Radiotherapy positioning alignment control method and system based on image recognition

Abstract

The invention discloses a radiotherapy positioning alignment control method and system based on image recognition, and belongs to the technical field of medical instruments, and the method comprises the steps: shooting an image containing a laser cross curve irradiated by a positioning laser lamp on the body surface of a patient and a simulation positioning cross curve in real time; calculating an actual distance between the laser cross curve and the simulated positioning cross curve in the image based on an image recognition algorithm; and adjusting the displacement and posture of the six-dimensional radiotherapy bed based on the actual distance, and when the actual distance is smaller than a preset standard value, completing radiotherapy positioning. According to the scheme, the radiotherapy positioning efficiency, the radiotherapy positioning progress and the radiotherapy positioning quality can be improved.

Description

Technical Field

[0001] The present invention relates to the field of medical device technology, and in particular to a radiotherapy positioning alignment control method, system, computing device and storage medium based on image recognition. Background Art

[0002] At present, most patients with malignant tumors require radiotherapy, the goal of which is to minimize the dose to the surrounding normal tissues while fully administering the dose to the target area. During radiotherapy, factors such as respiratory motion, partial internal motion error, and radiotherapy positioning error have a certain impact on the accuracy of the dose and the selection of the target range during radiotherapy.

[0003] Among them, radiotherapy positioning runs through the entire radiotherapy process, and radiotherapy positioning directly affects the accuracy of the radiotherapy prescription dose for tumors. Radiotherapy positioning is usually completed in three independent steps. In the first step, the therapist assists the patient to lie on his side or flat in the position fixation device and place him on the treatment bed. The second step is divided into initial positioning and fractionated positioning according to the execution time. The initial positioning needs to be aligned with the CT simulation positioning center first, and the accelerator treatment bed is used to move the center point to the center of the treatment light field. The fractionated positioning marks the position after the initial positioning is completed. The third step is to perform target area matching based on cone CT. Before each treatment, the cone CT integrated with the accelerator is used to track the position of the tumor so that the tumor position matches the preset image position.

[0004] With the continuous development of radiotherapy equipment, the third step of positioning has achieved a one-click automatic matching function, but the first two steps still require manual operation, which affects the efficiency and accuracy of radiotherapy. Summary of the invention

[0005] In order to improve the efficiency of radiotherapy positioning, the present invention proposes a material placement alignment control method and system based on image recognition, which calculates the positional relationship between the laser cross line irradiated by the laser light on the patient's body surface and the simulated positioning cross line in real time through image recognition, and adjusts the position of the treatment bed based on the positional relationship so that the laser cross line coincides with the simulated positioning cross line, thereby completing the automatic positioning of radiotherapy.

[0006] According to a first aspect of the present invention, there is provided a radiotherapy positioning alignment control method based on image recognition, comprising: real-time photographing of an image containing a laser cross line and a simulated positioning cross line irradiated by a positioning laser light on the patient's body surface; calculating the actual distance between the laser cross line and the simulated positioning cross line in the image based on an image recognition algorithm; adjusting the displacement and posture of a six-dimensional radiotherapy bed based on the actual distance, and completing the radiotherapy positioning when the actual distance is less than a preset standard value.

[0007] According to the above technical solution, real-time image recognition can provide higher positioning accuracy, reduce the error of traditional manual adjustment, and improve the efficiency of radiotherapy positioning.

[0008] Optionally, in the radiotherapy positioning and alignment control method based on image recognition provided by the present invention, a first positioning laser light, a first depth of field camera, a second depth of field camera, a second positioning laser light, a third depth of field camera, and a third positioning laser light are respectively arranged on the left side, the right side, and the top of the six-dimensional treatment bed, and the first positioning laser light, the second positioning laser light, and the third positioning laser light simultaneously emit a first laser cross line, a second laser cross line, and a third laser cross line; When the patient lies on the six-dimensional treatment bed in the positioning device, the first simulated positioning cross mark, the second simulated positioning cross mark, and the third simulated positioning cross mark are marked on the patient's body surface or the positioning device; Based on the first depth of field camera, the second depth of field camera and the third depth of field camera, an image containing the first laser cross line, the second laser cross line and the third laser cross line and the first simulated positioning cross mark, the second simulated positioning cross mark and the third simulated positioning cross mark is captured in real time.

