Intelligent calibration method and device for tumor radiotherapy bed

Abstract

The invention discloses an intelligent calibration method for a tumor radiotherapy bed, and the method comprises a primary intelligent calibration process: controlling a treatment bed to rise to an electrical origin, and obtaining an encoder value Y (0) through an encoder disposed on the treatment bed; controlling the treatment bed to perform fixed motor pulse increment descending motion to collect sample points, and recording a corresponding encoder value Y (i) (i = 1, 2, 3,...) through an encoder arranged on the treatment bed; performing normalization processing on each fixed motor pulse increment to obtain a (j), and converting an encoder numerical value Y (i) into a lifting displacement numerical value b (i); taking the a (j) as an input variable, taking the b (i) as an output variable, and obtaining a polynomial function C1 by utilizing high-order polynomial fitting; b (i) is used as an input variable, a (j) is used as an output variable, and a polynomial function C2 is obtained through high-degree polynomial fitting; a group of input variables d are defined, the input variables d are expected motion displacement of the treatment bed, and an output variable D is obtained in combination with the polynomial function C2; combining the output variable D with the polynomial function C1 to obtain an output variable E; the average error errormi n and the maximum error errormax of the output variable E and the input variable d are calculated; when the average error errormi n and the maximum error errormax are both smaller than the preset technical parameter P (1) of the primary intelligent scale, the primary intelligent scale is completed.

Description

Technical Field

[0001] The present invention relates to the technical field of radiotherapy equipment, and in particular to an intelligent calibration method and device for a tumor radiotherapy bed. Background Art

[0002] In a medical electron linear accelerator, the tumor radiotherapy bed is the only device that supports the patient and is also responsible for delivering the lesion to the central location of the accelerator for treatment, which is called positioning in the industry. Therefore, motion accuracy is a key parameter of the treatment bed.

[0003] For circular medical electron linear accelerators, patients can only be moved by the treatment bed. The lifting movement of the treatment bed and the rotational movement of the motor are generally in a nonlinear relationship. Therefore, the relationship between these two types of movement must be clarified to ensure the movement accuracy of the treatment bed, which directly affects the radiotherapy effect on the target area.

[0004] The applicant also filed a Chinese utility model patent application with application number CN202422562261.4, entitled A medical accelerator treatment bed system, which can solve the problem of bed sinking of the treatment bed and improve the positioning accuracy of the treatment bed; however, the patent does not involve the problem of motion accuracy calibration of the treatment bed.

[0005] In the prior art, there is no clear technical solution to solve this problem. In view of this, the present invention patent is specially proposed. Summary of the invention

[0006] In order to solve the above technical problems, the present invention provides an intelligent calibration method and device for a tumor radiotherapy bed. Specifically, the following technical solutions are adopted:

[0007] An intelligent calibration method for a tumor radiotherapy bed includes a primary intelligent calibration process:

[0008] Control the treatment bed to rise to the electrical origin, and obtain the encoder value Y(0) through the encoder set on the treatment bed;

[0009] Control the treatment bed to descend with a fixed motor pulse increment to collect sample points, and at the same time record the corresponding encoder value Y(i) (i=1, 2, 3, ...) through the encoder set on the treatment bed;

[0010] Normalize each fixed motor pulse increment to get a(j), and convert the encoder value Y(i) into the lifting displacement value b(i);

[0011] With a(j) as input variable and b(i) as output variable, high-order polynomial fitting is used to obtain the polynomial function C1;

[0012] Taking b(i) as input variable and a(j) as output variable, high-order polynomial fitting is used to obtain polynomial function C2;

[0013] Define a set of input variables d, where the input variable d is the expected motion displacement of the treatment bed, and combine it with the polynomial function C2 to obtain the output variable D;

[0014] Combine the output variable D with the polynomial function C1 to obtain the output variable E;

[0015] Calculate the average error error_min and maximum error error_max between the output variable E and the input variable d;

[0016] When the average error error_min and the maximum error error_max are both less than the preset primary intelligent calibration technical parameter P(1), the primary intelligent calibration is completed.

[0017] As an optional implementation manner of the present invention, during the process of controlling the treatment bed to move downward with a fixed motor pulse increment, when the treatment bed descends to the lowest position, the sample point collection is completed and m sample data are obtained.

