A target area real-time tracking method, electronic device, system and storage medium

Abstract

The embodiment of the present application relates to the field of radiotherapy equipment, and discloses a target area real-time tracking method, electronic equipment, system and storage medium, comprising: using a current prediction model and respiratory phase change, tracking a target area in real time by controlling the synchronous movement of a main mechanical arm and an auxiliary mechanical arm, the prediction model is used to represent the corresponding relationship between the respiratory phase and the target area movement information, and the target area movement information includes six degrees of freedom information;According to a preset frequency, a single projection image is obtained;Using the single projection image, a monitoring value of the target area movement information is obtained;Matching the monitoring value with the predicted value of the target area movement information at the same respiratory phase in the prediction model;In the case of inconsistent matching, a prediction model is re-established.The method solves the problem of improving the accuracy of real-time tracking of the target area, and dynamically corrects the prediction model according to the monitoring information in the treatment stage of real-time tracking of the target area, so as to improve the effect of tracking accuracy of the target area.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of radiotherapy equipment, and in particular to a target region real-time tracking method, electronic device, system and storage medium. BACKGROUND

[0002] In radiotherapy of tumors, due to respiratory motion, the tumor target moves, and accurate tumor target position needs to be obtained to emit treatment beams to achieve precise radiotherapy. Current solutions include: (1) controlling respiratory motion, such as emitting beams at deep expiration or deep inspiration, for example, using an abdominal pressure plate to reduce the amplitude of motion, however, this way needs human intervention to control respiratory motion, and cannot guarantee the control effect of respiratory motion; (2) observing the motion range of the target region through imaging, for example, using 4DCT (Four-dimensional computed tomography) for positioning and 4DCBCT (Four-Dimensional Cone Beam Computed Tomography) for treatment, to determine the motion range of the target region, and emitting treatment beams within the motion range, but the target region position obtained in this way has errors; (3) respiratory gating technology, in this way, the patient can breathe freely, the patient wears a respiratory detection device to monitor the respiratory phase, and treatment beams are only emitted at a certain respiratory phase in the respiratory cycle. However, in this way, the relationship between the respiratory phase and the motion of the target region changes, that is, the motion position of the target region may not be consistent at the same respiratory phase, so the target region position obtained has errors; (4) real-time tracking technology, the treatment beam moves with the target region, this way needs to predict the motion position of the target region in advance. However, the current real-time tracking technology needs to emit cross X-rays through two fixed position ball tubes, and determine the position of the target region through two orthogonal projection images with fixed projection positions, the shooting angle is limited and the calculation is complicated, the real-time tracking target region position is not accurate enough, so the real-time tracking effect cannot meet the high precision requirement of radiotherapy guidance. SUMMARY

[0003] The purpose of the present application is to at least provide a target region real-time tracking method, electronic device, system and storage medium, which can at least solve the problem of improving the accuracy of real-time tracking of the target region, and at least achieve the effect of dynamically correcting the prediction model according to the monitoring information in the treatment stage of real-time tracking of the target region to improve the accuracy of tracking the target region.

[0004] To solve the above technical problems, at least one embodiment of the present application provides a target region real-time tracking method, which is realized based on an image-guided radiotherapy system, the image-guided radiotherapy system comprising a main mechanical arm and an auxiliary mechanical arm, a terminal end of the main mechanical arm being provided with a transmission device for transmitting a cone-beam imaging beam and a treatment device for transmitting a treatment beam, a terminal end of the auxiliary mechanical arm being provided with a receiving device for receiving the cone-beam imaging beam; the main mechanical arm drives the treatment device and the transmission device to move, while the auxiliary mechanical arm drives the receiving device to move synchronously so that the cone-beam imaging beam can pass through the target region to reach the receiving device and the receiving device avoids the irradiation of the treatment beam; the target region real-time tracking method comprises: using a current prediction model and a breathing phase change, real-time tracking of the target region is realized by controlling the main mechanical arm and the auxiliary mechanical arm to move synchronously, the prediction model being used to represent a corresponding relationship between the breathing phase and target region motion information, the target region motion information comprising six degrees of freedom information; using the transmission device and the receiving device to image according to a preset frequency, a single projection image is obtained; using the single projection image, a monitoring value of the target region motion information is obtained; the monitoring value is matched with a prediction value of the target region motion information at the same breathing phase in the prediction model; in the case that the matching result shows that the monitoring value is inconsistent with the prediction value, a prediction model is re-established, the re-established prediction model being determined as the current prediction model, so as to continue to use the current prediction model and the breathing phase change, real-time tracking of the target region is realized by controlling the main mechanical arm and the auxiliary mechanical arm to move synchronously.

[0005] At least one embodiment of the present application further provides an electronic device, comprising: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to execute the above-mentioned target region real-time tracking method.

[0006] At least one embodiment of the present application also provides an image-guided radiotherapy system, comprising: a main mechanical arm, the end of which is provided with a transmission device for transmitting a cone-beam imaging beam and a treatment device for transmitting a treatment beam, the main mechanical arm being capable of driving the treatment device and the transmission device to move synchronously; an auxiliary mechanical arm, the end of which is provided with a receiving device for receiving the cone-beam imaging beam, the auxiliary mechanical arm driving the receiving device to move synchronously while the main mechanical arm drives the treatment device and the transmission device to move, so that the cone-beam imaging beam can pass through a target region to reach the receiving device and the receiving device avoids irradiation of the treatment beam; a control device for tracking the target region in real time by controlling the main mechanical arm and the auxiliary mechanical arm to move synchronously using a current prediction model and a change in a breathing phase; acquiring a single projection image by imaging using the transmission device and the receiving device according to a preset frequency; obtaining a monitoring value of target region motion information using the single projection image; matching the monitoring value with a predicted value of the target region motion information at the same breathing phase in the prediction model; in the case where the matching result shows that the monitoring value is inconsistent with the predicted value, re-establishing a prediction model, determining the re-established prediction model as the current prediction model, and continuing to track the target region in real time by using the current prediction model and the change in the breathing phase through the synchronous movement of the main mechanical arm and the auxiliary mechanical arm; the prediction model is used to represent the corresponding relationship between the breathing phase and the target region motion information, and the target region motion information includes six degrees of freedom information.

[0007] At least one embodiment of the present application also provides a computer-readable storage medium storing a computer program, the computer program being executed by a processor to implement the above-mentioned target region real-time tracking method.

[0008] The target region real-time tracking method, electronic device, system and storage medium provided by the embodiments of the present application drive the treatment device to project and track the target region in real time through the main mechanical arm, at the same time, synchronous rotary motion of the transmission device is also driven, and the receiving device is driven to reach a corresponding position capable of receiving the imaging beam passing through the target region through the auxiliary mechanical arm. In order to improve the accuracy of target region projection, a single projection image is obtained when a set frequency is reached, and only the projection image is used to obtain a monitoring value of target region motion information, thereby realizing dynamic monitoring of the target region in the treatment stage, and the prediction model capable of predicting the accurate target region is used for real-time tracking according to the monitoring result, so as to improve the accuracy of target region real-time tracking.

[0009] In some optional embodiments, the target region is tracked in real time by controlling the synchronous movement of the main mechanical arm and the auxiliary mechanical arm, including: acquiring a respiratory motion curve representing the respiratory phase change, which is monitored in real time; predicting target region movement information in real time by using the current prediction model and the respiratory phase change; and controlling the main mechanical arm to move the treatment device so that the treatment beam emitted by the treatment device irradiates the target region according to the predicted target region movement information. By combining the respiratory phase change with the prediction model, dynamic tracking of the target region is achieved, ensuring the accuracy of the target region during the treatment stage.

[0010] In some optional embodiments, the target region real-time tracking method further includes: the main mechanical arm and the auxiliary mechanical arm respectively drive the emission device and the receiving device to move synchronously, and imaging is performed while rotating to obtain a cone-beam CT projection image sequence; 4D cone-beam CT projection images are reconstructed according to the cone-beam CT projection image sequence; target region movement information at each respiratory phase is calculated according to the 4D cone-beam CT projection images; and a prediction model representing the corresponding relationship between the respiratory phase and the target region movement information is established according to the target region movement information at each respiratory phase. By reconstructing the 4D cone-beam CT projection images, an accurate prediction model can be constructed for dynamic tracking of the target region.