[0009] According to the above technical solution, by setting positioning laser lights and depth-of-field cameras at different positions of the six-dimensional treatment bed, positioning can be performed from multiple directions and angles to ensure that all directions of the treatment bed can be accurately adjusted. By combining the data of laser positioning and depth-of-field cameras, positioning errors can be significantly reduced, ensuring that radiotherapy is accurately aligned with the predetermined radiation field center, thereby improving the safety and effectiveness of treatment.

[0010] Optionally, in the radiotherapy positioning alignment control method based on image recognition provided by the present invention, the first laser cross line, the second laser cross line and the third laser cross line intersect at one point, and the intersection of a perpendicular line through the third simulated positioning cross mark perpendicular to the line connecting the first simulated positioning cross mark and the second simulated positioning cross mark and the line is the positioning reference origin.

[0011] According to the above technical solution, using the vertical line and the intersection as the reference point can effectively reduce the accumulation of small errors between different marks and laser lines. This method helps to improve the accuracy of alignment in radiotherapy and reduce the inconsistency caused by error accumulation.

[0012] Optionally, in the radiotherapy positioning and alignment control method based on image recognition provided by the present invention, the feature points of the laser cross line and the simulated positioning cross line are extracted from the real-time acquired image based on a straight line detection algorithm; the identified feature point coordinates are converted into actual physical distances, and the first distance between the first simulated positioning cross mark and the center point of the cross irradiated by the first positioning laser light, the second distance between the second simulated positioning cross mark and the center point of the cross irradiated by the third positioning laser light, and the third distance between the third simulated positioning cross mark and the center point of the cross irradiated by the second positioning laser light are calculated respectively; the calculated first distance, second distance and third distance are fed back to the radiotherapy accelerator control system.

[0013] According to the above technical solution, through image recognition and straight line detection algorithms, the feature points of the laser cross line and the simulated positioning cross line can be accurately extracted, and multi-point distance information is comprehensively considered, which helps to more comprehensively adjust and optimize the positioning.

[0014] Optionally, in the radiotherapy positioning alignment control method based on image recognition provided by the present invention, the first distance, the second distance and the third distance are respectively compared with preset standard values. If the first distance, the second distance and the third distance are all smaller than the preset standard values, the radiotherapy positioning is completed; otherwise, the position and posture of the six-dimensional treatment bed are continued to be adjusted until the radiotherapy positioning is completed when the first distance, the second distance and the third distance are all smaller than the preset standard values.

[0015] According to the above technical solution, after each adjustment, the system will update the distance measurement results in real time based on the new image data to ensure that the alignment state of the treatment device and the patient's body surface always remains within the optimal range. This real-time feedback mechanism can ensure the patient's precise positioning before treatment and reduce the risks during treatment.

[0016] According to a second aspect of the present invention, a radiotherapy positioning alignment control system based on image recognition is provided, comprising: a six-dimensional treatment bed equipped with a radiotherapy accelerator, a first positioning laser light, a first depth of field camera, a second depth of field camera, a second positioning laser light, a third depth of field camera, and a third positioning laser light, wherein the first positioning laser light and the first depth of field camera are located on the right side of the six-dimensional treatment bed, the third depth of field camera and the third positioning laser light are located on the left side of the six-dimensional treatment bed, the second depth of field camera and the second positioning laser light are located on the top of the six-dimensional treatment bed, the first depth of field camera is located directly above the first positioning laser light, the third depth of field camera is located directly above the third positioning laser light, and the second depth of field camera is displaced to the side of the second positioning laser light; When the patient is fixed on the positioning device and lies on the six-dimensional treatment bed, the first simulated positioning cross mark, the second simulated positioning cross mark and the third simulated positioning cross mark are located on the patient's body surface or the surface of the positioning device; The system is used to capture images containing laser cross lines and simulated positioning cross lines irradiated by the positioning laser light on the patient's body surface in real time through the first depth of field camera, the second depth of field camera and the third depth of field camera; calculate the actual distance between the laser cross lines and the simulated positioning cross lines in the image based on the image recognition algorithm; adjust the displacement and posture of the six-dimensional radiotherapy bed based on the actual distance, and complete the radiotherapy positioning when the actual distance is less than the preset standard value.