[0018] As an optional embodiment of the present invention, when the average error error_min and the maximum error error_max do not satisfy the requirement that they are both less than the preset technical parameter P(1), the treatment bed is controlled to rise to the electrical origin, and a new round of primary intelligent calibration process is cyclically executed;

[0019] In a new round of primary intelligent calibration process, the number of sample data m is modified, and / or the average error error_min and the maximum error error_max between the output variable E and the input variable d are calculated by changing the order of the polynomial function C1 and the polynomial function C2;

[0020] Determine whether the average error error_min and the maximum error error_max are both less than the preset technical parameter P(1). If so, the primary intelligent calibration is completed. If not, the loop execution continues.

[0021] As an optional embodiment of the present invention, the present invention provides an intelligent calibration method for a tumor radiotherapy bed, comprising executing a secondary intelligent calibration process after the primary intelligent calibration process is completed, and the secondary intelligent calibration process includes:

[0022] Control the treatment bed to rise to the electrical origin, and obtain the encoder value F(0) through the encoder set on the treatment bed;

[0023] Based on the polynomial function C1 and the polynomial function C2 in the primary intelligent calibration process, the treatment bed is controlled to move according to the random target position Z(j) (j=1,2,3,…) within the maximum lifting and lowering motion space of the treatment bed, and the encoder value F(i) (i=1,2,3,…) is obtained through the encoder set on the treatment bed, and n rounds are executed;

[0024] Convert the encoder value F(i) into a displacement value and remove the offset F(0) to obtain G(i);

[0025] Calculate the deviation between G(i) and Z(j) to obtain Dv(i,j);

[0026] Based on the input data set Z(j) and the deviation data set Dv(i,j), a neural network NET is established, training parameters are set, and the neural network NET is trained to obtain a treatment bed lifting motion position deviation prediction model FUN;

[0027] Combined with the prediction model FUN, the movement of the treatment bed lifting motor is corrected. The average error and maximum error between the target position and the actual position are both less than the preset secondary intelligent scale technical parameter P(2), and the secondary intelligent scale is completed.

[0028] As an optional implementation mode of the present invention, when the average error and the maximum error do not satisfy the requirement that they are both less than the preset secondary intelligent scale technical parameter P(2), a new round of secondary intelligent scale process is executed cyclically;

[0029] In a new round of secondary intelligent calibration process, modify the number of rounds n of controlling the treatment bed to execute according to the random target position Z(j), and / or calculate the average error error_min and the maximum error error_max between the output variable E and the input variable d by changing the training parameters of the training neural network NET;

[0030] It is determined whether the average error and the maximum error are both less than the preset secondary intelligent scale technical parameter P(2). If so, the secondary intelligent scale is completed. If not, the loop execution continues.

[0031] The present invention also provides an intelligent calibration device for the intelligent calibration method of the tumor radiotherapy bed, comprising:

[0032] A treatment bed, comprising a treatment bed board and a driving motor for driving the treatment bed board to move up and down;

[0033] Data acquisition and positioning device, used to obtain the pulse value of the driving motor and locate the lifting position of the treatment bed;

[0034] A positioning auxiliary device, comprising an encoder, wherein the encoder is mounted on a treatment bed board;

[0035] The auxiliary device is placed outside the treatment bed, and comprises a magnetic strip fixing plate, on which a magnetic strip opposite to the encoder is installed.

[0036] As an optional embodiment of the present invention, the auxiliary device includes a bearing base and a displacement platform, the bearing base has a plurality of supporting feet, and the height and posture of the bearing base can be adjusted, the displacement platform can be installed on the bearing base for reciprocating linear motion, and the magnetic strip fixing plate is installed on the displacement platform;

[0037] The bearing base is placed outside the treatment bed, and the relative distance between the magnetic strip on the magnetic strip fixing plate and the encoder is adjusted by controlling the displacement platform to perform reciprocating linear motion.

[0038] As an optional embodiment of the present invention, the auxiliary device includes an angle adjustment rod group, the bottom end of the magnetic strip fixing plate is rotatably connected to the displacement platform, the top end of the magnetic strip fixing plate is rotatably connected to one end of the angle adjustment rod group, and the other end of the angle adjustment rod group is rotatably connected to the displacement platform;

[0039] By adjusting the telescopic length of the angle adjustment rod group, the relative angle between the magnetic strip on the magnetic strip fixing plate and the encoder is changed, so that the horizontal distance between the magnetic strip on the fixing plate and the encoder is constant.

