Collision prediction method, device and readable storage medium

Abstract

This application relates to a collision prediction method, apparatus, and readable storage medium. The method is applied to a radiotherapy device, which includes moving parts. The method includes: determining the real-time outer contour of the object based on a real-time acquired object image; and before performing radiotherapy, superimposing the expected motion model of the moving parts during radiotherapy with the real-time outer contour to perform collision prediction. This solves the problem of being unable to predict the collision risk between moving parts and objects during radiotherapy.

Description

Technical Field

[0001] This application relates to the field of medical devices, and in particular to a collision prediction method, apparatus, and readable storage medium. Background Technology

[0002] Radiotherapy is an important treatment for malignant tumors. During radiotherapy, the patient is alone in a treatment room with a radiation environment, and the equipment operator cannot directly observe the patient from outside the treatment room. Although images of the patient in the treatment room can be acquired using image acquisition devices, the obstruction of the treatment equipment and the patient's body prevents full-angle, multi-part observation. Radiotherapy equipment includes medical accelerator systems, which contain mechanically moving parts such as treatment heads. These parts pose a potential risk of colliding with the patient during treatment, endangering their safety. Existing technology provides a simulation method to assess the risk of collision during treatment, comparing the expected trajectory of moving parts with the patient's current position before treatment begins to evaluate the likelihood of a collision. However, this method cannot predict the collision risk caused by individual differences in the patient or changes in the posture of moving parts and the patient during treatment. Summary of the Invention

[0003] This embodiment provides a collision prediction method, apparatus, and readable storage medium to address the problem in related technologies that cannot predict the collision risk between moving parts and objects during radiotherapy.

[0004] Firstly, this embodiment provides a collision prediction method applied to a radiotherapy device, the radiotherapy device including moving parts, the collision prediction method comprising:

[0005] Determine the real-time outer contour of the object based on the real-time acquired object image;

[0006] Prior to the administration of radiotherapy, the expected motion model of the moving part during the radiotherapy is superimposed on the real-time outer contour to perform collision prediction.

[0007] In some embodiments, superimposing the expected motion model of the moving part during radiotherapy with the real-time outer contour for collision prediction includes:

[0008] Based on the superposition result of the expected motion model and the real-time outer contour, at least one spacing value between the expected motion model and the real-time outer contour is determined;

[0009] If any one or more of the at least one spacing value is less than a preset spacing threshold, it is determined that there is a risk of collision between the moving part and the object.

[0010] In some embodiments, the step of overlaying the expected motion model of the moving part during radiotherapy with the real-time outer contour for collision prediction further includes:

[0011] The result of overlaying the expected motion model with the real-time outer contour is displayed.

[0012] In some embodiments, the collision prediction method further includes:

[0013] If it is determined that there is a risk of collision between the moving part and the object, the collision angle between the moving part and the object is obtained; based on the collision angle, the spatial position corresponding to the collision risk is magnified and displayed, and a collision warning is issued.

[0014] In some embodiments, displaying the superposition result of the expected motion model and the real-time outer contour includes:

[0015] Based on user-inputted perspective adjustment commands, adjust the superimposed display angle of the expected motion model and the real-time outer contour; and / or

[0016] Based on the user's zoom command and display area, the expected motion model and real-time outer contour corresponding to the display area are scaled down or enlarged.

[0017] In some embodiments, the collision prediction method further includes:

[0018] During radiotherapy, the expected motion model of the moving part corresponding to a future moment after the current moment is superimposed on the real-time outer contour to perform collision prediction.

[0019] In some of these embodiments, the expected motion model is generated through the following steps:

[0020] Based on multiple image acquisition devices, images of moving parts at multiple angles corresponding to preset treatment times are obtained.

[0021] Based on the multi-angle motion component images and the planned trajectory of the motion component, the motion parameters of the motion component at the preset treatment time are determined;

[0022] Based on the motion parameters, a motion model of the moving part after a preset time is generated.

[0023] In some embodiments, prior to determining the real-time outer contour of the object based on the real-time acquired object image, the method includes:

[0024] The image of the object acquired by the image acquisition device is displayed, and the image of the object includes the surface markings of the object;

[0025] The object image is compared with a pre-generated object placement model to obtain the placement deviation;

[0026] The placement of the object is adjusted based on the placement deviation.

[0027] Secondly, this embodiment provides a collision prediction device for radiotherapy, which is applied to a radiotherapy system. The radiotherapy system includes an image acquisition device and moving parts of the radiotherapy equipment. The device includes:

[0028] A contour determination module is used to determine the real-time outer contour of an object based on an object image acquired by the image acquisition device during the treatment process.

[0029] A collision detection module is used to overlay the expected motion model of the moving part during the radiotherapy treatment onto the real-time outer contour to perform collision prediction before the radiotherapy is performed.

[0030] Thirdly, this embodiment provides a computer-readable storage medium having instructions stored thereon that, when executed, cause a processor to perform the collision prediction method as described in the first aspect.

