Treatment plan generation method, electronic equipment and storage medium

Abstract

The invention provides a treatment plan generation method, electronic equipment and a storage medium, relates to the technical field of medical treatment, in particular to the technical field of radiotherapy, and is used for solving the problem of relatively low quality of treatment plan generation in the prior art. The method comprises the following steps: acquiring an image of a target region, a contour of the target region and a group of one or more optimization targets; for the target section of each layer of sub-image, determining a symbol distance map of the target section according to the contour of the target section; determining a treatment bed control point set corresponding to the target region and one or more radiation delivery parameters associated with each treatment bed control point in the treatment bed control point set according to the symbol distance map of the target region slice of each layer of sub-image; the treatment bed control point set relates to relative continuous movement between a treatment bed and a radiation beam focus point; a treatment plan is generated based on a set of one or more optimization objectives, the radiation delivery parameters associated with the treatment couch control points in the target region of the optimization objectives.

Description

Technical Field

[0001] The present disclosure relates to the field of medical technology, and in particular to a treatment plan generation method, electronic equipment, and storage medium. Background Art

[0002] Gamma-ray stereotactic radiotherapy is an effective method for treating tumors. The gamma-ray stereotactic radiotherapy system (also known as the "gamma knife") can focus gamma rays, so that the target area at the focal point receives a high dose of radiation, while surrounding healthy tissue receives a lower dose.

[0003] When delivering treatment using a gamma-ray stereotactic radiotherapy system, collimators of varying sizes are typically used to conform radiation arriving at different locations within the target volume into approximate "spheres" of varying diameters. These "spheres" are then used to fill the target volume. By assigning these "spheres" different weights, the dose field formed by the superposition of all the "spheres" within the target volume is ensured to cover as much of the target volume as possible while minimizing damage to normal tissue. This process is also known as the "sphere-filling" process (also known as the "sphere-filling algorithm"). Therefore, the essence of the "sphere-filling algorithm" is to place "spheres" of varying sizes and weights at different locations within the target volume to deliver radiation therapy to the patient.

[0004] Currently, selecting the number, location, size, and weight of "spheres" (also known as "targets") during the sphere-filling process is a critical and difficult issue, crucially impacting the effectiveness of radiotherapy. Furthermore, the larger and more irregular the tumor shape, the more targets are needed, making the selection of target size, location, and weighting exponentially more difficult. In clinical practice, this process often relies on the physician's experience, making treatment planning time-consuming and, when tumors are complex, making optimal selection difficult. Furthermore, because the dose distribution of a single target is high in the center and gradually decreases at the periphery, when multiple targets are superimposed, the dose is inevitably high in the superimposed areas and low in the non-superimposed areas, resulting in uneven dose distribution within the target volume. Traditional "sphere-filling" algorithms also struggle to fully match the dose field to the target contour at the target boundary. Therefore, to accommodate the target boundary shape or irregular inflections, traditional "sphere-filling" algorithms often use smaller targets to fit the target shape, but this also increases treatment time. Summary of the Invention

[0005] The present disclosure provides a treatment plan generation method, an electronic device, and a storage medium, which can improve the quality and efficiency of treatment plan generation.

[0006] In a first aspect, the present disclosure provides a treatment plan generation method, comprising: acquiring an image of a target region, an outline of the target region, and a set of one or more optimization targets, wherein the set of one or more optimization targets includes a desired dose distribution of the target region; the image of the target region includes a sequence of multi-layer sub-images of the target region acquired continuously along a certain anatomical direction, and the outline of the target region includes an outline of a target region slice of each sub-image in the multi-layer sub-image sequence; determining a signed distance map of the target region slice based on the outline of the target region slice for each sub-image layer; the signed distance map representing the distance between each voxel point in the target region slice and a boundary of the outline of the target region slice; determining a treatment couch control point set corresponding to the target region and one or more radiation delivery parameters associated with each treatment couch control point in the treatment couch control point set based on the signed distance map of the target region slice for each sub-image layer; the treatment couch control point set involving continuous relative motion between the treatment couch and a focal point of a radiation beam; and optimizing the radiation delivery parameters associated with the treatment couch control points in the target region based on the set of one or more optimization targets to generate a treatment plan.

[0007] In some embodiments, determining a treatment couch control point set corresponding to the target area based on a signed distance map of a target area slice of each sub-image layer includes: determining, for the target area slice of each sub-image layer, a plurality of key points of the target area slice based on the signed distance map of the target area slice; the plurality of key points are used to characterize contour features of the target area slice; determining a convex hull of the plurality of key points to obtain a treatment couch motion sub-trajectory of the target area slice; and determining a treatment couch control point set corresponding to the target area based on the treatment couch motion sub-trajectory of the target area slice of each sub-image layer.

[0008] In some embodiments, in the signed distance map, the signed distance value of a keypoint is smaller than the signed distance value of a voxel point adjacent to the keypoint.

