Radiation treatment bed anti-collision method and system

Abstract

The invention discloses a radiation treatment bed anti-collision method and system, and the method comprises the steps: drawing a 3D envelope boundary for constraining the motion space of a treatment bed; establishing an incidence relation model among the position of the treatment bed in the 3D envelope boundary, the motor operation current variable quantity and the displacement variable quantity; in the radiotherapy process, the motion space position of the radiotherapy bed and the motor operation current variable quantity and the displacement variable quantity corresponding to the motion space position are monitored in real time, and whether the treatment bed has the collision risk or not is judged based on the incidence relation model. According to the scheme, automatic collision prevention is achieved, when collision occurs, the treatment bed stops moving immediately, and a collision early warning mechanism is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of radiotherapy, and in particular to a method and system for preventing collision of a radiotherapy bed. Background Art

[0002] During radiotherapy, the treatment couch serves as the patient's sole support and positioning device. The accuracy and safety of its movement are directly related to the treatment effect and patient safety. Currently, treatment couches are typically driven by motors to achieve multi-degree-of-freedom adjustment (such as lifting, translation, rotation, etc.) to ensure that the patient is in the optimal treatment position. However, during movement, the treatment couch carries the risk of collision with treatment equipment (such as accelerator heads, multi-leaf collimators, image detectors, etc.) or other peripheral devices, which may cause equipment damage, treatment interruption, or even accidental injury to the patient.

[0003] In existing technologies, the anti-collision mechanism of treatment beds mainly relies on sensor detection (such as infrared sensors, pressure sensors or limit switches, etc.), but these solutions have significant limitations:

[0004] Passive response: Existing sensors only trigger an alarm or stop movement at the moment a collision occurs or is about to occur. This is a post-intervention and cannot provide active warning.

[0005] Blind spot problem: Due to the limitations of sensor layout and detection range, dynamic collision risks in complex three-dimensional space (such as path interference in rotational motion) are difficult to fully cover.

[0006] Dependence on manual operation: The movement of the treatment bed relies on the operator's observation and experience. In an emergency, delayed human response may make it impossible to avoid a collision.

[0007] Therefore, there is an urgent need for a technical solution that can predict collision risks in real time and actively avoid them before or during the movement of the treatment bed, so as to improve the safety and reliability of radiotherapy.

[0008] In view of this, the present invention patent is proposed. Summary of the Invention

[0009] To address the aforementioned issues, the present invention provides a radiation therapy couch collision prevention method and system. This system uses real-time monitoring before and during couch movement to predict collision risks, identify risks before they occur, and automatically adjust the movement path or stop motion. This proactively provides early warning and avoidance, significantly reducing the risk of collisions between the couch, patient, and surrounding equipment. Specifically, the system employs the following technical solutions:

[0010] A radiation therapy bed anti-collision method, comprising:

[0011] Draw the 3D envelope boundary that constrains the movement space of the treatment bed;

[0012] Establish a correlation model between the position of the treatment bed within the 3D envelope boundary, the change in motor operating current, and the change in displacement;

[0013] During radiotherapy, the motion spatial position of the radiotherapy bed and the change in motor operating current and displacement corresponding to the motion spatial position are monitored in real time, and whether there is a collision risk of the treatment bed is determined based on the association relationship model.

[0014] As an optional embodiment of the present invention, in a radiation therapy couch anti-collision method of the present invention, establishing a correlation model between the position of the treatment couch within the 3D envelope boundary, the change in motor operating current, and the change in displacement includes:

[0015] When the treatment bed is unloaded, the position data set GK(i) (i=1, 2, 3...), the current change data set HK(i) (i=1, 2, 3...), and the displacement change data set DK(i) (i=1, 2, 3...) are obtained, a neural network NET is established, training parameters are set, and the mathematical model FUN1 of the unloaded treatment bed is obtained by training the neural network NET;

[0016] Under the maximum load condition of the treatment bed, the position data set GM(i) (i=1, 2, 3...), the current variation data set HM(i) (i=1, 2, 3...), and the displacement variation data set DM(i) (i=1, 2, 3...) are obtained, a neural network NET is established, and training parameters are set. The neural network NET is trained to obtain the mathematical model FUN2 of the maximum load of the treatment bed;

[0017] Through the mathematical model FUN1 of the treatment bed with no load and the mathematical model FUN2 of the treatment bed with maximum load, the displacement change range S(j) (i=1, 2, 3...) between the maximum load and the no load at N positions under the same current change is obtained. S(j) is used as the reference threshold space P(i) (i=1, 2, 3...) of position N(i).

