method or spline interpolation to obtain a continuous measured dose rate curve, which is used to describe the trend of dose rate changes in space. The Monte Carlo simulation program is used to calculate the theoretical simulated dose rate level based on the architectural structure, material properties and radiation source parameters of the treatment center. The measured dose rate curve and the simulated dose rate level are then data-fused, taking into account both measurement error and simulation accuracy.

[0051] In some embodiments, obtaining a measured dose rate curve and determining the actual dose rate level can be achieved through various methods: Optionally, the measured dose rate level can be first fitted using a polynomial regression method to obtain a measured dose rate curve represented by a polynomial function; then, the geometric model and material composition of the proton therapy center can be established using MCNP software, and Monte Carlo simulation can be performed to obtain the simulated dose rate level; then, a Bayesian inference method can be used, using the measured dose rate curve as the prior distribution and the simulated dose rate level as the likelihood function to calculate the posterior distribution to obtain the actual dose rate level. Optionally, the measured dose rate level can first be spatially interpolated using a radial basis function interpolation method to obtain a continuous measured dose rate distribution field; then, the Geant4 toolkit can be used to construct a physical model of the proton therapy center and simulate the particle transport process to obtain a simulated dose rate field; then, data assimilation techniques, such as ensemble Kalman filtering, can be used to dynamically fuse the measured dose rate field and the simulated dose rate field to obtain the actual dose rate level at each building structure location. It is understood that other methods can also be used and are not limited here.

[0052] S104 , mapping the actual dose rate level to the three-dimensional building model to obtain a three-dimensional dose distribution map, which includes a dose isosurface, a dose value at each building structure position, and a dose distribution slice map of any plane.

[0053] Among them, the actual dose rate level represents the accurate dose rate distribution obtained by fusing the measured data and the simulated data. The three-dimensional building model refers to the digital model obtained in the previous step that contains the actual building structure and equipment layout information. The three-dimensional dose distribution map is used to represent the distribution of the dose rate in three-dimensional space. The dose isosurface refers to the three-dimensional surface formed by spatial points with the same dose rate. The dose distribution slice map represents the two-dimensional dose rate distribution on any plane.

[0054] In some embodiments, the mapping of actual dose rate levels to three-dimensional dose distribution maps can be achieved in a variety of ways: optionally, first using a three-dimensional interpolation algorithm to expand the discrete actual dose rate level data to the entire three-dimensional space; then using volume rendering techniques, such as ray casting, to render the interpolated continuous dose rate field into the three-dimensional building model; then generating multiple dose isosurfaces and distinguishing them with different colors; finally, through an interactive slicing function, allowing the user to obtain two-dimensional dose distribution slices at any position and direction. Optionally, first convert the actual dose rate level data into a voxel data structure, with each voxel corresponding to a dose rate value; then calculating the dose rate distribution of the entire three-dimensional space, and using an isosurface extraction algorithm to generate multiple dose isosurfaces; finally, a real-time volume data cutting function is implemented, allowing the user to obtain dose distribution slices at any position by dragging and dropping. It is understandable that other methods can also be used to achieve the mapping of actual dose rate levels to three-dimensional dose distribution maps, which are not limited here.

[0055] The following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the method for intelligent monitoring and evaluation of radiation protection performance of the hospital proton area in the embodiment of the present application.

[0056] S201. Model the target proton therapy center in a Monte Carlo program based on a preset building structure and a preset equipment layout to obtain a three-dimensional grid model of the target proton therapy center.

[0057] The preset building structure refers to the building structure specified in the design drawings of the proton therapy center in the initial planning stage, including the dimensions, materials, and location information of components such as walls, floors, and ceilings. The preset equipment layout represents the planned placement and configuration of proton therapy equipment within the treatment center in the initial planning stage. The Monte Carlo program refers to professional software used for Monte Carlo simulation calculations, such as MCNP (Monte Carlo N-Particle) or Geant4. The target proton therapy center refers to a specific proton therapy center that requires radiation protection performance monitoring and evaluation. The three-dimensional mesh model refers to a BIM model composed of multiple small geometric units.