[0031] Compared with related technologies, the collision prediction method provided in this embodiment determines the real-time outer contour of the object based on real-time acquired object images, thereby obtaining the real-time posture changes of the object before radiotherapy. By superimposing the expected motion model of the moving part during radiotherapy with the real-time outer contour before performing radiotherapy to perform collision prediction, the correctness of the planned trajectory of the moving part is verified and it is determined whether there is a collision risk between the moving part and the object. This solves the problem in related technologies that cannot predict the collision risk between the moving part and the object during radiotherapy, and improves the safety of radiotherapy.

[0032] Fourthly, this embodiment provides a quality control method for a radiotherapy device, the method comprising:

[0033] The quality control execution time for the radiotherapy equipment is determined based on the usage time of the radiotherapy equipment.

[0034] Based on the quality control execution time, the radiotherapy equipment is controlled to automatically perform quality control.

[0035] In some embodiments, the method further includes:

[0036] Send the quality control results to the interactive terminal.

[0037] In some embodiments, determining the quality control execution time of the radiotherapy equipment based on its usage time includes:

[0038] The usage time of the radiotherapy equipment is analyzed, and the expected idle time of the radiotherapy equipment within a preset future date is determined based on the analysis results.

[0039] The quality control execution time is determined based on the expected idle period.

[0040] In some embodiments, the analysis of the usage time of the radiotherapy equipment and the determination of the expected idle time of the radiotherapy equipment within a preset future time period based on the analysis results include:

[0041] By inputting the historical usage times of multiple radiotherapy devices into a pre-trained machine learning model, the expected idle time periods of the radiotherapy devices within a preset future time period are obtained.

[0042] In some embodiments, the quality control includes equipment quality control and / or radiotherapy plan quality control.

[0043] In some embodiments, controlling the radiotherapy equipment to automatically perform quality control based on the quality control execution time includes:

[0044] Based on the quality control execution time, the radiotherapy equipment is started and put into equipment quality control mode;

[0045] The equipment quality control is performed based on the preset first quality control item.

[0046] In some embodiments, after performing the equipment quality control based on a preset first quality control item, the method further includes:

[0047] Based on the predetermined radiotherapy plan, obtain the corresponding second quality control item;

[0048] The radiotherapy plan quality control is performed based on the second quality control item.

[0049] In some embodiments, the interactive terminal is a mobile terminal, and sending the quality control results to the interactive terminal includes:

[0050] The execution result can be sent to the interactive terminal through one or more of the following methods: application, mini-program, SMS, and voice message.

[0051] Fifthly, this embodiment provides a quality control device for a radiation delivery device, the device comprising:

[0052] The acquisition module is used to determine the quality control execution time of the radiotherapy equipment based on the usage time of the radiotherapy equipment;

[0053] The control module is used to control the radiotherapy equipment to automatically perform quality control based on the quality control execution time.

[0054] In a sixth aspect, this embodiment provides an automatic quality control execution system, which includes a radiotherapy device and a controller. The controller is used to control the radiotherapy device to automatically perform quality control based on the quality control method for the radiotherapy device described in the fourth aspect.

[0055] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0056] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0057] Figure 1 These are structural block diagrams of radiotherapy systems according to some embodiments of this application;

[0058] Figure 2 This is a flowchart of a collision prediction method for radiotherapy according to some embodiments of this application;

[0059] Figure 3 This is a flowchart of collision prediction after model superposition in some embodiments of this application;

[0060] Figure 4 This is a flowchart showing the display results of model overlay in some embodiments of this application;

[0061] Figure 5 This is a flowchart illustrating the expected motion model of a moving part generated according to some embodiments of this application;

[0062] Figure 6 This is a flowchart of the placement adjustment in some embodiments of this application;

[0063] Figure 7 This is a flowchart of a collision prediction method for radiotherapy according to some preferred embodiments of this application;

[0064] Figure 8 This is a structural block diagram of a collision prediction device for radiotherapy according to some embodiments of this application. Detailed Implementation

[0065] To better understand the purpose, technical solution, and advantages of this application, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0066] Unless otherwise defined, the technical or scientific terms used in this application shall have the general meaning as understood by one of ordinary skill in the art to which this application pertains. Words such as “a,” “an,” “an,” “the,” “the,” and “these,” used in this application, do not indicate quantitative limitation and may be singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or modules (units) is not limited to the listed steps or modules (units) but may include steps or modules (units) not listed, or may include other steps or modules (units) inherent to such processes, methods, products, or devices. The terms “connected,” “linked,” and “coupled,” used in this application, are not limited to physical or mechanical connections but may include electrical connections, whether direct or indirect. The term “multiple” used in this application refers to two or more. The "and / or" operator describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: A alone, A and B simultaneously, and B alone. Typically, the character " / " indicates that the objects before and after it are in an "or" relationship. The terms "first," "second," and "third," etc., used in this application are merely for distinguishing similar objects and do not represent a specific ordering of the objects.

[0067] The collision prediction method for radiotherapy provided in this embodiment can be applied to, for example... Figure 1 The radiotherapy system shown. Figure 1 This is a schematic diagram of the structure of a radiotherapy system according to some embodiments of this application. The radiotherapy system includes an image acquisition device arranged in the radiotherapy area. Figure 1 (Not shown in the image) and the moving parts of the treatment device, the moving parts including a rotating frame 10 and a treatment head 11 fixed on the rotating frame 10. During treatment, the rotating frame 10 and the treatment head 11 rotate about a central axis. The treatment bed 20 is used to support the object 30 on the central axis of the rotating frame 10. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned radiotherapy system. For example, the radiotherapy system may also include components that are more advanced than those described above. Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown are illustrated.