[0011] In some optional embodiments, the target region real-time tracking method further includes: the main mechanical arm and the auxiliary mechanical arm respectively drive the emission device and the receiving device to move synchronously, and imaging is performed while rotating to obtain a cone-beam CT projection image sequence; images of the same respiratory phase in the cone-beam CT projection image sequence are divided into a group; target region movement information is calculated according to each group of images of the same respiratory phase, and the calculated target region movement information is averaged to determine the average value as the target region movement information at the corresponding respiratory phase; and a prediction model representing the corresponding relationship between the respiratory phase and the target region movement information is established according to the target region movement information at each respiratory phase. By calculating the target region movement information of the cone-beam CT projection images of the same respiratory phase and then averaging the values, more accurate target region movement information at different respiratory phases is obtained, and modeling is achieved.

[0012] In some optional embodiments, the monitoring value of the target region movement information obtained from the single projection image includes: acquiring a reference CT image used to generate a treatment plan; performing 2D-3D registration based on the single projection image and the reference CT image to obtain the projection position of the single projection image; performing 2D-3D registration based on the single projection image and the reference CT image to obtain the position change of the target region relative to the reference CT image at the current time; and determining the target region movement information in the patient coordinate system according to the position change of the target region relative to the reference CT image at the current time as the monitoring value of the target region movement information.

[0013] In some optional embodiments, the positional change of the target area relative to the reference CT image at the current moment includes the translational and rotational changes of the target area relative to the reference CT image in the projected coordinate system. The target area motion information in the patient coordinate system is determined by the following geometric relationship between the projected coordinate system and the patient coordinate system:

[0014]

[0015]

[0016]

[0017]

[0018]

[0019]

[0020] In the formula, ( This represents the translational and rotational changes of the target area relative to the reference CT image in the projected coordinate system. Indicates the geometric magnification factor, ( This represents the translational and rotational changes of the target area relative to the reference CT image in the projected coordinate system. This represents the angle by which the projection plane A rotates about the x-axis.

[0021] In some optional embodiments, obtaining the target motion information monitoring value using the single projection image includes: performing 2D registration between the single projection image and each image in the cone-beam CT projection image sequence; determining a second target image from the cone-beam CT projection image sequence that best matches the single projection image; determining the target motion information at the same respiratory phase in the 4D cone-beam CT projection image based on the respiratory phase of the second target image; and determining this target motion information as the monitoring value of the target motion information. By determining the image that best matches the currently captured single projection image from the cone-beam CT projection image sequence, the target motion information at the same respiratory phase can be quickly determined from the 4D cone-beam CT projection image as the monitoring value. Attached Figure Description

[0022] One or more embodiments are illustrated by way of example with reference to the accompanying drawings, and these illustrative descriptions do not constitute a limitation on the embodiments.

[0023] Figure 1 This is a flowchart of a real-time target tracking method provided in an embodiment of this application;

[0024] Figure 2 This is a schematic diagram of a cross-section of the human body and target area provided in an embodiment of this application;

[0025] Figure 3 is a schematic diagram of a projection coordinate system provided by an embodiment of the present application;

[0026] Figure 4 is a schematic diagram of the relationship between a patient coordinate system xyz and a projection coordinate system x A y A z A provided by an embodiment of the present application;

[0027] Figure 5 is a schematic diagram of the relationship between three coordinate systems provided by an embodiment of the present application;

[0028] Figure 6 is a schematic diagram of a target region real-time tracking device provided by an embodiment of the present application;

[0029] Figure 7 is a schematic diagram of an image-guided radiotherapy system provided by an embodiment of the present application;

[0030] Figure 8 is a schematic diagram of the relationship between a treatment beam and an imaging beam provided by an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to make the objects, technical solutions and advantages of embodiments of the present application clearer, the following will be combined with the accompanying drawings to describe the embodiments of the present application in detail. However, those skilled in the art can understand that, in the embodiments of the present application, many technical details are presented in order to make the readers better understand the present application. However, the technical solutions claimed by the present application can be implemented even without these technical details and based on various changes and modifications of the following embodiments. The following division of the embodiments is for the convenience of description, and should not constitute any limitation on the specific implementation of the present application, and the embodiments can be combined and referenced with each other on the premise of no contradiction.

[0032] In order to facilitate the understanding of the embodiments of the present application, the related content about target region real-time tracking is introduced first.

[0033] In radiotherapy of tumors, due to respiratory motion, the tumor target moves, and accurate tumor target position needs to be obtained to emit treatment beams to achieve precise radiotherapy. Current solutions include: (1) controlling respiratory motion, such as emitting beams at deep expiration or deep inspiration, for example, using an abdominal pressure plate to reduce the amplitude of motion, however, this way needs human intervention to control respiratory motion, and cannot guarantee the control effect of respiratory motion; (2) observing the motion range of the target area through imaging, for example, using 4DCT for positioning and 4DCBCT for treatment, and then determining the motion range of the target area, and emitting treatment beams within the motion range, but the target position obtained in this way has errors; (3) respiratory gating technology, in this way, the patient can breathe freely, the patient wears a respiratory detection device to monitor the respiratory phase, and treatment beams are emitted only at a certain respiratory phase in the respiratory cycle. However, in this way, the relationship between the respiratory phase and the motion of the target area is changing, that is, the motion position of the target area may not be consistent at the same respiratory phase, so the target position obtained has errors; (4) real-time tracking technology, the treatment beam moves with the target area, this way needs to predict the motion position of the target area in advance. However, the current real-time tracking technology needs to emit cross X-rays through two fixed position ball tubes, and the target position is determined by projecting two orthogonal projection images with fixed positions, the shooting angle is limited and the calculation is complicated, the real-time tracking target position is not accurate enough, so the real-time tracking effect is difficult to meet the high precision requirement of radiotherapy guidance.

[0034] The current real-time tracking technology is a relatively accurate method, and the respiratory tracking system in the related technology predicts the position of the target area by establishing the relationship between the motion of the target area in the body and the respiratory curve outside the body, and then transmits the predicted target position to the mechanical arm, so that the treatment mechanical arm can move synchronously with the target area in the body. In this scheme, the image-guided radiotherapy device is to place the treatment head on the mechanical arm, and the two ball tubes and the corresponding two detectors arranged on the ceiling and the floor form an imaging device. When installing, the X-rays emitted by the two ball tubes intersect. The image quality of the positioning and guidance of this device is poor, and CBCT imaging cannot be realized to obtain 3D spatial information. In addition, only two orthogonal 2D projection images are used in the positioning stage, and the patient needs to be irradiated multiple times, which is time-consuming and significantly increases the radiation exposure of the patient. Moreover, due to the fixed positions of the patient and the two orthogonal images, if the tumor target is not clear or is blocked in the captured image, it is impossible to obtain an image containing a clear tumor target by changing the shooting angle, thereby affecting the positioning accuracy of the target area.

[0035] In order to solve the technical problem of improving the accuracy of real-time tracking of the target area, the present application provides a target real-time tracking method, and the implementation details of the target real-time tracking method of the present embodiment will be described in detail below. The following content is only provided to facilitate understanding of the implementation details of the present application, and is not necessary for implementing the present scheme.

[0036] Embodiment one:

[0037] The target region real-time tracking method of the embodiment is realized based on an image-guided radiotherapy system, which includes a main mechanical arm and an auxiliary mechanical arm. The end of the main mechanical arm is provided with a transmission device for transmitting a cone-beam imaging beam and a treatment device for transmitting a treatment beam. The end of the auxiliary mechanical arm is provided with a receiving device for receiving the cone-beam imaging beam. The main mechanical arm drives the treatment device and the transmission device to move, and at the same time, the auxiliary mechanical arm drives the receiving device to move synchronously so that the cone-beam imaging beam can pass through the target region to reach the receiving device and the receiving device avoids the irradiation of the treatment beam.

[0038] In one example, the transmission device of the image-guided radiotherapy system is used as an X-ray source, which can be an X-ray tube, for transmitting a cone-beam imaging beam. The receiving device is used as an imaging detection device capable of detecting the imaging beam, which can be a detector.

[0039] The target region real-time tracking method of the embodiment can be applied to an electronic device with communication, calculation and data storage capabilities. The specific process can be as shown in Figure 1 , which includes:

[0040] In step 101, the target region is tracked in real time by controlling the synchronous movement of the main mechanical arm and the auxiliary mechanical arm by using the current prediction model and the respiratory phase change, wherein the prediction model is used to represent the corresponding relationship between the respiratory phase and the target region movement information, and the target region movement information includes six degrees of freedom information.