[0058] First, a CAD data file containing a preset building structure and equipment layout is read, including floor plans, elevations, and equipment layout drawings. The two-dimensional drawing information is then converted into a three-dimensional geometric model, including the physical properties of the building materials, such as density and elemental composition. The converted three-dimensional geometric model is then imported into the Monte Carlo program through its application programming interface. Within the program, the imported model is meshed, dividing the entire space into a large number of small grid cells, each of which is assigned corresponding material properties and geometric information. Finally, the generated mesh model is quality-checked to eliminate any mesh overlap or gaps. For a standard proton therapy room, the walls are typically divided into cubic grid cells with side lengths of 1 mm to 10 mm.

[0059] It should be noted that the three-dimensional grid model is constructed in the Monte Carlo program based on the preset building structure and preset equipment layout. It is composed of multiple small geometric units (grid units). These grid units are arranged according to certain rules to form a digital representation of the building structure and equipment layout of the target proton therapy center in the initial planning stage. Each grid unit in the model is assigned corresponding material properties and geometric information.

[0060] The specific parameters of the three-dimensional grid model include grid unit parameters and material property parameters. The grid unit parameters include the size and number of grids, and the material property parameters include density, element composition, and mass content. For example, for critical protective structures such as walls, the grid unit can be set to a cubic grid unit with a side length of 1mm-10mm; for non-critical areas, the grid unit size may be increased to 10cm×10cm×10cm. For ordinary concrete materials, the density may be between 2.0-2.4g / cm³; for radiation-proof concrete, the density may be between 2.2-2.8g / cm³. The element composition and mass content are determined according to the actual composition of the building materials.

[0061] The arrangement and combination of grid cells should accurately represent the geometry of the building structure and equipment layout within acceptable tolerances. For example, the representation of wall locations should be within ±1 cm, and the representation of equipment locations should be within ±5 cm. The material properties assigned to each grid cell should be consistent with the actual building material within acceptable tolerances. For example, the tolerance for material density should be within ±0.2 g / cm³. The tolerance for elemental composition and mass content should be determined based on actual conditions and testing accuracy.

[0062] S202. Performing a dose rate level simulation in a Monte Carlo program based on building material data of each building structure in the three-dimensional grid model and treatment parameters of the proton therapy equipment in the target proton therapy center to obtain a simulated dose rate level at each building structure location in the building structure, wherein the building material data includes density, elemental composition, and mass content, and the treatment parameters include target material and beam intensity.

[0063] In some embodiments, this step specifically includes:

[0064] The display accuracy requirement of each building structure part is obtained, and the three-dimensional grid model is divided into spatial units based on the display accuracy requirement to obtain grid units.

[0065] Simulation parameters of the corresponding Monte Carlo procedure are matched for each grid cell, and the simulation parameters include spatial resolution, statistical error threshold and number of iterations.

[0066] The building material data and the treatment parameters are input into the Monte Carlo program, and a dose rate level simulation calculation is performed on each grid unit to obtain a simulated dose rate level of each grid unit.

[0067] The simulated dose rate level is mapped to the corresponding building structure position in the three-dimensional grid model to obtain the simulated dose rate level of each building structure position in the building structure part.

[0068] Specifically, the display accuracy requirement indicates the level of detail required for displaying each part of the building structure in a three-dimensional model. A three-dimensional grid model refers to a digital three-dimensional representation composed of multiple geometric units. Spatial unit division refers to the process of dividing a three-dimensional space into smaller, regular geometric units. A grid unit refers to the smallest geometric unit obtained after spatial unit division. The simulation parameters of the Monte Carlo procedure include key parameters that control simulation accuracy and efficiency. Spatial resolution represents the minimum spatial scale of the simulation calculation. The statistical error threshold specifies the acceptable error range of the simulation results. The number of iterations determines the number of times the simulation calculation is repeated. Building material data includes the physical and chemical properties of each part of the building structure. Treatment parameters include related parameters such as the energy and intensity of the proton beam.

[0069] Specifically, the display accuracy requirements for each building structure are determined, and the 3D mesh model is divided into spatial units based on these requirements. This can be achieved by using an adaptive meshing algorithm that dynamically adjusts the mesh density based on the importance and complexity of different areas. For example, for critical protective structures such as walls, a higher mesh density can be used, with a mesh size of 1cm×1cm×1cm; while for non-critical areas, a larger mesh size, such as 10cm×10cm×10cm, can be used.

