Real-time image guidance system

Abstract

The present invention relates to a real-time image guidance system, and relates to the field of image guidance technology. The real-time image guidance system of the present invention includes an image robot, which includes a first image robot and a second image robot. The first image robot can dynamically adjust its posture and position so that the imaging beam it emits can be received by the second image robot; the second image robot can dynamically adjust its posture and position so that the imaging beam it emits can be received by the first image robot, and the imaging beam emitted by the first image robot and the imaging beam emitted by the second image robot intersect at a specified position to obtain a three-dimensional real-time image. The real-time image guidance system of the present invention can avoid the problem of introducing new errors by requiring multiple positioning of the patient; and because the first image robot and the second image robot can dynamically adjust their posture and position, the treatment efficiency and patient compliance can be improved.

Description

Technical Field

[0001] The present invention relates to the field of image guidance technology, and in particular to a real-time image guidance system. Background Art

[0002] The CyberKnife image-guided system in radiotherapy equipment can clearly display the patient's internal anatomy and tumor location, providing accurate imaging information for subsequent treatment. It typically consists of an X-ray source that emits X-rays and a digital image detector that receives them. However, because the source is mounted on the treatment room ceiling, the X-ray convergence point is fixed, limiting the therapeutic beam to tumors located near it. Tumors located further away from this convergence point cannot be tracked in real time, requiring patient repositioning to bring the treatment area closer to the convergence point. However, each patient repositioning not only introduces new errors and reduces treatment accuracy, but also significantly reduces treatment efficiency due to the need for multiple imaging verifications, impacting patient compliance. Summary of the Invention

[0003] The present invention provides a real-time image guidance system for solving at least one of the above-mentioned technical problems.

[0004] The present invention provides a real-time image guidance system, comprising:

[0005] An imaging robot comprising a first imaging robot and a second imaging robot, wherein the first imaging robot is capable of dynamically adjusting its posture and position so that an imaging beam emitted by it can be received by the second imaging robot; the second imaging robot is capable of dynamically adjusting its posture and position so that an imaging beam emitted by it can be received by the first imaging robot, and the imaging beams emitted by the first imaging robot and the imaging beams emitted by the second imaging robot intersect at a specified position to obtain a three-dimensional real-time image; and

[0006] A treatment robot is used to generate a treatment beam. The treatment robot adjusts its posture and displacement according to the degree of three-dimensional alignment between the three-dimensional real-time image obtained by the imaging robot and the three-dimensional planned image, so that the treatment beam it generates is aligned with the specified position.

[0007] In one embodiment, the first imaging robot includes a first imaging mechanical arm, a first imaging support connected to the first imaging mechanical arm, and a first X-ray generator and a first X-ray receiver respectively rotatably connected to the first imaging support;

[0008] The second imaging robot includes a second imaging mechanical arm, a second imaging support connected to the second imaging mechanical arm, and a second X-ray generator and a second X-ray receiver respectively connected to the second imaging support;

[0009] The first imaging robot arm and the second imaging robot arm can synchronously adjust their abduction or adduction distances. The first X-ray generator or the first X-ray receiver can adjust its rotation angle relative to the first imaging support. The second X-ray generator or the second X-ray receiver can adjust the angle of rotation relative to the second imaging support. .

[0010] In one embodiment, the first imaging robot and / or the second imaging robot can dynamically adjust its posture and position so that the imaging beam emitted by the first X-ray generator and the imaging beam emitted by the second X-ray generator intersect at a specified position, and the intersection area can cover the specified position, and the area of ​​the intersection area is obtained according to the following relationship:

[0011]

[0012] in, A is the area of ​​the intersection;

[0013] D is the distance between the first X-ray generator and the second X-ray receiver, or the distance between the second X-ray generator and the first X-ray receiver;

[0014] α It is the angle between the imaging beam emitted by the first X-ray generator and the imaging beam emitted by the second X-ray generator.

[0015] In one embodiment, the angle through which the first X-ray generator or the first X-ray receiver rotates relative to the first imaging support The following relationship is satisfied:

[0016] The angle of rotation of the second X-ray generator or the second X-ray receiver relative to the second imaging support The following relationship is satisfied:

[0017] ;

[0018] An adjustment angle of the first X-ray generator or the first X-ray receiver;

[0019] An adjustment angle of the second X-ray generator or the second X-ray receiver;

[0020] is the angular error between the first image support and the second image support at the current moment

[0021] is the proportionality coefficient;

[0022] is the integration coefficient;

[0023] is the differential coefficient.

[0024] In one embodiment, the first imaging robot arm and the second imaging robot arm synchronously adjust their abduction or adduction distance according to the following relationship: :

[0025] );

[0026] in, ΔS The displacement between the position of the key feature point in the 3D real-time image at the current moment and the position of the feature point at the previous moment;

[0027] α It is the angle between the imaging beam emitted by the first X-ray generator and the imaging beam emitted by the second X-ray generator.

[0028] In one embodiment, the first imaging robot and the second imaging robot extract feature points of different scales in the three-dimensional real-time image according to the pre-trained model and select key feature points. The first imaging robot arm and the second imaging robot arm synchronously adjust their abduction or retraction distance according to the key feature points. , wherein the feature point is a bony landmark point,

[0029] In one embodiment, the first imaging support is provided with a first hinge device and a second hinge device, and the rotating joint of the first hinge device and the rotating joint of the second hinge device are respectively connected to the first X-ray generator and the first X-ray receiver, so that the first X-ray generator and the first X-ray receiver can adjust their rotation angles relative to the first imaging support;

[0030] A third hinge device and a fourth hinge device are provided on the second image support. The rotating joint of the third hinge device and the rotating joint of the fourth hinge device are respectively connected to the second X-ray generator and the second X-ray receiver, so that the second X-ray generator and the second X-ray receiver can adjust their rotation angle relative to the first image support.

