Radiotherapy body position adjusting method, device and system based on millimeter wave radar

Abstract

The invention relates to the technical field of medical treatment, and discloses a radiotherapy body position adjusting method, device and system based on millimeter wave radar, and the method comprises the steps: obtaining target millimeter wave echo data of a body surface region covered by a fixed film in a state that the body surface of a patient is covered by the fixed film; according to the target millimeter wave echo data, an actual three-dimensional model reflecting the actual body position of the patient is generated; a reference three-dimensional model of the standard body position of the patient is obtained; the actual three-dimensional model and the reference three-dimensional model are registered, and the pose deviation and the positioning confidence coefficient of the current body position of the patient relative to the standard body position are determined; and according to the pose deviation and the positioning confidence coefficient, generating a body position adjustment guide instruction or prompt information of the patient. According to the technical scheme, the problem that in the prior art, the patient body position adjusting efficiency is low is solved, and the patient body position adjusting efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the medical technology field, and in particular to a radiotherapy position adjustment method, device and system based on a millimeter wave radar. BACKGROUND

[0002] Radiotherapy is one of the core means of malignant tumor treatment, and its treatment effect is highly dependent on the accuracy of target positioning. In order to ensure that the patient's position is consistent with the standard position in the computed tomography (CT) positioning stage every time the patient is treated, a thermoplastic fixing film or a vacuum film is usually used to fix the patient's position in the clinic, and physical constraints are used to reduce the position deviation in the treatment process, so as to avoid damage to the surrounding normal tissues by radiotherapy. With the development of radiotherapy technology towards high precision and high dose, the requirement for position repeatability is increasingly stringent, and position deviation detection as a key link of positioning calibration directly affects the safety and effectiveness of treatment.

[0003] In related technologies, deviation detection mainly relies on visible light imaging or laser positioning, but it cannot penetrate the thermoplastic fixing film and can only judge the position by observing the external shape of the fixing film, which is difficult to truly reflect the possible incomplete fitting problem between the patient's body surface and the fixing film, resulting in distorted detection results. Although some positioning technologies based on millimeter wave radars have the advantage of non-contact detection, they mostly use traditional signal processing methods, which are difficult to effectively filter out the interference of fixing film body reflection and environmental noise, and are difficult to meet the high precision requirement of the radiotherapy scene, resulting in low efficiency of patient position adjustment.

[0004] In other words, there is a problem of low efficiency of patient position adjustment in related technologies. SUMMARY

[0005] The present application provides a radiotherapy position adjustment method, device and system based on a millimeter wave radar to solve the problem of low efficiency of patient position adjustment in related technologies.

[0006] In a first aspect, the present application provides a radiotherapy position adjustment method based on a millimeter wave radar, which comprises: In a state where the patient's body surface is covered with a fixing film, target millimeter wave echo data of the body surface region covered by the fixing film is acquired; According to the target millimeter wave echo data, an actual three-dimensional model reflecting the real position of the patient is generated; A reference three-dimensional model of the standard position of the patient is acquired, and the reference three-dimensional model indicates a three-dimensional surface model of the patient in a state where the fixing film is not covered; The actual three-dimensional model and the reference three-dimensional model are registered to determine the pose deviation and the position confidence of the current position of the patient relative to the standard position, and the position confidence indicates whether there is a fitting abnormality between the fixing film and the patient's body surface. Based on posture deviation and positional reliability, generate postural adjustment guidance instructions or prompts for the patient.

[0007] In one alternative implementation, obtaining a reference three-dimensional model of the patient in a standard position includes: From the patient's radiotherapy plan CT image set, the image data sequence of the patient's body surface is segmented, wherein the radiotherapy plan CT image set includes images in the standard position; Generate a reference 3D model based on the image data sequence; or, When the patient is in a standard position, a reference three-dimensional model is generated and stored by collecting millimeter-wave echo data without a fixed membrane.

[0008] In one optional implementation, the actual 3D model is registered with a reference 3D model to determine the patient's current pose deviation relative to a standard pose and the positional reliability, including: The spatial transformation matrix between the actual 3D model and the reference 3D model is determined by the ICP algorithm. The spatial transformation matrix is ​​used to characterize the pose deviation. The location reliability is determined based on at least one of the following: the residual distribution of the local key target area after registration, the point cloud coverage of the actual 3D model in the corresponding area of ​​the reference 3D model, and the signal-to-noise ratio of the target millimeter-wave echo data.

[0009] In one optional implementation, acquiring target millimeter-wave echo data over a body surface region covered by a fixed membrane includes: The detection parameters of the millimeter-wave radar are set to the operating parameters that are adapted to the penetration characteristics of the fixed membrane. The operating parameters include the transmission frequency, signal bandwidth and sampling rate. Based on the operating parameters, raw millimeter-wave echo data is acquired using millimeter-wave radar. Background noise removal and fixed membrane reflection signal filtering were performed on the raw millimeter-wave echo data to obtain effective echo data that retains the reflection from the patient's body surface, which was then used as the target millimeter-wave echo data.

[0010] In one optional implementation, generating an actual three-dimensional model of the outer surface of the fixed membrane based on the target millimeter-wave echo data includes: The target millimeter-wave echo data is subjected to range-dimensional Fourier transform and phase unwrapping processing to extract the three-dimensional coordinate information of the body surface; Initial point cloud data is generated based on the three-dimensional coordinate information of the body surface. Discrete noise points are removed by statistical filtering algorithm, and the actual three-dimensional model is generated by Poisson surface reconstruction algorithm.