[0070] Match the Monte Carlo simulation parameters to each grid cell. Parameter settings can be based on predefined rules or lookup tables. For example, for areas requiring high precision, the spatial resolution can be set to 0.1mm, the statistical error threshold to 1%, and the number of iterations to 10^6; for areas requiring low precision, the spatial resolution can be set to 1mm, the statistical error threshold to 5%, and the number of iterations to 10^4.

[0071] Building material data and treatment parameters are input into the Monte Carlo simulation program. Building material data, including density, elemental composition, and atomic number, can be retrieved through database queries. Treatment parameters, such as proton beam energy, can be set between 60 and 250 MeV, and beam current between 1 and 5 nA. Dose rate level simulations are performed for each grid cell, using parallel computing technology to improve computational efficiency.

[0072] The simulated dose rate levels are mapped to the corresponding building structure locations in the 3D mesh model. Spatial indexing techniques can be used to locate the spatial location corresponding to each dose rate value, obtaining the simulated dose rate level for each building structure location within the building structure, thus forming a complete 3D dose distribution dataset.

[0073] Steps S201 to S202 are completed before the construction of the target proton therapy center, and a radiation level numerical simulation is performed on a preset model of the target proton therapy center using professional software for Monte Carlo simulation calculations.

[0074] S203. Obtain the actual building structure and actual equipment layout of the target proton therapy center, perform a three-dimensional scan on the actual building structure and the actual equipment layout to obtain three-dimensional scan data, and modify the preset BIM model based on the three-dimensional scan data to obtain a three-dimensional building model.

[0075] It can be understood that this step is similar to step S101 and will not be described again here.

[0076] In step S203 , the target proton therapy center has been completed based on the three-dimensional building model, so the fineness of the three-dimensional building model is greater than that of the three-dimensional grid model constructed before construction.

[0077] S204: After the detection device is turned on, a measured dose rate level of the target proton therapy center at a preset target measurement point is obtained.

[0078] It can be understood that this step is similar to step S102 and will not be repeated here.

[0079] S205: Input each building structure position in the three-dimensional grid model into a preset credibility evaluation model to obtain simulation credibility corresponding to all building structure positions in the three-dimensional grid model, and normalize the simulation credibility to obtain initial fusion weights.

[0080] The preset credibility assessment model is an algorithm or mathematical model used to evaluate the reliability of simulation results. Simulation credibility is a measure of the accuracy of simulation results, typically expressed as a value between 0 and 1. Normalization is the mathematical operation of scaling data to a specific range (such as 0 to 1). The initial fusion weight is the initial weight coefficient when fusing simulation results with measured data.

[0081] In this step, the device first inputs the coordinates of each building structure location in the 3D mesh model into a pre-trained credibility assessment model. This model evaluates the reliability of the simulation results for each location based on various factors (such as simulation parameters, mesh accuracy, material properties, etc.) and outputs a credibility value between 0 and 1. For example, locations close to the proton beam source receive higher credibility, while locations far from the source or within complex structures receive lower credibility. The device then normalizes the credibility values ​​of all locations, linearly mapping them to the range of 0 to 1 to obtain the initial fusion weights.

[0082] It should be noted that the training and parameter determination process for the pre-set credibility assessment model is as follows: During the data collection phase, a large amount of data on known building structures of various types and sizes is collected, including information related to their 3D mesh models and corresponding actual measurement data. For each building structure, feature information corresponding to the simulated and actual measurement data is extracted. Simulation data features include simulation parameters such as spatial resolution, statistical error threshold, and number of iterations, as well as mesh size (grid accuracy) for different regions and material properties such as density, elemental composition, and mass content of building materials. The actual measurement data includes data such as radiation dose rates measured at key locations within the building structure.

[0083] The feature information corresponding to the simulated data and the actual measured data is combined as the input for the training sample. For example, a training sample may include the simulation parameters for a specific location of a building structure (e.g., spatial resolution of 0.5 mm, statistical error threshold of 3%, number of iterations of 50,000), grid accuracy (e.g., the grid size of the area at that location is 5 cm × 5 cm × 5 cm), and material properties (e.g., building material density of 2.5 g / cm³, elemental composition of [specific elemental composition], and mass content of [specific mass content]).