[0031] In one embodiment, the first vision robot and / or the second vision robot adjusts its posture and position based on a real-time collision avoidance algorithm and a fast random tree algorithm.

[0032] In one embodiment, the treatment robot includes a treatment robotic arm and a treatment head connected to the treatment robotic arm. When the treatment head generates a treatment beam, the first X-ray generator and the first X-ray receiver and the second X-ray generator and the second X-ray receiver are all outside the beam range of the treatment beam.

[0033] Compared with the existing technology, the advantage of the present invention is that the first imaging robot and the second imaging robot can adjust their posture and position to obtain three-dimensional real-time images of specified positions in real time, thereby automatically adjusting the direction of the imaging light beam, avoiding the need to position the patient multiple times and introducing new errors; and because the first imaging robot and the second imaging robot can dynamically adjust their posture and position, the treatment efficiency and patient compliance can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Hereinafter, the present invention will be described in more detail based on embodiments with reference to the accompanying drawings.

[0035] Figure 1a is a schematic diagram of the three-dimensional structure of a real-time image guidance system in an embodiment of the present invention;

[0036] Figure 1b is a top view of a real-time image guidance system according to an embodiment of the present invention;

[0037] Figure 2 is a schematic diagram of the three-dimensional structure of the real-time image guidance system in an embodiment of the present invention, wherein the treatment robot is hidden;

[0038] Figure 3a and Figure 3b is a schematic diagram of the three-dimensional structure of a first imaging robot in an embodiment of the present invention;

[0039] Figure 3c is a schematic diagram of the three-dimensional structure of the second imaging robot in an embodiment of the present invention;

[0040] Figure 4 yes Figure 3a A schematic diagram of the three-dimensional structure of the first imaging support;

[0041] Figure 5 and Figure 6 yes Figure 4 A schematic diagram of the three-dimensional structure of the first hinge device;

[0042] Figure 7 yes Figure 4 A schematic diagram of the three-dimensional structure of the second hinge device;

[0043] Figure 8is a schematic diagram of the three-dimensional structure of the real-time image guidance system in an embodiment of the present invention, which shows the cone-beam CT scanning trajectory of the imaging robot;

[0044] Figure 9 and Figure 10 yes Figure 8 A view showing the intersection of the first imaging beam and the second imaging beam;

[0045] Figure 11 yes Figure 1a Schematic diagram of the three-dimensional structure of the treatment robot.

[0046] Reference numerals:

[0047] 100, first imaging robot; 200, second imaging robot; 300, treatment robot; 400, treatment bed; 500, patient;

[0048] 110, first imaging robot arm; 120, first imaging support; 130, first X-ray generator; 140, first X-ray receiver; 101, first imaging beam; 102, intersection area; 103, cone-beam CT scanning trajectory;

[0049] 111. First arm; 112. Second arm; 113. Third arm; 114. Fourth arm; 115. Base; 116. Flange; 117. Support claw;

[0050] 121. First hinge assembly; 122. Second hinge assembly; 123. First rotation joint; 124. Second rotation joint; 125. First rotation support; 126. Second rotation support;

[0051] 1231, upper booth; 1232, lower booth;

[0052] 210, second imaging robot arm; 220, second imaging support; 230, second X-ray generator; 240, second X-ray receiver; 201, second imaging beam;

[0053] 310. Treatment robot arm; 320. Treatment head; 301. Treatment beam; DETAILED DESCRIPTION

[0054] The present invention will be further described below with reference to the accompanying drawings.

[0055] like Figure 1a and Figure 1b As shown, the present invention provides a real-time image guidance system, including an image robot and a treatment robot 300. Figure 2As shown, the imaging robot includes a first imaging robot 100 and a second imaging robot 200 symmetrically arranged with the patient 500 as the center. The first imaging robot 100 can adjust its posture and position so that the imaging beam it emits can be received by the second imaging robot 200; similarly, the second imaging robot 200 can adjust its posture and position so that the imaging beam it emits can be received by the first imaging robot 100. The imaging beams emitted by the first imaging robot 100 and the imaging beams emitted by the second imaging robot 200 intersect at a specified position to obtain a three-dimensional real-time image.

[0056] The treatment robot 300 is used to generate the treatment beam. It adjusts its posture and displacement based on the degree of 3D registration between the real-time 3D image acquired by the imaging robot and the 3D planning image, ensuring that the generated treatment beam 301 is consistently aligned with the designated location (lesion location). The real-time 3D image is the DRR (Digitally Reconstructed Radiography) image acquired by the imaging robot during treatment, while the 3D planning image is the DRR (Digitally Reconstructed Radiography) image acquired by the imaging robot before treatment or generated by a CT scan. 3D registration allows two images, either from the same or different sources, that are relevant to the patient's anatomy to be precisely aligned in 3D space, enabling better planning, evaluation, and implementation of radiotherapy treatment plans.

[0057] like Figure 3a and Figure 3b As shown, the first imaging robot 100 includes a first imaging robot arm 110, a first imaging support 120 connected to the first imaging robot arm 110, and a first X-ray generator 130 and a first X-ray receiver 140 respectively connected to the first imaging support 120. Figure 3c As shown, the second imaging robot 200 includes a second imaging robot arm 210 , a second imaging support 220 connected to the second imaging robot arm 210 , and a second X-ray generator 230 and a second X-ray receiver 240 rotatably connected to the second imaging support 220 .