[0068] The radiotherapy system also includes a computer device for running the collision prediction method for radiotherapy according to this embodiment. The computer device may include one or more processors and a memory for storing data, wherein the processor may include, but is not limited to, a central processing unit (CPU). The number of CPUs may be one or more, and this embodiment is not limited thereto. The aforementioned computer device may also include a transmission device for communication functions and input / output devices. The transmission device can be used to receive images acquired by an image acquisition device and output the generated model to a display or interactive terminal for display. The display or interactive terminal may be located outside the radiotherapy area for easy viewing and operation by the operator.

[0069] This embodiment provides a collision prediction method. Figure 2 This is a flowchart of a collision prediction method for radiotherapy according to some embodiments of this application, such as... Figure 2 As shown, the process includes the following steps:

[0070] Step S201: Determine the real-time outer contour of the object based on the real-time acquired object image.

[0071] Specifically, the image acquisition device can be a binocular image acquisition device or other types of image acquisition devices, which can be used to acquire images containing depth information of the object and moving parts. This image can be used to acquire spatial position information of the object and moving parts. Furthermore, multiple binocular image acquisition devices can be set at different locations within the radiotherapy area to cover multiple viewing angles of the object and moving parts. For example, multiple image acquisition devices can be set at locations where the object and moving parts may come into contact. Based on the object images acquired by the image acquisition devices, the spatial position of the object's outer contour under multiple viewing angles is obtained, and the object's outer contour is generated. There are many mature technologies for obtaining spatial position data of the outer contour from object images acquired by binocular image acquisition devices, and for performing 3D modeling based on spatial position data; these will not be elaborated upon in this embodiment.

[0072] In one specific embodiment, throughout the treatment process, the image acquisition device repeatedly acquires and updates the object images at regular intervals to obtain the object's real-time outer contour. This interval can be preset as needed. In another specific embodiment, the image acquisition device acquires video of the object, and the object's real-time outer contour is generated based on each frame of the video image.

[0073] Step S202: Before performing radiotherapy, the expected motion model of the moving part during the radiotherapy is superimposed on the real-time outer contour to perform collision prediction.

[0074] In some embodiments, prior to radiotherapy, the planned trajectory of the moving parts during radiotherapy is predetermined based on the patient's treatment plan, including the speed and direction of movement at each treatment moment. Based on images of the moving parts acquired by the image acquisition device, the spatial position of the moving parts can also be obtained, and a three-dimensional model of the moving parts can be established.

[0075] Therefore, a three-dimensional model of the moving component can be established based on its spatial position at the current moment. By combining the component's velocity and direction of motion at various treatment moments during radiotherapy, the spatial position of the component after a preset time can be calculated, thus generating the expected motion model after the preset time. Assuming the preset time is Δt, the expected motion model corresponding to the radiotherapy execution time t+Δt can be obtained.

[0076] In other embodiments, three-dimensional models of each component of the radiotherapy device can be directly obtained, and the expected motion model of the moving component at the execution time t+Δt of the radiotherapy can be calculated based on the planned trajectory of the moving component during the radiotherapy.

[0077] The expected motion model at time t+Δt and the current real-time outer contour are superimposed according to their spatial positions to determine whether the planned trajectory of the moving part is correct. Collision prediction is then performed based on the distance between the expected motion model and the current real-time outer contour to determine whether there is a risk of collision between the moving part and the object. Specifically, the prediction method can be determined by calculating the distance between the two models. This distance value can be one or more, with each distance value corresponding to an adjacent surface between the object and the moving part. If the distance value is less than 0 or less than a preset threshold, a collision risk between the moving part and the object can be determined. The expected motion model and the current real-time outer contour can be simultaneously displayed to the user via a display device, facilitating real-time observation and evaluation of their positional relationship. In cases where there is a risk of collision between the moving part and the object, the parts of the moving part and / or the object that may collide or interfere can be highlighted.

[0078] Through steps S201 to S202, the real-time outer contour of the object is determined based on the real-time acquired object image, and the real-time posture change of the object before radiotherapy is obtained. By superimposing the expected motion model of the moving part during radiotherapy with the real-time outer contour before performing radiotherapy, collision prediction is performed to verify the correctness of the planned trajectory of the moving part and determine whether there is a collision risk between the moving part and the object. This solves the problem in related technologies that cannot predict the collision risk between the moving part and the object during radiotherapy, and improves the safety of radiotherapy.

[0079] In some embodiments, Figure 3This is a flowchart of collision prediction after model superposition in some embodiments of this application, such as... Figure 3 As shown, the process includes the following steps:

[0080] Step S301: Based on the superposition result of the expected motion model and the real-time outer contour, determine at least one spacing value between the expected motion model and the real-time outer contour.