[0011] In one optional implementation, based on posture deviation and positioning reliability, postural adjustment guidance instructions or prompts are generated for the patient, including: If the positional confidence is greater than the preset threshold and the positional deviation exceeds the preset range, then the six-degree-of-freedom adjustment parameters of the radiotherapy treatment bed are generated based on the positional deviation, and the body position adjustment guidance command is generated. If the location confidence level is less than or equal to the preset threshold, a prompt message will be generated, indicating that the fixing film has an adhesion abnormality and needs to be re-fixed.

[0012] Secondly, this application provides a radiotherapy positioning device based on millimeter-wave radar, the device comprising: The echo acquisition module is used to acquire target millimeter wave echo data in the area of ​​the body surface covered by the fixation film when the patient's body surface is covered by a fixation film. The actual model generation module is used to generate an actual three-dimensional model that reflects the patient's true position based on the target millimeter wave echo data. The reference model acquisition module is used to acquire a reference three-dimensional model of the patient in a standard position. The reference three-dimensional model indicates the three-dimensional surface model of the patient without the fixation membrane. The pose determination module is used to register the actual 3D model with the reference 3D model, determine the pose deviation of the patient's current position relative to the standard position and the position determination reliability. The position determination reliability indicates whether there is an abnormal fit between the fixation film and the patient's body surface. The adjustment guidance module is used to generate postural adjustment guidance instructions or prompts for patients based on posture deviation and positional reliability.

[0013] Thirdly, this application provides a radiotherapy positioning system based on millimeter-wave radar, characterized in that the system includes at least two sets of millimeter-wave sensors, a treatment bed, and a controller. The at least two sets of millimeter-wave sensors are deployed on both sides of the radiotherapy bed, and the detection range of the at least two sets of millimeter-wave sensors covers the entire body surface area covered by the fixation membrane set on the radiotherapy bed. The controller is used to control the at least two sets of millimeter-wave sensors and the treatment bed, and the controller executes the radiotherapy positioning method based on millimeter-wave radar according to the first aspect or any corresponding embodiment described above.

[0014] Fourthly, this application provides an electronic device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the above-described method for adjusting radiotherapy position based on millimeter-wave radar, or any of its corresponding embodiments.

[0015] Fifthly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the millimeter-wave radar-based radiotherapy positioning method described in the first aspect or any corresponding embodiment.

[0016] According to the method for adjusting radiotherapy positioning based on millimeter-wave radar provided in this application, the following beneficial technical effects can be achieved compared with the prior art: With the patient's body surface covered by a fixation membrane, target millimeter-wave echo data of the area covered by the membrane is acquired. This eliminates the need to cut holes or create windows in the membrane, avoiding damage to its integrity. This ensures fixation strength to reduce motion errors, simplifies positioning preparation, improves positioning efficiency, and protects patient privacy and comfort. Based on the target millimeter-wave echo data, a true 3D model reflecting the patient's actual position is generated. Leveraging the ability of millimeter waves to penetrate non-metallic fixation membranes, this overcomes the limitations of optical systems that obstruct observation, accurately capturing the patient's true surface condition and avoiding model distortion caused by the fixation membrane. This provides reliable data support for subsequent deviation calculations. A reference 3D model of the patient in a standard position is also acquired. This reference model indicates the 3D surface model of the patient without the fixation membrane, providing a benchmark directly comparable to the actual position. Both models converge. The model focuses on the patient's actual body morphology, eliminating interference from the fixation membrane on the registration reference and ensuring the accuracy of posture deviation calculation. The actual 3D model is registered with a reference 3D model to determine the patient's current posture deviation relative to the standard position and the positioning reliability. The positioning reliability indicates whether there are any abnormalities in the fit between the fixation membrane and the patient's body surface. This accurately calculates the six-degree-of-freedom posture deviation, meeting the high-precision positioning requirements of radiotherapy, and can also identify fixation membrane adhesion abnormalities in real time, avoiding adjustment failures due to poor fit and improving the reliability of posture adjustment. Based on the posture deviation and positioning reliability, the model generates posture adjustment guidance instructions or prompts for the patient, achieving precise and intelligent posture adjustment. It automatically outputs the six-degree-of-freedom adjustment parameters of the treatment bed or prompts for adhesion abnormalities, reducing manual intervention and repeated calibration, and significantly improving the efficiency of posture adjustment and the safety of radiotherapy. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0018] Figure 1 This is a flowchart of a radiotherapy positioning method based on millimeter-wave radar according to an embodiment of this application; Figure 2 This is a flowchart of another method for adjusting the position of a patient in radiotherapy based on millimeter-wave radar, according to an embodiment of this application; Figure 3 This is a structural block diagram of a radiotherapy positioning device based on millimeter-wave radar according to an embodiment of this application; Figure 4 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] It is understood that before using the technical solutions disclosed in the various embodiments of this application, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0021] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0022] Radiotherapy demands stringent precision in patient positioning. Clinically, thermoplastic fixation films, masks, and body films are commonly used to cover and immobilize the patient's body surface, minimizing motion errors between and within fractions and ensuring treatment accuracy. Existing surface-guided radiotherapy systems often employ optical surface monitoring systems (OSMS), which use structured light / infrared cameras to acquire point clouds of the patient's body surface. After registration with a reference surface, the OSMS outputs the pose deviation, guiding bed adjustments and serving as a commonly used clinical method for patient positioning.

[0023] However, in scenarios where a fixation membrane covers the body surface, the optical system cannot penetrate the membrane, making it difficult to directly observe the skin surface and significantly reducing the efficiency of body positioning. To address this issue, clinicians need to cut holes in the fixation membrane or use an open fixation membrane to expose the skin observation area. However, cutting holes is a complex and time-consuming procedure, and the preparation and adaptation process for open fixation membranes is cumbersome, directly extending the patient's positioning time. Furthermore, the fixation strength of the membrane decreases after cutting holes, potentially causing body position shifts, requiring repeated adjustments and calibrations, further reducing adjustment efficiency. In cases where opening holes is unsuitable for certain areas or patient conditions, the optical system may become completely ineffective, necessitating alternative adjustment methods and increasing procedural redundancy.