[0058] The first X-ray generator 130 and the second X-ray receiver 240 are aligned with each other, so that the first X-ray generator 130 emits the first imaging beam 101 (X-ray beam) to the second X-ray receiver 240; similarly, the second X-ray generator 230 and the first X-ray receiver 140 are aligned with each other, so that the second X-ray generator 230 emits the first imaging beam 201 (X-ray beam) to the first X-ray receiver 140. Figure 2 、 Figure 9 and Figure 10 As described above, the first imaging beam 101 and the second imaging beam 201 intersect each other at a designated position (eg, a lesion position).

[0059] The first X-ray receiver 140 and the second X-ray receiver 240 can receive X-rays emitted by corresponding X-ray emitters and convert them into digital signals to form a three-dimensional image.

[0060] The first imaging robot arm 110 and the second imaging robot arm 210 may adopt the same configuration. The following description will take the first imaging robot arm 110 as an example.

[0061] like Figure 3a As shown, the first imaging robot arm 110 includes a first arm 111, a second arm 112, a third arm 113, a fourth arm 114 and a base 115. The front end of the first arm 111 is connected to the first imaging bracket 120. Figure 4 As shown, the first image support 120 is provided with a flange 116 having a plurality of supporting claws 117, and the flange 116 is rotatably connected to the front end of the first arm 111. Therefore, the first arm 111 can rotate relative to the first image support 120 with the axis of the flange 116 as the rotation axis.

[0062] like Figure 4 As shown, the rear end of the first arm 111 is constructed as a U-shaped structure, and a rotating shaft perpendicular to the U-shaped opening is provided in the U-shaped structure. Figure 3a The front end of the second arm 112 is rotatably connected to the rotating shaft, so that the second arm 112 can rotate relative to the first arm 111 with the rotating shaft as the rotating axis; in addition, the second arm 112 can also rotate with its own axis as the rotating axis.

[0063] Please continue to see Figure 3a The rear end of the second arm 112 is rotatably connected to the front end of the third arm 113, the rear end of the third arm 113 is rotatably connected to the front end of the fourth arm 114, and the fourth arm 114 is rotatably connected to the base 115. Therefore, the third arm 113 and the second arm 112, the third arm 113 and the fourth arm 114, and the fourth arm 114 and the base 115 can all rotate relative to each other. Furthermore, the connecting cables of the various arms of the first imaging robot 110 can converge at the fourth arm 114 and connect to external devices such as a control unit or power supply unit through the base 115.

[0064] like Figure 4 As shown, a flange 116 with multiple supporting claws 117 is provided on one side of the first imaging support 120. The supporting claws 117 are spaced apart along the circumference of the flange 116 to provide support and stability. A first X-ray generator 130 and a first X-ray receiver 140 are connected to the other side of the first imaging support 120.

[0065] Specifically, if Figure 4 and Figure 5As shown, the first image support 120 is provided with a first hinge device 121 and a second hinge device 122. Figure 5 As shown, the first hinge assembly 121 includes a first rotation joint 123 and a first rotation support 125. The first rotation support 125 is fixedly connected to the first image support 120, and the rear end of the first rotation joint 123 is rotationally connected to the first rotation support 125. The first rotation joint 123 and the first rotation support 125 can be connected by a rotating shaft, so that the first rotation joint 123 can rotate about the rotating shaft; or the first rotation support 125 can be configured as a spherical seat, forming a spherical connection between the first rotation joint 123 and the first rotation support 125, so that the first rotation joint 123 can rotate in all directions.

[0066] The front end of the first rotating joint 123 is connected to the first X-ray generator 130. Therefore, when the first rotating joint 123 rotates relative to the first hinge device 121, it can drive the first X-ray generator 130 to transmit, thereby adjusting the angle of rotation of the first X-ray generator 130 relative to the first imaging bracket 120.

[0067] like Figure 6 As shown, the first rotating joint 123 includes an upper clamping seat 1231 and a lower clamping seat 1232 , which are engaged to form a columnar space in the middle to accommodate the first X-ray generator 130 .

[0068] The second hinge device 122 has a similar structure to the first hinge device 121. Figure 7 As shown, the second hinge assembly 122 includes a second rotational joint 124 and a second rotational support 126. The second rotational support 126 is fixedly connected to the first image support 120. The second rotational support 126 and the first rotational support 125 are respectively located at the left and right ends of the first image support 120. The rear end of the second rotational joint 124 is rotationally connected to the second rotational support 126. The second rotational joint 124 and the second rotational support 126 can be connected by a rotating shaft, so that the second rotational joint 124 can rotate about the rotating shaft; or the second rotational support 126 can be constructed as a spherical seat, forming a spherical connection between the second rotational joint 124 and the second rotational support 126, so that the second rotational joint 124 can rotate in all directions.

[0069] The front end of the second rotating joint 124 is connected to the first X-ray receiver 140. The first X-ray receiver 140 is constructed as a roughly flat structure. The second rotating joint 124 can adaptively adjust its structural shape according to the first X-ray receiver 140, so that when the second rotating joint 124 rotates relative to the second hinge device 122, it can drive the first X-ray receiver 140 to transmit, thereby adjusting the angle of rotation of the first X-ray receiver 140 relative to the first imaging bracket 120.

[0070] The first rotation joint 123 and the second rotation joint 124 may be connected to a power unit (eg, a motor) to drive the power unit to rotate.