[0017] Optionally, in the radiotherapy positioning and alignment control system based on image recognition provided by the present invention, the visible band laser cross lines emitted by the first positioning laser light, the second positioning laser light and the third positioning laser light coincide at one point; the intersection of a perpendicular line through the third simulated positioning cross mark perpendicular to the line connecting the first simulated positioning cross mark and the second simulated positioning cross mark and the line is the positioning reference origin, and the position between the center of the tumor radiotherapy field in the patient's body and the reference origin is fixed.

[0018] Optionally, in the radiotherapy positioning and alignment control system based on image recognition provided by the present invention, the first depth of field camera, the second depth of field camera and the third depth of field camera are used to continuously capture images of the patient and the positioning device within the same shooting range at different angles.

[0019] According to the above technical solution, views from different angles can reduce the occlusion problem that may exist in a single perspective, and multi-angle image fusion technology can improve the depth perception and resolution of the image, which helps to optimize the effects of image recognition and processing algorithms.

[0020] According to a third aspect of the present invention, there is provided a computing device comprising: at least one processor; and a memory storing program instructions, wherein the program instructions are configured to be suitable for execution by at least one processor, and the program instructions include instructions for executing the above-mentioned image recognition-based radiotherapy positioning alignment control method.

[0021] According to a fourth aspect of the present invention, a readable storage medium storing program instructions is provided. When the program instructions are read and executed by a computing device, the computing device executes the above-mentioned radiotherapy positioning alignment control method based on image recognition.

[0022] The radiotherapy positioning alignment control method and system based on image recognition provided by the present invention can at least achieve the following beneficial effects: By capturing and processing images containing laser crosshairs and simulated positioning crosshairs in real time, instant displacement and posture adjustments can be achieved. This dynamic adjustment capability helps to quickly respond to changes in patient position or device misalignment, thereby improving the accuracy and efficiency of treatment.

[0023] The automated image recognition and calculation process reduces the need for manual operation and judgment, thereby reducing the possibility of human error. By capturing and processing images in real time, it can adapt to slight changes in the patient's position, ensuring that the system can make timely adjustments and maintain the accuracy of treatment even when the patient's position moves slightly.

[0024] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 A schematic diagram of the structure of a material placement and alignment control system based on image recognition according to an embodiment of the present invention is shown; Figure 2 A schematic diagram showing the relationship between a patient's tumor positioning mark and a treatment plan radiation field center according to an embodiment of the present invention is shown; Figure 3 A schematic diagram showing the working principle of a radiotherapy positioning and alignment control system based on image recognition is shown; Figure 4 A schematic flow chart of a radiotherapy positioning and alignment control method 400 based on image recognition according to an embodiment of the present invention is shown; Figure 5 FIG. 1 shows a structural diagram of a computing device 100 according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to improve the efficiency of radiotherapy positioning, shorten the treatment time, and improve the accuracy of radiotherapy, this solution proposes a fully automatic radiotherapy positioning solution based on image recognition, which combines multiple devices to achieve accurate automatic radiotherapy positioning. The depth of field camera is used to capture the laser positioning crosshairs and simulated positioning crosshairs irradiated on the patient's body surface in real time. The distance between the laser positioning crosshairs and the simulated positioning crosshairs is calculated based on the image recognition algorithm, and the distance between the laser positioning crosshairs and the simulated positioning crosshairs is corrected by moving the treatment bed, ultimately achieving fully automatic positioning of radiotherapy.

[0027] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0028] Figure 1 FIG. 1 is a schematic diagram showing a structure of a material placement and alignment control system based on image recognition according to an embodiment of the present invention. Figure 1 As shown, the system includes a six-dimensional treatment bed 1 equipped with an electron linear accelerator, a first positioning laser light 2, a first depth of field camera 3, a second depth of field camera 4, a second positioning laser light 5, a third depth of field camera 6, and a third positioning laser light 7. Among them, the first positioning laser light 2 and the first depth of field camera 3 are located on the right side of the six-dimensional treatment bed 1, the third depth of field camera 6 and the third positioning laser light 7 are located on the left side of the six-dimensional treatment bed 1, and the second depth of field camera 4 and the second positioning laser light 5 are located on the top of the six-dimensional treatment bed 1.