[0081] By overlaying the expected motion model with the real-time outer contour, the spatial coordinates of any point in either model can be obtained. During treatment, the real-time outer contour of the object and the expected motion model of the moving part may collide in one or more directions. For example, the movement of the object's body may cause a collision with the front or side of a moving part (such as the treatment head). Therefore, the distance between the two models can be calculated based on the spatial coordinates of points on the adjacent surfaces of the two models.

[0082] Specifically, one or more pairs of adjacent surfaces of the expected motion model and real-time outer contour can be predetermined. Based on the spatial coordinates of each point on each pair of adjacent surfaces, the spacing value corresponding to each pair of adjacent surfaces can be calculated. This spacing value is the minimum spacing value from any point on one adjacent surface to any point on another adjacent surface.

[0083] Step S302: If any one or more of the at least one spacing values ​​are less than a preset spacing threshold, it is determined that there is a risk of collision between the moving part and the object.

[0084] If one or more of the spacing values ​​corresponding to adjacent surfaces are less than a preset spacing threshold, then it is determined that there is a risk of collision between the moving part and the object. The preset spacing threshold can be determined according to the actual situation.

[0085] Through steps S301 to S302, at least one distance value between the expected motion model and the real-time outer contour is obtained based on the superposition result of the expected motion model and the real-time outer contour. The distance between the outer contour of the object and the moving part after a preset time is obtained. If any one or more of the at least one distance value is less than the preset distance threshold, it is determined that there is a collision risk between the moving part and the object. Early warning of collision risk is provided, which improves the safety of radiotherapy.

[0086] In some embodiments, a method for superimposing a prospective motion model onto the real-time outer contour of an object for collision prediction is also involved, the method comprising:

[0087] The result of overlaying the expected motion model with the real-time outer contour is displayed.

[0088] The radiotherapy system in this embodiment includes a display device located outside the radiotherapy area. This display device can be a monitor or an interactive terminal, etc. The superposition of the expected motion model and the real-time outer contour is displayed on the display device, facilitating the operator's observation of the subject's posture changes and the movement trajectory of moving parts before and during radiotherapy.

[0089] The collision prediction method in this embodiment displays the superposition result of the expected motion model and the real-time outer contour, enabling operators to obtain the object posture and moving part position within the radiotherapy area more clearly and intuitively, avoiding the problem of line-of-sight obstruction caused by image observation through image acquisition devices.

[0090] In a further embodiment, the method of superimposing the expected motion model onto the real-time outer contour of the object for collision prediction further includes:

[0091] If a collision risk is identified between a moving part and an object, the collision angle between the moving part and the object is obtained; based on the collision angle, the spatial location corresponding to the collision risk is magnified and displayed, and a collision warning is issued.

[0092] If one or more spacing values ​​are less than a preset spacing threshold, the collision angle between the moving part and the object is obtained, which is the spatial position of the adjacent surface corresponding to that spacing value. Based on the spatial position of the adjacent surface, the corresponding area of ​​the expected motion model and the real-time outer contour is magnified and displayed, and a collision warning is issued, so that the operator can observe the area where a collision may occur in a timely manner and correct the object's posture.

[0093] The collision prediction method in this embodiment obtains the collision angle between the moving part and the object when it is determined that there is a collision risk. Based on the collision angle, the spatial position corresponding to the collision risk is magnified and displayed, and a collision warning is issued. When there is a collision risk, the location of the collision is given and displayed at an appropriate angle, which further improves the convenience of observation for operators and the efficiency of eliminating collision risks.

[0094] In some embodiments, Figure 4 This is a flowchart showing the display results of model overlay in some embodiments of this application, such as... Figure 4 As shown, the process includes the following steps:

[0095] Step S401: Based on the user's input perspective adjustment command, adjust the superposition display angle of the expected motion model and the real-time outer contour.

[0096] During the treatment process, the operator can adjust the superimposed display angle of the two models on the monitor or interactive terminal according to observation needs. The operator can input viewpoint adjustment commands on the input / output device, either through an input device such as a mouse, or directly through the viewpoint adjustment controls on the touch interactive terminal.

[0097] Step S402: Based on the user's input scaling command and display area, the expected motion model and real-time outer contour corresponding to the display area are scaled down or enlarged.

[0098] Similarly, the display area of ​​the expected motion model and real-time outer contour can be selected via input / output devices and then zoomed in or out. Alternatively, the selected area can be zoomed on a touch-screen interactive terminal.

[0099] Furthermore, the interactive terminal can also display images from multiple angles captured by the image acquisition device, as well as the subject's vital signs data, parameters of the treatment equipment, etc.

[0100] The execution order of steps S401 and S402 can be interchanged, or either step can be executed as needed.

[0101] Through steps S401 and S402, the superimposed display angle of the expected motion model and the real-time outer contour is adjusted based on the user-inputted perspective adjustment command. This allows operators to observe the relative position between the object and the moving parts from all angles without obstruction, avoiding the problem of incomplete observation angle caused by image observation through the image acquisition device. Based on the user-inputted zoom command and display area, the expected motion model and the real-time outer contour corresponding to the display area are zoomed out or zoomed in. The overall position and local details of the object and the moving parts can be displayed according to the operator's needs, providing accurate information for the operator's risk assessment and decision-making.