[0071] The second imaging robot arm 210 has the same structure and configuration as the first imaging robot arm 110. For example, the second imaging support 220 is provided with a third hinge device (which can adopt the same configuration as the first hinge device 121) and a fourth hinge device (which can adopt the same configuration as the second hinge device 122), which are respectively connected to the second X-ray generator 230 and the second X-ray receiver 240.

[0072] Therefore, it can be understood that when the first X-ray generator 130 on the first imaging robot arm 110 adjusts its rotation angle relative to the first imaging support 120, the second X-ray receiver 240 on the second imaging robot arm 210 also needs to adjust its rotation angle relative to the second imaging support 220 accordingly to ensure that the first imaging beam 101 emitted by the first X-ray generator 130 can be accurately received by the second X-ray receiver 240 on the opposite side of the device. Similarly, when the second X-ray generator 230 on the second imaging robot arm 210 adjusts its rotation angle relative to the second imaging support 220, the first X-ray receiver 140 on the first imaging robot arm 110 also needs to adjust its rotation angle relative to the first imaging support 120 accordingly to ensure that the second imaging beam 201 emitted by the second X-ray generator 230 can be accurately received by the first X-ray receiver 140 on the opposite side of the device.

[0073] When the first imaging robot arm 110 and the second imaging robot arm 210 adjust their postures and positions, the two move in coordination. Figure 8 As shown, when performing cone-beam CT scanning before or during radiotherapy, the first imaging robot arm 110 and the second imaging robot arm 210 perform circular motion with the designated position (lesion position) as the center, so that their cone-beam CT scanning trajectory is a circle with the lesion position as the center; and they always maintain a parallel positional relationship with each other (for example, the first imaging support 120 and the second imaging support 220 remain parallel to each other) and maintain the distance between the first X-ray generator 130 and the second X-ray receiver 240 (source-image distance SID) and the distance between the second X-ray generator 230 and the first X-ray receiver 140 (source-image distance SID) equal. For example, the first imaging robot arm 110 and the second imaging robot arm 210 can synchronously adjust their extension or retraction distances. The first X-ray generator 130 or the first X-ray receiver 140 can adjust its rotation angle relative to the first imaging support 120. The second X-ray generator 230 or the second X-ray receiver 240 can adjust its rotation angle relative to the second imaging support 220. In addition, the first imaging robot arm 110 and the second imaging robot arm 210 adjust their outward or inward distances, thereby changing the distance between the first imaging support 120 and the second imaging support 220. Accordingly, the angles between the first X-ray generator 130 and the second X-ray receiver 240 and the angles between the second X-ray generator 230 and the first X-ray receiver 140 need to be adjusted to ensure that the imaging beam can be accurately received by the X-ray receiver on the opposite side.

[0074] The source-image distance (SID) is related to the designated location (or target location). For example, if the designated location is on the patient's head, the SID is small (i.e., the distances between the first X-ray generator 130 and the second X-ray receiver 240, and between the second X-ray generator 230 and the first X-ray receiver 140, are relatively close). If the designated location is on the patient's lungs, the SID is large (i.e., the distances between the first X-ray generator 130 and the second X-ray receiver 240, and between the second X-ray generator 230 and the first X-ray receiver 140, are relatively far). Therefore, the SID of the first and second imaging robot arms 110 and 210 must be adjusted based on the designated location.

[0075] The first imaging robot 100 and / or the second imaging robot 200 can adjust their posture and position so that the first imaging beam 101 emitted by the first X-ray generator 130 and the second imaging beam 201 emitted by the second X-ray generator 230 intersect at a specified position, and the intersection area 102 (such as Figure 9 As shown in FIG. 1 , the area of ​​the intersection region 102 can cover the specified position, and the area of ​​the intersection region 102 is obtained according to the following relationship: .

[0076] in, A is the area of ​​the intersection; D is the distance between the first X-ray generator 130 and the second X-ray receiver 240 (source-image distance SID), or the distance between the second X-ray generator 230 and the first X-ray receiver 140 (source-image distance SID). Figure 10 As shown, α is the angle between the first imaging beam 101 emitted by the first X-ray generator 130 and the second imaging beam 202 emitted by the second X-ray generator 230, for example α It can be adjusted within the range of 90°±5°.

[0077] Optionally, whether the intersection of the first imaging beam 101 and the second imaging beam 201 covers the designated location (or whether the coverage of the intersection meets the required standards) can be determined by the number of key feature points in the intersection. For example, if the number of key feature points in the intersection is greater than or equal to 10, it can be considered that the intersection covers the designated location or that the coverage of the intersection meets the required standards. If the number of key feature points in the intersection is less than 10, additional manually marked feature points can be added.

[0078] Alternatively, whether the intersection of the first imaging beam 101 and the second imaging beam 201 covers the designated location (or whether the coverage of the intersection meets the standard) can be determined by comparing the area of ​​the intersection with the area of ​​the designated location. For example, if the area of ​​the intersection is larger than the area of ​​the designated location (lesion location), it can be considered that the intersection covers the designated location or that the coverage of the intersection meets the standard.

[0079] On the contrary, if the intersection area fails to cover the specified position (or the coverage of the intersection area does not meet the standard), secondary parameter optimization can be performed, that is, the posture and position of the first imaging robot 100 and / or the second imaging robot 200 are adjusted again until the intersection area can cover the specified position (or the coverage of the intersection area can meet the standard).