[0029] The first depth-of-field camera 3 is located directly above the first positioning laser light 2, the third depth-of-field camera 6 is located directly above the third positioning laser light 7, and the second depth-of-field camera 4 is located to the right of the second positioning laser light 5. These cameras acquire depth information of the patient's body surface and surrounding space by capturing images of multiple focal lengths to assist in precise positioning.

[0030] The six-dimensional treatment bed provides adjustment capabilities in multiple directions (three translation directions of X, Y, and Z and three rotation directions) to accurately position the patient. The light emitted by the first positioning laser light 2 and the third positioning laser light 7 is on the horizontal plane, while the light emitted by the second positioning laser light 5 is perpendicular to the horizontal plane. The irradiation light of the first positioning laser light 2, the second positioning laser light 5, and the third positioning laser light 7 coincides at one point. At the same time, the depth of field camera captures the image of the area aligned with the laser.

[0031] When the patient is fixed on the positioning device and lies on the six-dimensional treatment bed 1, the first simulated positioning cross mark 8, the second simulated positioning cross mark 11 and the third simulated positioning cross mark 12 are marked on the patient's body surface or the surface of the positioning device.

[0032] Figure 2 FIG. 1 is a schematic diagram showing the relationship between the patient tumor positioning mark and the treatment plan radiation field center according to an embodiment of the present invention. Figure 2As shown, the first simulated positioning cross mark 8 and the second simulated positioning cross mark 11 are connected to form a straight line, and the third simulated positioning cross mark 12 is used as a perpendicular line to the straight line. The intersection of the perpendicular line and the straight line is the coordinate reference origin 13, and the position between the tumor radiotherapy field center 10 in the patient 9 and the reference origin 13 is fixed. Therefore, the automatic positioning process is completed by only aligning the first simulated positioning cross mark 8, the second simulated positioning cross mark 11 and the third simulated positioning cross mark 12 to the first positioning laser light 2, the second positioning laser light 5 and the third positioning laser light 7 respectively to irradiate the patient's cross light.

[0033] Figure 3 The figure shows the working principle of the radiotherapy positioning and alignment control system based on image recognition. Figure 3 As shown, multiple depth-of-field cameras are used to continuously capture images including laser cross lines and simulated positioning cross lines irradiated by the positioning laser light on the patient's body surface.

[0034] Specifically, the patient lies flat or sideways on the six-dimensional treatment bed 1, so that the patient is within the shooting range of the first depth-of-field camera 3, the second depth-of-field camera 4, and the third depth-of-field camera 6. At the same time, the first positioning laser light 2, the second positioning laser light 5, and the third positioning laser light 7 are turned on, so that the first depth-of-field camera 3, the second depth-of-field camera 4, and the third depth-of-field camera 6 are used to continuously shoot images of the patient and the positioning device within the same shooting range at different angles, and obtain images containing simulated cross marks and laser irradiation cross lines.

[0035] Then, the actual distance value between the laser crosshairs and the simulated positioning crosshairs in the image is calculated based on image recognition. It is determined whether the actual distance value meets the actual accuracy requirements. The actual distance value is returned to the radiotherapy control system, and the displacement and posture of the six-dimensional radiotherapy bed are adjusted based on the actual distance. When the actual distance is less than the preset standard value, the radiotherapy positioning is completed and the next step of cone CT (CBCT) positioning or other operations is started. Otherwise, the photo shooting, image recognition and the displacement and posture of the six-dimensional radiotherapy bed are adjusted based on the calculated actual distance.

