A positioning method for tumor radiotherapy
By using individualized fixation devices and AI dynamic compensation technology, combined with AR vision and respiratory coordinated control, the accuracy problems caused by body position drift and respiratory movements in tumor radiotherapy have been solved, realizing a high-precision positioning method and improving treatment efficacy and safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-02-14
- Publication Date
- 2026-06-16
AI Technical Summary
In current tumor radiotherapy, traditional positioning methods are easily affected by skin traction, body position drift and respiratory movements, resulting in insufficient irradiation accuracy. In particular, in the treatment of thoracic and abdominal tumors, the target area can move by 2-3 centimeters, affecting the treatment effect.
The device employs an individualized fixation device combined with an AR vision module and an optical tracking system. It uses 3D printing to create individualized shaping pads and thermoplastic films for fixation. Combined with AI dynamic compensation and respiratory coordination control, it achieves multi-source image registration and real-time compensation to ensure positioning accuracy.
It significantly improves positioning accuracy, with errors controlled within 0.3mm, shortens positioning time, reduces additional radiation exposure, improves tumor control rate, and enhances the safety and comfort of treatment.
Abstract
Description
Technical Field
[0001] This invention belongs to the field of radiotherapy support technology, and particularly relates to a positioning method for tumor radiotherapy. Background Technology
[0002] Tumor radiotherapy is a fractionated treatment method, typically requiring 5-35 sessions to complete. Because ionizing radiation damages normal tissue, precise and repeated positioning is necessary to ensure the patient's position and location remain consistent with the first treatment, guaranteeing sufficient dose to the target area while maximizing the protection of surrounding healthy tissue. Currently, commonly used positioning methods primarily rely on laser crosshairs on the patient's surface or a fixation pattern for repeated positioning.
[0003] Traditional laser beam localization relies on surface markers, which are easily affected by skin traction and body positional drift. CBCT-guided technology requires operators to repeatedly enter and exit the treatment room, increasing patients' additional radiation exposure. While AR visualization technology improves the observation perspective, it does not address dynamic errors caused by respiratory motion. Personalized fixation devices improve static stability but lack a real-time compensation mechanism for changes in body position during treatment. Especially for thoracic and abdominal tumors, respiratory motion can cause the target area to shift by 2-3 centimeters, severely affecting irradiation accuracy. Summary of the Invention
[0004] The purpose of this invention is to provide a positioning method for tumor radiotherapy, so as to solve the technical problems mentioned in the background art.
[0005] To achieve the above objectives, the specific technical solution of the present invention is as follows: A positioning method for tumor radiotherapy, comprising the following steps: S1. Pre-shaping and reference positioning of individualized fixation devices: Based on the patient's localization CT images, the body surface contour data and the three-dimensional coordinates of the tumor target area are extracted. A personalized shaping pad is made using 3D printing technology. The pad is fitted and shaped in the patient's treatment position. More than three optical positioning markers are set on the surface of the shaping pad. The coordinates of the markers are bound to the coordinate system of the CT image. After the patient lies on the shaping pad, a thermoplastic film is used for secondary fixation. S2. Multi-source image registration and coordinate system calibration: The AR vision module and optical tracking system are activated. The AR device acquires images of the treatment room scene and identifies orthogonal laser lines in the machine room. The optical tracking system acquires the dynamic coordinates P2(x2,y2,z2) of the positioning markers in real time. Combined with the three-dimensional images of the treatment obtained by CBCT scan, the patient's body surface contour and internal anatomical structure features are extracted. The image registration is completed through the iterative nearest point algorithm, and the coordinate deviation value ΔP=P2-P1 is calculated. S3, AI dynamic compensation and respiratory coordination control: Input the deviation value ΔP, treatment bed deformation data and patient weight change ratio into the artificial intelligence processing module, start the respiratory management system, capture the patient's respiratory cycle through the respiratory gating device, and synchronously trigger the treatment bed motor drive module to perform compensation actions. S4. Positioning Verification and Locking: The AR device overlays the outline of the planned target area with real-time patient images, allowing operators to perform visual verification, initiate the dose pre-verification procedure, simulate the radiation path, confirm that the target area coverage is ≥98% and the dose to organs at risk is within the safe threshold, lock the position of the treatment bed and fixation device, generate a positioning report, and simultaneously upload it to the treatment planning system for archiving.
[0006] Preferably, the shaping pad in step S1 is made of a highly oxygen-permeable polymer material.
[0007] Preferably, in step S1, a treatment planning machine coordinate system XYZ1 is established through the treatment planning system, with the center of the tumor target area as the origin (0,0,0), and the reference coordinates P1 (x1,y1,z1) of the positioning marker point in XYZ1 are recorded.
[0008] Preferably, in step S2, the intersection of the laser lines is defined as the origin of the XYZ2 coordinate system of the treatment machine in the machine room, and the transformation matrix M1 between XYZ2 and the planning coordinate system XYZ1 is calculated to achieve registration and overlap of the two coordinate systems.