[0041] Specifically, the target region movement information includes six degrees of freedom information of the current target region relative to the target region in the reference CT image, which indicates the offset of the real-time tumor position of the patient relative to the tumor position in the original reference CT image.

[0042] In the specific implementation, step 101 is a step performed in the treatment stage. After entering the treatment stage, the system controls the main mechanical arm to drive the treatment device to align the target region to emit the treatment beam to perform radiotherapy on the tumor. Before entering the treatment stage, the patient needs to go through the positioning stage.

[0043] In some examples, in the patient positioning stage, the main mechanical arm drives the emission device to rotate along the transverse section of the human body around the target region in an arc path, so that the cone-beam image beam is directed towards the target region, and the auxiliary mechanical arm synchronously drives the receiving device to rotate along the transverse section of the human body around the target region in an arc path. The synchronous rotation of the main and auxiliary mechanical arms makes the center of the cone-beam image beam at each rotation position pass through the back of the human body and be perpendicular to the center of the receiving device. During the synchronous rotation of the main and auxiliary mechanical arms, the emission device is controlled to emit the imaging beam and the receiving device is controlled to receive the imaging beam passing through the human body, projection images are acquired at a certain frequency, and a CBCT image is obtained according to a CBCT reconstruction algorithm, and then according to the CBCT image result, the bed or the mechanical arm is moved to make the positioning of the radiotherapy system and the bed reach a state in which the treatment beam can accurately irradiate the target region.

[0044] Step 102: A single projection image is acquired by imaging using the emission device and the receiving device at a preset frequency.

[0045] In the treatment stage, the current prediction model and the respiratory phase change are used to track the target region in real time by controlling the synchronous movement of the main mechanical arm and the auxiliary mechanical arm, and the emission device emits a cone-beam image beam at a position where the target region movement information needs to be detected at a preset frequency, and the auxiliary mechanical arm drives the receiving device to receive the imaging beam passing through the human body on the opposite side of the human body to acquire a single projection image. For example, a single projection image is acquired at a frequency of once every 1 minute, and the projection position of the single projection image is the position where the target region movement information needs to be detected.

[0046] In a specific implementation, the mechanical installation of the radiotherapy system needs to ensure that both the treatment beam and the imaging beam can pass through the target region. Further, in order to obtain good image quality, the receiving device uses a kV-level detector, but since the treatment beam is an MV-level beam, if the MV-level beam irradiates the detector, it will affect the service life and image quality of the detector. Therefore, the receiving device needs to be shielded from the irradiation of the treatment beam in the case that the cone-beam image beam of the emission device can pass through the target region to reach the receiving device.

[0047] Step 103: A monitoring value of the target region movement information is obtained using the single projection image.

[0048] Since the emission device and the treatment device are both installed on the main mechanical arm, are synchronously rotated, and have similar installation angles, the projection direction of the single projection image is similar to the direction of the treatment beam. Therefore, the single projection image can accurately represent the target region movement information in a plane perpendicular to the treatment beam. This information is an important basis for accurate and reliable dynamic tracking in the treatment stage, and only a small amount of information (a single projection image) is needed to obtain an accurate monitoring value of the target region movement information, so as to further accurately determine whether the current prediction model needs to be corrected and improve the real-time tracking effect.

[0049] Step 104, match the monitoring value with the predicted value of the target region movement information in the same respiratory phase in the prediction model.

[0050] By matching the monitoring value with the predicted value of the target region movement information in the same respiratory phase in the prediction model, the prediction result accuracy of the current prediction model can be verified.

[0051] Step 105, in the case where the matching result shows that the monitoring value is inconsistent with the predicted value, re-establish the prediction model, and determine the re-established prediction model as the current prediction model, so as to continue to use the current prediction model and the respiratory phase change to track the target region in real time by controlling the synchronous movement of the main mechanical arm and the auxiliary mechanical arm. In the case where the matching result shows that the monitoring value is consistent with the predicted value, continue to use the current prediction model and the respiratory phase change to track the target region in real time by controlling the synchronous movement of the main mechanical arm and the auxiliary mechanical arm, that is, the prediction model remains unchanged.

[0052] In this embodiment, the main mechanical arm drives the treatment device to project the target region tracked in real time, at the same time, it also drives the synchronous rotation movement of the emission device, and the auxiliary mechanical arm drives the receiving device to reach the corresponding position capable of receiving the imaging beam passing through the target region. In order to improve the accuracy of target region projection, when reaching the position where the target region movement information needs to be detected, that is, reaching the set frequency, a single projection image at this position is obtained, and the monitoring value of the target region movement information can be obtained only according to this projection image, the dynamic monitoring of the target region in the treatment stage is realized, the prediction model is corrected in time according to the monitoring result, so that the real-time tracking always uses the prediction model capable of predicting the accurate target region, and the accuracy of real-time tracking of the target region is improved.

[0053] In some embodiments, the real-time tracking of the target region by controlling the synchronous movement of the main mechanical arm and the auxiliary mechanical arm using the current prediction model and the respiratory phase change comprises:

[0054] Step 1011, obtaining the real-time monitored respiratory movement curve representing the respiratory phase change.

[0055] In a specific implementation, the respiratory movement curve of the patient can be monitored by wearing a respiratory monitoring device.

[0056] Step 1012, using the current prediction model and the respiratory phase change to predict the target region movement information in real time.

[0057] Specifically, the respiratory phase change can be obtained through the respiratory movement curve, and since the prediction model represents the corresponding relationship between the respiratory phase and the target region movement information, the target region movement information can be predicted according to the respiratory phase change.

[0058] Step 1013, according to the predicted target region motion information, controlling the main mechanical arm to drive the treatment device to move, so that the treatment device emits a treatment beam to irradiate the target region.

[0059] In some embodiments, the modeling can be achieved by reconstructing 4D cone beam CT projection images, and specifically, the above target region real-time tracking method further includes the following modeling process:

[0060] Step 1001, the main mechanical arm and the auxiliary mechanical arm drive the emission device and the receiving device to move synchronously, and the imaging is performed while the rotation is performed, so that a cone beam CT projection image sequence is obtained.

[0061] Specifically, according to the preset motion trajectory of the CBCT, the main and auxiliary mechanical arms perform imaging while rotating, so that a CBCT projection sequence image is obtained.

[0062] Step 1002, reconstructing 4D cone beam CT projection images according to the cone beam CT projection image sequence.

[0063] Step 1003, calculating the target region motion information at each breathing phase according to the 4D cone beam CT projection images.

[0064] Step 1004, establishing a prediction model for representing the corresponding relationship between the breathing phase and the target region motion information according to the target region motion information at each breathing phase.

[0065] In other embodiments, the modeling can also be achieved by calculating the target region motion information from the cone beam CT projection images at the same breathing phase and then averaging the values, so that more accurate target region motion information at different breathing phases is obtained. Specifically, the target region real-time tracking method further includes the following modeling process:

[0066] Step 100a, the main mechanical arm and the auxiliary mechanical arm drive the emission device and the receiving device to move synchronously, and the imaging is performed while the rotation is performed, so that a cone beam CT projection image sequence is obtained.

[0067] Step 100b, dividing the images at the same breathing phase in the cone beam CT projection image sequence into a group.

[0068] Step 100c, calculating the target region motion information according to each group of images at the same breathing phase, averaging the calculated target region motion information, and determining the average value as the target region motion information at the corresponding breathing phase.

[0069] Step 100d, establishing a prediction model for representing the corresponding relationship between the breathing phase and the target region motion information according to the target region motion information at each breathing phase.

[0070] In practice, a prediction model can be established using one of the two modeling methods described above, and then used to track the target area in real time. If the matching results show that the monitored value and the predicted value are inconsistent, a new prediction model can also be established using one of the two modeling methods described above.

[0071] In some embodiments, a specific implementation method is provided for obtaining monitoring values ​​of target area motion information using a single projection image, including:

[0072] Step 1031: Obtain reference CT images for generating a treatment plan.

[0073] Specifically, the reference CT image can refer to the original CT image obtained before the treatment plan is developed, based on which the target area can be located and the treatment plan can be generated.

[0074] Step 1032: Perform 2D-3D registration based on a single projection image and a reference CT image to obtain the positional change of the target area relative to the reference CT image at the current moment. The target area motion information in the patient coordinate system determined by the positional change of the target area relative to the reference CT image at the current moment is determined as the monitoring value of the target area motion information.