[0102] In some embodiments, a specific method for collision prediction during radiotherapy is also involved, the method comprising:

[0103] During radiotherapy, the expected motion model of the moving part corresponding to the future moment after the current moment is superimposed on the real-time outer contour to perform collision prediction.

[0104] During radiotherapy, assuming the current time is Tc, based on the 3D model of the moving part and its planned trajectory during radiotherapy, the expected motion model of the moving part at a future time Tc+Δt after the current time Tc can be obtained. This expected motion model is then superimposed on the real-time outer contour of the object at the current time Tc to perform collision prediction.

[0105] The collision prediction method in this embodiment predicts the collision risk between the moving part and the object during radiotherapy by superimposing the expected motion model of the moving part corresponding to the future time after the current time with the real-time outer contour. This avoids collisions caused by changes in the object's posture during radiotherapy and further improves the safety of radiotherapy.

[0106] In some embodiments, Figure 5 This is a flowchart illustrating the expected motion model of a moving part generated according to some embodiments of this application, such as... Figure 5 As shown, the process includes the following steps:

[0107] Step S501: Based on multiple image acquisition devices, acquire multi-angle motion component images corresponding to the preset treatment time.

[0108] The preset treatment time can be a pre-defined moment Ts during the radiotherapy process. Specifically, it can be the start time of radiotherapy. Images or videos of the moving parts are acquired from different angles at moment Ts using multiple image acquisition devices, resulting in multi-angle images of the moving parts corresponding to the preset treatment time Ts. These multi-angle images can consist of multiple images of the moving parts from different angles, and each image contains spatial position information of the moving parts.

[0109] Step S502: Based on the multi-angle images of the moving parts and the planned trajectory of the moving parts, determine the motion parameters of the moving parts at the preset treatment time.

[0110] From multiple images of a moving part taken from different angles, its spatial position information can be obtained, such as the coordinates of points on the outer contour of the moving part. Based on this spatial position information, a three-dimensional model of the moving part can be created.

[0111] Motion parameters can include the direction and velocity of the moving parts. Based on the planned trajectory of the moving parts and the three-dimensional model at the preset treatment time Ts, the direction and velocity of the moving parts at the preset treatment time Ts can be calculated.

[0112] Step S503: Based on the motion parameters, generate the expected motion model of the moving part after a preset time.

[0113] The preset time is Δt. Based on the three-dimensional model, direction of motion, and speed of the moving part at the preset treatment time Ts, the position coordinates of each point on the moving part after the preset time (at time Ts+Δt) can be calculated, thereby generating the expected motion model after the preset time.

[0114] Through steps S501 to S503, multi-angle images of the moving parts corresponding to the preset treatment time are acquired using multiple image acquisition devices, thereby establishing a three-dimensional model of the moving parts at the preset treatment time. Based on the multi-angle images of the moving parts and the planned trajectory of the moving parts, the motion parameters of the moving parts at the preset treatment time are determined. Based on these motion parameters, the expected motion model of the moving parts after the preset time is generated. During radiotherapy, the motion model after the preset time is generated based on the images of the moving parts acquired at any time, which facilitates timely judgment of collision risk based on the real-time motion trajectory of the moving parts during treatment, thereby improving the accuracy of collision prediction for the moving parts.

[0115] In some embodiments, the procedure also involves positioning adjustments prior to radiotherapy. Figure 6 This is a flowchart of the placement adjustment in some embodiments of this application, such as... Figure 6 As shown, the process includes the following steps:

[0116] Step S601: Display the object image acquired by the image acquisition device, wherein the object image includes the object's surface markings.

[0117] Radiation therapy requires precisely targeting the lesions within the patient's body. If the radiation is misaligned, it can damage healthy tissues. Since the location of lesions varies from patient to patient, pre-set surface markers are used to position the patient correctly before treatment. This embodiment displays an image of the patient captured by the image acquisition device, and can automatically zoom in on the surface markers. If multiple surface markers are present, the viewing angle can be adjusted to display them simultaneously.

[0118] Furthermore, before positioning, the facial image of the object captured by the image acquisition device can be compared with a pre-stored facial image of the object to confirm whether the object is correct. If the facial recognition of the object is inconsistent, an alarm will be issued to the operator, including but not limited to audible alarms and pop-up alarms.

[0119] Step S602: Compare the object image with the pre-generated object placement model to obtain the placement deviation.

[0120] The display device can display both the object's surface markings and a pre-generated positioning model of the object. The positioning model is a body posture model designed based on the object's lesion location and treatment needs, and includes virtual markers corresponding to the object's surface markings. The object image is compared with the positioning model; specifically, the object image acquired by the image acquisition device can be overlaid with the positioning model to obtain the positioning deviation between each surface marking and its corresponding virtual marker.

[0121] Step S603: Adjust the placement of the object based on the placement deviation.

[0122] If there is no deviation between the surface markings and the corresponding virtual markings, the object placement can be determined to be accurate.

[0123] Through steps S601 to S603, the object image acquired by the image acquisition device is displayed. The object image includes the object's surface markings. The object image is compared with a pre-generated object positioning model to obtain the positioning deviation, thereby improving the accuracy of object positioning and the radiotherapy effect.