[0009] Preferably, in step S2, the optical tracking system acquires the dynamic coordinates P2(x2,y2,z2) of the positioning marker in real time, combines them with the three-dimensional images obtained during treatment from CBCT scans, extracts the patient's body surface contour and internal anatomical structure features, completes image registration through an iterative nearest point algorithm, and calculates the coordinate deviation value ΔP=P2-P1.
[0010] Preferably, in step S3, the artificial intelligence processing module generates six-degree-of-freedom compensation instructions based on a deep learning model.
[0011] Preferably, in step S3, the coordinates P3(x3,y3,z3) of the compensated marker point are monitored in real time. If the deviation value |ΔP'|=|P3-P1|≤0.3mm, the setup calibration is completed. If the deviation exceeds the standard, the above steps are repeated until the accuracy requirements are met.
[0012] The positioning method for tumor radiotherapy according to the present invention has the following advantages: 1. This invention provides triple protection through "individualized fixation + AI dynamic compensation + respiratory coordination", controlling the positioning error to within 0.3mm, which is more than 60% lower than the traditional method. It significantly improves the tumor control rate and reduces damage to normal tissues. Moreover, it eliminates the need for repeated entry and exit from the machine room for image verification, shortening the single positioning time to within 5 minutes, while avoiding radiation exposure from additional CBCT scans.
[0013] 2. This invention is suitable for tumors in multiple locations such as the head and neck, chest and abdomen, and is compatible with various radiotherapy techniques such as intensity-modulated radiotherapy and stereotactic radiotherapy. It solves the problem of body position drift caused by multiple factors such as weight changes, respiratory movements, and treatment bed deformation. The positioning repeatability error is ≤0.2mm. The combination design of individualized shaping pad and thermoplastic film improves body position comfort, and respiratory coordination control reduces the burden of breath-holding for patients and improves treatment compliance. Detailed Implementation
[0014] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the embodiments of the invention. Therefore, the description is considered to be exemplary in nature and not restrictive.
[0015] In the description of the embodiments of the present invention, it should be understood that the terms "length", "vertical", "horizontal", "top", "bottom", etc., indicating the orientation or positional relationship are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the embodiments of the present invention.
[0016] Furthermore, 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. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of embodiments of the present invention, "a plurality of" means two or more, unless otherwise explicitly specified.
[0017] In this embodiment of the invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection, an electrical connection, or a communication connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this embodiment of the invention according to the specific circumstances.
[0018] The following disclosure provides many different implementations or examples for carrying out different structures of the embodiments of the present invention. To simplify the disclosure of the embodiments of the present invention, specific examples of components and arrangements are described below. Of course, these are merely examples and are not intended to limit the embodiments of the present invention. Furthermore, reference numerals and / or reference letters may be repeated in different examples of the embodiments of the present invention; such repetition is for simplification and clarity and does not in itself indicate a relationship between the various implementations and / or arrangements discussed.
[0019] To better understand the purpose, structure, and function of this invention, a positioning method for tumor radiotherapy according to this invention will be described in further detail below.
[0020] A positioning method for tumor radiotherapy according to the present invention includes the following steps: S1. Pre-shaping and reference positioning of individualized fixation devices: Based on the patient's localization CT images, surface contour data and three-dimensional coordinates of the tumor target area are extracted. An individualized shaping pad is fabricated using 3D printing technology. The pad is fitted and shaped in the patient's treatment position to ensure no gaps in key support areas such as the head, neck, chest, and abdomen. At least three optical positioning markers are set on the surface of the shaping pad. The coordinates of the markers are bound to the CT image coordinate system. A treatment planning system (TPS) is used to establish a treatment planning coordinate system XYZ1 with the center of the tumor target area as the origin (0,0,0). The reference coordinates P1 (x1,y1,z1) of the positioning markers in XYZ1 are recorded. After the patient lies on the shaping pad, a thermoplastic membrane is used for secondary fixation. The membrane covers the tumor area and adjacent joints, forming a double fixation structure of "shaping pad + thermoplastic membrane". S2. Multi-source image registration and coordinate system calibration: The AR vision module and optical tracking system are activated. The AR device acquires images of the treatment room scene, identifies orthogonal laser lines in the machine room, defines the intersection of the laser lines as the origin of the machine room's treatment coordinate system XYZ2, calculates the transformation matrix M1 between XYZ2 and the planning coordinate system XYZ1, and achieves registration and overlap of the two coordinate systems. The optical tracking system acquires the dynamic coordinates P2(x2,y2,z2) of the positioning markers in real time. Combined with the three-dimensional images obtained from CBCT scans during treatment, the patient's surface contour and internal anatomical structure features are extracted. Image registration is completed through the Iterative Closest Point (ICP) algorithm, and the coordinate deviation value ΔP=P2-P1 is calculated. S3, AI dynamic compensation and respiratory coordination control: The deviation value ΔP, treatment bed deformation data, and patient weight change ratio are input into the artificial intelligence processing module. This module, based on a deep learning model (training data includes the correspondence between positioning errors and compensation parameters from over 1000 clinical cases), generates six-degree-of-freedom compensation commands (X / Y / Z-axis translation + pitch / roll / yaw rotation). It then activates the respiratory management system, captures the patient's respiratory cycle through a respiratory gating device, determines the end-expiratory stable phase (respiratory amplitude ≤ 0.5cm), and synchronously triggers the treatment bed motor drive module to execute compensation actions, ensuring the compensation process aligns with the stable respiratory phase. The coordinates of the compensated marker point P3 (x3, y3, z3) are monitored in real-time. If the deviation value |ΔP'| = |P3 - P1| ≤ 0.3mm, the positioning calibration is complete; if the deviation exceeds the limit, the above steps are repeated until the accuracy requirements are met. S4. Positioning Verification and Locking: The AR device overlays the outline of the planned target area with real-time patient images, allowing operators to perform visual verification, initiate the dose pre-verification procedure, simulate the radiation path, confirm that the target area coverage is ≥98% and the dose to organs at risk is within the safe threshold, lock the position of the treatment bed and fixation device, generate a positioning report (including coordinate deviation, compensation parameters, and respiratory cycle data), and simultaneously upload it to the treatment planning system for archiving.
