Radiotherapy anti-collision method and system based on three-dimensional scanning and real-time simulation

Abstract

The embodiment of the invention provides a radiotherapy anti-collision method and system based on three-dimensional scanning and real-time simulation, and the method comprises the steps: generating an initial three-dimensional model based on the body surface data of a patient; based on the initial three-dimensional model, anti-collision simulation in the radiotherapy process is executed, and a first planning path in the radiotherapy process is determined.

Description

Technical Field

[0001] The present specification relates to the field of radiation therapy collision avoidance, and in particular to a radiation therapy collision avoidance method and system based on three-dimensional scanning and real-time simulation. Background Art

[0002] During radiotherapy, it is very important to prevent collisions between patients, treatment beds, treatment heads, and equipment in the treatment room. However, conventional anti-collision methods have blind spots. For example, anti-collision technology based only on CT or cameras fails to fully consider the patient's whole body posture, especially the hands and feet, as well as the influence of the supporting structure. Therefore, it is hoped to provide a radiotherapy anti-collision method and system based on three-dimensional scanning and real-time simulation. Summary of the invention

[0003] One or more embodiments of the present specification provide a method for collision avoidance in radiotherapy based on three-dimensional scanning and real-time simulation, the method comprising: generating an initial three-dimensional model based on the patient's body surface data, the initial three-dimensional model comprising at least the three-dimensional information of the patient; based on the initial three-dimensional model, performing a simulation of collision avoidance during radiotherapy to determine a first planned path during the radiotherapy.

[0004] One or more embodiments of the present specification provide a radiation therapy collision avoidance system based on three-dimensional scanning and real-time simulation, the system comprising a model generation module and a simulation module; the model generation module is configured to generate an initial three-dimensional model based on the patient's body surface data, the initial three-dimensional model at least including the patient's three-dimensional information; the simulation module is configured to perform simulation based on the initial three-dimensional model to determine a first planned path.

[0005] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method described in the above embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0006] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0007] Figure 1 is a system schematic diagram of a radiation therapy collision avoidance system based on three-dimensional scanning and real-time simulation according to some embodiments of this specification;

[0008] Figure 2 is an exemplary flow chart of a radiation therapy collision avoidance method based on three-dimensional scanning and real-time simulation according to some embodiments of this specification;

[0009] Figure 3 is an exemplary schematic diagram of a risk prediction model according to some embodiments of this specification;

[0010] Figure 4 is a schematic diagram of an exemplary process of obtaining a second planned path according to some embodiments of this specification;

[0011] Figure 5 This is an exemplary flowchart for determining a first planned path according to some embodiments of this specification. DETAILED DESCRIPTION

[0012] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly introduces the drawings required for describing the embodiments. The drawings do not represent all implementation methods.

[0013] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. If other words can achieve the same purpose, the words can be replaced by other expressions.

[0014] Unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0015] When the operations are performed according to the step description in the embodiments of this specification, unless otherwise specified, the order of the steps is interchangeable, the steps may be omitted, and other steps may be included in the operation process.

[0016] Figure 1 It is a system schematic diagram of a radiation therapy collision avoidance system based on three-dimensional scanning and real-time simulation according to some embodiments of this specification.

[0017] In some embodiments, the radiation therapy collision avoidance system 100 based on three-dimensional scanning and real-time simulation includes a model generation module 110 and a simulation module 120 .

[0018] The model generation module is configured to generate an initial three-dimensional model based on the patient's body surface data.

[0019] The simulation module is configured to perform a simulation of collision avoidance during radiotherapy based on the initial three-dimensional model, and determine a first planned path during radiotherapy.

[0020] In some embodiments, the radiation therapy collision avoidance system 100 based on three-dimensional scanning and real-time simulation further includes a processor and a memory.

[0021] The processor is configured to process data from at least one module of the radiation therapy collision avoidance system based on three-dimensional scanning and real-time simulation 100 or an external data source. In some embodiments, the processor includes a central processing unit, a dedicated integrated circuit, an image processing unit, a controller, etc. or any combination thereof.

[0022] The memory is configured to store data, instructions and / or any other information. In some embodiments, the memory includes a mass storage, a removable storage, etc., or any combination thereof.

[0023] For detailed description of the above, please refer to Figures 2 to 5 Related description.

[0024] It should be understood that Figure 1 The radiation therapy collision avoidance system based on three-dimensional scanning and real-time simulation and its modules shown can be implemented in various ways. It should be noted that the above description of the system and its modules is only for the convenience of description and cannot limit this specification to the scope of the embodiments. It is understandable that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the modules or form a subsystem to connect with other modules without deviating from this principle. In some embodiments, Figure 1 The model generation module 110 and the simulation module 120 disclosed in the specification can be different modules in a system, or a module can realize the functions of two or more modules. For example, each module can share a storage module, or each module can have its own storage module. Such variations are within the protection scope of this specification.