[0084] The degree of difference between the actual measured and simulated results is used as the output label for the training sample (i.e., the simulation credibility). This degree of difference can be calculated using a variety of methods, such as calculating the relative error between the actual measured dose rate and the simulated dose rate and mapping this relative error to a range of 0-1 as the simulation credibility. If the actual measured dose rate is exactly the same as the simulated dose rate, the simulation credibility is 1; if the difference is large, the simulation credibility is close to 0.

[0085] The pre-set credibility assessment model is trained using the backpropagation algorithm. The constructed training samples are sequentially input into the model. The model makes predictions based on the input feature information, obtaining the predicted simulation credibility. This predicted simulation credibility is then compared with the actual simulation credibility (output label) in the training sample, and the loss function is calculated. The mean squared error (MSE) function can be selected as the loss function, which measures the average squared error between the predicted value and the true value. Based on the value of the loss function, the model weights and biases are adjusted using the backpropagation algorithm. Starting from the output layer, the error is backpropagated layer by layer, updating the weights and biases of each neuron layer to make the model's predictions closer to the actual simulation credibility. This training process is repeated for multiple iterations on a large number of training samples until the model's loss function value converges to a smaller value.

[0086] Determine the number of neurons through experimentation and validation. Start with a small number of neurons, such as 10, and gradually increase the number of neurons to observe the model's performance on the validation dataset. The validation dataset is a portion of the collected building structure data that is not used for model training but is used to evaluate the model's generalization ability. If the model's performance on the validation dataset (such as the average error between the predicted and actual simulation credibility) begins to decline, it indicates that the number of neurons is too large, potentially leading to overfitting. The optimal number of neurons should be chosen just before performance begins to decline. For example, if the model's performance on the validation dataset begins to decline after increasing to 50 neurons, a range of 30-40 neurons can be selected. The specific value can be determined through further experimentation. The ReLU function should also be selected as the activation function. The optimal learning rate can be determined through multiple experimental validations. Start with a small learning rate, such as 0.001, and gradually increase it to observe the model's performance on both the training and validation datasets.

[0087] S206: Calculate the distance attenuation coefficient of each building structure position according to the initial fusion weight and the distance from the building structure position to the nearest preset target measurement point.

[0088] The initial fusion weight is a normalized value obtained in the previous step, reflecting the confidence level of the simulation results. The building structure location refers to a specific spatial point in the 3D mesh model. The preset target measurement point is the fixed location where the radiation dose measurement is actually performed. The distance refers to the straight-line distance from the building structure location to the nearest measurement point. The distance decay coefficient is a factor that decreases with increasing distance and is used to adjust the fusion weight.

[0089] In this step, the device first calculates the spatial distance from each structure to the nearest preset target measurement point by calculating the Euclidean distance between the two points. Then, the distance decay function is set to the inverse function (1 / d), and the distance decay coefficient is calculated using the inverse function, where d is the distance from the structure to the nearest preset target measurement point, and the unit of distance d is meters. When d is 0, the distance decay coefficient is defined as 1.

[0090] S207: Multiply the initial fusion weight by the distance attenuation coefficient to obtain the final fusion weight of each building structure position.

[0091] The final fusion weight is the weight value after comprehensively considering the simulation credibility and distance factors.

[0092] In this step, the device performs the following operations for each building structure location: first, it retrieves the initial fusion weight and distance decay coefficient corresponding to that location. Then, it multiplies these two values ​​together to obtain the final fusion weight for that location. This multiplication takes into account two factors: the initial fusion weight reflects the credibility of the simulation results themselves, while the distance decay coefficient reflects the impact of the spatial relationship between the location and the actual measurement point on credibility. For example, if the initial fusion weight for a location is 0.8 and the distance decay coefficient is 0.6, the final fusion weight is 0.48. The result of this step is the final fusion weight for each building structure location.

[0093] S208. Curve fitting is performed on the measured dose rate level to obtain a measured dose rate curve. Based on the final fusion weight, a weighted average is performed on the simulated dose rate level and the corresponding position dose rate obtained by interpolation according to the measured dose rate curve to obtain the actual dose rate level of each building structure part. The simulated dose rate level is simulated in the Monte Carlo procedure.

[0094] The measured dose rate curve is a function obtained after fitting that describes the spatial variation of dose rate, and the simulated dose rate level is the predicted dose rate value obtained by simulation calculation using the Monte Carlo program.