[0075] In some cases, a single 2D projection image (X-ray image) is the current-moment image, containing the real-time pose of the target area. In 2D-3D registration from a single 2D projection image (X-ray image) to a 3D reference CT image, digitally reconstructed radiographs (DRRs) need to be generated from the 3D CT volume. Intensity-based 2D-3D image registration alters the translation and rotation of the CT volume, generating a set of DRR images for each location. Similarity measurements between the X-ray image and this set of DRR images are calculated, and the DRR image with the highest similarity to the X-ray image is found. The translation and rotation of the CT volume when generating this most similar DRR image represent the rigid transformation (displacement and rotation) of the X-ray image relative to the reference CT image. The region of interest for similarity measurement may differ depending on the scenario. For example, during positioning, or for organs unaffected by respiratory motion, the region of interest might be bony tissue; for organs affected by respiratory motion, the region of interest might be tissue or the target area. Figure 2 The diagram shows cross-sections of the human body and target area, defining a 3D patient (human body) coordinate system xyz, where the x-axis points inwards from the paper, the z-axis is perpendicular to the patient's body, and the y-axis is parallel to the patient's body. The patient's position is determined by three translations and three rotations. These six degrees of freedom are represented. Assume the projection plane A represents a single projected image, S... A It is the source of a single projected image. Figure 3The projection coordinate system x of projection plane A A y A z A , Figure 4 The patient coordinate system (xyz) and the projected coordinate system (x) are... A y A z A The relationship, x A The direction is the same as the x-direction, and the projection plane A is equivalent to rotating θ around the x-axis. A Angle, such that y and y A Parallel, z and z A Parallel. Following 2D-3D registration, traverse the reference CT images ( A set of DRR images is generated by transforming ( ), and the DRR image with the highest similarity is used ( ). This indicates the change in the position of the target area relative to the target area in the reference CT image at the current moment.

[0076] Generating a set of DRR images by traversing six degrees of freedom and then calculating similarity for each image is a relatively time-consuming process. Therefore, in some other examples, to establish the relationship between the 3D patient coordinate system and the projected coordinate system and to accelerate the computation by reducing the amount of traversal required to generate DRR images, another 3D coordinate system x' y'z' is introduced, where z' is related to z... A The directions are consistent, such as Figure 5 As shown. In the 2D projection coordinate system where the projection plane A is located, the 3D rigid transformation is decomposed into in-plane transformations ( , ) and two out-of-plane rotations ( , ),z A The position of direction is used Geometric magnification factor representation. For projection plane A, only the CT volume θx' and θy' need to be changed to generate a set of references. Images, these references The image corresponds to two out-of-plane rotations of the projection plane A. , Different combinations of ) and transformations in the two-dimensional plane ( Estimate the out-of-plane rotation by comparing 2D-2D images (X-ray image and the most similar DRR image). , ) is calculated from the best match of the X-ray image and the DRR image. After the reference DRR image is identified, the in-plane transformation can be accurately obtained. In this way, the position change of the target region in the projection coordinate system relative to the target region in the reference CT image is obtained, the calculation is accelerated, the traversal amount of generating DRR images is reduced, and more accurate target region motion perpendicular to the treatment beam plane is directly obtained, which can more accurately track the lesion. Further, the position change of the target region at the current time relative to the reference CT image includes the translation change and the rotation change of the target region in the projection coordinate system relative to the reference CT image, and the geometric relationship between the projection coordinate system of the projection plane A and the patient coordinate system can be expressed as follows: the target region motion information (translation change and rotation change) in the patient coordinate system can be determined by the following geometric relationship:

[0077]

[0078]

[0079]

[0080]

[0081]

[0082]

[0083] In the formula, (T ) represents the translation change and the rotation change of the target region in the projection coordinate system relative to the reference CT image, represents a geometric magnification factor, (T ) represents the translation change and the rotation change of the target region in the patient coordinate system relative to the reference CT image, and θ A represents the angle of rotation of the projection plane A around the x-axis.

[0084] In one example, the target region relative motion information in the patient coordinate system obtained by the above conversion is converted to the treatment beam direction, the mechanical arm is controlled to follow the target region motion in the treatment beam direction, that is, the treatment beam tracking projection target region is realized. In another example, the geometric conversion relationship and the foregoing geometric relationship are the same, and the difference lies in that represents the y-direction angle between the treatment beam and the imaging beam, so that the target region relative motion information to the treatment beam direction is directly obtained, the mechanical arm is controlled to follow the target region motion in the treatment beam direction, that is, the treatment beam tracking projection target region is realized.

[0085] In some embodiments, another specific implementation of the monitoring value of the target region motion information obtained by using a single projection image is provided, which includes:

[0086] Step 103a, 2D registration is performed between the single projection image and each image in the cone-beam CT projection image sequence to determine a second target image that is most matched with the single projection image from the cone-beam CT projection image sequence.

[0087] Step 103b, target region motion information in the same respiratory phase in the 4D cone-beam CT projection image sequence is determined according to the respiratory phase of the second target image, and the target region motion information is determined as the monitoring value of the target region motion information.

[0088] By performing 2D-2D registration between the monitored single projection image and the cone-beam CT projection image sequence obtained in the foregoing modeling process, a most matched cone-beam CT projection image is found, and then the target region motion value in the same respiratory phase as the cone-beam CT projection image is found in the reconstructed 4D-CBCT projection image sequence according to the cone-beam CT projection image, that is, the monitoring value of the target region motion information is determined.

[0089] In addition, in the process of modeling by averaging the target region motion information calculated from the cone-beam CT projection images in the same respiratory phase, the target region motion information can also be calculated according to each group of images in the same respiratory phase, and one of the specific implementation manners of the foregoing two methods for obtaining the monitoring value of the target region motion information by using a single projection image can be used.

[0090] Compared with the existing ring gantry or C-arm gantry radiotherapy system, the target region can be tracked in real time by using the main and auxiliary mechanical arms and the foregoing method in the embodiment, a larger treatment angle can be obtained, and normal tissue damage can be greatly reduced while the tumor target region is treated. The CBCT image obtained by using the main and auxiliary mechanical arms and the foregoing method has better image quality, the patient can be positioned faster, the target region position can be tracked in real time, and more accurate treatment can be performed. Compared with the prior art, the angle of the treatment beam and the imaging beam is closer in the method, and the tumor target region motion information provided to the direction of the treatment beam is more accurate relative to the orthogonal image.

[0091] Embodiment two:

[0092] Another embodiment of the present application relates to a target area real-time tracking device, and the implementation details of the target area real-time tracking device of the present embodiment are specifically described as follows. The following implementation details are provided for the convenience of understanding, and are not essential for implementing the present embodiment. The target area real-time tracking device of the present embodiment is implemented based on an image-guided radiotherapy system. The image-guided radiotherapy system includes a main mechanical arm and an auxiliary mechanical arm. The end of the main mechanical arm is provided with a transmission device for transmitting a cone-beam imaging beam and a treatment device for transmitting a treatment beam. The end of the auxiliary mechanical arm is provided with a receiving device for receiving the cone-beam imaging beam. The main mechanical arm drives the treatment device and the transmission device to move, and at the same time, the auxiliary mechanical arm drives the receiving device to move synchronously so that the cone-beam imaging beam can pass through the target area to reach the receiving device and the receiving device avoids the irradiation of the treatment beam. A schematic diagram of the target area real-time tracking device can be shown as follows. Figure 6 The target area real-time tracking device includes a real-time tracking module 201, an image acquisition module 202, a monitoring calculation module 203, an information matching module 204, and a model establishing module 205.

[0093] The real-time tracking module 201 is configured to track the target area in real time by controlling the synchronous movement of the main mechanical arm and the auxiliary mechanical arm according to the current prediction model and the respiratory phase change. The prediction model is used to represent the corresponding relationship between the respiratory phase and the target area movement information, and the target area movement information includes six degrees of freedom information.

[0094] The image acquisition module 202 is configured to acquire a single projection image by imaging using the transmission device and the receiving device according to a preset frequency.

[0095] The monitoring calculation module 203 is configured to obtain a monitoring value of the target area movement information by using the single projection image.

[0096] The information matching module 204 is configured to match the monitoring value with a predicted value of the target area movement information at the same respiratory phase in the prediction model.

[0097] The model establishing module 205 is configured to re-establish the prediction model in the case where the matching result shows that the monitoring value is inconsistent with the predicted value, and determine the re-established prediction model as the current prediction model, so as to continue to track the target area in real time by controlling the synchronous movement of the main mechanical arm and the auxiliary mechanical arm according to the current prediction model and the respiratory phase change.