[0018] As an optional embodiment of the present invention, in a radiation therapy couch anti-collision method of the present invention, generating the reference threshold space P(i) includes:

[0019] At N preset positions N(i) (i=1, 2, 3…) of the treatment bed, the displacement change output values ​​of the no-load mathematical model FUN1 and the maximum load mathematical model FUN2 under the same current change are extracted respectively, and the difference interval S(j) between the two is calculated, and S(j) is used as the reference threshold space P(i) of position N(i).

[0020] As an optional embodiment of the present invention, in a radiation therapy couch anti-collision method of the present invention, the reference threshold space P(i) is dynamically adjusted according to the real-time load state of the treatment couch, including:

[0021] If the real-time load is between no-load and maximum load, a threshold space P'(i) adapted to the current real-time load is generated by linear interpolation between the displacement change intervals corresponding to the no-load mathematical model FUN1 and the maximum load mathematical model FUN2.

[0022] As an optional embodiment of the present invention, in a radiation therapy couch collision prevention method of the present invention, during the radiation therapy process, real-time monitoring of the motion spatial position of the radiation therapy couch, as well as changes in motor operating current and displacement corresponding to the motion spatial position, and determining whether there is a collision risk for the treatment couch based on the association model includes:

[0023] During radiotherapy, real-time monitoring of the current motion spatial position of the radiotherapy bed and the current motor operating current of each motor corresponding to the motion spatial position;

[0024] Calculate the displacement change of adjacent sampling points based on the current motion space position, and determine whether the displacement change meets the reference threshold space P(i). If not, there is a collision risk for the treatment bed;

[0025] Further, according to the current motor operating current of each motor corresponding to the motion spatial position, the motor with the largest current motor operating current is controlled to stop moving.

[0026] As an optional embodiment of the present invention, in a radiation therapy couch collision prevention method of the present invention, drawing a 3D envelope boundary constraining the motion space of the therapy couch includes:

[0027] The motion range of the radiotherapy bed in all directions is calculated through forward kinematics to determine the theoretical reachable space and obtain the initial 3D envelope boundary.

[0028] Verify the actual reachable position of the radiotherapy bed end effector through inverse kinematics and correct the initial 3D envelope boundary;

[0029] Combined with the collision detection algorithm of the radiotherapy bed, the interference area with the external equipment of the radiotherapy bed is eliminated, and the final 3D envelope boundary of the radiotherapy bed motion space is obtained.

[0030] As an optional embodiment of the present invention, a radiation therapy couch anti-collision method of the present invention includes:

[0031] During radiotherapy, when it is detected that the minimum distance between the current position of the radiotherapy bed and the boundary of the 3D envelope is not greater than a first preset threshold value delta01, the following operations are performed:

[0032] According to the current position and movement trend of the radiotherapy bed, the target motor that needs to be decelerated is calculated and active deceleration control is implemented on the target motor;

[0033] Send collision warning signal to the host computer system and output collision warning electrical signal to the outside;

[0034] When the minimum distance between the radiotherapy bed and the 3D envelope boundary is restored to be greater than the first preset threshold delta01, the warning signal is automatically released.

[0035] As an optional embodiment of the present invention, a radiation therapy couch anti-collision method of the present invention includes:

[0036] During the radiotherapy process, when it is monitored that the minimum distance between the current position of the radiotherapy bed and the 3D envelope boundary is not greater than the second preset threshold delta02, the following operations are performed:

[0037] Real-time calculation determines the target motor X (X=1, 2, ...) that requires emergency braking, and immediately stops the movement of the target motor X;

[0038] Send the motor X motion limit signal to the upper computer system and output the motor X motion limit electrical signal to the outside;

[0039] When the minimum distance between the treatment couch and the 3D envelope boundary is restored to be greater than the second preset threshold delta02, the motion limit signal is automatically released.

[0040] As an optional embodiment of the present invention, a radiation therapy couch anti-collision method of the present invention includes:

[0041] The first preset threshold delta01 is dynamically adjusted according to the real-time movement speed of the treatment bed. The greater the movement speed, the greater the value of the first preset threshold delta01.

[0042] The second preset threshold delta02 is dynamically calculated based on the real-time movement speed v of the treatment bed: delta02 = k·v + delta00, where k is the proportional coefficient and delta00 is the minimum safety distance reference value;

[0043] The second preset threshold delta02 is greater than the first preset threshold delta01.

[0044] The present invention also provides a radiation therapy couch anti-collision system, comprising:

[0045] 3D envelope boundary module, which draws the 3D envelope boundary that constrains the movement space of the treatment bed;

[0046] The treatment bed anti-collision model module establishes a correlation model between the treatment bed's position within the 3D envelope boundary, the change in motor operating current, and the change in displacement;

[0047] The main control module monitors the motion spatial position of the radiotherapy bed, as well as the change in motor operating current and displacement corresponding to the motion spatial position, in real time during radiotherapy, and determines whether there is a collision risk of the treatment bed based on the association relationship model.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] Active warning: Through real-time dynamic modeling and threshold comparison, risks can be identified before a collision occurs, avoiding the lag of traditional sensors' "after-the-fact warnings".