[0124] The present embodiment will now be described and illustrated through preferred embodiments. The collision prediction method for radiotherapy in this embodiment is applied to a radiotherapy system, which includes a binocular image acquisition device and moving parts of the treatment equipment. These moving parts undergo mechanical movement during treatment. Figure 7 This is a flowchart of a collision prediction method for radiotherapy according to some preferred embodiments of this application, such as... Figure 7 As shown, the process includes the following steps:

[0125] Step S701: Load the treatment information of the object and acquire the facial image of the object on the treatment bed through the image acquisition device;

[0126] Step S702: Compare the object's facial image with the object's facial image in the treatment information to determine whether the comparison results are consistent.

[0127] Step S703: If the conditions are met, proceed to step S704; otherwise, issue an alarm message.

[0128] Step S704: Display the image of the object's body acquired by the image acquisition device on the display screen, and automatically adjust the viewing angle while displaying all surface markings on the object's body.

[0129] Step S705: Overlay the object's body image with the positioning model to obtain the positioning deviation between each body surface mark and the corresponding virtual mark in the positioning model;

[0130] Step S706: Adjust the placement of the object based on the placement deviation;

[0131] Step S707: Based on the object's body images acquired by multiple image acquisition devices, generate the object's static outer contour;

[0132] Step S708: Based on the planned trajectory of the moving parts, generate a planned motion model of the moving parts;

[0133] Step S709: Overlay the planned motion model and the static outer contour to obtain one or more spacing values ​​between the two;

[0134] Step S710: Determine whether all spacing values ​​are greater than the preset threshold. If not, determine that there is a collision risk in the planned trajectory of the moving part and issue an alarm message. If yes, proceed to step S711 to perform radiotherapy.

[0135] Step S711: During the treatment process, based on multiple image acquisition devices, acquire multi-angle object images and multi-angle moving part images corresponding to the current treatment moment;

[0136] Step S712: Based on the multi-angle object image and the multi-angle moving part image, obtain the spatial position of the outer contour of the object at the current treatment time and the spatial position of the moving part at the current treatment time, respectively.

[0137] Step S713: Generate the real-time outer contour of the object based on its spatial position.

[0138] Step S714: Based on the planned trajectory of the moving part, obtain the direction and speed of the moving part at the current treatment moment;

[0139] Step S715: Based on the spatial position, direction of motion, and velocity of the moving part at the current treatment moment, generate the expected motion model of the moving part after a preset time.

[0140] Step S716: Overlay and display the expected motion model and the real-time outer contour;

[0141] Step S717: Determine whether there is a risk of collision between the moving part and the object based on the distance between the expected motion model and the real-time outer contour;

[0142] Step S718: If a collision risk is determined, obtain the collision angle between the moving part and the object; based on the collision angle, magnify and display the spatial position corresponding to the collision risk, and issue a collision warning;

[0143] Step S719: If there is no risk of collision, repeat steps S711 to S719 until the treatment process is completed.

[0144] Through steps S701 to S719, by overlaying the object image with the positioning model, the positioning deviation is obtained, improving the accuracy of object positioning and the effect of radiotherapy. Before radiotherapy, collision assessment is performed by overlaying the planned motion model and the static outer contour to determine whether there is a collision risk in the planned trajectory of the moving parts. Radiotherapy is performed when there is no collision risk, improving the safety of radiotherapy. By generating the real-time outer contour of the object and the expected motion model of the moving parts at each treatment moment during radiotherapy and overlaying them, it is easier for operators to observe and judge more directly, avoiding problems such as line of sight obstruction and incomplete angles. The spacing value between the models determines whether there is a collision risk between the moving parts and the object, providing early warning of collision risks and improving the safety of radiotherapy and the object.

[0145] This embodiment also provides a collision prediction device for radiotherapy, which is applied to a radiotherapy system, the radiotherapy system including an image acquisition device and moving parts of the treatment equipment. Figure 8 This is a structural block diagram of a collision prediction device for radiotherapy according to some embodiments of this application, such as... Figure 8 As shown, the device includes:

[0146] The contour determination module 801 is used to determine the real-time outer contour of an object based on an object image acquired by an image acquisition device during the treatment process.

[0147] The collision detection module 802 is used to overlay the expected motion model of the moving part during the radiotherapy with the real-time outer contour to perform collision prediction before the radiotherapy is performed.

[0148] The collision prediction device in this embodiment determines the real-time outer contour of the object based on the real-time acquired object image by the contour determination module 801, thereby obtaining the real-time posture change of the object before radiotherapy. Before performing radiotherapy, the collision detection module 802 superimposes the expected motion model of the moving part during radiotherapy with the real-time outer contour to perform collision prediction, verify the correctness of the planned trajectory of the moving part, and determine whether there is a collision risk between the moving part and the object. This solves the problem in related technologies that cannot predict the collision risk between the moving part and the object during radiotherapy, and improves the safety of radiotherapy.

[0149] This embodiment also provides a computer-readable storage medium storing instructions that, when executed by a processor, implement the steps of the collision prediction method in the above embodiment.

[0150] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated in this embodiment.

[0151] This embodiment also provides a quality control method for radiotherapy equipment, the quality control method for radiotherapy equipment including:

[0152] Step S901: Determine the quality control execution time for the radiotherapy equipment based on its usage time.