[0024] Therefore, there is an urgent need for a non-contact surface-guided positioning technology that can be directly implemented under fixed membrane coverage to overcome the efficiency bottleneck of optical surface monitoring in obstructed scenarios. Millimeter waves have the ability to penetrate most non-metallic media and can obtain distance and angle information through echo signals. They also have the advantages of being non-contact and insensitive to low light, making them suitable for the surface positioning guidance needs under fixed membrane coverage. However, the radiotherapy room environment has strong metal reflections, complex multipath interference, and large differences in fixed membrane materials. How to quickly and stably reconstruct the surface information of the fixed membrane-covered area, efficiently calculate the six degrees of freedom deviation, and output positioning reliability and abnormality prompts while avoiding repeated calibration has become a key issue in improving the efficiency of patient positioning.

[0025] According to an embodiment of this application, a method for adjusting body position in radiotherapy based on millimeter-wave radar is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0026] This embodiment provides a method for adjusting the position of a patient during radiotherapy based on millimeter-wave radar, which can be used in a dedicated controller or industrial control unit for radiotherapy systems. Figure 1 This is a flowchart of a radiotherapy positioning method based on millimeter-wave radar according to an embodiment of this application, as shown below. Figure 1 As shown, the process includes the following steps: Step S101: With the patient's body surface covered by a fixation film, acquire the target millimeter wave echo data in the area of ​​the body surface covered by the fixation film.

[0027] Specifically, fixation membranes refer to non-metallic membranes used in clinical radiotherapy to fix the patient's position, including thermoplastic fixation membranes, body membranes, and face masks. Target millimeter-wave echo data refers to effective millimeter-wave data that retains the patient's surface reflection signal after optimization processing.

[0028] In this embodiment, the detection parameters of the millimeter-wave radar, such as the transmission frequency and signal bandwidth, are first adjusted to adapt to the penetration characteristics of the fixed membrane. After acquiring the raw echo data, the target millimeter-wave echo data is obtained through background noise removal and fixed membrane reflection signal filtering. This solution eliminates the need to cut holes or create windows in the fixed membrane, ensuring both fixation strength and rapid acquisition of effective data, laying the foundation for subsequent model generation and improving the efficiency of the pre-positioning adjustment process.

[0029] Step S102: Generate an actual three-dimensional model reflecting the patient's true position based on the target millimeter-wave echo data.

[0030] Specifically, the actual body position refers to the patient's actual body posture (such as trunk tilt angle, limb placement, etc.) when covered by the fixation membrane. The actual 3D model refers to a 3D surface model reconstructed based on the patient's actual body surface reflection signals, which can accurately restore the current body surface morphology.

[0031] The target millimeter-wave echo data is subjected to range-dimensional Fourier transform and phase unwrapping processing to extract the three-dimensional coordinates of the body surface and generate an initial point cloud. After statistical filtering to remove noise points, a model is generated by reconstructing using a Poisson surface. By leveraging the penetrating properties of millimeter waves, the model can overcome the obstruction of the fixed membrane, avoiding model distortion and providing high-precision data support for subsequent deviation calculations.

[0032] Step S103: Obtain a reference three-dimensional model of the patient in a standard position. The reference three-dimensional model indicates the three-dimensional surface model of the patient without the fixation membrane.

[0033] Specifically, the standard position refers to the treatment baseline posture determined during CT localization of the patient (such as the standard placement of the head and torso when supine). The reference 3D model refers to a 3D surface model reconstructed based on this standard position, which serves as the benchmark for comparing positional deviations.

[0034] This model can be generated by segmenting surface data from radiotherapy planning CT image sets or by acquiring uncoated millimeter-wave echo data while the patient is in a standard position. It focuses on the patient's true surface morphology, forming a precise comparison benchmark with the actual 3D model, eliminating interference from the fixation membrane on registration, and ensuring the accuracy of deviation calculations.

[0035] Step S104: Register the actual three-dimensional model with the reference three-dimensional model to determine the patient's current position deviation from the standard position and the positional reliability. The positional reliability indicates whether there is an abnormal fit between the fixation film and the patient's body surface.

[0036] Specifically, posture deviation refers to the deviation of the current body position from the standard body position in six degrees of freedom (such as head-to-toe / left-right / up-down translation, three-dimensional rotation angle, etc.). Position reliability is a quantitative indicator characterizing the reliability of body position detection, used to determine whether the fixation membrane adheres well.

[0037] The spatial transformation matrix of the two models is solved by the Iterated Closest Points (ICP) algorithm to determine the pose deviation. The positioning reliability is calculated by combining at least one of the following: registration residual distribution, point cloud coverage, and echo signal-to-noise ratio. This method achieves high-precision deviation calculation and can identify abnormalities in the fixation membrane in real time, avoiding adjustment failure due to poor adhesion and improving the reliability of body position adjustment.

[0038] Step S105: Based on the posture deviation and positional reliability, generate postural adjustment guidance instructions or prompts for the patient.

[0039] Specifically, the body position adjustment guidance command refers to the parameter command (such as head height adjustment, bed rotation angle, etc.) used to control the radiotherapy treatment bed to make six-degree-of-freedom adjustments.

[0040] If the positional reliability exceeds a preset threshold and the posture deviation exceeds the allowable range, treatment bed adjustment parameters are generated based on the posture deviation; if the positional reliability fails to meet the standard, a prompt message indicating abnormal fixation membrane adhesion is generated. This achieves precise and intelligent body position adjustment, reduces manual intervention and repeated calibration, and improves adjustment efficiency and radiotherapy safety.