[0050] Automated intervention: The radiotherapy bed can autonomously stop or adjust its movement without relying on manual intervention by the operator, reducing collision accidents caused by delayed human response.

[0051] Adaptive optimization: The 3D envelope boundary and associated model can be dynamically updated with the configuration of the treatment device, which is suitable for complex and changing clinical scenarios (such as different treatment machine models or patient positions).

[0052] Improved safety and reliability: Combined with dual monitoring of motor current and displacement, it reduces the misjudgment rate and ensures the accuracy and robustness of the collision avoidance system. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A flow chart of a method for preventing collision of a radiotherapy couch according to an embodiment of the present invention;

[0054] Figure 2 A schematic diagram of the arrangement of an emergency device in a radiation therapy couch anti-collision system according to an embodiment of the present invention;

[0055] Figure 3 A schematic diagram of the arrangement of force sensors in a radiation therapy couch anti-collision system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0056] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them.

[0057] Therefore, the following detailed description of the embodiments of the present invention is not intended to limit the scope of the claimed invention, but merely represents some embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0058] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features and technical solutions therein may be combined with each other.

[0059] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0060] In the description of the present invention, it should be noted that the terms "upper" and "lower" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, or the orientations or positional relationships in which the inventive product is typically placed when in use, or the orientations or positional relationships commonly understood by those skilled in the art. Such terms are intended solely to facilitate the description of the present invention and simplify the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limitations on the present invention. Furthermore, the terms "first" and "second" and the like are used solely for distinction and should not be construed as indicating or implying relative importance.

[0061] See also Figure 1 As shown, this embodiment provides a radiation therapy couch anti-collision method, comprising:

[0062] Draw the 3D envelope boundary that constrains the movement space of the treatment bed;

[0063] Establish a correlation model between the position of the treatment bed within the 3D envelope boundary, the change in motor operating current, and the change in displacement;

[0064] During radiotherapy, the motion spatial position of the radiotherapy bed and the change in motor operating current and displacement corresponding to the motion spatial position are monitored in real time, and whether there is a collision risk of the treatment bed is determined based on the association relationship model.

[0065] Specifically, in a radiation therapy couch anti-collision method of this embodiment, establishing a 3D envelope boundary includes:

[0066] Based on the degrees of freedom of motion of the radiotherapy bed (such as lifting, translation, and rotation) and the physical structure of the treatment equipment (such as the accelerator head, multi-leaf collimator, and image detector), the motion constraint boundary (3D envelope boundary) of the radiotherapy bed in three-dimensional space is constructed.

[0067] Geometric modeling or machine learning methods are used to dynamically update the 3D envelope boundary to adapt to different treatment scenarios (such as the intervention of different body position fixation devices or auxiliary equipment).

[0068] Specifically, in a radiation therapy couch anti-collision method according to this embodiment, constructing an association relationship model includes:

[0069] When the treatment bed is moving normally without collision, its position coordinates (X, Y, Z), motor current change (ΔI) and displacement change (ΔD) are collected, and a dynamic correlation model between the three is established;

[0070] The model is trained using historical data to determine the normal threshold range for motor current and displacement changes (e.g., a sudden increase in current exceeding 10% or a displacement deviation exceeding 2mm triggers an early warning).

[0071] Specifically, a radiation therapy couch anti-collision method of this embodiment includes real-time monitoring and collision risk assessment, including:

[0072] During radiotherapy, the current position, motor current and displacement data of the treatment bed are collected in real time;

[0073] Input the real-time data into the association model and calculate the deviation between the current motion state and the expected state:

[0074] If the deviation exceeds the threshold, it is determined that there is a collision risk (for example, if the motor current increases abnormally but the displacement does not change as expected, it indicates that the mechanical resistance has increased);

[0075] If the trajectory of the treatment bed approaches the 3D envelope boundary, a pre-collision warning is triggered.

[0076] Specifically, a radiation therapy couch anti-collision method according to this embodiment implements an automatic anti-collision strategy:

[0077] When a collision risk is detected, the treatment bed automatically stops moving or adjusts its movement path (such as returning to a safe position);

[0078] Synchronously send visual / auditory warning signals to the operation interface and record risk event data for retrospective analysis.