[0036] Specifically, based on the image recognition algorithm, the first laser cross line, the second laser cross line and the third laser cross line irradiated on the patient 9 by the first positioning laser light 2, the second positioning laser light 5 and the third positioning laser light 7 are identified, and the first simulated positioning cross mark 8, the second simulated positioning cross mark 11 and the third simulated positioning cross mark 12 are identified, and the first distance S1 between the first simulated positioning cross mark and the center point of the cross irradiated by the first positioning laser light, the second distance S2 between the second simulated positioning cross mark and the center point of the cross irradiated by the third positioning laser light, and the third distance S3 between the third simulated positioning cross mark and the center point of the cross irradiated by the second positioning laser light are calculated respectively.

[0037] The above three distance values ​​S1, S2, and S3 are fed back to the radiotherapy accelerator to control the six-dimensional treatment bed 1 to move the first simulated positioning cross mark 8 to the center point of the cross irradiated by the first positioning laser light 2, move the second simulated positioning cross mark 11 to the center point of the cross irradiated by the third positioning laser light 7, and move the third simulated positioning cross mark 12 to the center point of the cross irradiated by the second positioning laser light 5.

[0038] The first depth of field camera 3, the second depth of field camera 4 and the third depth of field camera 6 continue to take pictures to determine whether the distance S1 between the center point of the cross irradiated by the first simulated positioning cross mark 8 and the first positioning laser light 2, the distance S2 between the center point of the cross irradiated by the second simulated positioning cross mark 11 and the third positioning laser light 7, and the distance S3 between the center point of the cross irradiated by the third simulated positioning cross mark 12 and the second positioning laser light 5 reach the preset standard value. If the preset standard value is reached, the next step of CT positioning is carried out. If not, the step of moving the treatment bed is repeated.

[0039] Figure 4 FIG. 4 is a flow chart of a radiotherapy positioning alignment control method 400 based on image recognition according to an embodiment of the present invention. Figure 4 As shown, in step S410, an image including a laser cross line irradiated by a positioning laser light on the patient's body surface and a simulated positioning cross line is captured in real time.

[0040] In one embodiment of the present invention, a first positioning laser light, a first depth of field camera, a second depth of field camera, a second positioning laser light, a third depth of field camera, and a third positioning laser light are respectively arranged on the left side, the right side, and the top of the six-dimensional treatment bed, and the first positioning laser light, the second positioning laser light, and the third positioning laser light simultaneously emit a first laser cross line, a second laser cross line, and a third laser cross line.

[0041] When the patient lies on the six-dimensional treatment bed in the positioning device, the first simulated positioning cross mark, the second simulated positioning cross mark, and the third simulated positioning cross mark are marked on the patient's body surface or the positioning device. The first depth of field camera, the second depth of field camera, and the third depth of field camera are used to capture images containing the first laser cross line, the second laser cross line, the third laser cross line, and the first simulated positioning cross mark, the second simulated positioning cross mark, and the third simulated positioning cross mark in real time.

[0042] Among them, the first laser cross line, the second laser cross line and the third laser cross line intersect at one point, and the intersection of the perpendicular line through the third simulated positioning cross mark perpendicular to the line connecting the first simulated positioning cross mark and the second simulated positioning cross mark and the line is the positioning reference origin.

[0043] Then in step S420, the actual distance between the laser crosshairs and the simulated positioning crosshairs in the image is calculated based on the image recognition algorithm.

[0044] For example, based on the straight line detection algorithm, the feature points of the laser cross line and the simulated positioning cross line are extracted from the real-time collected image. The identified feature point coordinates are converted into actual physical distances, and the first distance between the first simulated positioning cross mark and the center point of the cross irradiated by the first positioning laser light, the second distance between the second simulated positioning cross mark and the center point of the cross irradiated by the third positioning laser light, and the third distance between the third simulated positioning cross mark and the center point of the cross irradiated by the second positioning laser light are calculated respectively; the calculated first distance, second distance, and third distance are fed back to the radiotherapy accelerator control system.

[0045] Finally, in step S430, the displacement and posture of the six-dimensional radiotherapy bed are adjusted based on the actual distance. When the actual distance is less than the preset standard value, the radiotherapy positioning is completed.

[0046] The radiotherapy accelerator control system compares the fed-back first distance, second distance and third distance with the preset standard values ​​respectively. If the first distance, the second distance and the third distance are all smaller than the preset standard values, the radiotherapy positioning is completed; otherwise, the position and posture of the six-dimensional treatment bed are continued to be adjusted until the first distance, the second distance and the third distance are all smaller than the preset standard values, and the radiotherapy positioning is completed.