[0041] This embodiment provides a method for radiotherapy positioning based on millimeter-wave radar. With the patient's body surface covered by a fixation membrane, it acquires target millimeter-wave echo data of the area covered by the membrane. This eliminates the need to cut holes or create windows in the fixation membrane, avoiding damage to its integrity. This ensures fixation strength to reduce motion errors, simplifies positioning preparation, improves positioning efficiency, and protects patient privacy and comfort. Based on the target millimeter-wave echo data, a realistic 3D model reflecting the patient's true position is generated. Leveraging the ability of millimeter waves to penetrate non-metallic fixation membranes, this overcomes the limitations of optical systems that obstruct observation, accurately capturing the patient's true surface state and avoiding model distortion caused by the fixation membrane. This provides reliable data support for subsequent deviation calculations. A reference 3D model of the patient's standard position is also acquired. This reference 3D model indicates the 3D surface model of the patient without the fixation membrane, providing a direct correlation with the actual position. Using comparable benchmarks, both models focus on the patient's actual body surface morphology, eliminating the interference of the fixation membrane on the registration benchmark and ensuring the accuracy of posture deviation calculation. The actual 3D model is registered with the reference 3D model to determine the posture deviation of the patient's current position relative to the standard position and the positioning reliability. The positioning reliability indicates whether there is an abnormal fit between the fixation membrane and the patient's body surface. This not only accurately calculates the six-degree-of-freedom posture deviation to meet the high-precision positioning requirements of radiotherapy, but also identifies fixation membrane adhesion abnormalities in real time, avoiding adjustment failures caused by poor fit and improving the reliability of posture adjustment. Based on the posture deviation and positioning reliability, the system generates posture adjustment guidance instructions or prompts for the patient, achieving precise and intelligent posture adjustment. It automatically outputs the six-degree-of-freedom adjustment parameters of the treatment bed or prompts for adhesion abnormalities, reducing manual intervention and repeated calibration, and significantly improving the efficiency of posture adjustment and the safety of radiotherapy.

[0042] This embodiment provides a method for adjusting the position of a patient during radiotherapy based on millimeter-wave radar, which can be used in the dedicated controller or industrial control host of the aforementioned radiotherapy system. Figure 2 This is a flowchart of another radiotherapy positioning method based on millimeter-wave radar according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps: Step S201: With the patient's body surface covered by a fixation film, acquire the target millimeter wave echo data in the area of ​​the body surface covered by the fixation film.

[0043] Specifically, step S201 above includes the following steps: Step S2011: Set the detection parameters of the millimeter-wave radar to the working parameters adapted to the penetration characteristics of the fixed membrane. The working parameters include the transmission frequency, signal bandwidth and sampling rate.

[0044] Specifically, the penetration characteristics of a fixed film refer to the ability of millimeter waves to penetrate non-metallic films such as thermoplastic fixed films and bulk films (e.g., penetration depth, signal attenuation). Operating parameters refer to the core operating parameters of millimeter-wave radar, including transmission frequency (e.g., 60 GHz), signal bandwidth, and sampling rate.

[0045] Based on the penetration characteristics of the fixation membrane, such as its material and thickness, the transmission frequency, signal bandwidth, and sampling rate of the millimeter-wave radar are adjusted to ensure that the radar signal can effectively penetrate the fixation membrane. This step ensures that the radar signal accurately captures the patient's surface reflection information, providing high-quality raw data for subsequent data processing and improving the reliability of penetration detection.

[0046] Step S2012: Based on the operating parameters, use millimeter-wave radar to acquire raw millimeter-wave echo data.

[0047] Specifically, raw millimeter-wave echo data refers to unfiltered reflected signal data (including reflected signals from the patient's body surface, fixation membrane, environmental interference, etc.) directly collected by millimeter-wave radar.

[0048] Based on operating parameters adapted to the penetration characteristics of the fixed membrane, the millimeter-wave radar is controlled to transmit signals to the area covered by the fixed membrane and receive reflected signals, thus acquiring raw echo data. This achieves comprehensive signal capture of the target area, providing a complete data foundation for subsequent screening of effective signals and generation of accurate models.

[0049] Step S2013: Background noise removal and fixed membrane reflection signal filtering are performed on the original millimeter wave echo data to obtain effective echo data that retains the reflection from the patient's body surface as the target millimeter wave echo data.

[0050] Specifically, background noise removal refers to removing irrelevant signals such as metal reflections and electromagnetic interference from the radiotherapy room. Fixation membrane reflection signal filtering refers to filtering out signals reflected from the surface of the fixation membrane by millimeter waves. Target millimeter wave echo data refers to retaining effective signal data reflected from the patient's body surface that can be used for subsequent modeling.

[0051] By using signal processing algorithms to remove environmental background noise and filter out interfering signals reflected from the fixation membrane surface, only valid signals reflected from the patient's body surface are retained. This step improves data purity, prevents noise and fixation membrane reflection signals from affecting modeling accuracy, and provides reliable data support for generating realistic body position models.

[0052] Step S202: Generate an actual three-dimensional model reflecting the patient's true position based on the target millimeter-wave echo data.

[0053] Specifically, step S202 above includes the following steps: Step S2021: Perform range dimension Fourier transform and phase unwrapping processing on the target millimeter wave echo data to extract the three-dimensional coordinate information of the body surface.

[0054] Specifically, the distance-dimensional Fourier transform refers to performing frequency domain analysis on the echo signal to calculate the distance information between the target and the radar. Phase unwrapping refers to eliminating phase folding and restoring the true phase value to improve ranging accuracy. Three-dimensional coordinate information of the body surface refers to the spatial location data (such as x, y, and z axis coordinates) of each sampling point on the patient's body surface.