[0079] Therefore, the radiation therapy couch anti-collision method of this embodiment has the following technical effects:

[0080] Active warning: Through real-time dynamic modeling and threshold comparison, risks can be identified before a collision occurs, avoiding the lag of traditional sensors' "after-the-fact warnings".

[0081] Automated intervention: The radiotherapy bed can autonomously stop or adjust its movement without relying on manual intervention by the operator, reducing collision accidents caused by delayed human response.

[0082] Adaptive optimization: The 3D envelope boundary and associated model can be dynamically updated with the configuration of the treatment device, which is suitable for complex and changing clinical scenarios (such as different treatment machine models or patient positions).

[0083] Improved safety and reliability: Combined with dual monitoring of motor current and displacement, it reduces the misjudgment rate and ensures the accuracy and robustness of the collision avoidance system.

[0084] Furthermore, as an optional implementation of this embodiment, in a radiation therapy couch anti-collision method of this embodiment, establishing a correlation model between the position of the treatment couch within the 3D envelope boundary, the change in motor operating current, and the change in displacement includes:

[0085] When the treatment bed is unloaded, the position data set GK(i) (i=1, 2, 3...), the current change data set HK(i) (i=1, 2, 3...), and the displacement change data set DK(i) (i=1, 2, 3...) are obtained, a neural network NET is established, training parameters are set, and the mathematical model FUN1 of the unloaded treatment bed is obtained by training the neural network NET;

[0086] Under the maximum load condition of the treatment bed, the position data set GM(i) (i=1, 2, 3...), the current variation data set HM(i) (i=1, 2, 3...), and the displacement variation data set DM(i) (i=1, 2, 3...) are obtained, a neural network NET is established, and training parameters are set. The neural network NET is trained to obtain the mathematical model FUN2 of the maximum load of the treatment bed;

[0087] Through the mathematical model FUN1 of the treatment bed with no load and the mathematical model FUN2 of the treatment bed with maximum load, the displacement change range S(j) (i=1, 2, 3...) between the maximum load and the no load at N positions under the same current change is obtained. S(j) is used as the reference threshold space P(i) (i=1, 2, 3...) of position N(i).

[0088] Specifically, in a radiation therapy couch anti-collision method according to this embodiment, generating the reference threshold space P(i) includes:

[0089] At N preset positions N(i) (i=1, 2, 3…) of the treatment bed, the displacement change output values ​​of the no-load mathematical model FUN1 and the maximum load mathematical model FUN2 under the same current change are extracted respectively, and the difference interval S(j) between the two is calculated, and S(j) is used as the reference threshold space P(i) of position N(i).

[0090] Based on the above approach, in a radiation therapy couch anti-collision method of this embodiment, the establishment of the association relationship model has the following technical features:

[0091] 1. Data collection and neural network modeling

[0092] No-load data acquisition (FUN1 model training)

[0093] Control the treatment bed to move along a preset path within the 3D envelope (e.g., uniform lifting, translation, rotation), and record the following data:

[0094] Position data set GK(i): three-dimensional coordinates (X, Y, Z) of each sampling point;

[0095] Current variation dataset HK(i): Current variation of the drive motor per unit time (ΔI);

[0096] Displacement change data set DK(i): actual displacement of the treatment bed per unit time (ΔD).

[0097] The model NET is constructed using a deep neural network (DNN) or LSTM. The input is the position GK(i) and the current change HK(i), and the output is the predicted displacement change DKpred(i). The model is trained by minimizing the mean square error (MSE) between the predicted value and the actual value DK(i) to obtain the no-load mathematical model FUN1.

[0098] Maximum load data collection (FUN2 model training)

[0099] Apply the maximum design load (such as the weight of an obese patient) to the treatment bed and repeat the above motion and data collection process to obtain:

[0100] Position data set GM(i), current change data set HM(i), displacement change data set DM(i).

[0101] The maximum load mathematical model FUN2 is obtained by training using the same neural network structure.

[0102] 2. Calculation of displacement change range

[0103] For the same position point N(i), the same current change ΔI is input, and the displacement changes DKpred(i) and DMpred(i) under no-load and maximum load are calculated by FUN1 and FUN2 respectively.

[0104] Calculate the difference between the two to form the displacement change interval S(j) = [DKpred(i), DMpred(i)]S(j) = [DKpred(i), DMpred(i)] of the position point, which serves as the reference threshold space P(i) of the position.

[0105] Repeat this process for all location points to build a full-space threshold mapping table.

[0106] 3. Real-time collision risk assessment

[0107] During the treatment process, the current position N(i), the current change ΔIreal, and the actual displacement change ΔDreal are monitored in real time.

[0108] Query the threshold space P(i) corresponding to the current position. If ΔDreal exceeds the range S(j) (for example, the actual displacement is less than the no-load prediction value or greater than the maximum load prediction value), it is determined to be abnormal resistance and a collision warning is triggered.