[0040] As an optional embodiment of the present invention, the positioning auxiliary device includes a fixing fixture, a connecting plate and a displacement sensor, the fixing fixture is clamped on one side of the treatment bed board, the connecting plate is fixedly connected to the fixing fixture, the displacement sensor and the encoder are selectively or simultaneously installed on the connecting plate, and a positioning straight line parallel to the magnetic strip is provided on the magnetic strip fixing plate;

[0041] The bearing base is placed outside the treatment bed, and a detection signal is emitted to the magnetic strip fixing plate through the displacement sensor, and the detection signal is aligned with the positioning straight line; the lifting and lowering movement of the treatment bed board is controlled, and the detection signal emitted by the displacement sensor is monitored to determine whether it is lifted and lowered along the positioning straight line, and the height and posture of the bearing base are changed by adjusting the supporting feet of the bearing base according to the offset between the detection signal and the positioning straight line, until the detection signal emitted by the displacement sensor is lifted and lowered along the positioning straight line;

[0042] Control the lifting movement of the treatment bed board, monitor the detection signal emitted by the displacement sensor, detect the horizontal distance between the connecting plate and the magnetic strip fixing plate, and adjust the angle adjustment rod group until the horizontal distance between the connecting plate and the magnetic strip fixing plate is constant;

[0043] The displacement platform is controlled to perform reciprocating linear motion, and the horizontal distance between the connecting plate and the magnetic strip fixing plate is detected until the relative distance required by the intelligent scale is met. As an optional embodiment of the present invention, the connecting plate has a first fixing position for installing a displacement sensor, and a second fixing position for installing an encoder; the relative horizontal position relationship between the first fixing position and the second fixing position is the same as the relative horizontal position relationship between the magnetic strip and the positioning straight line on the magnetic strip fixing plate.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] The present invention proposes an intelligent calibration method for a tumor radiotherapy bed, by calculating the average error error_min and the maximum error error_max between an output variable E and an input variable d; when the average error error_min and the maximum error error_max are both less than a preset primary intelligent calibration technical parameter P(1), primary intelligent calibration for the movement of the treatment bed is realized, the lifting and lowering accuracy of the treatment bed is improved, and the reliability of the treatment bed movement is guaranteed.

[0046] The intelligent calibration method of a tumor radiotherapy bed of the present invention executes a secondary intelligent calibration process after the primary intelligent calibration process is completed, and combines the prediction model FUN to correct the movement of the treatment bed lifting motor. The average error and the maximum error between the target position and the actual position are both less than the preset secondary intelligent calibration technical parameter P(2). The secondary intelligent calibration is completed, which further improves the accuracy of the treatment bed lifting movement and ensures the reliability of the treatment bed movement. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A schematic structural diagram of an intelligent calibration device for a tumor radiotherapy couch according to an embodiment of the present invention;

[0048] Figure 2 A schematic structural diagram of an auxiliary device of an intelligent calibration device of a tumor radiotherapy couch according to an embodiment of the present invention. DETAILED DESCRIPTION

[0049] To make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be described clearly and completely in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them.

[0050] Therefore, the following detailed description of the embodiments of the present invention is not intended to limit the scope of the invention claimed for protection, but merely represents some embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0051] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features and technical solutions in the embodiments may be combined with each other.

[0052] 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, further definition and explanation thereof is not required in subsequent drawings.

[0053] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper", "lower", etc. is based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the invention product is usually placed when in use, or the orientation or positional relationship commonly understood by those skilled in the art. Such terms are only for the convenience of describing 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, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0054] The intelligent calibration method of a tumor radiotherapy bed in this embodiment includes the following steps:

[0055] Control the treatment bed to rise to the electrical origin, and obtain the encoder value Y(0) through the encoder set on the treatment bed;

[0056] Control the treatment bed to descend with a fixed motor pulse increment to collect sample points, and at the same time record the corresponding encoder value Y(i) (i=1, 2, 3, ...) through the encoder set on the treatment bed;

[0057] Normalize each fixed motor pulse increment to get a(j), and convert the encoder value Y(i) into the lifting displacement value b(i);