[0095] In this step, the device first performs curve fitting on the acquired measured dose rate level data to obtain a continuous measured dose rate curve. This fitting can use methods such as polynomial fitting, exponential fitting or spline interpolation, and the specific choice depends on the characteristics of the data. Then, the device uses the final fusion weight calculated previously to perform a weighted average of the simulated dose rate level simulated by the Monte Carlo program and the dose rate at the corresponding position obtained by interpolation based on the measured dose rate curve. The interpolation process can use linear interpolation or higher-order interpolation methods to obtain estimated dose rate values ​​at locations outside the measurement point. The calculation formula for weighted average can be expressed as: actual dose rate = final fusion weight * simulated dose rate + (1-final fusion weight) * interpolated dose rate.

[0096] S209: Compare the three-dimensional grid model with the three-dimensional building model, identify a newly added structural part in the three-dimensional building model, and create a new data point in the newly added structural part.

[0097] Newly added structures refer to building structures that are added or changed during the actual construction process relative to the original design. Newly added data points refer to spatial sampling points created to describe the radiation dose distribution of newly added structures.

[0098] In this step, the device first compares the 3D mesh model with the 3D building model. This comparison can be achieved using spatial registration algorithms, such as the Iterative Closest Point (ICP) algorithm or feature matching. Recognition can be based on voxel comparison or mesh difference analysis. After identifying new structural components, new data points are created in these areas. The distribution of these new data points can be based on a uniform grid. For example, a data point can be created at regular intervals (e.g., every 10 centimeters) on the surface and interior of a new wall, or a denser sampling strategy can be used for curved surfaces.

[0099] S210: Assign an initial dose value to the newly added data point based on the actual dose rate level.

[0100] Specifically, in this step, the device uses the previously obtained actual dose rate level data to assign initial dose values ​​to the newly created data points, and uses the Kriging interpolation method to estimate the initial dose values ​​for the newly added data points taking into account spatial correlation and anisotropy.

[0101] For example, suppose a 30-cm-thick concrete shield is added to a wall of a proton therapy room. The system first creates a series of data points within this new structure, for example, one point every 5 cm through the thickness. Then, based on the known dose rates in the surrounding area, the system uses kriging interpolation to estimate an initial dose value for each of these new data points. The first data point, near the inside of the treatment room, receives a relatively high initial value due to the nearby higher dose rates, while the last data point, near the outside, receives a significantly lower initial value due to the radiation attenuation characteristics of concrete. Furthermore, the system adjusts for the anisotropy of the dose distribution based on the relative position and angle of the wall to the proton beam source. For possible scattered radiation hotspots, a multiscale analysis is performed to capture these local features and reflect them in the initial dose value. Finally, an uncertainty estimate is assigned to each initial dose value. For example, data points near known measurement points are assigned lower uncertainties, while data points farther away or within complex geometry are assigned higher uncertainties.

[0102] S211. Acquire building material data of the newly added structural part in the three-dimensional building model, and calculate the attenuation coefficient corresponding to the initial dose value based on the building material data, wherein the building material data includes material parameters and geometric characteristics.

[0103] Building material data is a collection of information that describes the physical properties of building materials, including material parameters (such as density, atomic number, electron density, etc.) and geometric characteristics (such as thickness, shape, size, etc.). The attenuation coefficient is a physical quantity that indicates the degree to which the intensity of radiation is weakened when passing through the material, and is related to the composition and thickness of the material.

[0104] Specifically, the detailed information of the newly added structural part is first extracted from the three-dimensional building model, including its spatial position, shape and size. Then, the device accesses the preset building material database and obtains the corresponding material parameters according to the type of the newly added structure (such as walls, shielding doors, etc.). For composite materials or special structures, the device may need to perform material composition analysis, such as using an X-ray fluorescence spectrometer to conduct on-site measurements of the material. After obtaining the material data, the device uses a radiation physics model to calculate the attenuation coefficient. This process can use a simplified analytical method (such as an exponential decay model) or a more complex Monte Carlo simulation. For radiation with strong energy dependence (such as proton beams), the device will take into account the attenuation characteristics of different energy ranges. The calculation of the attenuation coefficient will also calculate the geometric characteristics of the material. For example, for curved structures, the device will calculate the effective thickness through which the radiation passes.

[0105] S212: Multiply the attenuation coefficient by the initial dose value to obtain a simulated dose level corresponding to the newly added data point.