[0025] Figure 2 This is an exemplary flow chart of a radiation therapy collision avoidance method based on three-dimensional scanning and real-time simulation according to some embodiments of this specification. In some embodiments, process 200 is performed by a radiation therapy collision avoidance system based on three-dimensional scanning and real-time simulation (hereinafter referred to as collision avoidance system).

[0026] In some embodiments, the collision avoidance system generates an initial three-dimensional model 220 based on the patient's body surface data 210, and performs a collision avoidance simulation during radiotherapy based on the initial three-dimensional model 220 to determine a first planned path 230 during radiotherapy.

[0027] For more information about the anti-collision system, see Figure 1 The corresponding description.

[0028] The body surface data refers to data related to the body surface of the patient, for example, at least one of the patient's body shape, height, size of each part, posture, etc. The patient includes a person who needs radiotherapy.

[0029] In some embodiments, the anti-collision system is communicatively connected to a data acquisition device, and acquires body surface data through the data acquisition device.

[0030] In some embodiments, the data acquisition device may be deployed around the patient or at any feasible location, including at least one of a 3D scanning device, an optical camera, and an ultrasonic scanning device, etc. The 3D scanning device includes a laser or a photosensitive sensor, etc.

[0031] The body surface data acquired by a 3D scanning device is represented by a three-dimensional point cloud. The body surface data acquired by an optical camera is represented by an image. The body surface data acquired by an ultrasonic scanning device is represented by ultrasonic reflection data.

[0032] The initial three-dimensional model refers to a three-dimensional model obtained by modeling based on body surface data. The initial three-dimensional model includes the patient's three-dimensional information, and the three-dimensional information refers to the information in the three-dimensional model that corresponds to the body surface data. For example, the three-dimensional information includes the size of the three-dimensional model corresponding to the patient's body shape, etc.

[0033] In some embodiments, the collision avoidance system generates an initial three-dimensional model based on body surface data through any feasible modeling method (such as factor decomposition method, neural network method, etc.) and / or external modeling software.

[0034] In some embodiments, the collision avoidance system may also acquire structural data of a supporting structure supporting the patient, and generate an initial three-dimensional model based on the body surface data and the structural data.

[0035] Support structures refer to structures that support the patient's body or come into contact with the patient's body during radiotherapy, such as the bed on which the patient receives treatment and equipment connected to the patient's body surface.

[0036] The structural data refers to data related to the physical dimensions of the support structure, for example, at least one of the dimensions of the support structure and the relative position of the support structure to the patient.

[0037] In some embodiments, the anti-collision system acquires the structural data through a data acquisition device. The data format of the structural data is similar to the data format of the body surface data.

[0038] In some embodiments, the anti-collision system generates an initial three-dimensional model based on the structural data and the body surface data by any feasible modeling method and / or external modeling software. If the anti-collision system generates an initial three-dimensional model based on the structural data and the body surface data, the three-dimensional information includes information corresponding to the structural data in the three-dimensional model. For example, the size of the three-dimensional model corresponding to the support structure, etc.

[0039] In some embodiments of the present specification, the support structure related to the patient is also taken into consideration when establishing the initial three-dimensional model, thereby constructing a more accurate initial three-dimensional model, which is beneficial to improving the authenticity and reliability of subsequent simulations.

[0040] The planned path refers to the path that indicates the movement of the treatment device. The first planned path refers to the planned path set before the start of radiotherapy. The treatment device refers to the device that performs radiotherapy (such as a CT machine, etc.). The anti-collision system is connected to the treatment device in communication.

[0041] In some embodiments, the collision avoidance system generates motion control instructions based on the first planned path, and sends the motion control instructions to the treatment device to control the treatment device to move along the first planned path after the radiotherapy begins to perform radiotherapy on the patient.

[0042] In some embodiments, the anti-collision system uses the reference path as the first planned path by querying the reference path corresponding to the body surface data and the structure data in the path preset table based on the body surface data and the structure data. The path preset table is pre-set based on historical data and includes multiple groups of body surface data and structure data, and the reference path corresponding to each group of data.

[0043] The anti-collision system records the historical body surface data and historical structure data in the historical radiotherapy process as a set of data in the path preset table, and records the first planned path in the historical radiotherapy process that actually did not collide as a reference path in the path planning table. The reference path includes the coordinates of multiple spatial points arranged in sequence.

[0044] In some embodiments, the collision avoidance system performs a simulation of collision avoidance during radiotherapy based on the initial three-dimensional model to determine a first planned path.

[0045] Simulation refers to the simulation of the movement of treatment equipment.

[0046] In some embodiments, to prevent the patient and / or the supporting structure from colliding with the treatment device during radiotherapy, the anti-collision system performs simulation based on multiple candidate first paths through simulation software, and selects any one of the candidate first paths that did not collide in the simulation as the first planned path. The simulation software includes any feasible simulation software such as built-in simulation software of the system or external simulation software (such as ADAMS, SolidWorks, etc.).