[0058] With a(j) as input variable and b(i) as output variable, high-order polynomial fitting is used to obtain the polynomial function C1;

[0059] Taking b(i) as input variable and a(j) as output variable, high-order polynomial fitting is used to obtain polynomial function C2;

[0060] Define a set of input variables d, where the input variable d is the expected motion displacement of the treatment bed, and combine it with the polynomial function C2 to obtain the output variable D;

[0061] Combine the output variable D with the polynomial function C1 to obtain the output variable E;

[0062] Calculate the average error error_min and maximum error error_max between the output variable E and the input variable d;

[0063] When the average error error_min and the maximum error error_max are both less than the preset primary intelligent calibration technical parameter P(1), the primary intelligent calibration is completed.

[0064] This embodiment proposes an intelligent calibration method for a tumor radiotherapy bed, by calculating the average error error_min and the maximum error error_max between the output variable E and the input variable d; when the average error error_min and the maximum error error_max are both less than the preset primary intelligent calibration technical parameter P(1), primary intelligent calibration for the treatment bed movement is achieved, thereby improving the accuracy of the treatment bed lifting movement and ensuring the reliability of the treatment bed movement.

[0065] This embodiment proposes an intelligent calibration method for a tumor radiotherapy bed. Electrical origin: an origin that can be changed by setting. For example, if you want to start processing parts from a certain point, you can set that point as the electrical origin, and return to the electrical origin after a cycle of work.

[0066] As an optional implementation of this embodiment, in a method for intelligently calibrating a tumor radiotherapy bed in this embodiment, during the process of controlling the bed to descend with fixed motor pulse increments, when the bed descends to the lowest position, the sample point collection ends, and m sample data are obtained. Therefore, the bed in this embodiment covers the entire movement displacement during the descent process, ensuring that the primary intelligent calibration of the bed movement includes the entire lifting movement displacement of the bed.

[0067] Furthermore, in the intelligent calibration method of a tumor radiotherapy bed of the present embodiment, when the average error error_min and the maximum error error_max do not satisfy the requirement that they are both less than the preset technical parameter P(1), the treatment bed is controlled to rise to the electrical origin, and a new round of primary intelligent calibration process is cyclically executed;

[0068] In a new round of primary intelligent calibration process, the number of sample data m is modified, and / or the average error error_min and the maximum error error_max between the output variable E and the input variable d are calculated by changing the order of the polynomial function C1 and the polynomial function C2;

[0069] Determine whether the average error error_min and the maximum error error_max are both less than the preset technical parameter P(1). If so, the primary intelligent calibration is completed. If not, the loop execution continues.

[0070] In the intelligent calibration method for a tumor radiotherapy bed of the present embodiment, when the primary intelligent calibration process does not meet the requirement that the values ​​are all less than the preset technical parameter P(1), the number of sample data m is modified, and / or the primary intelligent calibration process is performed again by changing the orders of the polynomial function C1 and the polynomial function C2.

[0071] As an optional implementation of this embodiment, a method for intelligent calibration of a tumor radiotherapy bed in this embodiment includes executing a secondary intelligent calibration process after the primary intelligent calibration process is completed, and the secondary intelligent calibration process includes:

[0072] Control the treatment bed to rise to the electrical origin, and obtain the encoder value F(0) through the encoder set on the treatment bed;

[0073] Based on the polynomial function C1 and the polynomial function C2 in the primary intelligent calibration process, the treatment bed is controlled to move according to the random target position Z(j) (j=1,2,3,…) within the maximum lifting and lowering motion space of the treatment bed, and the encoder value F(i) (i=1,2,3,…) is obtained through the encoder set on the treatment bed, and n rounds are executed;

[0074] Convert the encoder value F(i) into a displacement value and remove the offset F(0) to obtain G(i);

[0075] Calculate the deviation between G(i) and Z(j) to obtain Dv(i,j);

[0076] Based on the input data set Z(j) and the deviation data set Dv(i,j), a neural network NET is established, training parameters are set, and the neural network NET is trained to obtain a treatment bed lifting motion position deviation prediction model FUN;

[0077] Combined with the prediction model FUN, the movement of the treatment bed lifting motor is corrected. The average error and maximum error between the target position and the actual position are both less than the preset secondary intelligent scale technical parameter P(2), and the secondary intelligent scale is completed.