[0106] The attenuation coefficient is a physical quantity that describes the degree to which radiation intensity is reduced when passing through a material. The initial dose value is a preliminary radiation dose estimate assigned to each newly added data point. The newly added data point is a spatial sampling point created within the newly added structure. The simulated dose level is the calculated theoretical radiation dose rate at each spatial point.

[0107] In this step, the device performs a dose attenuation calculation for each new data point. The device first reads the attenuation coefficient calculated in step S211 and the initial dose value assigned in step S210. The device then multiplies these two values ​​to obtain a simulated dose level that takes into account the material attenuation effect. This calculation process can be expressed as: simulated dose level = initial dose value × attenuation coefficient. For complex geometric structures or inhomogeneous materials, the device uses a ray tracing algorithm to simulate the transmission path of radiation in the material, or uses the Monte Carlo method for more accurate dose deposition simulation. In addition, the device also considers the effects of scattered radiation and secondary particles. In particular, for high-energy proton beams, it may be necessary to simulate the contribution of secondary particles such as neutrons produced by nuclear reactions.

[0108] S213. Map the numerical value corresponding to the actual dose rate level to the three-dimensional building model, and map the numerical value corresponding to the simulated dose level to the newly added structural part to obtain a three-dimensional dose distribution map, which includes a dose isosurface, a dose value at each building structure position, and a dose distribution slice map of any plane.

[0109] First, a high-density dot matrix corresponding to the building model's geometry is created in three-dimensional space. For existing structures, the fused actual dose rate data is assigned to the corresponding dot matrix locations. For newly added structures, the simulated dose level data calculated in step S212 is assigned to the corresponding dot matrix locations. During this data assignment process, dose values ​​between adjacent points are linearly interpolated to ensure continuity of the dose distribution.

[0110] The process for generating a 3D dose distribution map is as follows: First, all points in 3D space are traversed to identify sets of points with equal dose values. These sets of points are then connected to construct dose isosurfaces. To improve efficiency, a step-by-step refinement approach is employed, first determining the general outline on a coarser grid, followed by refinement in areas of high dose gradient. The entire 3D space is then divided into multiple nested cubes, each containing a specific number of dose data points. For each cube, the maximum and minimum dose values ​​are recorded, forming a hierarchical data structure.

[0111] Next, we implement the generation of dose distribution slices for any plane. The specific process is as follows: first, the position and orientation of the slice plane in three-dimensional space are determined, and then the intersection of this plane and the dose data points is calculated. For each pixel on the plane, a ray passing through the pixel is traced, and information from all dose data points along the ray path is collected. The dose value for that pixel is calculated through a weighted average. Finally, the calculated dose value is converted into color information to generate a two-dimensional dose distribution image.

[0112] In some embodiments, after step S206, the following steps may also be included:

[0113] If the simulated dose rate level at a target building location exceeds a preset simulation threshold, a local correction is performed on the target building location, where the local correction includes increasing the wall thickness and the wall material density;

[0114] Based on the partially corrected building material data, the dose rate level simulation is re-performed in the Monte Carlo program to obtain the corrected dose rate level;

[0115] The local correction and the dose rate level simulation are repeated until the simulated dose rate level at the target building location does not exceed the preset simulation threshold.

[0116] Specifically, the preset simulation threshold is a pre-determined maximum acceptable dose rate level used to determine whether protective modifications are necessary. Local modifications are structural or material adjustments made to specific building locations to reduce radiation dose rates. Increasing wall thickness refers to increasing the thickness of shielding materials to improve radiation attenuation. Increasing wall material density refers to using higher-density materials to enhance radiation shielding capabilities.

[0117] First, the simulated dose rate level at each target building location in the three-dimensional building model is checked. When the simulated dose rate level at a certain location is found to exceed the preset simulation threshold, a local correction is made to the target building location, and the thickness that needs to be increased is calculated to achieve sufficient radiation attenuation, or a suitable alternative material is selected from the preset high-density material database. The device then inputs the corrected building material data into the Monte Carlo program and re-simulates the dose rate level. If the dose rate level still exceeds the threshold, the device repeats the local correction and dose rate level simulation process. In each iteration, the device fine-tunes the correction plan based on the previous simulation results, further increasing the wall thickness or selecting a higher density material, until the simulated dose rate levels at all target building locations do not exceed the preset simulation threshold.