[0047] A candidate first path refers to a planned path to be determined as a first planned path. In some embodiments, the anti-collision system obtains multiple candidate first paths through user input or other means. For example, the candidate first path includes a path formed by a plurality of spatial points arranged in sequence, and the positions of the spatial points in different candidate first paths are different or partially the same. Users include doctors and the like. Users can manually set multiple planned paths as candidate first paths based on the patient's treatment needs. Treatment needs include at least one of the parts requiring radiotherapy, the amount of radiation required for each part, or the duration of radiation.

[0048] In some embodiments, the process of the anti-collision system performing simulation based on a single candidate first path includes: the anti-collision system sets an initial three-dimensional model in the simulation software, and sets a motion path of the virtual device based on the candidate first path, so that the virtual device performs a virtual motion in the simulation software, and records whether the virtual device collides with the initial three-dimensional model during the virtual motion. The virtual device refers to a model used to simulate a treatment device in the simulation software.

[0049] In some embodiments, the collision avoidance system may also perform at least one simulation based on the initial three-dimensional model and the target path library, and determine the first planned path based on the simulation results of the at least one simulation. Figure 5 and its related description.

[0050] In some embodiments of the present specification, a three-dimensional model that can accurately reflect the patient's body surface data is constructed based on the patient's complete body surface data, which can effectively eliminate the error influence of the body surface data, thereby effectively improving the accuracy and efficiency of path planning. Through simulation, it is possible to effectively predict the possible collision of the treatment device during movement, and then adjust the movement path of the treatment device to reduce the possibility of a real collision with the patient.

[0051] In some embodiments, the anti-collision system can also obtain real-time scanning data of the patient during treatment, update the initial three-dimensional model based on the real-time scanning data, obtain a real-time three-dimensional model, and perform simulation based on the real-time three-dimensional model.

[0052] Real-time scan data refers to the body surface data of the patient obtained during radiotherapy. If the patient's posture changes during radiotherapy, the real-time scan data will be inconsistent with the body surface data obtained before the start of radiotherapy.

[0053] In some embodiments, the real-time scan data may also include structural data acquired during the radiation therapy process.

[0054] In some embodiments, the data acquisition device may continuously acquire body surface data and structure data as real-time scanning data during the radiotherapy process, and send the data to the anti-collision system.

[0055] The real-time 3D model refers to a 3D model obtained after the initial 3D model is updated.

[0056] In some embodiments, the anti-collision system updates the initial three-dimensional model based on the real-time scanning data through real-time three-dimensional reconstruction technology (such as BundleFusion, etc.) to obtain a real-time three-dimensional model.

[0057] For example, for real-time scanning data acquired by an optical camera, the anti-collision system can pre-process the real-time scanning data, and extract information related to the patient and / or the supporting structure in the image by image recognition and processing technology, etc., convert the obtained information into three-dimensional information, and use real-time three-dimensional reconstruction technology (such as BundleFusion, etc.) to update the initial three-dimensional model to obtain a real-time three-dimensional model. The pre-processing includes at least one of removing noise, adjusting resolution, and cropping the region of interest. The region of interest includes the area where the patient needs to undergo radiotherapy, etc.

[0058] In some embodiments, after obtaining the real-time three-dimensional model, the anti-collision system may further update the real-time three-dimensional model based on subsequently acquired real-time scanning data by using the above method for updating the initial three-dimensional model.

[0059] In some embodiments, after obtaining the real-time three-dimensional model, the collision avoidance system may further perform simulation based on the real-time three-dimensional model to determine whether the patient and / or the supporting structure may collide with the treatment device.

[0060] In some embodiments of the present specification, by real-time monitoring of relevant information of the patient and / or supporting structure and updating the initial three-dimensional model based on the obtained information, the accuracy of the three-dimensional model can be effectively improved, thereby improving the accuracy of the simulation and facilitating the judgment of subsequent operations.

[0061] In some embodiments, the anti-collision system may also determine a first collision risk based on the real-time three-dimensional model and the first planned path, and generate warning information and issue a warning in response to the first collision risk satisfying a warning condition.

[0062] The first collision risk refers to the collision risk corresponding to the first future time. The collision risk is used to characterize the possibility of collision between the therapeutic device and the patient and / or the supporting structure when the therapeutic device is moving. In some embodiments, the collision risk is represented by a numerical value or the like, and the larger the numerical value, the higher the collision risk.

[0063] The first future time refers to the future time after the real-time three-dimensional model is obtained.

[0064] In some embodiments, the first future time includes at least one future time point. The number of future time points is related to the motion characteristics of the treatment device.

[0065] The motion feature is used to characterize the motion of the therapeutic device. In some embodiments, the motion feature includes at least one of motion speed, motion acceleration, etc. The number of future time points may be positively correlated to the motion speed or motion acceleration, and the greater the motion speed or motion acceleration, the greater the number of future time points.

[0066] In some embodiments of the present specification, the number of future time points is related to the motion characteristics of the treatment device, and more future time points can be determined when the treatment device runs faster, thereby predicting the collision risk for a longer period of time in the future, which is beneficial to improving the safety of radiotherapy.