[0055] The target millimeter-wave echo data is sequentially subjected to range-dimensional Fourier transform and phase unwrapping processing to extract the three-dimensional coordinate information of various points on the patient's body surface from the processed signal. This step can accurately resolve the spatial position data in the millimeter-wave echo, providing a high-precision coordinate basis for subsequent three-dimensional model reconstruction and ensuring the consistency between the model and the patient's actual position.

[0056] Step S2022: Generate initial point cloud data based on the three-dimensional coordinate information of the body surface, remove discrete noise points through statistical filtering algorithm, and generate the actual three-dimensional model through Poisson surface reconstruction algorithm.

[0057] Specifically, initial point cloud data refers to a set of discrete spatial points directly generated from the three-dimensional coordinate information of the body surface. Statistical filtering algorithms are algorithms that remove outliers based on the statistical characteristics of the point cloud's neighborhood (such as filtering based on the mean and variance of distances between neighboring points). Discrete noise points refer to isolated points in the point cloud that deviate excessively from the main point cloud (such as points generated by environmental stray reflections). Poisson surface reconstruction algorithms are three-dimensional reconstruction algorithms that fit a smooth surface to the topological structure of the point cloud.

[0058] The extracted 3D coordinates of the body surface are converted into initial point cloud data. A statistical filtering algorithm is used to remove discrete noise points, and then a Poisson surface reconstruction algorithm is used to fit and generate a continuous, realistic 3D model. This step filters out point cloud interference, improves model smoothness and accuracy, restores the patient's true positional morphology, and provides high-quality model support for subsequent registration and deviation calculations.

[0059] Step S203: Obtain a reference three-dimensional model of the patient in a standard position. The reference three-dimensional model indicates the three-dimensional surface model of the patient without the fixation membrane.

[0060] Specifically, step S203 above includes the following steps: Step S2031: From the patient's radiotherapy plan CT image set, segment the image data sequence of the patient's body surface, wherein the radiotherapy plan CT image set includes images in the standard position.

[0061] Specifically, the radiotherapy planning CT image set refers to the collection of continuous tomographic CT images acquired during patient CT localization for developing a radiotherapy plan. The image data sequence refers to a sequence of continuous image frames segmented from the CT image set, representing the patient's body surface contours.

[0062] From the CT image set used to develop the radiotherapy plan, image data sequences corresponding to the patient's body surface are extracted using image segmentation algorithms. This approach directly reuses existing CT data from the radiotherapy plan, eliminating the need for additional data acquisition and saving operational costs. Simultaneously, it ensures consistency between the reference model and the patient's position in the radiotherapy plan, providing a precise benchmark for subsequent deviation comparisons.

[0063] Step S2032: Generate a reference 3D model based on the image data sequence; or, When the patient is in a standard position, a reference three-dimensional model is generated and stored by collecting millimeter-wave echo data without a fixed membrane.

[0064] Specifically, millimeter-wave echo data refers to the signal data received after the millimeter-wave radar transmits a signal and it is reflected off the patient's body surface.

[0065] In this embodiment, two methods are provided for generating a reference 3D model: one is to perform 3D reconstruction based on the segmented body surface image data sequence; the other is to acquire millimeter-wave echo data and model and store it when the patient is in a standard position and without diaphragm. Both methods are flexibly selectable, allowing for the reuse of CT data from the radiotherapy plan or direct acquisition via millimeter waves, ensuring the accuracy of the reference model and providing a reliable benchmark for subsequent positioning registration.

[0066] Step S204: Register the actual 3D model with the reference 3D model to determine the patient's current position deviation from the standard position and the positional reliability. The positional reliability indicates whether there is an abnormal fit between the fixation film and the patient's body surface.

[0067] Specifically, step S204 above includes the following steps: Step S2041: Determine the spatial transformation matrix between the actual 3D model and the reference 3D model using the ICP algorithm. The spatial transformation matrix is ​​used to characterize the pose deviation.

[0068] Specifically, the spatial transformation matrix refers to the matrix (including translation and rotation parameters) that characterizes the six-degree-of-freedom spatial transformation relationship between the actual 3D model and the reference 3D model.

[0069] The ICP algorithm is used to perform registration iterative calculations between the actual 3D model and the reference 3D model to obtain the corresponding spatial transformation matrix. This matrix can directly quantify the degree of deviation of the current body position relative to the standard body position, achieving high-precision calculation of pose deviation and providing a quantitative basis for subsequent body position adjustment.

[0070] Step S2042: Determine the location confidence based on at least one of the following: residual distribution of the registered local key target area, point cloud coverage of the actual 3D model in the corresponding area of ​​the reference 3D model, and signal-to-noise ratio of the target millimeter-wave echo data.

[0071] Specifically, the residual distribution of the local key target area refers to the distribution of point positional deviations between the actual model and the reference model in key locations such as the tumor target area after registration. Point cloud coverage refers to the proportion of the actual model's point cloud covering the corresponding area of ​​the reference model. The signal-to-noise ratio of the target millimeter-wave echo data refers to the ratio of the effective signal reflected from the patient's body surface to the noise signal.

[0072] At least one of the following indicators—residual distribution in the local key target area, point cloud coverage, and target echo signal-to-noise ratio—is selected and quantitatively calculated to determine the positioning reliability. This scheme can accurately determine the reliability of body position detection results and identify abnormal adhesion between the fixation membrane and the body surface, avoiding adjustment errors caused by unreliable data and improving the safety and accuracy of body position adjustment.

[0073] Step S205: Based on the posture deviation and positional reliability, generate postural adjustment guidance instructions or prompts for the patient.

[0074] Specifically, step S205 includes: Step S2051: If the positional confidence is greater than the preset threshold and the positional deviation exceeds the preset range, then generate the six-degree-of-freedom adjustment parameters of the radiotherapy treatment bed based on the positional deviation and generate the body position adjustment guidance command.