[0109] In the radiation therapy couch anti-collision method of this embodiment, the establishment of the association relationship model has the following technical effects:

[0110] Dynamic load adaptability:

[0111] By comparing the no-load and maximum load models, it automatically adapts to load changes caused by different patient weights or assistive devices, avoiding misjudgments caused by traditional fixed thresholds.

[0112] High-sensitivity detection:

[0113] The neural network model can capture nonlinear relationships (such as the complex mapping of motor current and displacement) and identify subtle anomalies (such as mechanical jamming or light contact) earlier than traditional linear thresholds.

[0114] Reduce false positives:

[0115] The dynamic threshold space (S(j)) based on the load interval can distinguish normal load fluctuations from real collisions and reduce the probability of false triggering.

[0116] No additional sensors required:

[0117] It only relies on the built-in motor current and encoder data of the treatment bed, without the need to install additional force sensors or distance detectors, reducing hardware costs.

[0118] Self-learning optimization:

[0119] The model can be iteratively updated through continuous collection of clinical data (such as data on patients of different body shapes) to further improve prediction accuracy.

[0120] As an optional implementation manner of this embodiment, in a radiation therapy couch anti-collision method of this embodiment, the reference threshold space P(i) is dynamically adjusted according to the real-time load state of the treatment couch, including:

[0121] If the real-time load is between no-load and maximum load, a threshold space P'(i) adapted to the current real-time load is generated by linear interpolation between the displacement change intervals corresponding to the no-load mathematical model FUN1 and the maximum load mathematical model FUN2.

[0122] Specifically, the real-time load detection and dynamic threshold adjustment of this embodiment include:

[0123] 1. Load status monitoring:

[0124] The current load (such as patient weight + auxiliary fixation device weight) is estimated in real time through the pressure sensor or motor current feedback of the treatment bed, which is recorded as Wreal, where the no-load weight is Wmin and the maximum load is Wmax.

[0125] Dynamic interpolation calculation:

[0126] For the current position point N(i), the displacement change range is adjusted by linear interpolation according to the ratio of the real-time load Wreal between no load (Wmin) and maximum load (Wmax):

[0127]

[0128] Among them, FUN1(i) and FUN2(i) are the boundary values ​​of the displacement change range of the position under no-load and maximum load, respectively.

[0129] 2. Non-linear load expansion:

[0130] If the relationship between load and displacement is nonlinear (such as the influence of elastic deformation), segmented interpolation or high-order polynomial fitting can be used to optimize the threshold space P′(i).

[0131] In this embodiment, a radiation therapy couch anti-collision method is provided for real-time collision risk assessment: the current displacement change ΔDreal is monitored, and if it exceeds the dynamic threshold space P′(i), the following actions are triggered:

[0132] Warning level:

[0133] Slightly exceeding the limit (e.g. within 5%): reduce the movement speed and prompt the operator to check;

[0134] Severely exceeding the limit (e.g. more than 10%): Immediately stop the movement of the treatment bed and sound a visual and audible alarm.

[0135] Adaptive retraction: Automatically controls the treatment bed to retract along the original path to the nearest safe position.

[0136] Load history learning:

[0137] Record the actual displacement data under different loads, dynamically update the FUN1 and FUN2 models, and improve the interpolation accuracy.

[0138] In a radiation therapy couch collision prevention method according to this embodiment, during the radiation therapy process, the motion spatial position of the radiation therapy couch, as well as the change in motor operating current and displacement corresponding to the motion spatial position, are monitored in real time. Determining whether the treatment couch faces a collision risk based on the association model includes:

[0139] During radiotherapy, real-time monitoring of the current motion spatial position of the radiotherapy bed and the current motor operating current of each motor corresponding to the motion spatial position;

[0140] Calculate the displacement change of adjacent sampling points based on the current motion space position, and determine whether the displacement change meets the reference threshold space P(i). If not, there is a collision risk for the treatment bed;

[0141] Further, according to the current motor operating current of each motor corresponding to the motion spatial position, the motor with the largest current motor operating current is controlled to stop moving.

[0142] Specifically, a radiation therapy couch anti-collision method according to this embodiment includes:

[0143] 1. Real-time data monitoring and processing

[0144] (1) Motion space position monitoring

[0145] The current three-dimensional coordinates (X, Y, Z) are collected in real time through the encoder or optical positioning system of the treatment bed and marked as the motion space position point N(i).

[0146] Kalman filtering is used to denoise the position data to reduce interference from mechanical vibration or measurement errors.