[0153] Quality control of radiotherapy equipment refers to a series of necessary measures taken to ensure that each stage of the radiotherapy process meets quality assurance requirements. This reduces uncertainty in the entire radiotherapy process, including simulation positioning, treatment planning, and treatment implementation, thereby improving the accuracy and efficacy of the treatment. Specifically, quality control items mainly include mechanical testing, dose measurement testing, and safety testing.

[0154] Specifically, the usage time of a radiotherapy device can be any combination of one or more of the following: historical usage time of one or more radiotherapy devices, current operating time, and future scheduled working time.

[0155] Step S902: Based on the quality control execution time, control the radiotherapy equipment to automatically perform quality control.

[0156] Through steps S901 to S902, the quality control execution time of the radiotherapy equipment is determined based on the usage time of the radiotherapy equipment, and the radiotherapy equipment is automatically controlled to perform quality control based on the quality control execution time, thereby improving the automation level of quality control execution and improving the operating efficiency and quality of the radiotherapy equipment.

[0157] In some embodiments, after controlling the radiotherapy device to automatically perform quality control, the method further includes:

[0158] Send the quality control results to the interactive terminal.

[0159] Specifically, the quality control results can include the execution results of each quality control item.

[0160] In a further embodiment, the interactive terminal is a mobile terminal.

[0161] Specifically, the execution result can be sent to the interactive terminal through any one or more of the following methods: application, mini-program, SMS, and voice message.

[0162] The quality control method for radiotherapy equipment in this embodiment sends the quality control results to an interactive terminal, enabling physicists or relevant personnel to obtain the quality control results of the radiotherapy equipment in a timely manner and to arrange the treatment plan of the radiotherapy equipment in a timely manner based on the quality control results, thereby improving the efficiency and safety of radiotherapy.

[0163] In some embodiments, determining the quality control execution time of the radiotherapy equipment based on its usage time includes:

[0164] Step S1001: Analyze the usage time of the radiotherapy equipment and determine the expected idle time of the radiotherapy equipment within a preset future date based on the analysis results.

[0165] Specifically, the analysis method can be to statistically analyze the historical usage time, current operating time, and future scheduled working time of one or more radiotherapy devices to obtain the analysis results. These results can be the usage of radiotherapy devices in different time periods on historical dates or the current date, or the probability of idle time periods in preset future dates.

[0166] Step S1002: Determine the quality control execution time based on the expected idle period.

[0167] Through steps S1001 to S1002, the usage time of the radiotherapy equipment is analyzed, and the expected idle time period of the radiotherapy equipment within a preset future date is determined based on the analysis results. Based on the expected idle time period, the quality control execution time is determined, which improves the effectiveness of the quality control execution time and reduces the probability of conflict between quality control execution and treatment time.

[0168] In a further embodiment, a specific method for obtaining the expected idle time period is also involved, the method comprising:

[0169] By inputting the historical usage times of multiple radiotherapy devices into a pre-trained machine learning model, the expected idle time periods of the radiotherapy devices within a preset future time period can be obtained.

[0170] The quality control method for radiotherapy equipment in this embodiment analyzes the historical usage time of multiple radiotherapy equipment through a pre-trained machine learning model to obtain the expected idle time period of the radiotherapy equipment within a preset future time period, thereby improving the prediction accuracy of the expected idle time period.

[0171] In some embodiments, the quality control includes equipment quality control and / or radiotherapy plan quality control.

[0172] Specifically, equipment quality control can include quality assurance of various equipment parameters such as MLC operating accuracy, EPID accuracy, treatment head rotation speed, and motion accuracy, similar to quality inspection.

[0173] Specifically, radiotherapy plan quality control may include pre-treatment plan quality control based on treadmills, ionization chambers, dosimeters, etc., similar to simulating radiotherapy plans under no-load conditions.

[0174] Equipment quality control and radiotherapy plan quality control can correspond to different quality control items.

[0175] In a further embodiment, the specific steps involving equipment quality control include:

[0176] Step S1101: Based on the quality control execution time, start the radiotherapy equipment and put the radiotherapy equipment into the equipment quality control mode.

[0177] Step S1102: Perform equipment quality control based on the preset first quality control item.

[0178] Specifically, the first quality control item is a pre-determined equipment quality control item.

[0179] Through steps S1101 to S1102, the radiotherapy equipment is started and put into equipment quality control mode based on the quality control execution time. Equipment quality control is performed based on the preset first quality control item. Equipment quality control is automatically performed without human intervention, which improves the automation and intelligence of equipment quality control and improves the operating efficiency of radiotherapy equipment.

[0180] In a further embodiment, after performing equipment quality control based on a preset first quality control item, the specific steps for performing radiotherapy plan quality control include:

[0181] Step S1201: Based on the predetermined radiotherapy plan, obtain the corresponding second quality control item.

[0182] Step S1202: Perform radiotherapy plan quality control based on the second quality control item.

[0183] Through steps S1201 to S1202, based on a predetermined radiotherapy plan, the corresponding second quality control item is obtained, and radiotherapy plan quality control is performed based on the second quality control item. Radiotherapy plan quality control is automatically performed without human intervention, ensuring the safety and therapeutic effect of radiotherapy.