[0075] Specifically, the preset threshold refers to the critical value for determining the reliability of positional positioning (e.g., 0.8). The preset range refers to the clinically permissible range of positional deviation. The six degrees of freedom adjustment parameters refer to the adjustment values ​​for the head-to-toe / left-right / up-down translation and three-dimensional rotation of the treatment bed; the positional adjustment guidance command refers to the command to control the treatment bed to perform adjustment actions.

[0076] When the positional confidence level exceeds a preset threshold and the pose deviation exceeds the allowable range, the system generates six-degree-of-freedom adjustment parameters for the treatment bed based on the calculated pose deviation, and then outputs positional adjustment guidance commands. This achieves automated and precise positional adjustment, reduces manual intervention, improves adjustment efficiency, and ensures the accuracy of radiotherapy positioning.

[0077] In step S2052, if the location confidence is less than or equal to a preset threshold, a prompt message is generated, indicating that the fixing film has an adhesion abnormality and needs to be re-fixed.

[0078] Specifically, the notification information refers to the warning messages (such as pop-ups, voice reminders, etc.) pushed to the operating terminals of medical staff.

[0079] When the positioning reliability is lower than or equal to a preset threshold, an abnormal fit between the fixation membrane and the patient's body surface is determined. A prompt message is then generated and sent, instructing medical staff to re-fix the membrane. This step can promptly identify detection failures caused by poor fixation membrane fit, avoiding incorrect adjustments and ensuring the safety and reliability of radiotherapy positioning.

[0080] In one optional implementation, this embodiment is applicable to conventional radiotherapy scenarios for head and neck, chest and abdominal tumors, etc. The core principle is to reuse the patient's existing radiotherapy plan CT data to generate a reference 3D model, eliminating the need for additional baseline data acquisition and balancing patient positioning efficiency with clinical compatibility. Regarding equipment deployment, at least two sets of millimeter-wave radar sensors are used, symmetrically deployed on both sides of the radiotherapy bed to ensure complete coverage of the entire surface area covered by the fixation membrane, eliminating blind spots. For the commonly used head and neck thermoplastic mask (non-metallic material, 2-3mm thick), the operating parameters of the millimeter-wave radar are adjusted to adapt to the penetration characteristics of the fixation membrane. The transmission frequency is set to 60GHz, balancing penetration capability and detection accuracy; the signal bandwidth is 5GHz; and the sampling rate is 100MHz. These parameter settings allow the millimeter-wave signal to effectively penetrate the fixation membrane, reducing signal attenuation while avoiding insufficient penetration depth due to excessively high frequencies.

[0081] The patient lies supine on the radiotherapy bed according to the radiotherapy plan, wears a thermoplastic fixation diaphragm, and is positioned to ensure a smooth, wrinkle-free fit. The controller then controls the radar to emit millimeter-wave signals and receives mixed signals reflected from the fixation diaphragm, the patient's surface, and the radiotherapy room environment. This data is directly stored as raw millimeter-wave echo data. This raw data includes effective signals reflected from the patient's surface, interference signals reflected from the fixation diaphragm surface, and background noise signals reflected from metal equipment in the radiotherapy room (such as the treatment bed frame). The raw millimeter-wave echo data is then preprocessed to extract target millimeter-wave echo data. An adaptive thresholding algorithm is first used to analyze the signal intensity distribution of the raw data and set a noise threshold, eliminating background noise such as metal reflections and electromagnetic radiation with intensity below the threshold. Then, a signal separation algorithm is used, based on the phase difference characteristics of the reflected signals between the fixation diaphragm and the patient's surface, to precisely filter out interference signals reflected from the fixation diaphragm surface, ultimately retaining only the effective signals reflected from the patient's surface.

[0082] The process of generating a realistic 3D model reflecting the patient's current position based on target millimeter-wave echo data is as follows: First, the target echo data undergoes a range-dimensional Fourier transform and phase unwrapping processing sequentially. The range-dimensional Fourier transform is used to calculate the distance information between each sampling point and the radar. Phase unwrapping processing eliminates signal phase folding and restores the true phase value, thereby improving ranging accuracy. After integrating the distance and phase information, the x, y, and z 3D coordinates of each sampling point on the patient's body surface are generated. Initial point cloud data is generated based on these 3D coordinates. Then, a statistical filtering algorithm is used, setting the mean distance of neighboring points ± 2 times the variance as the filtering range, to remove discrete noise points formed by environmental stray reflections, obtaining clean point cloud data. Finally, a Poisson surface reconstruction algorithm is used to perform smooth surface fitting on the clean point cloud data to complete the generation of the actual 3D model.

[0083] The reference 3D model is generated by reusing CT data from the radiotherapy plan. The patient's radiotherapy plan CT image set is retrieved from the hospital's radiotherapy system. This image set was acquired during the CT positioning phase and contains continuous tomographic CT images of the patient in a standard position. An edge segmentation algorithm is used to process each frame of the CT image set to extract the patient's body surface contour boundary. Then, the continuous tomographic body surface contour data is reconstructed in 3D to obtain a reference 3D model of the patient in a standard position without a fixation membrane, which serves as the core benchmark for comparing positional deviations.