[0147] (2) Synchronous acquisition of motor current and displacement

[0148] The operating current Ireal of each drive motor (such as a lifting motor, a translation motor, and a rotating motor) is monitored in real time by a current sensor, and the current change ΔI within adjacent sampling time windows (such as 100ms) is calculated.

[0149] Combined with the encoder data, the actual displacement change ΔDreal of adjacent sampling points is calculated (e.g., millimeter-level accuracy).

[0150] 2. Dynamic determination of collision risk

[0151] (1) Displacement change threshold comparison

[0152] Query the dynamic reference threshold space P(i) corresponding to the current position N(i).

[0153] If ΔDreal exceeds the range of P(i):

[0154] Slight overrun (e.g., 5% reduction in displacement): Determined as potential friction resistance, triggering a Level 1 warning (yellow alert, reduced speed).

[0155] Severe over-limit (such as displacement reduction of 15%): It is determined as a collision risk and triggers the second-level alarm (red alarm, emergency stop).

[0156] (2) Motor current collaborative analysis

[0157] If the displacement is abnormal, further analyze the current of each motor:

[0158] Identify the motor with the largest current change ΔI (such as a sudden 30% increase in the current of a lifting motor), and determine that there is a collision object in the direction of the motor drive shaft.

[0159] Perform directional braking: only the abnormal motor is stopped, and other motors keep running (for example, the rotating motor can still adjust the angle to avoid obstacles).

[0160] As an optional implementation manner of this embodiment, in a radiation therapy couch collision avoidance method of this embodiment, drawing a 3D envelope boundary constraining the motion space of the therapy couch includes:

[0161] The motion range of the radiotherapy bed in all directions is calculated through forward kinematics to determine the theoretical reachable space and obtain the initial 3D envelope boundary.

[0162] Verify the actual reachable position of the radiotherapy bed end effector through inverse kinematics and correct the initial 3D envelope boundary;

[0163] Combined with the collision detection algorithm of the radiotherapy bed, the interference area with the external equipment of the radiotherapy bed is eliminated, and the final 3D envelope boundary of the radiotherapy bed motion space is obtained.

[0164] Furthermore, a radiation therapy couch anti-collision method according to this embodiment includes:

[0165] During radiotherapy, when it is detected that the minimum distance between the current position of the radiotherapy bed and the 3D envelope boundary is not greater than a first preset threshold delta01, the following operations are performed:

[0166] According to the current position and movement trend of the radiotherapy bed, the target motor that needs to be decelerated is calculated and active deceleration control is implemented on the target motor;

[0167] Send collision warning signal to the host computer system and output collision warning electrical signal to the outside;

[0168] When the minimum distance between the radiotherapy bed and the 3D envelope boundary is restored to be greater than the first preset threshold delta01, the warning signal is automatically released.

[0169] Furthermore, a radiation therapy couch anti-collision method according to this embodiment includes:

[0170] During the radiotherapy process, when it is monitored that the minimum distance between the current position of the radiotherapy bed and the 3D envelope boundary is not greater than the second preset threshold delta02, the following operations are performed:

[0171] Real-time calculation determines the target motor X (X=1, 2, ...) that requires emergency braking, and immediately stops the movement of the target motor X;

[0172] Send the motor X motion limit signal to the upper computer system and output the motor X motion limit electrical signal to the outside;

[0173] When the minimum distance between the treatment couch and the 3D envelope boundary is restored to be greater than the second preset threshold delta02, the motion limit signal is automatically released.

[0174] In a radiation therapy couch anti-collision method according to this embodiment:

[0175] The first preset threshold delta01 is dynamically adjusted according to the real-time movement speed of the treatment bed. The greater the movement speed, the greater the value of the first preset threshold delta01.

[0176] The second preset threshold delta02 is dynamically calculated based on the real-time movement speed v of the treatment bed: delta02 = k·v + delta00, where k is the proportional coefficient and delta00 is the minimum safety distance reference value;

[0177] The second preset threshold delta02 is greater than the first preset threshold delta01.

[0178] This embodiment also provides a radiation therapy couch anti-collision system, including:

[0179] 3D envelope boundary module, which draws the 3D envelope boundary that constrains the movement space of the treatment bed;

[0180] The treatment bed anti-collision model module establishes a correlation model between the treatment bed's position within the 3D envelope boundary, the change in motor operating current, and the change in displacement;

[0181] The main control module monitors the motion spatial position of the radiotherapy bed, as well as the change in motor operating current and displacement corresponding to the motion spatial position, in real time during radiotherapy, and determines whether there is a collision risk of the treatment bed based on the association relationship model.

[0182] Further, see Figure 2 An emergency device 300 is placed on the radiotherapy bed 100. The emergency device sends an electrical signal with the highest priority, which requires the operator to actively trigger and release it. It only stops all motor movements and does not affect other systems. It serves as an emergency measure in case the radiotherapy bed 100 loses control.