[0009] In some embodiments, determining a treatment couch control point set corresponding to the target area based on the treatment couch motion subtrajectory of the target area slice of each sub-image layer includes: discretizing the treatment couch motion subtrajectory of the target area slice of each sub-image layer to obtain a treatment couch control point subset corresponding to the target area slice of each sub-image layer; and selecting control points from the treatment couch control point subset corresponding to the target area slice of each sub-image layer to obtain a treatment couch control point set corresponding to the target area.

[0010] In some embodiments, determining a set of treatment couch control points corresponding to the target area based on the treatment couch motion subtrajectories of the target area slices of each sub-image layer includes: selecting trajectory segments from the treatment couch motion subtrajectories of the target area slices of each sub-image layer, and sequentially connecting the selected trajectory segments to obtain a treatment couch motion trajectory of the target area; and discretizing the treatment couch motion trajectory to obtain a set of treatment couch control points corresponding to the target area.

[0011] In some embodiments, radiation delivery parameters include target size, target weight, couch control point position, and beam angle.

[0012] In some embodiments, the target size of the treatment couch control point is determined by: determining the target size of the treatment couch control point based on the distance between the treatment couch control point and the contour boundary of the target volume slice to which the treatment couch control point belongs; or determining the target size of the treatment couch control point based on the minimum signed distance value in a signed distance map of the target volume slice to which the treatment couch control point belongs.

[0013] In some embodiments, when the radiation delivery parameters include target size and couch control point positions, the radiation delivery parameters associated with the couch control points in the target volume are optimized based on a set of one or more optimization objectives to generate a treatment plan, including: obtaining an average dose of voxels in the current target volume that are short of the prescribed dose; optimizing the target size and couch control point positions associated with the current couch control point in the target volume based on the set of one or more optimization objectives to obtain an optimized average dose of voxels in the target volume that are short of the prescribed dose; and optimizing the target size and couch control point positions associated with the next couch control point if the optimized average dose of voxels in the target volume that are short of the prescribed dose is less than the average dose of voxels in the current target volume, until the target sizes and couch control point positions associated with all couch control points are optimized to obtain a treatment plan.

[0014] In some embodiments, when the radiation delivery parameters include target weights, the radiation delivery parameters associated with the treatment bed control points in the target area are optimized based on a set of one or more optimization objectives to generate a treatment plan, including: optimizing the target weights associated with the treatment bed control points in the target area based on a set of one or more optimization objectives until the target optimization function reaches a target value, thereby obtaining a treatment plan; the target optimization function is constructed based on the target dose of the target area, the tissue dose of the tissue surrounding the target area, and the prescription dose.

[0015] In a second aspect, the present disclosure further provides an electronic device comprising: a processor and a memory configured to store processor-executable instructions; wherein the processor is configured to execute the instructions to implement any one of the optional treatment plan generation methods in the first aspect above.

[0016] In a third aspect, the present disclosure further provides a non-volatile storage medium having a computer program stored thereon, wherein when the computer program is read and executed, any one of the optional treatment plan generation methods in the first aspect is implemented.

[0017] Embodiments of the present disclosure provide a treatment plan generation method. After acquiring an image of a target region (including a multi-layer sub-image sequence of the target region acquired continuously along a certain anatomical direction), a contour of the target region (including the contour of a target slice in each sub-image layer in the multi-layer sub-image sequence), and a set of one or more optimization targets (including a desired dose distribution of the target region), a signed distance map of the target slice can be determined for each target slice in each sub-image layer based on the contour of the target slice. Furthermore, based on the signed distance map of the target slice in each sub-image layer, a treatment couch control point set corresponding to the target region and one or more radiation delivery parameters associated with each treatment couch control point in the treatment couch control point set can be determined. The signed distance map represents the distance between each voxel point in the target slice and the contour boundary of the target slice, and the treatment couch control point set involves the continuous relative movement between the treatment couch and the focal point of the radiation beam. Subsequently, based on the set of one or more optimization targets, the radiation delivery parameters associated with the treatment couch control points in the target region can be optimized to generate a treatment plan.

[0018] As can be seen from the above, the set of couch control points corresponding to the target area determined in this disclosure involves the continuous relative movement between the couch and the focal point of the radiation beam. Therefore, when the gantry of the radiotherapy device rotates to emit the radiation beam, the couch also moves synchronously, similar to scanning the target area with the radiation beam, thereby shortening treatment time. Furthermore, because the couch control point set is determined based on the signed distance map of the target area slices of each sub-image of the target area, and the signed distance map of the target area slices of each sub-image is derived based on the contours of each target area slice in the target area, the radiation beam can form a dose field that is consistent with the contour of the target area. In other words, the radiation beam can form a dose field that is more conformal to the target area, thereby improving the quality of the treatment plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to better understand the present invention and do not constitute a limitation of the present invention.