[0084] The ICP algorithm is used to perform iterative registration calculations between the actual 3D model and the reference 3D model. First, a set of key points is selected in the actual model and matched with the corresponding set of points in the reference model. Then, the spatial transformation relationship between the two set of points is calculated and the spatial transformation matrix is ​​solved. The matrix parameters are iteratively optimized until the registration error between the two set of points is less than a preset value. The six-degree-of-freedom pose deviation of the current body position relative to the standard body position can be extracted from the spatial transformation matrix, including the translation in the head-to-foot, left-right, and up-down directions, as well as the rotation angles around the three axes. At the same time, the positioning reliability is calculated by weighting three core indicators, with a value range of 0-1. These indicators are: the residual distribution of the tumor target area after registration (the smaller the deviation, the higher the weight); the coverage ratio of the actual model point cloud in the corresponding area of ​​the reference model (with a qualified threshold of ≥90%); and the signal-to-noise ratio of the target echo data (with a qualified threshold of ≥20dB). The final positioning reliability quantification is obtained by weighted summation of the three indicators.

[0085] The positioning reliability threshold is set to 0.8, meaning a reliability ≥ 0.8 indicates reliable detection results. The preset range for posture deviation is translation ±1mm and rotation ±0.5°, meeting the high precision requirements of radiotherapy positioning. If the positioning reliability is greater than 0.8 and the posture deviation exceeds the preset range, the controller generates six-degree-of-freedom adjustment parameters for the radiotherapy treatment bed based on the spatial transformation matrix, converts them into position adjustment guidance commands, and sends them to the treatment bed drive module to control the treatment bed to automatically adjust to the standard position. If the positioning reliability is less than or equal to 0.8, the controller generates a prompt message, which is pushed to the medical staff's operating terminal in the form of a pop-up window and voice reminder, prompting "Abnormal fixation membrane adhesion, please re-fix the patient's position." This embodiment reuses existing CT data, reduces the baseline data acquisition process, and, combined with precise signal filtering and modeling algorithms, significantly shortens the pre-position adjustment time while ensuring positioning accuracy, improving adjustment efficiency, adapting to the batch treatment needs of routine clinical radiotherapy, and the algorithm process is standardized, making it easy to promote clinically.

[0086] This embodiment also provides a radiotherapy positioning device based on millimeter-wave radar, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0087] This embodiment provides a radiotherapy positioning device based on millimeter-wave radar, such as... Figure 3 As shown, it includes: The echo acquisition module 301 is used to acquire target millimeter wave echo data in the area of ​​the body surface covered by the fixation film when the patient's body surface is covered by a fixation film. The actual model generation module 302 is used to generate an actual three-dimensional model that reflects the patient's true position based on the target millimeter wave echo data. The reference model acquisition module 303 is used to acquire a reference three-dimensional model of the patient in a standard position. The reference three-dimensional model indicates the three-dimensional surface model of the patient without the fixation membrane. The pose determination module 304 is used to register the actual three-dimensional model with the reference three-dimensional model, determine the pose deviation of the patient's current position relative to the standard position and the position determination reliability, and the position determination reliability indicates whether there is an abnormal fit between the fixation film and the patient's body surface. The adjustment guidance module 305 is used to generate postural adjustment guidance instructions or prompts for the patient based on the posture deviation and positional reliability.

[0088] In some optional implementations, the reference model acquisition module 303 includes: The data collection unit is used to segment and obtain image data sequences of the patient's body surface from the patient's radiotherapy plan CT image set, wherein the radiotherapy plan CT image set includes images in a standard position; The reference model generation unit is used to generate a reference 3D model based on the image data sequence; or, When the patient is in a standard position, a reference three-dimensional model is generated and stored by collecting millimeter-wave echo data without a fixed membrane.

[0089] In some alternative implementations, the pose determination module 304 includes: The transformation matrix determination unit is used to determine the spatial transformation matrix between the actual 3D model and the reference 3D model through the ICP algorithm. The spatial transformation matrix is ​​used to characterize the pose deviation. The location reliability determination unit is used to determine the location reliability based on at least one of the following: the residual distribution of the registered local key target area, the point cloud coverage of the actual 3D model in the corresponding area of ​​the reference 3D model, and the signal-to-noise ratio of the target millimeter-wave echo data.

[0090] In some alternative implementations, the echo acquisition module 301 includes: The parameter setting unit is used to set the detection parameters of the millimeter-wave radar to the working parameters adapted to the penetration characteristics of the fixed film. The working parameters include the transmission frequency, signal bandwidth and sampling rate. The echo acquisition unit is used to acquire raw millimeter-wave echo data using millimeter-wave radar based on operating parameters; The filtering unit is used to remove background noise and filter the fixed membrane reflection signal from the raw millimeter wave echo data to obtain effective echo data that retains the reflection from the patient's body surface as the target millimeter wave echo data.

[0091] In some alternative implementations, the actual model generation module 302 includes: The three-dimensional coordinate extraction unit is used to perform range dimension Fourier transform and phase unwrapping processing on the target millimeter wave echo data to extract the three-dimensional coordinate information of the body surface. The 3D model generation unit is used to generate initial point cloud data based on the 3D coordinate information of the body surface, remove discrete noise points through statistical filtering algorithm, and generate the actual 3D model through Poisson surface reconstruction algorithm.

[0092] In some alternative implementations, the adjustment guide module 305 includes: The adjustment guidance command generation unit is used to generate six-degree-of-freedom adjustment parameters of the radiotherapy treatment bed based on the positional deviation if the positional confidence is greater than a preset threshold and the positional deviation exceeds a preset range, and to generate positional adjustment guidance commands. The prompt message generation unit is used to generate a prompt message if the confidence level at a certain position is less than or equal to a preset threshold, indicating that the fixing film has an adhesion abnormality and needs to be re-fixed.

[0093] The radiotherapy positioning device based on millimeter-wave radar provided in this application can execute the radiotherapy positioning method based on millimeter-wave radar provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0094] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0095] The following is a detailed reference. Figure 4 The diagram illustrates a structural schematic suitable for implementing the electronic device described in the embodiments of this application. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 402 or a program loaded from memory 408 into random access memory (RAM) 403. The RAM 403 also stores various programs and data required for the operation of the electronic device. The processor 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0096] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0097] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 409, or installed from memory 408, or installed from ROM 402. When the computer program is executed by processor 401, it performs the functions defined in the millimeter-wave radar-based radiotherapy positioning method of this application.