[0067] In some embodiments, the anti-collision system determines the first collision risk in a variety of ways based on the real-time three-dimensional model and the first planned path. For example, the anti-collision system performs a simulation again based on the real-time three-dimensional model and the first planned path, and counts the number of collisions that occur during the simulation. The more collisions that occur, the greater the first collision risk.

[0068] For another example, the anti-collision system converts and / or fuses the real-time three-dimensional model and the first planned path into feature vectors to obtain a path vector, clusters the path vector as a cluster center among multiple historical path vectors, and determines the first collision risk based on the vector set corresponding to the cluster center. The anti-collision system can extract a preset number of historical path vectors from the vector set, obtain historical collision results corresponding to these historical path vectors from historical data, calculate the ratio of the number of collisions in the historical collision results to the preset number, and use the ratio as the first collision risk. The preset data is pre-set based on historical experience.

[0069] The historical path vector refers to the feature vector obtained by the anti-collision system by converting and / or fusing the historical real-time 3D model and the historical first planned path. The historical collision result corresponding to the historical path vector refers to the collision result actually occurred during the historical radiotherapy process corresponding to the historical path vector. The collision result includes collision and no collision.

[0070] In some embodiments, the collision avoidance system can also determine the first collision risk at each future time point in the first future time through a risk prediction model based on the real-time three-dimensional model and the first planned path. Figure 3 and its related description.

[0071] The early warning condition refers to the condition for determining whether to generate early warning information and issue an early warning. In some embodiments, the early warning condition is pre-set based on historical experience. For example, the first collision risk is greater than the risk threshold. The risk threshold is pre-set based on historical experience.

[0072] In some embodiments, if the collision avoidance system determines the first collision risk at each future time point in the first future time through a risk prediction model, the warning condition includes that the average value of the first collision risks at multiple future time points is greater than a risk threshold, etc.

[0073] Warning information refers to information related to the content of the warning. For example, reminding the user that the first collision risk is high or reminding the patient not to move around. In some embodiments, the way of issuing the warning includes any feasible way such as a prompt sound.

[0074] In some embodiments of the present specification, the collision risk in the future is dynamically calculated through a real-time three-dimensional model and a first planned path, thereby improving the accuracy and timeliness of the collision risk assessment, and issuing an early warning helps to take timely measures to avoid collisions and ensure the safety of patients and treatment equipment.

[0075] In some embodiments, the collision avoidance system may further modify the first planned path based on the real-time three-dimensional model to obtain a second planned path, and determine a second collision risk based on the real-time three-dimensional model and the second planned path.

[0076] In some embodiments, in response to the second collision risk satisfying the warning condition, the collision avoidance system generates warning information and issues a warning, and / or updates the second planned path.

[0077] The second planned path refers to a path indicating the movement of the treatment device after the real-time three-dimensional model is obtained.

[0078] In some embodiments, the collision avoidance system generates motion control instructions based on the second planned path, and sends the motion control instructions to the treatment device to control the treatment device to move along the second planned path to perform radiotherapy on the patient.

[0079] In some embodiments, the anti-collision system corrects the first planned path based on the real-time three-dimensional model to obtain multiple candidate second paths, and simulates each candidate second path to obtain the second planned path. The candidate second path refers to the planned path to be determined as the second planned path. The anti-collision system can select any one of the candidate second paths that did not collide in the simulation as the second planned path.

[0080] In some embodiments, the anti-collision system modifies the first planned path in a variety of ways. For example, the anti-collision system obtains the modified first planned path (i.e., the candidate second path) through user input. The user can manually modify the first planned path, generate multiple candidate second paths, and input them into the anti-collision system.

[0081] For another example, the anti-collision system can divide the first planned path into multiple spatial points based on a preset distance, and randomly adjust the coordinates of one or more of the spatial points, thereby completing the correction of the first planned path and obtaining multiple candidate second paths. The preset distance is pre-set based on historical experience.

[0082] The second collision risk refers to the collision risk corresponding to the second future time. The second future time refers to the future time after the second planned path is obtained. In some embodiments, the second future time is later than or equal to the first future time. The second future time includes at least one future time point.

[0083] In some embodiments, the method for the collision avoidance system to determine the second collision risk is similar to the method for determining the first collision risk. The implementation method thereof may refer to the method for determining the first collision risk.

[0084] In some embodiments, the warning condition also includes that the second collision risk is greater than a risk threshold, etc. In response to the second collision risk satisfying the warning condition, the anti-collision system generates warning information and issues a warning and / or updates the second planned path. The anti-collision system obtains the updated second planned path, and can also continue to determine the second collision risk corresponding to the updated second planned path, and in response to the new second collision risk satisfying the warning condition, updates the second planned path again.