[0080] The first imaging robot 100 and the second imaging robot 200 cooperate with PID control to adjust their posture and position so that the X-ray generator and X-ray receiver on the two can be dynamically balanced. The angle of rotation of the first X-ray generator 130 or the first X-ray receiver 140 relative to the first imaging support 120 is The following relationship is satisfied:

[0081] The angle through which the second X-ray generator 230 or the second X-ray receiver 240 rotates relative to the second imaging support 220 The following relationship is satisfied:

[0082] .

[0083] It is the adjustment angle of the first X-ray generator 130 or the first X-ray receiver 140. The adjustment angle of the second X-ray generator 230 or the second X-ray receiver 240 .

[0084] is the angular error between the first image support 120 and the second image support 220 at the current moment.

[0085] In the above formula, The proportional term means that the control unit is adjusted according to the current error amplitude; for example, according to the size of the current displacement deviation, a control quantity proportional to the deviation can be quickly output, thereby quickly correcting the current error.

[0086] is the integral term, which means that the control unit accumulates historical displacement deviations and gradually eliminates the accumulated error caused by the static error of the system over time;

[0087] It is a differential term, that is, the control unit predicts the changing trend of the error, outputs the control quantity in advance, enhances the stability of the system and prevents overshoot.

[0088] is the proportional coefficient, which directly affects the response speed of the image robot to the current error. The larger the value, the faster the response. However, too large a value may cause overshoot and oscillation. The integral coefficient can eliminate steady-state errors and adjust the output by accumulating historical errors. However, excessive integration may lead to integral saturation or oscillation. is the differential coefficient, which can predict the error change trend and suppress overshoot and oscillation, but is sensitive to noise and may amplify high-frequency interference.

[0089] When adjusting the first X-ray generator 130 or the first X-ray receiver 140, Determine the reaction strength when it is tilted relative to the first image support 120; Correcting long-term tilt, Avoid violent shaking.

[0090] against or The optimization strategies include: adaptive parameter adjustment or fuzzy fusion control.

[0091] Among them, adaptive parameter adjustment means dynamically adjusting the PID parameters according to the change of error during the control process. For example, when the error is large, increase value to speed up the response; when the error is close to zero, reduce and increase value to eliminate steady-state errors.

[0092] Fuzzy fusion control introduces fuzzy control theory, divides errors and error change rates into different fuzzy sets according to their different ranges, and dynamically adjusts PID parameters through fuzzy rule tables, thereby improving the robustness and adaptability of the system. as well as , for example, first adjust , and finally adjust .

[0093] For example, first use only proportional control (i.e. =0, =0): Step increase , until the system has critical oscillation (such as overshoot or periodic fluctuation), then Recorded as critical value , and record the oscillation period . Then the integral control (i.e. ≠0): from the smaller Start with , and gradually increase to eliminate steady-state errors. Set to 1 / 10~1 / 2 of the original value. Then add differential control ( ≠0): =0.1 At the beginning, gradually increase it to suppress overshoot, but pay attention to the influence of noise.

[0094] In addition, automatic tuning methods such as the Ziegler-Nichols critical ratio method can also be used for automatic adjustment.

[0095] In one embodiment, For example, it can be 0.5, It can be 0.1, For example, it can be 0.05.

[0096] The optimal value is calculated by the proportional term, integral term and differential term in the above formula. , so that the first X-ray generator 130 or the first X-ray receiver 140 gradually rotates the adjustment angle, thereby gradually reducing the angle error between the first image support 120 and the second image support 220 at the current moment . =the angle between the first image support 120 and the second image support 220 at the current moment - 180°, that is, the target angle (the angle between the first image support 120 and the second image support 220 at the current moment) is 180° (that is, the first image robot 100 and the second image robot 200 are parallel to each other).

[0097] In a specific embodiment, the angle adjustment amount of the first imaging robot 100 and the second imaging robot 200 is obtained based on the displacement of the feature point. and The process is as follows.

[0098] First, the deep learning automatic feature recognition module can be used to detect the parallelism deviation between the corresponding feature points of the first and second vision robots 100 and 200. As mentioned above, in the initial state, the first X-ray generator 130 of the first vision robot 100, the second vision robot 200, and the second X-ray receiver 240 (or the first X-ray receiver 140 of the first vision robot 100, the second vision robot 200, and the second X-ray generator 230) are strictly parallel, with a theoretical angle of 180°.

[0099] At a certain moment, the deep learning automatic feature recognition module detects that the current angle becomes 181°, then the angle error for:

[0100]

[0101] According to the above PID control formula (1): in, Take 0.5, Take 0.1, Take 0.05; and at the current moment, the integral term Since the error is just beginning to accumulate, its value is small (can be set to 0.1), and the differential term Set to 0 (because the error change rate is small at this moment).

[0102] therefore The calculation process is as follows:

[0103]

[0104] That is, the first vision robot 100 needs to rotate 0.51° clockwise, and the second vision robot 200 needs to rotate 0.51° counterclockwise to restore the parallelism between the two (and vice versa).

[0105] As described above, when the first X-ray generator 130 on the first imaging robot 110 adjusts its rotation angle relative to the first imaging support 120, the second X-ray receiver 240 on the second imaging robot 210 also needs to adjust its rotation angle relative to the second imaging support 220 accordingly. For example, if the first X-ray generator 130 adjusts + When the second X-ray receiver 240 adjusts .

[0106] The first imaging robot arm 110 and the second imaging robot arm 210 are both provided with sensors (angle sensors or magnetic sensors) to obtain the angles (current angles) through which the above-mentioned X-ray generators and X-ray receivers have rotated, or the current angles can be obtained through encoders of motors that drive the above-mentioned X-ray generators and X-ray receivers to rotate.