[0047] Figure 5 FIG. 1 shows a block diagram of a computing device 100 according to an embodiment of the present invention. Figure 5 As shown, in a basic configuration 102, computing device 100 typically includes system memory 106 and one or more processors 104. A memory bus 108 may be used for communication between processor 104 and system memory 106.

[0048] Depending on the desired configuration, the processor 104 can be any type of processor, including but not limited to: a microprocessor (µP), a microcontroller (µC), a digital signal processor (DSP), or any combination thereof. The processor 104 can include one or more levels of cache, such as a primary cache 110 and a secondary cache 112, a processor core 114, and registers 116. An example processor core 114 can include an arithmetic logic unit (ALU), a floating point unit (FPU), a digital signal processing core (DSP core), or any combination thereof. An example memory controller 118 can be used with the processor 104, or in some implementations, the memory controller 118 can be an internal part of the processor 104.

[0049] Depending on the desired configuration, the system memory 106 may be any type of memory, including but not limited to: volatile memory (such as RAM), non-volatile memory (such as ROM, flash memory, etc.), or any combination thereof. Physical memory in a computing device generally refers to volatile memory RAM, and data in a disk needs to be loaded into physical memory before it can be read by the processor 104. The system memory 106 may include an operating system 120, one or more applications 122, and program data 124.

[0050] In some embodiments, the application 122 may be arranged to execute instructions on an operating system by one or more processors 104 using program data 124. The operating system 120 may be, for example, Linux, Windows, etc., which includes program instructions for processing basic system services and performing hardware-dependent tasks. The application 122 includes program instructions for implementing various user-desired functions, and the application 122 may be, for example, a browser, instant messaging software, a software development tool (e.g., an integrated development environment IDE, a compiler, etc.), etc., but is not limited thereto. When the application 122 is installed in the computing device 300, a driver module may be added to the operating system 120.

[0051] When the computing device 100 starts running, the processor 104 reads and executes the program instructions of the operating system 120 from the memory 106. The application 122 runs on the operating system 120 and uses the interfaces provided by the operating system 120 and the underlying hardware to implement various functions desired by the user. When the user starts the application 122, the application 122 is loaded into the memory 106, and the processor 104 reads and executes the program instructions of the application 122 from the memory 106.

[0052] Computing device 100 also includes a storage device 132 including a removable storage 136 and a non-removable storage 138 , both of which are connected to storage interface bus 134 .

[0053] The computing device 100 may also include an interface bus 140 that facilitates communication from various interface devices (e.g., output devices 142, peripheral interfaces 144, and communication devices 146) to the basic configuration 102 via the bus / interface controller 130. Example output devices 142 include a graphics processing unit 148 and an audio processing unit 150. They can be configured to facilitate communication with various external devices such as a display or speakers via one or more A / V ports 152. Example peripheral interfaces 144 may include a serial interface controller 154 and a parallel interface controller 156, which may be configured to facilitate communication with external devices such as input devices (e.g., keyboards, mice, pens, voice input devices, touch input devices) or other peripherals (e.g., printers, scanners, etc.) via one or more I / O ports 158. Example communication devices 146 may include a network controller 160, which may be arranged to facilitate communication with one or more other computing devices 162 via a network communication link via one or more communication ports 164.

[0054] A network communication link may be an example of a communication medium. The communication medium may generally be embodied as a computer-readable instruction, data structure, program module in a modulated data signal such as a carrier wave or other transmission mechanism, and may include any information delivery medium. A "modulated data signal" may be a signal in which one or more of its data sets or its changes may be performed in a manner that encodes information in the signal. As a non-limiting example, the communication medium may include a wired medium such as a wired network or a dedicated network, and various wireless media such as sound, radio frequency (RF), microwave, infrared (IR) or other wireless media. The term computer-readable medium used herein may include both storage media and communication media. In a computing device 100 according to the present invention, the application 122 includes instructions for executing the image recognition-based radiotherapy positioning alignment control method 400 of the present invention.