[0085] In some embodiments, the anti-collision system updates the second planned path in a variety of ways. For example, the anti-collision system updates the second planned path by determining the second planned path in the above manner. For another example, the anti-collision system directionally adjusts the second planned path based on the second planned path, and simulates the adjusted second planned path. If no collision occurs in the simulation, the adjusted second planned path is used as the new second planned path. If a collision occurs in the simulation, the second planned path continues to be directionally adjusted.

[0086] In some embodiments, the directional adjustment of the second planned path includes: the anti-collision system divides the second planned path into multiple spatial points based on a preset distance, and adjusts the coordinates of the spatial points that are prone to collision in a direction away from the patient, thereby obtaining the adjusted second planned path. The adjustment range is pre-set based on historical experience. The anti-collision system can regard multiple spatial points that are too close to the real-time three-dimensional model or overlap as spatial points that are prone to collision.

[0087] In some embodiments of the present specification, the first planned path is corrected based on the real-time three-dimensional model to obtain the second planned path, so as to dynamically adjust the motion path of the treatment equipment during the radiotherapy process, thereby improving the accuracy, safety and intelligence level of the radiotherapy process.

[0088] Figure 3 It is an exemplary schematic diagram of the risk prediction model shown in some embodiments of this specification.

[0089] In some embodiments, the collision avoidance system determines the first collision risk 350 through the risk prediction model 340 based on the real-time three-dimensional model 310 and the first planned path 230. For a description of the real-time three-dimensional model, the first planned path, and the first collision risk, see Figure 2 and its related description.

[0090] The risk prediction model refers to a model used to determine the first collision risk. In some embodiments, the risk prediction model may be a machine learning model. For example, the risk prediction model may include any one or a combination of a convolutional neural network (CNN) model, a neural network (NN) model, or other custom model structures.

[0091] In some embodiments, the input of the risk prediction model includes a real-time three-dimensional model and a first planned path, and the output includes a first collision risk at each future time point in the first future time.

[0092] In some embodiments, the anti-collision system trains a risk prediction model based on a large number of first training samples with first labels by gradient descent method, etc. The first training sample includes a sample real-time three-dimensional model and a sample first planned path, and the first label of the first training sample can be the actual collision risk of each sample future time point in the sample first future time corresponding to the first training sample.

[0093] In some embodiments, the first training sample and the first label are determined based on historical data. For example, the anti-collision system uses historical real-time three-dimensional models and historical first planned paths in historical radiotherapy processes as the first training sample. For the first training sample where no collision actually occurred, the labels of all time points corresponding to the first training sample are set to 0. For the first training sample where a collision actually occurred, the label of the time point where the collision occurred is set to 1, and the label of the time point where no collision occurred is set to a value between 0 and 1. The closer the time point where no collision occurs is to the time point where the collision occurs, the closer its label is to 1.

[0094] In some embodiments, the risk prediction model can be trained in the following manner: multiple first training samples with first labels are input into the initial risk prediction model, a loss function is constructed by the first label and the prediction result of the initial risk prediction model, the initial risk prediction model is updated based on the iteration of the loss function, and the risk prediction model training is completed when the loss function of the initial risk prediction model meets the preset conditions. The preset conditions may be that the loss function converges, the number of iterations reaches a set value, etc.

[0095] In some embodiments, the input of the risk prediction model also includes the number of data blind spots 320 and the site activity 330 corresponding to each data blind spot.

[0096] The data blind area refers to the patient's body part where the data acquisition device cannot collect body surface data, for example, the patient's body part that is blocked by the treatment device during the movement of the treatment device.

[0097] In some embodiments, the anti-collision system determines the data blind area based on the real-time scanning data. For example, if the data acquisition device is an optical camera, the anti-collision system determines the body parts of the patient blocked by the treatment device based on the real-time scanning data through image recognition and processing technology, and determines such body parts as data blind areas. For another example, if the data acquisition device is a 3D scanning device, due to the difference between the three-dimensional space point cloud obtained by scanning the human body and scanning the treatment device, the anti-collision system can directly determine the body parts of the patient blocked by the treatment device based on the real-time scanning data, and determine such body parts as data blind areas.

[0098] Partial activity refers to the activity level of the part corresponding to the patient's data blind area. The part activity corresponding to each data blind area is determined separately. For instructions on how to determine part activity, see Figure 4 and its related description.

[0099] In some embodiments, if the input of the risk prediction model also includes the number of data blind spots and the activity of the parts corresponding to each data blind spot, then the first training sample also includes the number of sample data blind spots and the activity of the sample parts corresponding to each sample data blind spot.

[0100] In some embodiments of the present specification, the site activity of the data blind spot helps to reflect the movement tendency of the part corresponding to the patient's data blind spot in the absence of data support. Adding the site activity of the data blind spot to the input of the risk prediction model helps to improve the accuracy of the output of the first collision risk.

[0101] In some embodiments of the present specification, the real-time three-dimensional model and data such as the first planned path are processed through a risk prediction model. The self-learning ability of the machine learning model can be used to find patterns from a large amount of data, obtain the correlation between the real-time three-dimensional model and data such as the first planned path and the first collision risk, and improve the accuracy and efficiency of determining the user's first collision risk.