[0078] In the intelligent calibration method of a tumor radiotherapy bed of the present embodiment, after the primary intelligent calibration process is completed, the secondary intelligent calibration process is executed, and the movement of the treatment bed lifting motor is corrected in combination with the prediction model FUN. The average error and the maximum error between the target position and the actual position are both less than the preset secondary intelligent calibration technical parameter P(2). The secondary intelligent calibration is completed, which further improves the accuracy of the treatment bed lifting movement and ensures the reliability of the treatment bed movement.

[0079] Furthermore, in the intelligent calibration method of a tumor radiotherapy bed of this embodiment, when the average error and the maximum error do not satisfy the requirement that they are both less than the preset secondary intelligent calibration technical parameter P(2), a new round of secondary intelligent calibration process is executed cyclically;

[0080] In a new round of secondary intelligent calibration process, modify the number of rounds n of controlling the treatment bed to execute according to the random target position Z(j), and / or calculate the average error error_min and the maximum error error_max between the output variable E and the input variable d by changing the training parameters of the training neural network NET;

[0081] It is determined whether the average error and the maximum error are both less than the preset secondary intelligent scale technical parameter P(2). If so, the secondary intelligent scale is completed. If not, the loop execution continues.

[0082] In the intelligent calibration method for a tumor radiotherapy bed of the present embodiment, when the secondary intelligent calibration process does not meet the requirement that the values ​​are all less than the preset secondary intelligent calibration technical parameters P(2), the number of rounds n for controlling the treatment bed to execute according to the random target position Z(j) is modified, and / or the primary intelligent calibration process is re-performed by changing the training parameters of the training neural network NET.

[0083] See also Figure 1 and Figure 2 As shown, an intelligent calibration device for the intelligent calibration method of the tumor radiotherapy bed of this embodiment includes:

[0084] The treatment couch 200 includes a treatment couch board 201 and a driving motor (not shown) for driving the treatment couch board 201 to move up and down;

[0085] A data acquisition and positioning device, used to acquire the pulse value of the driving motor and locate the lifting position of the treatment bed 200;

[0086] The positioning auxiliary device 100A includes an encoder (not shown), which is installed on the treatment bed board 201;

[0087] The auxiliary device 100B is placed outside the treatment bed 200. The auxiliary device 100B includes a magnetic stripe fixing plate 105. A magnetic stripe 107 opposite to the encoder is installed on the magnetic stripe fixing plate 105.

[0088] In the intelligent calibration device of the intelligent calibration method for the tumor radiotherapy bed of the present embodiment, the magnetic strip 107 of the auxiliary device 100B is opposite to the encoder, so that the encoder can record the corresponding encoder value Y(i) (i=1,2,3,...) during the lifting and lowering process of the treatment bed plate 201, and the actual lifting and lowering displacement of the treatment bed plate 201 can be obtained through the encoder value Y(i) (i=1,2,3,...).

[0089] Furthermore, the auxiliary device 100B described in this embodiment includes a bearing base 103 and a displacement platform 104, the displacement platform 104 is installed on the bearing base 103 for reciprocating linear motion, and the magnetic stripe fixing plate 105 is installed on the displacement platform 104; the bearing base 103 is placed outside the treatment bed 200, and the posture of the bearing base is changed by adjusting the supporting feet of the bearing base 103; the relative distance between the magnetic stripe on the magnetic stripe fixing plate and the encoder is adjusted by controlling the displacement platform to perform reciprocating linear motion.

[0090] Furthermore, the auxiliary device 100B described in this embodiment includes an angle adjustment rod group 108, the bottom end of the magnetic stripe fixing plate 105 is rotatably connected to the displacement platform 104, the top end of the magnetic stripe fixing plate 105 is rotatably connected to one end of the angle adjustment rod group 108, and the other end of the angle adjustment rod group 108 is rotatably connected to the displacement platform 104; by adjusting the telescopic length of the angle adjustment rod group 108, the relative angle between the magnetic stripe 107 on the magnetic stripe fixing plate 105 and the encoder is changed, so that the horizontal distance between the magnetic stripe 107 on the magnetic stripe fixing plate 105 and the encoder is constant.