[0098] Figure 4 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0099] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the millimeter-wave radar-based radiotherapy positioning method shown in the above embodiments is implemented.

[0100] A portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0101] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for millimeter wave radar-based radiotherapy position adjustment, characterized in that, The method comprises: acquiring target millimeter wave echo data of a body surface area covered by a fixed film in a state of the fixed film covering the body surface of a patient; generating an actual three-dimensional model reflecting a real body position of the patient according to the target millimeter wave echo data; acquiring a reference three-dimensional model of a standard body position of the patient, the reference three-dimensional model indicating a three-dimensional surface model of the patient in a state of the fixed film not covering the body surface; registering the actual three-dimensional model and the reference three-dimensional model to determine a pose deviation and a position locating reliability of a current body position of the patient relative to the standard body position, the position locating reliability indicating whether there is an abnormal fit between the fixed film and the body surface of the patient; generating a body position adjustment guiding instruction or prompt information of the patient according to the pose deviation and the position locating reliability.

2. The method of claim 1, wherein, The acquiring of the reference three-dimensional model of the standard body position of the patient comprises: segmenting image data sequences of the body surface of the patient from a radiotherapy planning CT image set of the patient, wherein the radiotherapy planning CT image set comprises images of the standard body position; generating the reference three-dimensional model according to the image data sequences; or generating and storing the reference three-dimensional model by acquiring millimeter wave echo data in a state of the fixed film not covering the body surface when the patient is positioned in the standard body position.

3. The method of claim 1, wherein, The registering of the actual three-dimensional model and the reference three-dimensional model to determine the pose deviation and the position locating reliability of the current body position of the patient relative to the standard body position comprises: determining a spatial transformation matrix between the actual three-dimensional model and the reference three-dimensional model by an ICP algorithm, the spatial transformation matrix being used to represent the pose deviation; determining the position locating reliability based on at least one of a residual distribution of a local key target area after the registration, a point cloud coverage rate of the actual three-dimensional model on a corresponding area of the reference three-dimensional model, and a signal-to-noise ratio of the target millimeter wave echo data.

4. The method of claim 1, wherein, The acquiring of the target millimeter wave echo data of the body surface area covered by the fixed film comprises: setting detection parameters of a millimeter wave radar to working parameters adapted to a penetration characteristic of the fixed film, the working parameters comprising a transmission frequency, a signal bandwidth, and a sampling rate; acquiring original millimeter wave echo data based on the working parameters using the millimeter wave radar; performing background noise elimination and fixed film reflection signal filtering processing on the original millimeter wave echo data to obtain effective echo data retaining patient body surface reflections as the target millimeter wave echo data.

5. The method of claim 1, wherein, The generating of the actual three-dimensional model of an outer surface of the fixed film according to the target millimeter wave echo data comprises: performing distance dimension Fourier transform and phase unwrapping processing on the target millimeter wave echo data to extract body surface three-dimensional coordinate information; generating initial point cloud data based on the body surface three-dimensional coordinate information, eliminating discrete noise points by a statistical filtering algorithm, and generating the actual three-dimensional model by a Poisson surface reconstruction algorithm.

6. The method of claim 1, wherein, The generating of the body position adjustment guiding instruction or prompt information of the patient according to the pose deviation and the position locating reliability comprises: If the position determination reliability is greater than a preset threshold, and the pose deviation exceeds a preset range, a six-degree-of-freedom adjustment parameter of a radiotherapy treatment bed is generated according to the pose deviation, and the body position adjustment guiding instruction is generated. If the position determination reliability is less than or equal to the preset threshold, a prompt information is generated to indicate that the fixed film has a fitting abnormality and needs to be re-fixed.

7. A millimeter wave radar-based radiotherapy position adjustment device, characterized by, The device comprises: An echo acquisition module, configured to acquire target millimeter wave echo data of a body surface region covered by the fixed film in a state where the fixed film covers the body surface of the patient; An actual model generation module, configured to generate an actual three-dimensional model reflecting a real body position of the patient according to the target millimeter wave echo data; A reference model acquisition module, configured to acquire a reference three-dimensional model of a standard body position of the patient, the reference three-dimensional model indicating a three-dimensional surface model of the patient in a state where the fixed film does not cover the body surface; A pose determination module, configured to register the actual three-dimensional model and the reference three-dimensional model to determine a pose deviation of a current body position of the patient relative to the standard body position and a position determination reliability, the position determination reliability indicating whether there is a fitting abnormality between the fixed film and the body surface of the patient; An adjustment guiding module, configured to generate a body position adjustment guiding instruction or a prompt information of the patient according to the pose deviation and the position determination reliability.

8. A millimeter wave radar-based radiotherapy position adjustment system, characterized by, The system comprises at least two sets of millimeter wave sensors, a treatment bed and a controller, the at least two sets of millimeter wave sensors are arranged on both sides of the radiotherapy bed, the detection range of the at least two sets of millimeter wave sensors covers all body surface regions covered by the fixed film arranged on the radiotherapy bed, and the controller is configured to control the at least two sets of millimeter wave sensors and the treatment bed, and the controller executes the radiotherapy body position adjustment method based on millimeter wave radar in any one of claims 1 to 6.

9. An electronic device, comprising: Comprise: A memory and a processor, which are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to execute the radiotherapy body position adjustment method based on millimeter wave radar in any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions, and the computer instructions are used to make a computer execute the radiotherapy body position adjustment method based on millimeter wave radar in any one of claims 1 to 6.

Images