[0102] Figure 4 This is an exemplary flow diagram of obtaining a second planning path according to some embodiments of this specification. In some embodiments, process 400 is executed by a radiation therapy collision avoidance system based on three-dimensional scanning and real-time simulation (hereinafter referred to as collision avoidance system).

[0103] Step 410: Determine at least one safety buffer zone.

[0104] The safety buffer is the space reserved to prevent the patient from colliding with the treatment equipment. For example, the safety buffer is the space obtained by expanding the local contour of the 3D model by a certain distance, so the size of the safety buffer can be expressed by the expansion distance of the safety buffer.

[0105] In some embodiments, the anti-collision system determines at least one safety buffer zone in a variety of ways. For example, the anti-collision system sets a safety buffer zone based on a model boundary and a preset space size. The model boundary refers to the boundary points of the initial three-dimensional model or the real-time three-dimensional model and the edges connected by the boundary points. The preset space size is pre-set based on historical experience, such as a space extending 5 cm outward from the model boundary.

[0106] In some embodiments, the anti-collision system can also determine at least one safety buffer zone based on the regional characteristics of the data blind zone. Figure 3 and its related description.

[0107] The regional feature refers to information related to the data blind area. In some embodiments, the regional feature includes the patient's body part corresponding to the data blind area, etc. The regional feature is synchronously determined by the anti-collision system in the process of determining the data blind area.

[0108] Exemplarily, the anti-collision system searches for reference regional features that are identical to the regional features in a preset feature table based on the regional features of the data blind area, and determines the reference buffer corresponding to the reference regional features as the safety buffer corresponding to the data blind area, wherein each data blind area corresponds to a safety buffer.

[0109] The preset feature table is pre-set based on historical data, including multiple reference area features and a reference buffer corresponding to each reference area feature. In some embodiments, the anti-collision system counts the historical area features of the historical data blind area during the historical radiotherapy process as reference area features into the preset feature table, and counts the historical safety buffer (such as the 30 cm space extending outward from the data blind area) into the preset feature table.

[0110] In some embodiments, the regional feature also includes the regional area of ​​the data blind zone. The regional area refers to the area occupied by the part corresponding to the data blind zone. The anti-collision system can also determine at least one safety buffer zone based on the regional area. Exemplarily, the larger the regional area, the larger the outward expansion distance of the safety buffer zone corresponding to the data blind zone.

[0111] In some embodiments of the present specification, the larger the data blind area, the higher the potential collision risk. Increasing the size of the safety buffer area corresponding to the larger data blind area helps to further reduce the potential collision risk.

[0112] In some embodiments of the present specification, different safety buffer zones are set according to different data blind areas, thereby improving the flexibility of ensuring the safety of radiotherapy.

[0113] In some embodiments, the anti-collision system may also determine the activity of the part corresponding to the data blind area based on the regional characteristics, and determine at least one safety buffer zone based on the regional characteristics and the activity of the part. The safety buffer zone corresponding to each data blind area is determined based on the regional characteristics and the activity of the part of the data blind area.

[0114] In some embodiments, the anti-collision system determines the activity frequency and activity amplitude of the patient's body part before the data blind area based on the real-time scan data of the patient's body part corresponding to the regional features, calculates the weighted sum of the activity frequency and activity amplitude, and determines the weighted sum as the activity degree of the part in the data blind area. The activity frequency and activity amplitude can be determined by any feasible method such as image comparison, three-dimensional space point cloud change, etc.

[0115] In some embodiments, the anti-collision system queries a regional preset table based on regional features and part activity to determine at least one safety buffer zone. The regional preset table is pre-set based on historical experience and includes multiple groups of regional features and part activity, and the outer expansion distance of the safety buffer zone corresponding to each group of regional features and part activity. The outer expansion distance of the safety buffer zone is positively correlated to the area of ​​the data blind zone and the part activity corresponding to the data blind zone.

[0116] In some embodiments, the anti-collision system determines the outward expansion distance of the safety buffer zone corresponding to the data blind spot through a buffer prediction model based on regional characteristics and site activity.

[0117] The buffer prediction model refers to a model used to determine the expansion distance of the safety buffer zone. In some embodiments, the buffer prediction model may be a machine learning model. For example, the buffer prediction model may include any one or a combination of a convolutional neural network (CNN) model, a neural network (NN) model, or other custom model structures.

[0118] In some embodiments, the anti-collision system trains the buffer prediction model based on a large number of second training samples with second labels by gradient descent method, etc. The second training samples include sample area features and sample part activity, and the second label of the second training sample can be the actual expansion distance of the safety buffer zone corresponding to the second training sample.