[0107] The first imaging robot arm 110 and the second imaging robot arm 210 synchronously adjust their extension or retraction distances according to the following relationship: :

[0108] ) (2).

[0109] in, ΔS The displacement between the position of the key feature point in the 3D real-time image at the current moment and the position of the feature point at the previous moment; αThe angle between the first imaging beam 101 emitted by the first X-ray generator 130 and the second imaging beam 201 emitted by the second X-ray generator 230 is defined as the angle between the first imaging beam 101 and the second imaging beam 201. By adjusting the distance between the extension and retraction of the first imaging robot arm 110 and the second imaging robot arm 210, a dynamic source-image distance (SID) compensation mechanism is established to ensure that the first imaging beam 101 and the second imaging beam 102 converge at the designated location (target point), thereby achieving continuous and accurate coverage of the intersection area 102 during the control process.

[0110] The abduction of the first image robotic arm 110 means that the first image robotic arm 110 is extended toward the second image robotic arm 210, and the adduction of the first image robotic arm 110 means that the first image robotic arm 110 is retracted away from the second image robotic arm 210. The second robotic arm 210 is similar.

[0111] against The optimization strategies include: predictive adjustment and multi-objective optimization.

[0112] Predictive adjustment is achieved by analyzing the historical data of feature point displacement and establishing a displacement prediction model to predict in advance. ΔS of the changing trend, so as to make to reduce the lag of adjustment.

[0113] Multi-objective optimization is to adjust When performing the target area, not only the need to cover the intersection area should be considered, but also the need to avoid collision with the bed, patient or treatment head 320. Multi-objective optimization algorithms such as genetic algorithms can optimize multiple objective functions at the same time to find the optimal In one embodiment, the adjustment amount of the source image distance SID is calculated based on the displacement of the feature points. The process is as follows.

[0114] At this moment, the deep learning automatic feature recognition module detects the horizontal displacement of the feature point ΔS =5mm, and the angle between the first imaging beam 101 emitted by the first X-ray generator 130 and the second imaging beam 201 emitted by the second X-ray generator 230 (ie, the double beam angle) is α is 90°.

[0115] According to the above formula (2):

[0116] That is, the first imaging robot arm 110 and the second imaging robot arm 210 need to be extended synchronously (when ΔS is positive) or synchronous adduction (when ΔS is negative) about 7.07 mm; and simultaneously adjust the angles of the first hinge assembly and the second hinge assembly to keep the X-ray beams converging on the target.

[0117] Therefore, the PID control strategy of the first imaging robot 100 and the second imaging robot 200 is a PID compensation control based on the displacement between the position of the key feature point in the three-dimensional real-time image at the current moment and the position of the feature point at the previous moment, which can solve the problem of easy accumulation of errors in the synchronous movement of traditional robotic arms.

[0118] As described above, during compensation control, the first and second robot arms 100 and 200 each adjust their joint movements in real time based on the control parameters output by the control unit (PID controller). This approach dynamically corrects each movement based on the actual error at the previous moment. This prevents the first and second robot arms 100 and 200 from carrying over errors from the previous movement into the next, thus addressing the error accumulation problem associated with conventional robotic arm synchronization. Furthermore, the system continuously monitors the positions of key feature points and repeats this process, creating a closed-loop control system that ensures high-precision synchronization between the first and second robot arms 100 and 200 throughout the entire operation.

[0119] The first and second imaging robots 100 and 200 can extract feature points of varying scales from 3D real-time images based on a pre-trained model and select key feature points. Feature points can be bony landmarks. For example, the pre-trained model can be a bony landmark detection model trained using a deep convolutional neural network (e.g., a ResNet + Faster R-CNN architecture). The first and second imaging robots 100 and 200 can identify over 20 anatomical landmarks from 3D real-time images, including cranial sutures, vertebral spinous processes, and rib intersections. These feature points are then deduplicated using the non-maximum suppression (NMS) algorithm, retaining the most prominent ones. Ultimately, only those meeting a threshold (e.g., a confidence level >90%) are retained as key feature points. This allows for synchronous adjustment of the posture and position of the first and second imaging robots 100 and 200.

[0120] The first imaging robot 100 and the second imaging robot 200 dynamically adjust their posture and position based on the feature points and their displacements obtained through deep learning detection, that is, the automatic feature point recognition and imaging robot adjustment linkage mechanism are adopted to realize the closed-loop control of "detection-analysis-adjustment".

[0121] When adjusting their posture and position, the first imaging robot 100 and / or the second imaging robot 200 adjust their posture and position based on a real-time collision avoidance algorithm and a fast random tree algorithm (RRT) to avoid collisions with the treatment couch 400, the patient 500 on the treatment couch 400, the treatment head 320, and other objects that may block the movement of the first imaging robot 100 and / or the second imaging robot 200.

[0122] like Figure 11 As shown, the treatment robot 300 includes a treatment arm 310 and a treatment head 320 located at the front end of the treatment arm 310. The treatment arm 310 can adopt the same structure as the above-mentioned imaging robot arms, and its front end can be connected to the treatment head 320 through a flange, so that its relative position with the treatment head 320 can be adjusted.

[0123] The treatment head 320 includes a treatment beam generating component and a treatment beam shaping component (such as a multi-leaf grating). The treatment beam generating component is used to generate a cone-shaped treatment beam 301, and the treatment beam shaping component controls its shape to produce a specific shape suitable for each specific field of clinical treatment.