[0091] In this way, before starting the primary intelligent calibration process, by adjusting the supporting feet of the supporting base 103, changing the posture of the supporting base, and adjusting the telescopic length of the angle adjustment rod group 108, the relative angle between the magnetic strip 107 on the magnetic strip fixing plate 105 and the encoder is changed, and at the same time, the displacement platform is controlled to perform reciprocating linear motion, and the relative distance between the magnetic strip 107 on the magnetic strip fixing plate and the encoder is adjusted, so that the encoder and the magnetic strip 107 are always relative to each other during the lifting and lowering of the treatment bed board 201, ensuring the detection accuracy of the encoder.

[0092] The present embodiment is an intelligent calibration device for a tumor radiotherapy bed, wherein the positioning auxiliary device 100A comprises a fixing fixture 101, a connecting plate 111 and a displacement sensor 102. The fixing fixture 101 is clamped on one side of the treatment bed board 201, the connecting plate 111 is fixedly connected to the fixing fixture 101, the displacement sensor 111 and the encoder are selectively or simultaneously installed on the connecting plate 111, and a positioning straight line 106 parallel to the magnetic strip 107 is provided on the magnetic strip fixing plate 105.

[0093] The bearing base 103 is placed outside the treatment bed 200, and a detection signal is transmitted to the magnetic strip fixing plate 105 through the displacement sensor 102, and the detection signal is aligned with the positioning line 106. The treatment bed board 201 is controlled to move up and down, and the detection signal transmitted by the displacement sensor 102 is monitored to determine whether it moves up and down along the positioning line 106. According to the offset between the detection signal and the positioning line 106, the supporting feet of the bearing base 103 are adjusted to change the posture of the bearing base 103 until the detection signal transmitted by the displacement sensor 102 moves up and down along the positioning line 106.

[0094] The lifting movement of the treatment bed board 201 is controlled, and the detection signal emitted by the displacement sensor 102 is monitored, the horizontal distance between the connecting plate 111 and the magnetic strip fixing plate 105 is detected, and the angle adjustment rod group 108 is adjusted until the horizontal distance is constant.

[0095] The displacement platform 104 is controlled to perform reciprocating linear motion to detect the horizontal distance between the connecting plate 111 and the magnetic strip fixing plate 105 until the relative distance required by the intelligent scale is met.

[0096] The displacement sensor 102 of this embodiment adopts an infrared sensor to emit infrared light to the magnetic stripe fixing plate 105. On the one hand, it realizes the horizontal distance detection between the connecting plate 111 and the magnetic stripe fixing plate 105. At the same time, during the lifting and lowering movement of the treatment bed plate 201, it monitors whether the infrared light rises and falls along the positioning line 106, thereby determining the placement posture of the auxiliary device 100B.

[0097] Furthermore, in the intelligent calibration device of a tumor radiotherapy bed of the present embodiment, the connecting plate 111 has a first fixing position for installing the displacement sensor 102 and a second fixing position for installing the encoder; the relative horizontal position relationship between the first fixing position and the second fixing position is the same as the relative horizontal position relationship between the magnetic strip 107 and the positioning line 106 on the magnetic strip fixing plate 105. In this way, while the auxiliary device 100B is placed and positioned by the displacement sensor 102, the corresponding positioning of the encoder and the magnetic strip 107 is completed.

[0098] In the intelligent calibration device of a tumor radiotherapy bed of this embodiment, the magnetic strip fixing plate 105 is held in position by locking mechanisms 109 and 110 .

[0099] In the intelligent calibration device of a tumor radiotherapy couch of this embodiment, the supporting base 103 has a total of four supporting legs for supporting the auxiliary device 100B and adjusting the relative angle between the auxiliary device 100B and the displacement sensor 102 .

[0100] This embodiment also provides a computer-readable storage medium storing a computer-executable program. When the computer-executable program is executed, the intelligent calibration method for a tumor radiation therapy bed is implemented.

[0101] The computer-readable storage medium described in this embodiment may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, 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 combination with an instruction execution system, an apparatus, or a device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0102] This embodiment further provides an electronic device, including a processor and a memory, wherein the memory is used to store a computer executable program, and when the computer program is executed by the processor, the processor executes the intelligent calibration method for a tumor radiation therapy bed.