[0098] Specifically, the target area movement information includes six degrees of freedom information of the current target area relative to the target area in the reference CT image, which indicates the offset of the real-time tumor position of the patient relative to the tumor position in the original reference CT image.

[0099] In a specific implementation, after entering the treatment stage, the system controls the main mechanical arm to drive the treatment device to emit the treatment beam to align the target area to perform radiotherapy on the tumor. Before entering the treatment stage, the patient needs to go through the positioning stage, and then the target area is tracked in real time.

[0100] In some examples, in the patient positioning stage, the main mechanical arm drives the emission device to rotate along the transverse section of the human body around the target region in an arc path, so that the cone-beam image beam is directed to the target region, and the auxiliary mechanical arm synchronously drives the receiving device to rotate along the transverse section of the human body around the target region in an arc path. The synchronous rotation of the main and auxiliary mechanical arms makes the center of the cone-beam image beam at each rotation position pass through the center of the receiving device perpendicularly after passing through the human body. During the synchronous rotation of the main and auxiliary mechanical arms, the emission device is controlled to emit the imaging beam and the receiving device is controlled to receive the imaging beam passing through the human body, projection images are acquired at a certain frequency, and a CBCT image is obtained according to a CBCT reconstruction algorithm. Then, according to the CBCT image result, the bed or the mechanical arm is moved to make the positioning of the radiotherapy system and the bed reach a state in which the treatment beam can accurately irradiate the target region. This positioning method can quickly and accurately realize target region positioning without the need for multiple bed and system movements. Compared with the prior art, the target region position determined by the positioning is accurate, and the positioning time is significantly reduced, and the positioning efficiency is high.

[0101] In this embodiment, the main mechanical arm drives the treatment device to irradiate the real-time tracked target region in real time, and at the same time, the synchronous rotation movement of the emission device is also driven, and the receiving device is driven by the auxiliary mechanical arm to reach a corresponding position at which the imaging beam passing through the target region can be received. In order to improve the accuracy of target region irradiation, when a set frequency is reached, the position at which the target region movement information needs to be detected is reached, and a single projection image at this position is obtained. The monitoring value of the target region movement information can be obtained only according to this projection image, and the dynamic monitoring of the target region in the treatment stage is realized. The prediction model that can accurately predict the target region is used according to the monitoring result in time to correct the prediction model, so that the real-time tracking always uses the prediction model that can accurately predict the target region, and the accuracy of real-time tracking of the target region is improved.

[0102] In some embodiments, the current prediction model and the change in the respiratory phase are used to control the synchronous movement of the main mechanical arm and the auxiliary mechanical arm to track the target region in real time, including: acquiring a real-time monitored respiratory motion curve representing the change in the respiratory phase; using the current prediction model and the change in the respiratory phase to predict the target region movement information in real time; and controlling the main mechanical arm to drive the treatment device to move according to the predicted target region movement information, so that the treatment beam emitted by the treatment device irradiates the target region.

[0103] In some embodiments, the modeling can be achieved by reconstructing 4D cone beam CT projection images, and the model establishing module is further configured to implement the following modeling process: the primary mechanical arm and the secondary mechanical arm drive the emitting device and the receiving device to perform synchronous rotation movement, and imaging is performed at the same time of the rotation movement to obtain a sequence of cone beam CT projection images; 4D cone beam CT projection images are reconstructed according to the sequence of cone beam CT projection images; target motion information at each respiratory phase is calculated according to the target motion information at each respiratory phase; and a prediction model for representing the corresponding relationship between the respiratory phase and the target motion information is established according to the target motion information at each respiratory phase.

[0104] In other embodiments, the modeling can also be achieved by calculating the target motion information from the cone beam CT projection images at the same respiratory phase and then averaging the target motion information to obtain more accurate target motion information at different respiratory phases. The model establishing module is further configured to implement the following modeling process: the primary mechanical arm and the secondary mechanical arm drive the emitting device and the receiving device to perform synchronous rotation movement, and imaging is performed at the same time of the rotation movement to obtain a sequence of cone beam CT projection images; images at the same respiratory phase in the sequence of cone beam CT projection images are divided into a group; target motion information is calculated according to each group of images at the same respiratory phase, the calculated target motion information is averaged, and the average value is determined as the target motion information at the corresponding respiratory phase; and a prediction model for representing the corresponding relationship between the respiratory phase and the target motion information is established according to the target motion information at each respiratory phase.

[0105] In a specific implementation, the prediction model can be established by one of the above two modeling methods, and then the prediction model is used to track the target in real time. In the case where the matching result shows that the monitoring value and the predicted value are inconsistent, the prediction model can also be re-established by one of the above two modeling methods.

[0106] In some embodiments, a specific implementation of obtaining a monitoring value of target motion information from a single projection image is provided, including: obtaining a reference CT image used to generate a treatment plan; performing 2D-3D registration based on a single projection image and the reference CT image to obtain a position change of the target relative to the reference CT image at a current time, and determining target motion information in a patient coordinate system according to the position change of the target relative to the reference CT image at the current time as the monitoring value of the target motion information.

[0107] In some cases, a single 2D projection image (X-ray image) is the current-time image, containing the real-time pose of the target area. In 2D-3D registration from a single 2D projection image (X-ray image) to a 3D reference CT image, digitally reconstructed radiographs (DRRs) need to be generated from the 3D CT volume. Intensity-based 2D-3D image registration alters the translation and rotation of the CT volume, generating a set of DRR images for each location. Similarity measurements between the X-ray image and this set of DRR images are calculated, and the DRR image with the highest similarity to the X-ray image is found. The translation and rotation of the CT volume when generating this most similar DRR image represent the rigid transformation (displacement and rotation) of the X-ray image relative to the reference CT image. The region of interest for similarity measurement may differ depending on the scenario. For example, during positioning, or for organs unaffected by respiratory motion, the region of interest might be bony tissue; for organs affected by respiratory motion, the region of interest might be tissue or the target area. Figure 2 The diagram shows cross-sections of the human body and target area, defining a 3D patient (human body) coordinate system xyz, where the x-axis points inwards from the paper, the z-axis is perpendicular to the patient's body, and the y-axis is parallel to the patient's body. The patient's position is determined by three translations and three rotations. These six degrees of freedom are represented. Assume the projection plane A represents a single projected image, S... A It is the source of a single projected image. Figure 3 The projection coordinate system x of projection plane A A y A z A , Figure 4 The patient coordinate system (xyz) and the projected coordinate system (x) are... A y A z A The relationship, x A The direction is the same as the x-direction, and the projection plane A is equivalent to rotating θ around the x-axis. A Angle, such that y and y A Parallel, z and z A Parallel. Following 2D-3D registration, traverse the reference CT images ( ), The transformation generates a set of DRR images, and the DRR image with the highest similarity is used ( This indicates the change in the position of the target area relative to the target area in the reference CT image at the current moment.

[0108] Generating a set of DRR images by traversing six degrees of freedom and then calculating similarity for each image is a relatively time-consuming process. Therefore, in some other cases, to establish the relationship between the 3D patient coordinate system and the projected coordinate system and to accelerate the computation by reducing the amount of traversal required to generate DRR images, another 3D coordinate system x'y'z' is introduced, where z' is related to z... A The directions are consistent, such as Figure 5 As shown. In the 2D projection coordinate system where the projection plane A is located, the 3D rigid transformation is decomposed into in-plane transformations ( ) and two out-of-plane rotations ( , ),z A The position of direction is used Geometric magnification factor representation. For projection plane A, only the CT volume θx' and θy' need to be changed to generate a set of reference DRR images, which correspond to two out-of-plane rotations of projection plane A. , Different combinations of ) and transformations in the two-dimensional plane ( Estimate the out-of-plane rotation by comparing 2D-2D images (X-ray image and the most similar DRR image). , The target area is calculated by optimal matching of X-ray and DRR images. After identifying a reference DRR image with out-of-plane rotation close to the actual value, the in-plane transformation estimation can be accurately obtained. This allows us to obtain the positional change of the target area in the projection coordinate system relative to the target area in the reference CT image, accelerating the calculation, reducing the amount of traversal required to generate DRR images, and directly obtaining a more accurate target area motion in the plane perpendicular to the treatment beam, enabling more accurate lesion tracking. Furthermore, the positional change of the target area relative to the reference CT image at the current moment includes the translational and rotational changes of the target area relative to the reference CT image in the projection coordinate system. The geometric relationship between the projection coordinate system of projection plane A and the patient coordinate system can be expressed by the following geometric relationship, through which the target area motion information (translational and rotational changes) in the patient coordinate system can be determined:

[0109]

[0110]

[0111]

[0112]

[0113]

[0114]

[0115] In the formula, ( represents the translational and rotational changes of the target region relative to the reference CT image in the patient coordinate system, represents the geometric magnification factor, represents the translational and rotational changes of the target region relative to the reference CT image in the patient coordinate system, represents the angle of rotation of the projection plane A around the x-axis.