[0021] It is understood that the present invention has been described through some embodiments, and those skilled in the art will recognize that various changes or equivalent substitutions can be made to these features and embodiments without departing from the spirit and scope of the invention. Furthermore, under the teachings of the present invention, these features and embodiments can be modified to adapt to specific situations and materials without departing from the spirit and scope of the invention. Therefore, the present invention is not limited to the specific embodiments disclosed herein, and all embodiments falling within the scope of the claims of this application are within the protection scope of the present invention.
Claims
1. A positioning method for tumor radiotherapy, characterized in that: Includes the following steps: S1. Pre-shaping and reference positioning of individualized fixation devices: Based on the patient's localization CT images, the body surface contour data and the three-dimensional coordinates of the tumor target area are extracted. A personalized shaping pad is made using 3D printing technology. The pad is fitted and shaped in the patient's treatment position. More than three optical positioning markers are set on the surface of the shaping pad. The coordinates of the markers are bound to the coordinate system of the CT image. After the patient lies on the shaping pad, a thermoplastic film is used for secondary fixation. S2. Multi-source image registration and coordinate system calibration: The AR vision module and optical tracking system are activated. The AR device acquires images of the treatment room scene and identifies orthogonal laser lines in the machine room. The optical tracking system acquires the dynamic coordinates P2(x2,y2,z2) of the positioning markers in real time. Combined with the three-dimensional images of the treatment obtained by CBCT scan, the patient's body surface contour and internal anatomical structure features are extracted. The image registration is completed through the iterative nearest point algorithm, and the coordinate deviation value ΔP=P2-P1 is calculated. S3, AI dynamic compensation and respiratory coordination control: Input the deviation value ΔP, treatment bed deformation data and patient weight change ratio into the artificial intelligence processing module, start the respiratory management system, capture the patient's respiratory cycle through the respiratory gating device, and synchronously trigger the treatment bed motor drive module to perform compensation actions. S4. Positioning Verification and Locking: The AR device overlays the outline of the planned target area with real-time patient images, allowing operators to perform visual verification, initiate the dose pre-verification procedure, simulate the radiation path, confirm that the target area coverage is ≥98% and the dose to organs at risk is within the safe threshold, lock the position of the treatment bed and fixation device, generate a positioning report, and simultaneously upload it to the treatment planning system for archiving.
2. The positioning method for tumor radiotherapy according to claim 1, characterized in that: In step S1, the shaping pad is made of a high oxygen permeability polymer material.
3. The positioning method for tumor radiotherapy according to claim 1, characterized in that: In step S1, a treatment planning machine coordinate system XYZ1 is established through the treatment planning system, with the center of the tumor target area as the origin (0,0,0), and the reference coordinates P1 (x1,y1,z1) of the positioning marker point in XYZ1 are recorded.
4. The positioning method for tumor radiotherapy according to claim 1, characterized in that: In step S2, the intersection of the laser lines is defined as the origin of the XYZ2 coordinate system of the treatment machine in the machine room. The transformation matrix M1 between XYZ2 and the planning coordinate system XYZ1 is calculated to achieve registration and coincidence of the two coordinate systems.
5. The positioning method for tumor radiotherapy according to claim 1, characterized in that: In step S2, the optical tracking system acquires the dynamic coordinates P2(x2,y2,z2) of the positioning marker in real time. Combined with the three-dimensional images obtained from CBCT scans during treatment, the system extracts the patient's body surface contour and internal anatomical structure features. The system completes image registration through an iterative nearest point algorithm and calculates the coordinate deviation value ΔP=P2-P1.
6. The positioning method for tumor radiotherapy according to claim 1, characterized in that: In step S3, the artificial intelligence processing module generates six-degree-of-freedom compensation instructions based on a deep learning model.
7. The positioning method for tumor radiotherapy according to claim 1, characterized in that: In step S3, the coordinates of the compensated marker point P3(x3,y3,z3) are monitored in real time. If the deviation value |ΔP'|=|P3-P1|≤0.3mm, the setup calibration is completed. If the deviation exceeds the standard, the above steps are repeated until the accuracy requirements are met.