[0103] The electronic device is presented in the form of a general-purpose computing device. The processor may be one or more than one and work in coordination. The present invention does not exclude distributed processing, that is, the processor may be dispersed in 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.

[0104] The memory stores a computer executable program, which is usually a machine-readable code. The computer-readable program can be executed by the processor to enable the electronic device to perform the method of the present invention, or at least part of the steps in the method.

[0105] 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).

[0106] It should be understood that the electronic device 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 display screens, and some electronic devices also include human-computer interaction elements such as buttons and keyboards. As long as the electronic device can execute the computer-readable program in the memory to implement the method of the present invention or at least part of the steps of the method, it can be considered as an electronic device covered by the present invention.

[0107] 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 U disk, a mobile hard disk, etc.), and can also be distributed and stored on the network, as long as it can enable the electronic device to execute the method according to the present invention.

[0108] 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 the present invention has been described 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. An intelligent calibration method for a tumor radiotherapy bed, characterized in that: Including primary intelligent scale process: Control the treatment bed to rise to the electrical origin, and obtain the encoder value Y(0) through the encoder set on the treatment bed; Control the treatment bed to descend with a fixed motor pulse increment to collect sample points, and at the same time record the corresponding encoder value Y(i) (i=1, 2, 3, ...) through the encoder set on the treatment bed; Normalize each fixed motor pulse increment to get a(j), and convert the encoder value Y(i) into the lifting displacement value b(i); With a(j) as input variable and b(i) as output variable, high-order polynomial fitting is used to obtain the polynomial function C1; Taking b(i) as input variable and a(j) as output variable, high-order polynomial fitting is used to obtain polynomial function C2; Define a set of input variables d, where the input variable d is the expected motion displacement of the treatment bed, and combine it with the polynomial function C2 to obtain the output variable D; Combine the output variable D with the polynomial function C1 to obtain the output variable E; Calculate the average error error_min and maximum error error_max between the output variable E and the input variable d; When the average error error_min and the maximum error error_max are both less than the preset primary intelligent calibration technical parameter P(1), the primary intelligent calibration is completed.

2. The intelligent calibration method for a tumor radiotherapy bed according to claim 1, characterized in that: During the process of controlling the treatment bed to move downward with a fixed motor pulse increment, when the treatment bed descends to the lowest position, the sample point collection is completed and m sample data are obtained.

3. The intelligent calibration method for a tumor radiotherapy bed according to claim 2, characterized in that: When the average error error_min and the maximum error error_max do not meet the preset technical parameter P(1), the treatment bed is controlled to rise to the electrical origin and a new round of primary intelligent calibration process is executed cyclically; In a new round of primary intelligent calibration process, the number of sample data m is modified, and / or the average error error_min and the maximum error error_max between the output variable E and the input variable d are calculated by changing the order of the polynomial function C1 and the polynomial function C2; Determine whether the average error error_min and the maximum error error_max are both less than the preset technical parameter P(1). If so, the primary intelligent calibration is completed. If not, the loop execution continues.

4. The intelligent calibration method for a tumor radiotherapy bed according to claim 1, characterized in that: After the primary intelligent calibration process is completed, a secondary intelligent calibration process is executed, and the secondary intelligent calibration process includes: Control the treatment bed to rise to the electrical origin, and obtain the encoder value F(0) through the encoder set on the treatment bed; Based on the polynomial function C1 and the polynomial function C2 in the primary intelligent calibration process, the treatment bed is controlled to move according to the random target position Z(j) (j=1,2,3,…) within the maximum lifting and lowering motion space of the treatment bed, and the encoder value F(i) (i=1,2,3,…) is obtained through the encoder set on the treatment bed, and n rounds are executed; Convert the encoder value F(i) into a displacement value and remove the offset F(0) to obtain G(i); Calculate the deviation between G(i) and Z(j) to obtain Dv(i,j); Based on the input data set Z(j) and the deviation data set Dv(i,j), a neural network NET is established, training parameters are set, and the neural network NET is trained to obtain a treatment bed lifting motion position deviation prediction model FUN; Combined with the prediction model FUN, the movement of the treatment bed lifting motor is corrected. The average error and maximum error between the target position and the actual position are both less than the preset secondary intelligent scale technical parameter P(2), and the secondary intelligent scale is completed.