[0124] During real-time image-guided control, each imaging robot adjusts its posture and position, aligning the treatment beam 301 generated by the treatment head 320 with the designated location (lesion location). Each imaging robot adjusts its position to remain outside the beam range of the treatment beam 301 to avoid damage from exposure. During the control process, each imaging robot continuously acquires imaging information of the patient 500 and compares and analyzes it with the 3D planning image (e.g., the DRR generated by a pre-radiotherapy CT scan) to promptly identify discrepancies between the lesion location and the planned location. The control unit of the real-time image-guided system calculates the required direction and displacement of the treatment head 320 based on the degree of three-dimensional registration between the real-time image data (including lesion location, patient position changes, and other information) and the 3D planning image. The treatment arm 310 then adjusts the posture and position of the treatment head 320 in real time, ensuring that the treatment head 320 remains aligned with the lesion. During the adjustment process, each imaging robot continuously monitors the patient 500's imaging information to ensure accurate adjustments and effective control.

[0125] Example 1

[0126] During the image-guided control process using the real-time image guidance system described above, the patient lies flat on the treatment bed, the treatment head 320 is installed at the end of the treatment robot arm 310 and is located at the head of the treatment bed, and the first image robot 100 and the second image robot 200 are respectively deployed on both sides of the treatment bed.

[0127] During image-guided control, the first and second imaging robots 100 and 200 must adjust their posture and position in real time to ensure that the intersection of the X-ray beams accurately covers the target location while avoiding the risk of collision with the treatment couch, the patient's body, and the treatment head 320. Therefore, the specific process for adjusting the posture and position of the first and second imaging robots 100 and 200 is as follows.

[0128] First, in the initial state, the positions of the robots are: the initial coordinates of the first image robot 100 are , the initial coordinates of the second image robot are .

[0129] In the initial state, the postures of the robots are: the initial angle of the first image robot 100 is ; The initial angle of the second imaging robot 100 is .

[0130] In the initial state, the distance between the first X-ray generator 130 and the second X-ray receiver 240 (source-image distance SID) and the distance between the second X-ray generator 230 and the first X-ray receiver 140 (source-image distance SID) are respectively and .

[0131] Obstacle information: Data is collected through sensors such as lidar and visual cameras to construct a three-dimensional obstacle map that includes the position and shape information of obstacles such as the bed board of the treatment bed, the patient, and the treatment head 320.

[0132] Second, the target state is:

[0133] Target position: Calculate the target coordinates of the first imaging robot 100 based on the three-dimensional coordinates of the target position and the target coordinates of the second imaging robot 200 .

[0134] Target posture: The target angle of the first imaging robot 100 is , the second image robot target angle is The distance between the first X-ray generator 130 and the second X-ray receiver 240 (source-image distance SID) and the distance between the second X-ray generator 230 and the first X-ray receiver 140 (source-image distance SID) are respectively and . Third, the specific adjustment process is as follows.

[0135] The RRT algorithm is used for path planning, which includes the following steps:

[0136] The first step, sampling: in three-dimensional space , , Randomly generate points within the range .

[0137] The sampling range is , (unit: cm), its purpose is to define the sampling area in three-dimensional space.

[0138] The second step is to find the nearest node: find the node closest to the sampling point in the constructed fast random tree (RRT) .

[0139] The third step is to expand the tree: extend the distance from the nearest node to the sampling point , get the new node .

[0140] Among them, the extended distance It can be 5cm, which is used to define the length of each tree expansion.

[0141] Step 4, collision detection: Using a real-time collision avoidance algorithm, check whether the new node collides with obstacles such as the bed board, patient, and treatment head 320 in the three-dimensional obstacle map; if not, include the new node in the RRT tree; if so, discard the node and resample.

[0142] Step 5: Repeat the iteration: Loop through steps 1 to 4 until a feasible path from the initial node to the target node is found.

[0143] The maximum number of iterations is set to 1000 to avoid an infinite loop in the algorithm.

[0144] The calculation process of attitude and position adjustment is as follows:

[0145] Attitude adjustment amount : Calculate the posture adjustment amount of the first image robot 100 according to the planned path , the second image robot posture adjustment amount .

[0146] The angular resolution is 0.1°, which is the minimum adjustment angle of the postures of the first imaging robot 100 and the second imaging robot 200 .

[0147] Position adjustment amount : Calculate the source image distance adjustment value of the first vision robot 100 , the source image distance adjustment amount of the second imaging robot 200 .

[0148] The position resolution is 1 mm, that is, the minimum position adjustment distance of the first imaging robot 100 and the second imaging robot 200 .

[0149] Furthermore, the optimization strategy of the above RRT algorithm is as follows:

[0150] A bidirectional RRT algorithm is used, that is, RRT trees are constructed from the initial node and the target node at the same time. When the two trees meet, a path is quickly generated, which can significantly shorten the search time. Heuristic sampling is also used, that is, the sampling probability distribution is set according to the position of the target node, and sampling is prioritized near the target area to improve path search efficiency.

[0151] The posture and position adjustment optimization strategy utilizes both smooth and dynamic adjustments. Smooth adjustment utilizes a polynomial interpolation algorithm to generate smooth motion trajectories for the first and second image robots 100 and 200, preventing violent movements from impacting control accuracy and equipment. Real-time dynamic adjustment utilizes sensors to monitor the position and shape of obstacles in real time, dynamically correcting the path and posture based on the latest data to ensure safe and accurate control.

[0152] and as well as and The corresponding relationship is as follows:

[0153] After the RRT algorithm path planning is completed, the posture adjustment amount of each image robot at each step is calculated according to the posture and position information of the adjacent nodes in the path. 、 and position adjustment .