[0184] This embodiment also provides a quality control device for a radiation delivery device, the device comprising:

[0185] The acquisition module is used to determine the quality control execution time of the radiotherapy equipment based on the usage time of the equipment.

[0186] The control module is used to control the radiotherapy equipment to automatically perform quality control based on the quality control execution time.

[0187] The quality control device for the radiotherapy delivery equipment in this embodiment determines the quality control execution time of the radiotherapy equipment based on the usage time of the radiotherapy equipment by the acquisition module, and controls the radiotherapy equipment to automatically perform quality control based on the quality control execution time by the control module, thereby improving the automation level of quality control execution and improving the operating efficiency and operating quality of the radiotherapy equipment.

[0188] This embodiment also provides an automatic quality control execution system, which includes a radiotherapy device and a controller. The controller is used to control the radiotherapy device to automatically perform quality control based on the quality control method of the radiotherapy device in the above embodiment.

[0189] The automatic quality control execution system in this embodiment determines the quality control execution time of the radiotherapy equipment based on its usage time and controls the radiotherapy equipment to automatically perform quality control, thereby improving the automation level of quality control execution and enhancing the operating efficiency and quality of the radiotherapy equipment.

[0190] It should be understood that the specific embodiments described herein are merely illustrative of the application and not intended to limit it. All other embodiments derived by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0191] Obviously, the accompanying drawings are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar situations based on these drawings without any creative effort. Furthermore, it is understood that although the work done in this development process may be complex and lengthy, for those skilled in the art, certain design, manufacturing, or production modifications made based on the technical content disclosed in this application are merely conventional technical means and should not be considered as insufficient disclosure of this application.

[0192] The term "embodiment" in this application refers to a specific feature, structure, or characteristic described in connection with an embodiment that may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily imply the same embodiment, nor does it imply that it is mutually exclusive with or independent of other embodiments. It will be clearly or implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0193] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the appended claims.

Claims

1. A collision prediction method characterized by, The collision prediction method is applied to a radiotherapy device, which includes moving parts, and includes: Determine the real-time outer contour of the object based on the real-time acquired object image; Prior to the administration of radiotherapy, the expected motion model of the moving part during the radiotherapy is superimposed on the real-time outer contour to perform collision prediction.

2. The collision prediction method according to claim 1, characterized by, The step of superimposing the expected motion model of the moving part during radiotherapy with the real-time outer contour to perform collision prediction includes: Based on the superposition result of the expected motion model and the real-time outer contour, at least one spacing value between the expected motion model and the real-time outer contour is determined; If any one or more of the at least one spacing value is less than a preset spacing threshold, it is determined that there is a risk of collision between the moving part and the object.

3. The collision prediction method of claim 1, wherein, The method of superimposing the expected motion model of the moving part during radiotherapy with the real-time outer contour for collision prediction further includes: The result of overlaying the expected motion model with the real-time outer contour is displayed.

4. The collision prediction method according to claim 3, characterized by, Further includes: If it is determined that there is a risk of collision between the moving part and the object, the collision angle between the moving part and the object is obtained; The spatial location corresponding to the collision risk is magnified and displayed based on the collision angle, and a collision warning is issued.

5. The collision prediction method of claim 3, wherein, The step of displaying the superposition result of the expected motion model and the real-time outer contour includes: Based on user-inputted perspective adjustment commands, adjust the superimposed display angle of the expected motion model and the real-time outer contour; and / or Based on the user's zoom command and display area, the expected motion model and real-time outer contour corresponding to the display area are scaled down or enlarged.

6. The collision prediction method of claim 1, wherein, Further includes: During radiotherapy, the expected motion model of the moving part corresponding to a future moment after the current moment is superimposed on the real-time outer contour to perform collision prediction.

7. The collision prediction method of claim 1, wherein, The expected motion model is generated through the following steps: Based on multiple image acquisition devices, images of moving parts at multiple angles corresponding to preset treatment times are obtained. Based on the multi-angle motion component images and the planned trajectory of the motion component, the motion parameters of the motion component at the preset treatment time are determined; Based on the motion parameters, a motion model of the moving part after a preset time is generated.

8. The collision prediction method of claim 1, wherein, Before determining the real-time outer contour of the object based on the real-time acquired object image, the method includes: The image of the object acquired by the image acquisition device is displayed, and the image of the object includes the surface markings of the object; The object image is compared with a pre-generated object placement model to obtain the placement deviation; The placement of the object is adjusted based on the placement deviation.

9. A collision prediction device characterized by comprising: The device is used in a radiotherapy system, the radiotherapy system including an image acquisition device and moving parts of the radiotherapy equipment, and the device includes: A contour determination module is used to determine the real-time outer contour of an object based on an object image acquired by the image acquisition device during the treatment process. A collision detection module is used to overlay the expected motion model of the moving part during the radiotherapy treatment onto the real-time outer contour to perform collision prediction before the radiotherapy is performed.

10. A computer-readable storage medium having instructions stored thereon, characterized in that, When executed, the instructions cause the processor to perform the collision prediction method as described in any one of claims 1 to 8.

Images