[0118] In some embodiments, after step S206, the following steps may also be included:

[0119] Detecting whether there is a building location in the three-dimensional dose distribution map that exceeds a preset dose rate level threshold;

[0120] If it exists, a prompt message is sent to the target client, and the prompt message includes the location information of the building and the dose rate level data.

[0121] Specifically, the dose rate level at each point in the 3D dose distribution map is compared with a preset dose rate threshold. When a point is detected where the dose rate exceeds the threshold, a prompt message is generated. The device first organizes the data for all points exceeding the threshold and converts the spatial coordinates into more easily understandable location descriptions, such as "northwest corner of the first floor" or "doorway to the treatment room on the second floor." The device then generates a detailed prompt message for each point exceeding the threshold, including the location description and the precise dose rate value. These prompt messages are packaged into a structured data packet and sent to the target client.

[0122] The following describes the intelligent monitoring and evaluation equipment in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the physical device structure of the intelligent monitoring and evaluation equipment in the embodiment of the present application.

[0123] It should be noted that Figure 3 The structure of the intelligent monitoring and evaluation device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0124] like Figure 3 As shown, the intelligent monitoring and evaluation device includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes, such as the methods described in the above embodiments, based on programs stored in a read-only memory (ROM) 302 or programs loaded from a storage unit 308 into a random access memory (RAM) 303. RAM 303 also stores various programs and data required for system operation. CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0125] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, push button switches, and the like; an output section 307 including a liquid crystal display (LCD), an audio output device, indicator lights, and the like; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 310 as needed, so that computer programs read from the removable media can be installed in the storage section 308 as needed.

[0126] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for executing the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 309 and / or installed from removable media 311. When executed by the central processing unit (CPU) 301, the computer program performs the various functions defined in the present invention.

[0127] It should be noted that specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0128] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings.

[0129] Specifically, the intelligent monitoring and evaluation device of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the intelligent monitoring and evaluation method for the radiation protection performance of the hospital proton area provided in the above embodiment is implemented.

[0130] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the intelligent monitoring and evaluation device described in the above embodiments, or may exist independently and not be incorporated into the intelligent monitoring and evaluation device. The storage medium carries one or more computer programs, which, when executed by a processor of the intelligent monitoring and evaluation device, enable the intelligent monitoring and evaluation device to implement the method for intelligently monitoring and evaluating the radiation protection performance of a hospital's proton area, as provided in the above embodiments.

[0131] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0132] As used in the above embodiments, the term “when” may be interpreted to mean “if” or “after” or “in response to determining that” or “in response to detecting that”, depending on the context. Similarly, the phrases “upon determining that” or “if (stated condition or event) is detected” may be interpreted to mean “if determining that” or “in response to determining that” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0133] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for intelligent monitoring and evaluation of radiation protection performance of a hospital proton area, characterized in that: Applied to intelligent monitoring and evaluation equipment, the method includes: Modeling the target proton therapy center in a Monte Carlo simulation based on a preset building structure and a preset equipment layout to obtain a three-dimensional mesh model of the target proton therapy center; Obtaining the actual building structure and actual equipment layout of the target proton therapy center, performing a three-dimensional scan on the actual building structure and the actual equipment layout to obtain three-dimensional scan data, and modifying a preset BIM model based on the three-dimensional scan data to obtain a three-dimensional building model; After the detection device is turned on, the measured dose rate level of the target proton therapy center at the preset target measurement point is obtained; Performing curve fitting on the measured dose rate level to obtain a measured dose rate curve, inputting each building structure position in the three-dimensional grid model into a preset credibility assessment model to obtain simulation credibility corresponding to all building structure positions in the three-dimensional grid model, and normalizing the simulation credibility to obtain an initial fusion weight; Calculating a distance attenuation coefficient for each of the building structure positions according to the initial fusion weight and the distance from the building structure position to the nearest preset target measurement point; Multiplying the initial fusion weight by the distance attenuation coefficient to obtain a final fusion weight for each building structure position; performing a weighted average of the simulated dose rate level and the dose rate at the corresponding position obtained by interpolation according to the measured dose rate curve based on the final fusion weight to obtain the actual dose rate level of each building structure part, wherein the simulated dose rate level is simulated in a Monte Carlo procedure; The actual dose rate level is mapped to the three-dimensional building model to obtain a three-dimensional dose distribution map, which includes a dose isosurface, a dose value at each building structure position, and a dose distribution slice map of any plane.