[0183] Further, see Figure 3A force sensor 400 is arranged on the peripheral hardware of the radiotherapy bed 100, and a reasonable threshold is preset. When a signal is triggered, the radiotherapy bed 100 stops moving to avoid colliding with the frame 200; this serves as an emergency measure in case the radiotherapy bed 100 loses control.

[0184] This embodiment also provides a computer-readable storage medium storing a computer-executable program. When the computer-executable program is executed, the radiation therapy couch anti-collision method described above is implemented.

[0185] The computer-readable storage medium described in this embodiment may include a data signal propagated in baseband or as part of a carrier wave, which carries a readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or component. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0186] This embodiment further provides an electronic device, including a processor and a memory, wherein the memory is used to store a computer executable program. When the computer program is executed by the processor, the processor executes the radiation therapy couch collision avoidance method.

[0187] The electronic device is implemented as a general-purpose computing device. The processor may be one or multiple processors operating in concert. The present invention also does not exclude distributed processing, meaning the processors may be dispersed across different physical devices. The electronic device of the present invention is not limited to a single entity but may also be the sum of multiple physical devices.

[0188] The memory stores a computer executable program, typically a machine-readable code, which can be executed by the processor to enable the electronic device to perform the method of the present invention, or at least some of the steps in the method.

[0189] The memory includes a volatile memory, such as a random access memory unit (RAM) and / or a cache memory unit, and may also be a non-volatile memory, such as a read-only memory unit (ROM).

[0190] It should be understood that the electronic devices of the present invention may also include elements or components not shown in the above examples. For example, some electronic devices also include display units such as screens, and some electronic devices also include human-computer interaction elements such as buttons and keyboards. As long as the electronic device can execute a computer-readable program stored in its memory to implement the method of the present invention or at least some of the steps of the method, it can be considered an electronic device covered by the present invention.

[0191] Through the above description of the implementation mode, it is easy for those skilled in the art to understand that the present invention can be implemented by hardware capable of executing a specific computer program, such as the system of the present invention, and the electronic processing unit, server, client, mobile phone, control unit, processor, etc. contained in the system. The present invention can also be implemented by computer software that executes the method of the present invention, such as control software executed by a microprocessor, an electronic control unit, a client, a server, etc. However, it should be noted that the computer software that executes the method of the present invention is not limited to being executed by one or a specific hardware entity, and it can also be implemented in a distributed manner by unspecified specific hardware. For computer software, the software product can be stored in a computer-readable storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), or it can be distributed and stored on a network, as long as it enables an electronic device to execute the method according to the present invention.

[0192] The above embodiments are only used to illustrate the present invention and are not intended to limit the technical solutions described in the present invention. Although this specification has described the present invention in detail with reference to the above embodiments, the present invention is not limited to the above specific implementation methods. Therefore, any modification or equivalent replacement of the present invention; and all technical solutions and improvements thereof that do not depart from the spirit and scope of the invention are included in the scope of the claims of the present invention.

Claims

1. A radiation therapy bed anti-collision method, characterized in that: include: Draw the 3D envelope boundary that constrains the movement space of the treatment bed; Establish a correlation model between the position of the treatment bed within the 3D envelope boundary, the change in motor operating current, and the change in displacement; During radiotherapy, the motion spatial position of the radiotherapy bed and the change in motor operating current and displacement corresponding to the motion spatial position are monitored in real time, and whether there is a collision risk of the treatment bed is determined based on the association relationship model.

2. The radiation therapy couch anti-collision method according to claim 1, characterized in that: The establishment of the correlation relationship model between the position of the treatment bed within the 3D envelope boundary, the change in motor operating current, and the change in displacement includes: When the treatment bed is unloaded, the position data set GK(i) (i=1, 2, 3...), the current change data set HK(i) (i=1, 2, 3...), and the displacement change data set DK(i) (i=1, 2, 3...) are obtained, a neural network NET is established, training parameters are set, and the mathematical model FUN1 of the unloaded treatment bed is obtained by training the neural network NET; Under the maximum load condition of the treatment bed, the position data set GM(i) (i=1, 2, 3...), the current variation data set HM(i) (i=1, 2, 3...), and the displacement variation data set DM(i) (i=1, 2, 3...) are obtained, a neural network NET is established, and training parameters are set. The neural network NET is trained to obtain the mathematical model FUN2 of the maximum load of the treatment bed; Through the mathematical model FUN1 of the treatment bed with no load and the mathematical model FUN2 of the treatment bed with maximum load, the displacement change range S(j) (i=1, 2, 3...) between the maximum load and the no load at N positions under the same current change is obtained. S(j) is used as the reference threshold space P(i) (i=1, 2, 3...) of position N(i).