[0055] The radiotherapy positioning alignment control method and system based on image recognition provided by the present invention can at least achieve the following beneficial effects: By capturing and processing images containing laser crosshairs and simulated positioning crosshairs in real time, instant displacement and posture adjustments can be achieved. This dynamic adjustment capability helps to quickly respond to changes in patient position or device misalignment, thereby improving the accuracy and efficiency of treatment.

[0056] The automated image recognition and calculation process reduces the need for manual operation and judgment, thereby reducing the possibility of human error. By capturing and processing images in real time, it can adapt to slight changes in the patient's position, ensuring that the system can make timely adjustments and maintain the accuracy of treatment even when the patient's position moves slightly.

[0057] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0058] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof.

[0059] Those skilled in the art will appreciate that the modules or units or components of the devices in the examples disclosed herein may be arranged in the devices described in the embodiment, or alternatively may be located in one or more devices different from the devices in the examples. The modules in the foregoing examples may be combined into one module or may be divided into multiple submodules.

[0060] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of submodules or subunits or subcomponents.

[0061] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, the combination of features from different embodiments is meant to be within the scope of the present invention and to form different embodiments.

[0062] In addition, some of the embodiments are described herein as methods or combinations of method elements that can be implemented by a processor of a computer system or by other devices that perform the functions. Therefore, a processor with necessary instructions for implementing the method or method elements forms a device for implementing the method or method elements. In addition, the elements described herein of the device embodiments are examples of devices for implementing the functions performed by the elements for the purpose of implementing the invention.

[0063] As used herein, unless otherwise specified, the use of ordinal numbers "first," "second," "third," etc. to describe common objects merely indicates that different instances of similar objects are involved, and is not intended to imply that the objects so described must have a given order in time, space, order, or in any other manner.

[0064] Although the present invention has been described according to a limited number of embodiments, it will be apparent to those skilled in the art, with the benefit of the above description, that other embodiments may be envisioned within the scope of the invention thus described. In addition, it should be noted that the language used in this specification is selected primarily for readability and teaching purposes, rather than for explaining or defining the subject matter of the present invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the attached description. The disclosure of the present invention is illustrative rather than restrictive with respect to the scope of the present invention, and the scope of the present invention is defined by the attached description.

Claims

1. A radiotherapy positioning control method based on image recognition, characterized in that: include: Real-time shooting of images including laser cross lines of the positioning laser light irradiated on the patient's body surface and simulated positioning cross lines; Calculating the actual distance between the laser crosshairs and the simulated positioning crosshairs in the image based on an image recognition algorithm; The displacement and posture of the six-dimensional radiotherapy bed are adjusted based on the actual distance, and when the actual distance is less than a preset standard value, the radiotherapy positioning is completed.

2. The radiotherapy positioning and alignment control method based on image recognition according to claim 1, characterized in that: The step of real-time shooting of an image including a laser cross line irradiated by a positioning laser light on the patient's body surface and a simulated positioning cross line comprises: A first positioning laser light, a first depth-of-field camera, a second depth-of-field camera, a second positioning laser light, a third depth-of-field camera, and a third positioning laser light are respectively arranged on the left side, the right side, and the top of the six-dimensional treatment bed, and the first positioning laser light, the second positioning laser light, and the third positioning laser light simultaneously emit a first laser cross line, a second laser cross line, and a third laser cross line; When the patient lies on the six-dimensional treatment bed in the positioning device, the first simulated positioning cross mark, the second simulated positioning cross mark, and the third simulated positioning cross mark are marked on the patient's body surface or the positioning device; Based on the first depth of field camera, the second depth of field camera and the third depth of field camera, an image containing the first laser cross line, the second laser cross line and the third laser cross line and the first simulated positioning cross mark, the second simulated positioning cross mark and the third simulated positioning cross mark is captured in real time.

3. The radiotherapy positioning and alignment control method based on image recognition according to claim 2, characterized in that: The first laser cross line, the second laser cross line and the third laser cross line intersect at one point, and the intersection of a perpendicular line passing through the third simulated positioning cross mark and a line perpendicular to the first simulated positioning cross mark and the second simulated positioning cross mark and the line is the positioning reference origin.