2. The method according to claim 1, characterized in that Before the steps of obtaining the actual building structure and actual equipment layout of the target proton therapy center and performing a three-dimensional scan on the actual building structure and the actual equipment layout to obtain three-dimensional scanning data, the method further includes: A dose rate level simulation is performed in a Monte Carlo program based on building material data of each building structure part in the three-dimensional grid model and treatment parameters of the proton therapy equipment in the target proton therapy center to obtain a simulated dose rate level at each building structure position in the building structure part, wherein the building material data includes density, elemental composition and mass content, and the treatment parameters include target material and beam intensity.

3. The method according to claim 2, characterized in that The step of mapping the actual dose rate level to the three-dimensional building model to obtain a three-dimensional dose distribution map specifically includes: Comparing the three-dimensional grid model with the three-dimensional building model, identifying a newly added structural portion in the three-dimensional building model, and creating a new data point in the newly added structural portion; assigning an initial dose value to the newly added data point based on the actual dose rate level; Obtaining building material data of the newly added structural part in the three-dimensional building model, and calculating the attenuation coefficient corresponding to the initial dose value based on the building material data, wherein the building material data includes material parameters and geometric characteristics; Multiplying the attenuation coefficient by the initial dose value to obtain a simulated dose level corresponding to the newly added data point; The numerical value corresponding to the actual dose rate level is mapped to the three-dimensional building model, and the numerical value corresponding to the simulated dose level is mapped to the newly added structural part to obtain a three-dimensional dose distribution map.

4. The method according to claim 2, characterized in that The step of performing dose rate level simulation based on the building material data of each building structure part in the three-dimensional grid model and the treatment parameters of the proton therapy equipment in the target proton therapy center in the Monte Carlo program to obtain the simulated dose rate level of each building structure position in the building structure part specifically includes: Obtaining display accuracy requirements for each building structure part, and dividing the three-dimensional grid model into spatial units based on the display accuracy requirements to obtain grid units; Matching simulation parameters of a corresponding Monte Carlo procedure to each of the grid cells, wherein the simulation parameters include spatial resolution, statistical error threshold, and number of iterations; Inputting the building material data and the treatment parameters into the Monte Carlo program, performing a dose rate level simulation calculation on each grid unit, and obtaining a simulated dose rate level for each grid unit; The simulated dose rate level is mapped to the corresponding building structure position in the three-dimensional grid model to obtain the simulated dose rate level of each building structure position in the building structure part.

5. The method according to claim 2, characterized in that After the step of simulating the dose rate level based on the building material data of each building structure part in the three-dimensional grid model and the treatment parameters of the proton therapy equipment in the target proton therapy center in the Monte Carlo program to obtain the simulated dose rate level for each building structure position in the building structure part, the method further includes: If the simulated dose rate level at a target building location exceeds a preset simulation threshold, performing a local correction on the target building location, wherein the local correction includes increasing the wall thickness and the wall material density; Based on the locally corrected building material data, re-simulating the dose rate level in the Monte Carlo program to obtain a corrected dose rate level; The local correction and the dose rate level simulation are repeated until the simulated dose rate level at the target building location does not exceed the preset simulation threshold.

6. The method according to claim 1, characterized in that After the step of mapping the actual dose rate level into the three-dimensional building model to obtain a three-dimensional dose distribution map, the method further includes: detecting whether there is a building location in the three-dimensional dose distribution map that exceeds a preset dose rate level threshold; If so, a prompt message is sent to the target client, wherein the prompt message includes the location information of the building location and the dose rate level data.

7. An intelligent monitoring and evaluation device, characterized in that: The intelligent monitoring and evaluation device includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the intelligent monitoring and evaluation device to execute the method described in any one of claims 1-6.

8. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on the intelligent monitoring and evaluation device, the intelligent monitoring and evaluation device is caused to execute the method according to any one of claims 1 to 6.

9. A computer program product, characterized in that When the computer program product is run on an intelligent monitoring and evaluation device, the intelligent monitoring and evaluation device is enabled to perform the method according to any one of claims 1 to 6.

Images