[0116] Through the above geometric relationship, the target region motion information in the projection coordinate system can be converted to the patient coordinate system to obtain the monitoring value of the target region motion information in the patient coordinate system.

[0117] In one example, the relative motion information of the target region in the patient coordinate system obtained by the above conversion is converted to the treatment beam direction to control the mechanical arm to follow the target region motion in the treatment beam direction, i.e., to realize the treatment beam tracking projection of the target region. In another example, the geometric conversion relationship is the same as the aforementioned geometric relationship, and the difference lies in that the represents the y-direction angle between the treatment beam and the imaging beam, so as to directly obtain the relative motion information of the target region to the treatment beam direction, and control the mechanical arm to follow the target region motion in the treatment beam direction, i.e., to realize the treatment beam tracking projection of the target region.

[0118] In some embodiments, another specific implementation of obtaining the monitoring value of the target region motion information by using a single projection image is provided, which includes: performing 2D registration between the single projection image and each image in the cone beam CT projection image sequence to determine a second target image most matched with the single projection image from the cone beam CT projection image sequence; determining the target region motion information in the 4D cone beam CT projection image under the same respiratory phase according to the respiratory phase of the second target image, and determining the target region motion information as the monitoring value of the target region motion information.

[0119] By performing 2D-2D registration between the monitored single projection image and the cone beam CT projection image sequence obtained in the aforementioned modeling process, the most matched cone beam CT projection image is found, and then the target region motion value under the same respiratory phase as the cone beam CT projection image in the reconstructed 4D-CBCT projection image sequence is found according to the cone beam CT projection image, i.e., the monitoring value of the target region motion information is determined.

[0120] In addition, in the process of modeling by averaging the target region motion information calculated from the cone beam CT projection images under the same respiratory phase, the target region motion information can also be calculated according to each group of images under the same respiratory phase by using one of the above two specific implementation modes of obtaining the monitoring value of the target region motion information by using a single projection image.

[0121] Compared with the radiotherapy system of the existing ring gantry or C-shaped arm gantry, the target region real-time tracking in the embodiment can obtain a larger treatment angle, can greatly reduce the damage to normal tissues while treating the tumor target region, and can obtain a CBCT image with better image quality, faster patient positioning speed, real-time tracking of the target region position, and more accurate treatment. Compared with the prior art, the angle of the treatment beam and the imaging beam is closer, and the tumor target region movement information provided to the direction of the treatment beam is more accurate relative to the orthogonal image.

[0122] It is worth mentioning that each module involved in the embodiment is a logical module. In actual application, one logical unit can be one physical unit, or a part of one physical unit, or realized by a combination of multiple physical units. In addition, in order to highlight the innovative part of the present application, units not closely related to solving the technical problems proposed in the present application are not introduced in the embodiment, but this does not mean that there are no other units in the embodiment.

[0123] Embodiment three:

[0124] Another embodiment of the present application relates to an electronic device, comprising: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the target region real-time tracking method in each of the above embodiments.

[0125] The memory and the processor are connected in a bus mode, and the bus can include any number of interconnected buses and bridges. The bus connects various circuits of one or more processors and memories together. The bus can also connect various other circuits such as peripheral devices, voltage stabilizers, and power management circuits, etc. together, which are well known in the art, and therefore, they will not be further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements such as multiple receivers and transmitters, which provide a unit for communicating with various other devices on the transmission medium. The data processed by the processor is transmitted on the wireless medium through the antenna, and further, the antenna also receives data and transmits the data to the processor.

[0126] The processor is responsible for managing the bus and general processing, and can also provide various functions including timing, peripheral interface, voltage regulation, power management, and other control functions. The memory can be used to store data used by the processor during operation.

[0127] Embodiment four:

[0128] Another embodiment of the present application relates to an image-guided radiotherapy system, as shown in Figure 7 comprising:

[0129] a main mechanical arm 301, the end of which is installed with a transmission device 304 for transmitting a cone-beam and a treatment device 303 for transmitting a treatment beam, the main mechanical arm 301 being capable of driving the treatment device 303 and the transmission device 304 to move synchronously;

[0130] a secondary mechanical arm 302, the end of which is installed with a receiving device 305 for receiving a cone-beam, the secondary mechanical arm 302 driving the receiving device 305 to move synchronously while the main mechanical arm 301 drives the treatment device 303 and the transmission device 304 to move, so that the cone-beam can pass through the target region to reach the receiving device 305 and the receiving device 305 avoids the irradiation of the treatment beam, as shown in Figure 8

[0131] a control device, for tracking the target region in real time by controlling the main mechanical arm and the secondary mechanical arm to move synchronously using the current prediction model and the respiratory phase change; acquiring a single projection image by imaging using the transmission device and the receiving device according to a preset frequency; obtaining a monitoring value of the target region motion information using the single projection image; matching the monitoring value with a predicted value of the target region motion information at the same respiratory phase in the prediction model; in the case that the matching result shows that the monitoring value is inconsistent with the predicted value, re-establishing the prediction model, determining the re-established prediction model as the current prediction model, so as to continue tracking the target region in real time by controlling the main mechanical arm and the secondary mechanical arm to move synchronously using the current prediction model and the respiratory phase change; the prediction model is used to represent the corresponding relationship between the respiratory phase and the target region motion information, and the target region motion information includes six degrees of freedom information. The specific implementation mode of the control device can refer to the foregoing method and device embodiments.

[0132] Hereinafter, the working mode of the image-guided radiotherapy system of the present embodiment will be described by taking the transmission device as an X-ray tube and the receiving device as a detector as an example.

[0133] Working mode one:

[0134] (1) Patient positioning stage, the main mechanical arm 301 drives the X-ray tube to rotate around the target region of the tumor along the human transverse section in an arc trajectory, so that the X-ray is directed towards the target region. Correspondingly, the secondary mechanical arm drives the detector to rotate around the target region along the human transverse section in an arc trajectory, and the main and secondary mechanical arms rotate synchronously, so that the center of the X-ray at each rotation position passes through the human body and is perpendicular to the center of the detector. The system controls the transmission of the X-ray tube and the reception of the detector to acquire images according to a certain frequency. The acquired images are reconstructed into CBCT images according to the CBCT reconstruction algorithm. According to the CBCT image results, the bed 306 or the main and secondary mechanical arms are moved, so that the system knows the accurate tumor target region position. ​

[0135] (2) Target real-time tracking treatment stage, the system controls the main mechanical arm 301 with the treatment device 303 to aim at the target area to emit the treatment beam to perform radiotherapy on the tumor. As shown in FIG. 3B, the main mechanical arm 301 with the treatment device aims at the target area to emit the treatment beam 307, while the X-ray ball tube emits the imaging beam 308 at the position where the target area motion needs to be detected, and the auxiliary mechanical arm 302 drives the detector to receive the emitted X-ray on the opposite side of the human body. The mechanical installation ensures that the treatment beam 307 and the imaging beam 308 can pass through the target area. In order to obtain better image quality, the detector uses a kV level energy detector, but the treatment beam is of MV level energy, and the MV level energy irradiation to the detector will cause damage to the service life and image quality of the detector, so the detector needs to avoid the treatment beam. Figure 8

[0136] The first target real-time tracking scheme:

[0137] a) Configure a respiratory monitoring device outside the patient's body, which can display a respiratory motion curve.

[0138] b) According to the motion trajectory of CBCT, the double mechanical arms perform X-ray imaging while synchronously rotating to obtain a CBCT projection image sequence.

[0139] c) Respiratory modeling, according to the CBCT projection image sequence obtained in b), reconstruct a 4D-CBCT image, the 4D-CBCT image is related to the respiratory phase, and the target motion value at each respiratory phase is calculated according to the 4D-CBCT image to obtain a prediction model representing the relationship between the respiratory phase and the target motion.