5. The intelligent calibration method for a tumor radiotherapy bed according to claim 4, characterized in that: When the average error and the maximum error do not satisfy the preset secondary intelligent calibration technical parameter P(2), a new round of secondary intelligent calibration process is executed cyclically; In a new round of secondary intelligent calibration process, modify the number of rounds n of controlling the treatment bed to execute according to the random target position Z(j), and / or calculate the average error error_min and the maximum error error_max between the output variable E and the input variable d by changing the training parameters of the training neural network NET; It is determined whether the average error and the maximum error are both less than the preset secondary intelligent scale technical parameter P(2). If so, the secondary intelligent scale is completed. If not, the loop execution continues.

6. An intelligent calibration device for the intelligent calibration method of a tumor radiotherapy bed according to any one of claims 1 to 5, characterized in that: include: A treatment bed, comprising a treatment bed board and a driving motor for driving the treatment bed board to move up and down; Data acquisition and positioning device, used to obtain the pulse value of the driving motor and locate the lifting position of the treatment bed; A positioning auxiliary device, comprising an encoder, wherein the encoder is mounted on a treatment bed board; The auxiliary device is placed outside the treatment bed, and comprises a magnetic strip fixing plate, on which a magnetic strip opposite to the encoder is installed.

7. The intelligent calibration device for a tumor radiotherapy bed according to claim 6, characterized in that: The auxiliary device includes a bearing base and a displacement platform, the bearing base is provided with a plurality of supporting feet for adjusting the height and posture of the bearing base, the displacement platform can be installed on the bearing base for reciprocating linear motion, and the magnetic strip fixing plate is installed on the displacement platform; The bearing base is placed outside the treatment bed, and the relative distance between the magnetic strip on the magnetic strip fixing plate and the encoder is adjusted by controlling the displacement platform to perform reciprocating linear motion.

8. The intelligent calibration device for a tumor radiotherapy bed according to claim 7, characterized in that: The auxiliary device comprises an angle adjustment rod group, the bottom end of the magnetic strip fixing plate is rotatably connected to the displacement platform, the top end of the magnetic strip fixing plate is rotatably connected through one end of the angle adjustment rod group, and the other end of the angle adjustment rod group is rotatably connected to the displacement platform; By adjusting the telescopic length of the angle adjustment rod group, the relative angle between the magnetic strip on the magnetic strip fixing plate and the encoder is changed, so that the horizontal distance between the magnetic strip on the fixing plate and the encoder is kept constant.

9. The intelligent calibration device for a tumor radiotherapy bed according to claim 8, characterized in that: The positioning auxiliary device includes a fixing fixture, a connecting plate and a displacement sensor. The fixing fixture is clamped on one side of the treatment bed board, the connecting plate is fixedly connected to the fixing fixture, the displacement sensor and the encoder are installed on the connecting plate, or both, and a positioning straight line parallel to the magnetic strip is arranged on the magnetic strip fixing plate; The bearing base is placed outside the treatment bed, and a detection signal is emitted to the magnetic strip fixing plate through the displacement sensor, and the detection signal is aligned with the positioning straight line; the lifting and lowering movement of the treatment bed board is controlled, and the detection signal emitted by the displacement sensor is monitored to determine whether it is lifted and lowered along the positioning straight line, and the height and posture of the bearing base are changed by adjusting the supporting feet of the bearing base according to the offset between the detection signal and the positioning straight line, until the detection signal emitted by the displacement sensor is lifted and lowered along the positioning straight line; Control the lifting movement of the treatment bed board, monitor the detection signal emitted by the displacement sensor, detect the horizontal distance between the connecting plate and the magnetic strip fixing plate, and adjust the angle adjustment rod group until the horizontal distance between the connecting plate and the magnetic strip fixing plate is constant; The displacement platform is controlled to perform reciprocating linear motion to detect the horizontal distance between the connecting plate and the magnetic strip fixing plate until the relative distance required by the intelligent scale is met.

10. The intelligent calibration device for a tumor radiotherapy bed according to claim 9, characterized in that: The connecting plate has a first fixing position for installing a displacement sensor, and a second fixing position for installing an encoder; the relative horizontal position relationship between the first fixing position and the second fixing position is the same as the relative horizontal position relationship between the magnetic strip and the positioning straight line on the magnetic strip fixing plate.

Images