4. The radiotherapy positioning and alignment control method based on image recognition according to claim 2, characterized in that: The step of calculating the actual distance between the laser cross line and the simulated positioning cross line in the image based on the image recognition algorithm comprises: Extract the feature points of the laser cross line and simulate the positioning cross line from the real-time acquired image based on the straight line detection algorithm; Convert the identified feature point coordinates into actual physical distances, and calculate the first distance between the first simulated positioning cross mark and the center point of the cross irradiated by the first positioning laser light, the second distance between the second simulated positioning cross mark and the center point of the cross irradiated by the third positioning laser light, and the third distance between the third simulated positioning cross mark and the center point of the cross irradiated by the second positioning laser light; The calculated first distance, second distance and third distance are fed back to the radiotherapy accelerator control system.

5. The radiotherapy positioning alignment control method based on image recognition according to claim 4, wherein The step of adjusting the displacement and posture of the six-dimensional radiotherapy bed based on the actual distance, and completing the radiotherapy positioning when the actual distance is less than a preset standard value, includes: The first distance, the second distance and the third distance are respectively compared with the preset standard values. If the first distance, the second distance and the third distance are all smaller than the preset standard values, the radiotherapy positioning is completed. Otherwise, the position and posture of the six-dimensional treatment bed are continuously adjusted until the radiotherapy positioning is completed when the first distance, the second distance and the third distance are all smaller than the preset standard values.

6. A radiotherapy positioning and alignment control system based on image recognition, characterized in that: include: The radiotherapy accelerator is equipped with a six-dimensional treatment bed, a first positioning laser light, a first depth-of-field camera, a second depth-of-field camera, a second positioning laser light, a third depth-of-field camera, and a third positioning laser light. The first positioning laser light and the first depth-of-field camera are located on the right side of the six-dimensional treatment bed, and the third depth-of-field camera and the third positioning laser light are located on the left side of the six-dimensional treatment bed. The second depth-of-field camera and the second positioning laser light are located on the top of the six-dimensional treatment bed. The first depth-of-field camera is located directly above the first positioning laser light, and the third depth-of-field camera is located directly above the third positioning laser light. The second depth-of-field camera is displaced to the side of the second positioning laser light. When the patient is fixed on the positioning device and lies on the six-dimensional treatment bed, the first simulated positioning cross mark, the second simulated positioning cross mark and the third simulated positioning cross mark are located on the patient's body surface or the surface of the positioning device; The system is used to capture in real time an image containing a laser cross line and a simulated positioning cross line irradiated by a positioning laser light on the patient's body surface through the first depth of field camera, the second depth of field camera, and the third depth of field camera; calculate the actual distance between the laser cross line and the simulated positioning cross line in the image based on an image recognition algorithm; adjust the displacement and posture of the six-dimensional radiotherapy bed based on the actual distance, and complete the radiotherapy positioning when the actual distance is less than a preset standard value.

7. The radiotherapy positioning and alignment control system based on image recognition according to claim 6, characterized in that: The visible band laser cross lines emitted by the first positioning laser light, the second positioning laser light and the third positioning laser light coincide at one point; the intersection of the perpendicular line passing through the third simulated positioning cross mark and the line connecting the first simulated positioning cross mark and the second simulated positioning cross mark and the line is the positioning reference origin, and the position between the center of the tumor radiotherapy field in the patient's body and the reference origin is fixed.

8. The radiotherapy positioning and alignment control system based on image recognition according to claim 6, characterized in that: The first depth-of-field camera, the second depth-of-field camera and the third depth-of-field camera are used to continuously capture images of the patient and the positioning device within the same capturing range at different angles.

9. A computing device, characterized in that include: at least one processor; and a memory storing program instructions, wherein the program instructions are configured to be suitable for execution by the at least one processor, and the program instructions include instructions for executing the radiotherapy positioning alignment control method based on image recognition as described in any one of claims 1-5.

10. A readable storage medium storing program instructions, characterized in that: When the program instructions are read and executed by a computing device, the computing device executes the radiotherapy positioning and alignment control method based on image recognition as described in any one of claims 1-5.

Images