[0119] In some embodiments, the second training sample and the second label are determined based on historical data. For example, the anti-collision system counts historical radiotherapy processes in which no collision occurs and the radiotherapy efficiency is high, and uses the regional characteristics and site activity corresponding to the blind spots in the historical data of such historical radiotherapy processes as the second training sample, and uses the outer expansion distance of the safety buffer zone actually used in such historical radiotherapy processes as the second label. Among them, the radiotherapy efficiency can be represented by the radiotherapy time, etc. The shorter the radiotherapy time, the higher the radiation quality efficiency.

[0120] In some embodiments, the training process of the buffer prediction model is similar to the training process of the risk prediction model, and its implementation method refers to the training process of the risk prediction model.

[0121] In some embodiments of the present specification, the higher the part activity, the higher the potential collision risk. Based on the part activity, determining the size of the safety buffer corresponding to the data blind spot in a variety of ways helps to improve the efficiency of determining the safety buffer and further reduce the potential collision risk.

[0122] In some embodiments, the collision avoidance system executes step 420 based on the real-time three-dimensional model 310 and at least one safety buffer zone obtained in step 410 to obtain a second planned path 430 .

[0123] Step 420: Correct the first planned path.

[0124] In some embodiments, the anti-collision system fuses the safety buffer zone with the real-time 3D model through any feasible method such as point cloud union to obtain a fused 3D model, and based on the fused 3D model, corrects the first planned path to obtain a second planned path. The method for anti-collision to correct the first planned path based on the fused 3D model is similar to the method for correcting the first planned path based on the real-time 3D model. The implementation method can be found in Figure 2 and its related description.

[0125] In some embodiments of the present specification, a safety buffer zone is reserved to ensure that even if the patient moves slightly unexpectedly during radiotherapy, no collision will occur, thereby improving the safety of the radiotherapy process.

[0126] Figure 5 This is an exemplary flow chart for determining the first planning path according to some embodiments of the present specification. In some embodiments, process 500 is executed by a radiation therapy collision avoidance system based on three-dimensional scanning and real-time simulation (hereinafter referred to as collision avoidance system).

[0127] Step 510, determine the target path library.

[0128] The target path library refers to a database containing multiple planned paths. In some embodiments, the collision avoidance system stores multiple target path libraries, each of which corresponds to a type of treatment need. The collision avoidance system determines the corresponding type of target path library based on the current patient's treatment needs. For a description of treatment needs, see Figure 2 and its related description.

[0129] In some embodiments, the process of constructing the target path library includes: for each treatment need, the anti-collision system counts a large amount of historical data of historical treatment needs that are the same or similar to the treatment need, determines the historical radiotherapy process corresponding to such historical treatment needs as the target historical data, determines the target historical data with better radiotherapy effect in the target historical data as the preferred historical data, and adds the planning path used in the preferred historical data as the candidate planning path to the target path library. The radiotherapy effect is manually marked by the user based on historical experience.

[0130] The anti-collision system determines whether the treatment needs and historical treatment needs are similar by converting them into feature vectors and calculating vector similarity. Vector similarity is negatively correlated to vector distance. Vector distance includes Euclidean distance, etc.

[0131] Step 520: Perform at least one simulation based on the initial three-dimensional model and the target path library.

[0132] In some embodiments, the process of a single simulation includes:

[0133] S1: The anti-collision system selects a candidate planning path from the target path library based on a preset selection order as the target planning path for this simulation. The preset selection order includes selecting the candidate planning path with the most historical usage times among the candidate planning paths that have not been selected. Among them, the candidate planning path that has not been selected refers to the candidate planning path that has not been selected in at least one current simulation. The number of historical usage times is determined by the historical data statistics of the anti-collision system.

[0134] Exemplarily, at least one current simulation has been simulated once, recorded as the first simulation, and this simulation is the second simulation. If the target path library includes 5 paths (respectively recorded as paths 1 to 5, and the historical usage times of paths 1 to 5 are sorted from high to low), then the target planning path selected for the first simulation is path 1, and the target planning path selected for the second simulation is path 2. The candidate planning paths that have not been selected include paths 3 to 5.

[0135] S2: Based on the target planning path and the initial three-dimensional model, determine the test collision risk corresponding to the target planning path. The test collision risk is used to characterize the possibility of the therapeutic device colliding with the patient and / or the supporting structure when moving along the target planning path. The method for determining the test collision risk is similar to the method for determining the first collision risk. The implementation method thereof is shown in Figure 2 and its related description.

[0136] S3: In response to the test collision risk not meeting the termination condition, the next simulation is performed. The termination condition includes that the test collision risk is not less than the risk threshold. For an explanation of the risk threshold, see Figure 2 and its related description.

[0137] S4: In response to the collision risk corresponding to the target planned path satisfying an end condition, at least one simulation ends.

[0138] Step 530: Determine a first planned path based on the simulation result of at least one simulation.

[0139] For more information about the first planning path, see Figure 2 and its related description.

[0140] In some embodiments, the anti-collision system determines the candidate planning path with the lowest test collision risk in the simulation results as the first planning path based on the simulation results of at least one simulation. The simulation results include the test collision risk determined by each simulation.