[0140] d) During the target real-time tracking treatment process, the position of the target area at the next time is predicted according to the respiratory motion curve and the known prediction model relationship, the main mechanical arm drives the treatment device to move with the target area, and precise projection of the target area is realized.

[0141] e) In order to ensure the accuracy of the target area, a single X-ray image is obtained at a certain frequency to dynamically monitor the target real-time tracking treatment process, the position of the target area is obtained according to the single X-ray image, and then the model is matched. If the matching degree exceeds the threshold (the matching is inconsistent), it means that the model needs to be adjusted, and the model needs to be established again according to b) ~ c). If the matching is consistent, the treatment and monitoring continue.

[0142] One of the methods for obtaining the position of the target area from a single X-ray image: according to the single X-ray image, the position of the tumor center is calculated, and the target motion information corresponding to the corresponding respiratory curve is matched. The specific method is as follows:

[0143] ​The positional change of the target area relative to the reference CT image at the current moment is obtained. The target area motion information in the patient coordinate system determined by the positional change of the target area relative to the reference CT image at the current moment is determined as the monitoring value of the target area motion information.

[0144] In some cases, a single 2D projection image (X-ray image) is the current-moment image, containing the real-time pose of the target area. In 2D-3D registration from a single 2D projection image (X-ray image) to a 3D reference CT image, digitally reconstructed radiographs (DRRs) need to be generated from the 3D CT volume. Intensity-based 2D-3D image registration alters the translation and rotation of the CT volume, generating a set of DRR images for each location. Similarity measurements between the X-ray image and this set of DRR images are calculated, and the DRR image with the highest similarity to the X-ray image is found. The translation and rotation of the CT volume when generating this most similar DRR image represent the rigid transformation (displacement and rotation) of the X-ray image relative to the reference CT image. The region of interest for similarity measurement may differ depending on the scenario. For example, during positioning, or for organs unaffected by respiratory motion, the region of interest might be bony tissue; for organs affected by respiratory motion, the region of interest might be tissue or the target area. Figure 2 The diagram shows cross-sections of the human body and target area, defining a 3D patient (human body) coordinate system xyz, where the x-axis points inwards from the paper, the z-axis is perpendicular to the patient's body, and the y-axis is parallel to the patient's body. The patient's position is determined by three translations and three rotations. These six degrees of freedom are represented. Assume the projection plane A represents a single projected image, S... A It is the source of a single projected image. Figure 3 The projection coordinate system x of projection plane A A y A z A , Figure 4 The patient coordinate system (xyz) and the projected coordinate system (x) are... A y A z A The relationship, x A The direction is the same as the x-direction, and the projection plane A is equivalent to rotating about the x-axis. Angle, such that y and y A Parallel, z and z A Parallel. Following 2D-3D registration, traverse the reference CT images ( A set of DRR images is generated by transforming ( ), and the DRR image with the highest similarity is used ( ). This indicates the change in the position of the target area relative to the target area in the reference CT image at the current moment.

[0145] Generating a set of DRR images by traversing six degrees of freedom and then calculating similarity for each image is a relatively time-consuming process. Therefore, in some other examples, to establish the relationship between the 3D patient coordinate system and the projected coordinate system and to accelerate the computation by reducing the amount of traversal required to generate DRR images, another 3D coordinate system x' y'z' is introduced, where z' is related to z... A The directions are consistent, such as Figure 5 As shown. In the 2D projection coordinate system where the projection plane A is located, the 3D rigid transformation is decomposed into in-plane transformations ( ) and two out-of-plane rotations ( , ),z A The position of direction is used Geometric magnification factor representation. For projection plane A, only the CT volume θx' and θy' need to be changed to generate a set of reference DRR images, which correspond to two out-of-plane rotations of projection plane A. , Different combinations of ) and transformations in the two-dimensional plane ( Estimate the out-of-plane rotation by comparing 2D-2D images (X-ray image and the most similar DRR image). , The target area is calculated by optimal matching of X-ray and DRR images. After identifying a reference DRR image with out-of-plane rotation close to the actual value, the in-plane transformation estimation can be accurately obtained. This allows us to obtain the positional change of the target area in the projection coordinate system relative to the target area in the reference CT image, accelerating the calculation, reducing the amount of traversal required to generate DRR images, and directly obtaining a more accurate target area motion in the plane perpendicular to the treatment beam, enabling more accurate lesion tracking. Furthermore, the positional change of the target area relative to the reference CT image at the current moment includes the translational and rotational changes of the target area relative to the reference CT image in the projection coordinate system. The geometric relationship between the projection coordinate system of projection plane A and the patient coordinate system can be expressed by the following geometric relationship, through which the target area motion information (translational and rotational changes) in the patient coordinate system can be determined:

[0146]

[0147]

[0148]

[0149]

[0150]

[0151]

[0152] wherein, represents the translational and rotational changes of the target volume relative to the reference CT image in the projection coordinate system, represents the geometric magnification factor, represents the translational and rotational changes of the target volume relative to the reference CT image in the patient coordinate system, represents the angle of rotation of the projection plane A around the x-axis.

[0153] In one example, the target volume relative motion information in the patient coordinate system obtained by the above conversion is converted to the treatment beam direction, and the mechanical arm is controlled to follow the target volume motion in the treatment beam direction, i.e. to realize the treatment beam tracking projection of the target volume. In another example, the geometric conversion relationship and the aforementioned geometric relationship are the same, and the difference lies in that the represents the angle of rotation of the projection plane A around the x-axis.

[0154] Second target volume real-time tracking scheme:

[0155] a) Configure a respiratory monitoring device outside the patient's body, which can display a respiratory motion curve.

[0156] b) According to the motion trajectory of CBCT, the double mechanical arms perform X-ray imaging while rotating synchronously to obtain a CBCT projection image sequence.

[0157] c) Respiratory modeling: by calculating the target volume motion information of the same respiratory phase cone beam CT projection image and taking the average value, the more accurate target volume motion information under different respiratory phases is obtained, and the modeling is realized. Specifically, the main mechanical arm and the auxiliary mechanical arm drive the emitting device and the receiving device to rotate synchronously, and the imaging is performed while rotating to obtain a cone beam CT projection image sequence. The images of the same respiratory phase in the cone beam CT projection image sequence are divided into a group, the target volume motion information is calculated according to the images of the same respiratory phase in each group, the average value of the calculated target volume motion information is taken, and the average value is determined as the target volume motion information under the corresponding respiratory phase. According to the target volume motion information under each respiratory phase, a prediction model is established to represent the corresponding relationship between the respiratory phase and the target volume motion information.

[0158] d) In the treatment process of real-time tracking of the target volume, according to the respiratory motion curve and the known prediction model relationship, the position of the target volume at the next moment is predicted, the main mechanical arm is controlled to drive the treatment device to move with the target volume, and the precise projection of the target volume is realized.

[0159] e) In order to ensure the accuracy of the target area, a single X-ray image is obtained at a certain frequency to perform dynamic monitoring of the treatment process of the real-time tracking of the target area, the position of the target area is obtained according to the single X-ray image, and then the model is matched. If the matching degree exceeds the threshold (the matching is inconsistent), it means that the model needs to be adjusted, and the model needs to be established again according to b) ~ c). If the matching is consistent, the treatment and monitoring are continued.

[0160] Method two for obtaining the position of the target area according to the single X-ray image: 2D-2D registration is performed on the monitored single projection image and the cone beam CT projection image sequence obtained in the foregoing modeling process, the most matched cone beam CT projection image is found, and then the same respiratory phase target area motion value as the cone beam CT projection image in the reconstructed 4D-CBCT projection image sequence is found according to the cone beam CT projection image, that is, the monitoring value of the target area motion information is determined.

[0161] Compared with the existing ring gantry or C-arm gantry radiotherapy system, in the embodiment, the main auxiliary mechanical arm adopts the above method to perform real-time tracking of the target area, so that a larger treatment angle can be obtained, and normal tissue damage can be greatly reduced while the tumor target area is treated. The CBCT image obtained by using the main auxiliary mechanical arm in the above manner has better image quality, the patient positioning speed is faster, the target area position can be tracked in real time, and more accurate treatment can be performed. Compared with the prior art, the angles of the treatment beam and the imaging beam are closer, and the tumor target area motion information provided to the direction of the treatment beam is more accurate relative to the orthogonal image.