3. The radiation therapy couch anti-collision method according to claim 2, characterized in that: The generation of the reference threshold space P(i) includes: At N preset positions N(i) (i=1, 2, 3…) of the treatment bed, the displacement change output values ​​of the no-load mathematical model FUN1 and the maximum load mathematical model FUN2 under the same current change are extracted respectively, and the difference interval S(j) between the two is calculated, and S(j) is used as the reference threshold space P(i) of position N(i).

4. The radiation therapy couch anti-collision method according to claim 2, characterized in that: The reference threshold space P(i) is dynamically adjusted according to the real-time load state of the treatment bed, including: If the real-time load is between no-load and maximum load, a threshold space P'(i) adapted to the current real-time load is generated by linear interpolation between the displacement change intervals corresponding to the no-load mathematical model FUN1 and the maximum load mathematical model FUN2.

5. A radiation therapy couch anti-collision method according to any one of claims 2 to 4, characterized in that: During the radiotherapy process, real-time monitoring of the motion spatial position of the radiotherapy bed, and the change in motor operating current and displacement corresponding to the motion spatial position, and determining whether the treatment bed has a collision risk based on the association relationship model includes: During radiotherapy, real-time monitoring of the current motion spatial position of the radiotherapy bed and the current motor operating current of each motor corresponding to the motion spatial position; Calculate the displacement change of adjacent sampling points based on the current motion space position, and determine whether the displacement change meets the reference threshold space P(i). If not, there is a collision risk for the treatment bed; Further, according to the current motor operating current of each motor corresponding to the motion spatial position, the motor with the largest current motor operating current is controlled to stop moving.

6. The radiation therapy couch anti-collision method according to claim 1, characterized in that: Drawing the 3D envelope boundary constraining the motion space of the treatment couch includes: The motion range of the radiotherapy bed in all directions is calculated through forward kinematics to determine the theoretical reachable space and obtain the initial 3D envelope boundary. Verify the actual reachable position of the radiotherapy bed end effector through inverse kinematics and correct the initial 3D envelope boundary; Combined with the collision detection algorithm of the radiotherapy bed, the interference area with the external equipment of the radiotherapy bed is eliminated, and the final 3D envelope boundary of the radiotherapy bed motion space is obtained.

7. The radiation therapy couch anti-collision method according to claim 6, characterized in that: include: During radiotherapy, when it is detected that the minimum distance between the current position of the radiotherapy bed and the 3D envelope boundary is not greater than a first preset threshold delta01, the following operations are performed: According to the current position and movement trend of the radiotherapy bed, the target motor that needs to be decelerated is calculated and active deceleration control is implemented on the target motor; Send collision warning signal to the host computer system and output collision warning electrical signal to the outside; When the minimum distance between the radiotherapy bed and the 3D envelope boundary is restored to be greater than the first preset threshold delta01, the warning signal is automatically released.

8. The radiation therapy couch anti-collision method according to claim 7, characterized in that: include: During the radiotherapy process, when it is monitored that the minimum distance between the current position of the radiotherapy bed and the 3D envelope boundary is not greater than the second preset threshold delta02, the following operations are performed: Real-time calculation determines the target motor X (X=1, 2, ...) that requires emergency braking, and immediately stops the movement of the target motor X; Send the motor X motion limit signal to the upper computer system and output the motor X motion limit electrical signal to the outside; When the minimum distance between the treatment couch and the 3D envelope boundary is restored to be greater than the second preset threshold delta02, the motion limit signal is automatically released.

9. The radiation therapy couch anti-collision method according to claim 8, characterized in that: include: The first preset threshold delta01 is dynamically adjusted according to the real-time movement speed of the treatment bed. The greater the movement speed, the greater the value of the first preset threshold delta01. The second preset threshold delta02 is dynamically calculated based on the real-time movement speed v of the treatment bed: delta02 = k·v + delta00, where k is the proportional coefficient and delta00 is the minimum safety distance reference value; The second preset threshold delta02 is greater than the first preset threshold delta01.

10. A radiation therapy couch anti-collision system, characterized in that: include: 3D envelope boundary module, which draws the 3D envelope boundary that constrains the movement space of the treatment bed; The treatment bed anti-collision model module establishes a correlation model between the treatment bed's position within the 3D envelope boundary, the change in motor operating current, and the change in displacement; The main control module monitors the motion spatial position of the radiotherapy bed, as well as the change in motor operating current and displacement corresponding to the motion spatial position, in real time during radiotherapy, and determines whether there is a collision risk of the treatment bed based on the association relationship model.

Images