[0141] In some embodiments of the present specification, a target path library that is combined with the patient's treatment needs is used to comprehensively evaluate and determine the best first planned path, thereby improving the efficiency of determining the first planned path.

[0142] It should be noted that the above description of the process 400 and the process 500 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0143] Some embodiments of the present specification also provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes any of the methods in the above embodiments.

[0144] Furthermore, certain features, structures or characteristics in one or more embodiments of this specification may be appropriately combined.

[0145] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0146] If there is any inconsistency or conflict between the descriptions, definitions, and / or usage of terms in the materials cited in this specification and the contents described in this specification, the descriptions, definitions, and / or usage of terms in this specification shall prevail.

Claims

1. A radiation therapy anti-collision method based on three-dimensional scanning and real-time simulation, characterized in that: The method comprises: Based on the body surface data of the patient, an initial three-dimensional model is generated, wherein the initial three-dimensional model at least includes the three-dimensional information of the patient; Based on the initial three-dimensional model, a simulation of collision avoidance during radiotherapy is performed to determine a first planned path during the radiotherapy.

2. The method according to claim 1, characterized in that The method further comprises: Acquiring real-time scanning data of the patient during treatment; Based on the real-time scanning data, the initial three-dimensional model is updated to obtain a real-time three-dimensional model; The simulation is performed based on the real-time three-dimensional model.

3. The method according to claim 2, characterized in that The method further comprises: Determining a first collision risk based on the real-time three-dimensional model and the first planned path, where the first collision risk is a collision risk corresponding to a first future time; In response to the first collision risk satisfying a warning condition, warning information is generated and a warning is issued.

4. The method according to claim 3, characterized in that The determining the first collision risk based on the real-time three-dimensional model and the first planned path includes: Based on the real-time three-dimensional model and the first planned path, the first collision risk is determined by a risk prediction model, and the risk prediction model is a machine learning model.

5. The method according to claim 4, characterized in that The input of the risk prediction model also includes the number of data blind areas and the site activity corresponding to each data blind area, where the site activity is the activity level of the patient's site in the data blind area.

6. The method according to claim 3, characterized in that The first future time includes at least one future time point, and the number of the at least one future time point is related to the movement characteristics of the treatment device.

7. The method according to claim 2, characterized in that The method further comprises: Based on the real-time three-dimensional model, the first planned path is corrected to obtain a second planned path; Determining a second collision risk based on the real-time three-dimensional model and the second planned path, where the second collision risk is a collision risk corresponding to a second future time, where the second future time is later than or equal to the first future time; In response to the second collision risk satisfying a warning condition, warning information is generated and a warning is issued, and / or the second planned path is updated.

8. The method according to claim 1, characterized in that The method further comprises: Identify at least one safety buffer zone; Based on the real-time three-dimensional model and the at least one safety buffer zone, the first planned path is corrected to obtain a second planned path.

9. The method according to claim 8, characterized in that Determining at least one safety buffer zone comprises: Identify data blind spots; The at least one safety buffer zone is determined based on the regional characteristics of the data blind zone.

10. The method according to claim 9, characterized in that The regional feature includes the area of ​​the data blind area, and the determining the at least one security buffer area based on the regional feature of the data blind area includes: Based on the area of ​​the region, the at least one safety buffer zone is determined.

11. The method according to claim 10, characterized in that The determining of the at least one security buffer zone based on the regional characteristics of the data blind zone further comprises: Based on the regional characteristics, determining the activity of the part corresponding to the data blind area; The at least one safety buffer zone is determined based on the regional features and the part activity.

12. The method according to claim 1, characterized in that The method further comprises: acquiring structural data of a support structure supporting the patient; The initial three-dimensional model is generated based on the body surface data and the structural data, and the initial three-dimensional model also includes the structural data.

13. The method according to claim 1, characterized in that The performing of a simulation of collision avoidance during radiotherapy based on the initial three-dimensional model to determine a first planned path during radiotherapy comprises: Determine the target path library; At least one simulation is performed based on the initial three-dimensional model and the target path library, and the process of each simulation includes: Selecting a candidate planning path from the target path library based on a preset selection order as the target planning path for this simulation; Determining a test collision risk corresponding to the target planning path based on the target planning path and the initial three-dimensional model; In response to the test collision risk not satisfying an end condition, performing a next simulation; In response to the collision risk corresponding to the target planned path satisfying an end condition, the at least one simulation ends; Based on the simulation result of the at least one simulation, the first planned path is determined.

14. A radiation therapy anti-collision system based on three-dimensional scanning and real-time simulation, characterized in that: The system includes a model generation module and a simulation module; The model generation module is configured to generate an initial three-dimensional model based on the body surface data of the patient, wherein the initial three-dimensional model at least includes the three-dimensional information of the patient; The simulation module is configured to perform a simulation of collision avoidance during radiotherapy based on the initial three-dimensional model, and determine a first planned path during the radiotherapy.

15. A computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method according to any one of claims 1 to 13.

Images