[0162] Embodiment five:

[0163] Another embodiment of the present application relates to a computer readable storage medium storing a computer program. The computer program is executed by a processor to implement the above-mentioned target area real-time tracking method embodiment.

[0164] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by a program instructing related hardware, the program is stored in a storage medium, and includes a plurality of instructions for causing a device (which can be a single chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (Read-Only Memory, ROM for short), a random access memory (Random Access Memory, RAM for short), a magnetic disk or an optical disk, and various storage program codes.

[0165] Those skilled in the art can understand that the above-mentioned embodiments are specific embodiments for implementing the present application, and various changes can be made in form and details in actual application without departing from the spirit and scope of the present application.

Claims

1. A real-time target tracking device, implemented based on an image-guided radiotherapy system, the image-guided radiotherapy system comprising a main robotic arm and an auxiliary robotic arm, wherein the end of the main robotic arm is equipped with a transmitter for emitting a cone-shaped image beam and a treatment device for emitting a therapeutic beam, and the end of the auxiliary robotic arm is equipped with a receiver for receiving the cone-shaped image beam; characterized in that, While the main robotic arm drives the treatment device and the transmitting device to move, the auxiliary robotic arm drives the receiving device to move synchronously so that the cone-shaped imaging beam can pass through the target area to reach the receiving device and the receiving device avoids the irradiation of the treatment beam. The real-time target tracking device includes: The real-time tracking module is used to track the target area in real time by controlling the synchronous movement of the main robotic arm and the auxiliary robotic arm using the current prediction model and respiratory phase changes. The prediction model is used to characterize the correspondence between respiratory phase and target area motion information, and the target area motion information includes six degrees of freedom information. The image acquisition module is used to acquire a single projected image by using a transmitting device and a receiving device to form an image at a preset frequency. The monitoring and calculation module is used to obtain monitoring values ​​of target area motion information using the single projection image; The information matching module is used to match the monitored value with the predicted value of the target area motion information at the same respiratory phase in the prediction model; The model building module is used to rebuild the prediction model when the matching results show that the monitored value and the predicted value are inconsistent. The rebuilt prediction model is determined as the current prediction model so as to continue to use the current prediction model and respiratory phase changes to track the target area in real time by controlling the synchronous movement of the main robotic arm and the auxiliary robotic arm.

2. The real-time target tracking device according to claim 1, characterized in that, Utilizing current predictive models and respiratory phase changes, the target area is tracked in real time by controlling the synchronized movement of the main and auxiliary robotic arms, including: Obtain respiratory motion curves that characterize changes in respiratory phases in real time; Using current prediction models and respiratory phase changes, target area motion information can be predicted in real time; Based on the predicted target area motion information, the main robotic arm is controlled to move the treatment device so that the treatment beam emitted by the treatment device irradiates the target area.

3. The real-time target area tracking device according to claim 1, characterized in that, Also includes: The main robotic arm and the auxiliary robotic arm drive the transmitting device and the receiving device to rotate synchronously, and imaging is performed at the same time to obtain a cone-beam CT projection image sequence. Reconstruct 4D cone-beam CT projection images based on the cone-beam CT projection image sequence; Target motion information at each respiratory phase is calculated based on the 4D cone-beam CT projection images. Based on the target area motion information at each respiratory phase, a predictive model is established to characterize the correspondence between respiratory phases and target area motion information.

4. The real-time target tracking device according to claim 1, characterized in that, Also includes: The main robotic arm and the auxiliary robotic arm drive the transmitting device and the receiving device to rotate synchronously, and imaging is performed at the same time to obtain a cone-beam CT projection image sequence. Images with the same respiratory phase in the cone-beam CT projection image sequence are grouped together. Target motion information is calculated based on images of the same breathing phase in each group. The calculated target motion information is averaged and the average value is determined as the target motion information under the corresponding breathing phase. Based on the target area motion information at each respiratory phase, a predictive model is established to characterize the correspondence between respiratory phases and target area motion information.

5. The real-time target tracking device according to claim 1, characterized in that, The monitoring values ​​of target area motion information obtained using the single projection image include: Obtain reference CT images for generating a treatment plan; 2D-3D registration is performed based on the single projection image and the reference CT image to obtain the positional change of the target area relative to the reference CT image at the current moment. The target area motion information in the patient coordinate system determined by the positional change of the target area relative to the reference CT image at the current moment is determined as the monitoring value of the target area motion information.

6. The real-time target tracking device according to claim 5, characterized in that, The positional change of the target area relative to the reference CT image at the current moment includes the translational and rotational changes of the target area relative to the reference CT image in the projected coordinate system. The target area motion information in the patient coordinate system is determined by the following geometric relationship between the projected coordinate system and the patient coordinate system: In the formula, ( This represents the translational and rotational changes of the target area relative to the reference CT image in the projected coordinate system. Indicates the geometric magnification factor, ( This represents the translational and rotational changes of the target area relative to the reference CT image in the patient coordinate system. This represents the angle by which the projection plane A rotates about the x-axis.

7. The real-time target tracking device according to claim 3, characterized in that, The monitoring values ​​of target area motion information obtained using the single projection image include: By performing 2D registration between the single projection image and each image in the cone-beam CT projection image sequence, a second target image that best matches the single projection image is determined from the cone-beam CT projection image sequence; Based on the respiratory phase of the second target image, the target area motion information under the same respiratory phase in the 4D cone-beam CT projection image is determined, and this target area motion information is determined as the monitoring value of the target area motion information.

8. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor. These instructions are executed by the at least one processor to enable the at least one processor to perform at least the following: using a current prediction model and respiratory phase changes, tracking the target area in real time by controlling the synchronous movement of the main robotic arm and the auxiliary robotic arm; the prediction model characterizes the correspondence between respiratory phase and target area motion information, the target area motion information including six degrees of freedom; acquiring a single projection image at a preset frequency using a transmitting and receiving device; and obtaining the monitoring value of the target area motion information using the single projection image. The monitored value is matched with the predicted value of the target area motion information at the same respiratory phase in the prediction model; if the matching result shows that the monitored value is inconsistent with the predicted value, the prediction model is re-established and the re-established prediction model is determined as the current prediction model, so as to continue to use the current prediction model and respiratory phase changes to track the target area in real time by controlling the synchronous movement of the main robotic arm and the auxiliary robotic arm.

9. An image-guided radiotherapy system, characterized in that, include: The main robotic arm has a transmitter for emitting cones to form an image beam and a treatment device for emitting a treatment beam at its end. The main robotic arm can drive the treatment device and the transmitter to move synchronously. The auxiliary robotic arm has a receiving device at its end for receiving the cone-shaped imaging beam. While the main robotic arm moves the treatment device and the transmitting device, the auxiliary robotic arm moves the receiving device synchronously so that the cone-shaped imaging beam can pass through the target area to reach the receiving device and the receiving device avoids the irradiation of the treatment beam. The control device is used to track the target area in real time by controlling the synchronous movement of the main robotic arm and the auxiliary robotic arm, utilizing the current prediction model and respiratory phase changes. According to a preset frequency, a single projected image is acquired by using a transmitting and receiving device; the target area motion information is then obtained from the single projected image. The monitored value is matched with the predicted value of the target area motion information at the same respiratory phase in the prediction model. If the matching result shows that the monitored value and the predicted value are inconsistent, the prediction model is re-established and determined as the current prediction model. This allows for continued use of the current prediction model and respiratory phase changes to track the target area in real time through the synchronous movement of the main robotic arm and the auxiliary robotic arm. The prediction model is used to characterize the correspondence between the respiratory phase and the target area motion information, which includes six degrees of freedom information.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it at least performs the following: using the current prediction model and respiratory phase changes, it tracks the target area in real time by controlling the synchronous movement of the main robotic arm and the auxiliary robotic arm. The prediction model is used to characterize the correspondence between respiratory phase and target area motion information. The target area motion information includes six degrees of freedom information. It also performs imaging using a transmitting device and a receiving device at a preset frequency to obtain a single projection image. Finally, it uses the single projection image to obtain the monitoring value of the target area motion information. The monitored value is matched with the predicted value of the target area motion information at the same respiratory phase in the prediction model; if the matching result shows that the monitored value is inconsistent with the predicted value, the prediction model is re-established and the re-established prediction model is determined as the current prediction model, so as to continue to use the current prediction model and respiratory phase changes to track the target area in real time by controlling the synchronous movement of the main robotic arm and the auxiliary robotic arm.

Images