[0154] For example, the first imaging robot 100 is from the node i Move to Node i +1, Node i The posture is ,node i The position (source image distance SID) is ,node i +1 for the posture , the location is , then the attitude adjustment amount of this step is , position adjustment amount .

[0155] The second imaging robot 200 is connected to the slave node j Move to Node j +1, Node j The posture is ,node i The position (source image distance SID) is ,node j +1 for the posture , the location is , then the attitude adjustment amount of this step is , position adjustment amount .

[0156] While the present invention has been described with reference to preferred embodiments, various modifications may be made and equivalent components may be substituted without departing from the scope of the present invention. In particular, the various technical features described in the various embodiments may be combined in any manner, provided no structural conflicts exist. The present invention is not limited to the specific embodiments disclosed herein, but encompasses all technical solutions within the scope of the claims.

Claims

1. A real-time image guidance system, characterized in that: include: An imaging robot comprising a first imaging robot and a second imaging robot, wherein the first imaging robot is capable of dynamically adjusting its posture and position so that an imaging beam emitted by it can be received by the second imaging robot; the second imaging robot is capable of dynamically adjusting its posture and position so that an imaging beam emitted by it can be received by the first imaging robot, and the imaging beams emitted by the first imaging robot and the imaging beams emitted by the second imaging robot intersect at a specified position to obtain a three-dimensional real-time image; and a treatment robot configured to generate a treatment beam, the treatment robot adjusting its posture and displacement according to a degree of three-dimensional registration between the three-dimensional real-time image obtained by the imaging robot and the three-dimensional planned image so that the treatment beam generated by the robot is aligned with a designated position; The first imaging robot includes a first imaging mechanical arm, a first imaging support connected to the first imaging mechanical arm, and a first X-ray generator and a first X-ray receiver respectively connected to the first imaging support in rotation; The second imaging robot includes a second imaging mechanical arm, a second imaging support connected to the second imaging mechanical arm, and a second X-ray generator and a second X-ray receiver respectively connected to the second imaging support; The first imaging robot arm and the second imaging robot arm can synchronously adjust their abduction or adduction distances. The first X-ray generator or the first X-ray receiver can adjust its rotation angle relative to the first imaging support. The second X-ray generator or the second X-ray receiver can adjust the angle of rotation relative to the second imaging support. ; The first imaging robot and / or the second imaging robot can dynamically adjust its posture and position so that the imaging beam emitted by the first X-ray generator and the imaging beam emitted by the second X-ray generator intersect at a specified position, and the intersection area can cover the specified position, wherein the intersection area of ​​the first imaging beam and the second imaging beam can cover the specified position by judging the number of key feature points in the intersection area or by judging the area of ​​the intersection area and the area of ​​the specified position.

2. The real-time image guidance system according to claim 1, characterized in that: The area of ​​the intersection is obtained according to the following relationship: in, A is the area of ​​the intersection; D is the distance between the first X-ray generator and the second X-ray receiver, or the distance between the second X-ray generator and the first X-ray receiver; α It is the angle between the imaging beam emitted by the first X-ray generator and the imaging beam emitted by the second X-ray generator.

3. The real-time image guidance system according to claim 1, characterized in that: The angle through which the first X-ray generator or the first X-ray receiver rotates relative to the first image support The following relationship is satisfied: The angle of rotation of the second X-ray generator or the second X-ray receiver relative to the second imaging support The following relationship is satisfied: ； An adjustment angle of the first X-ray generator or the first X-ray receiver; An adjustment angle of the second X-ray generator or the second X-ray receiver; is the angular error between the first image support and the second image support at the current moment is the proportionality coefficient; is the integration coefficient; is the differential coefficient.

4. The real-time image guidance system according to claim 1, characterized in that: The first imaging robot arm and the second imaging robot arm synchronously adjust their abduction or retraction distance according to the following relationship: : )； in, ΔS The displacement between the position of the key feature point in the 3D real-time image at the current moment and the position of the feature point at the previous moment; α It is the angle between the imaging beam emitted by the first X-ray generator and the imaging beam emitted by the second X-ray generator.

5. The real-time image guidance system according to claim 4, characterized in that: The first imaging robot and the second imaging robot extract feature points of different scales in the three-dimensional real-time image according to the pre-trained model and select key feature points. The first imaging manipulator and the second imaging manipulator synchronously adjust their extension or retraction distance according to the key feature points. , wherein the feature points are bony landmark points.

6. The real-time image guidance system according to claim 1, characterized in that: The first imaging support is provided with a first hinge device and a second hinge device, wherein the rotating joint of the first hinge device and the rotating joint of the second hinge device are respectively connected to the first X-ray generator and the first X-ray receiver, so that the first X-ray generator and the first X-ray receiver can adjust their rotation angles relative to the first imaging support; A third hinge device and a fourth hinge device are provided on the second image support. The rotating joint of the third hinge device and the rotating joint of the fourth hinge device are respectively connected to the second X-ray generator and the second X-ray receiver, so that the second X-ray generator and the second X-ray receiver can adjust their rotation angle relative to the first image support.

7. The real-time image guidance system according to claim 1, characterized in that: The first image robot and / or the second image robot adjusts its posture and position based on a real-time collision avoidance algorithm and a fast random tree algorithm.

8. The real-time image guidance system according to claim 1, characterized in that: The treatment robot includes a treatment robotic arm and a treatment head connected to the treatment robotic arm. When the treatment head generates a treatment beam, the first X-ray generator and the first X-ray receiver as well as the second X-ray generator and the second X-ray receiver are all outside the beam range of the treatment beam.

Images