[0020] Figure 1 A schematic diagram of an implementation environment of a treatment plan generation method provided by an embodiment of the present disclosure;

[0021] Figure 2 A flowchart of a treatment plan generation method provided by an embodiment of the present disclosure;

[0022] Figure 3 A schematic diagram of a symbol distance graph provided in an embodiment of the present disclosure;

[0023] Figure 4 A schematic diagram of a coordinate system for determining a control point set of a treatment couch provided in an embodiment of the present disclosure;

[0024] Figure 5A flowchart of another treatment plan generation method provided in an embodiment of the present disclosure;

[0025] Figure 6 A flowchart of another treatment plan generation method provided in an embodiment of the present disclosure;

[0026] Figure 7 A schematic structural diagram of a treatment plan generating device provided in an embodiment of the present disclosure;

[0027] Figure 8 A schematic block diagram of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] The following will be combined with the accompanying drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0029] In the description of the present disclosure, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present disclosure and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present disclosure. In addition, the terms "first", "second" and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first", "second" and "third" may explicitly or implicitly include one or more of the said features. In the description of the present disclosure, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0030] In the description of this disclosure, the word "exemplary" is used to mean "serving as an example, illustration, or illustration." Any embodiment described in this disclosure as "exemplary" is not necessarily to be construed as being preferred or advantageous over other embodiments. The following description is given to enable any person skilled in the art to implement and use the present disclosure. In the following description, details are listed for the purpose of explanation. It should be understood that one of ordinary skill in the art will recognize that the present disclosure can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present disclosure with unnecessary details. Therefore, the present disclosure is not intended to be limited to the embodiments shown, but is to be consistent with the widest scope consistent with the principles and features disclosed herein.

[0031] It should be noted that since the treatment plan generation method provided in the embodiment of the present disclosure is executed in a treatment plan generation device, the processing objects of the treatment plan generation device are all in the form of data or information. For example, time is actually time information. It can be understood that if size, quantity, position, etc. are mentioned in subsequent embodiments, the corresponding data exist so that the treatment plan generation device can process them. The details will not be repeated here.

[0032] As described in the background, during radiotherapy with a gamma-ray stereotactic radiotherapy system, conventional techniques typically rely on the physician's experience to set the number, location, model, and weight of targets. This results in not only a time-consuming treatment plan but also difficulty selecting the optimal target when the tumor shape is complex. Furthermore, because the dose distribution of a single target is high in the center and gradually decreases around the edges, when multiple targets are superimposed, it is inevitable that the dose in the superimposed area will be too high, the dose in the non-superimposed area will be too low, and the dose distribution within the target area will be uneven. Conventional techniques also struggle to fully match the dose field to the target contour at the target boundary. Therefore, to adapt to the target boundary shape or irregular turning points, conventional techniques often use smaller targets to fit the target shape, but this also increases treatment time.

[0033] Based on the above technical issues, embodiments of the present disclosure provide a treatment plan generation method. After acquiring an image of a target area (including a multi-layer sub-image sequence of the target area continuously acquired along a certain anatomical direction), a contour of the target area (including the contour of the target area slice of each sub-image layer in the multi-layer sub-image sequence), and a set of one or more optimization targets (including a desired dose distribution of the target area), a signed distance map of the target area slice can be determined for each target area slice in each sub-image layer based on the contour of the target area slice. Furthermore, based on the signed distance map of the target area slice in each sub-image layer, a treatment couch control point set corresponding to the target area and one or more radiation delivery parameters associated with each treatment couch control point in the treatment couch control point set can be determined. The signed distance map is used to represent the distance between each voxel point in the target area slice and the contour boundary of the target area slice. The treatment couch control point set involves the continuous relative movement between the treatment couch and the focus of the radiation beam. Subsequently, based on the set of one or more optimization targets, the radiation delivery parameters associated with the treatment couch control points in the target area can be optimized to generate a treatment plan.

[0034] As can be seen from the above, the set of couch control points corresponding to the target area determined in this disclosure involves the continuous relative movement between the couch and the focal point of the radiation beam. Therefore, when the gantry of the radiotherapy device rotates to emit the radiation beam, the couch also moves synchronously, similar to scanning the target area with the radiation beam, thereby shortening treatment time. Furthermore, because the couch control point set is determined based on the signed distance map of the target area slices of each sub-image of the target area, and the signed distance map of the target area slices of each sub-image is derived based on the contours of each target area slice in the target area, the radiation beam can form a dose field that is consistent with the contour of the target area. In other words, the radiation beam can form a dose field that is more conformal to the target area, thereby improving the quality of the treatment plan.

[0035] Figure 1 Schematic diagram of an implementation environment of a treatment plan generation method provided by an embodiment of the present disclosure, the implementation environment includes: an image acquisition device 101, a treatment plan generation device 102 and a radiotherapy device 103.

[0036] The image acquisition device 101 is used to capture images of the tumor site and surrounding normal tissue of a target object (e.g., a patient to be treated, an experimental subject, a phantom, etc.). In the disclosed embodiment, the image acquisition device 101 can capture images of a target region of the target object (including a sequence of multi-layer sub-images of the target region captured continuously along a specific anatomical direction). The images of the target region are subsequently uploaded to the treatment plan generation device 102, so that the treatment plan generation device 102 can execute a subsequent treatment plan generation method based on the images of the target region.

[0037] In some embodiments, the image acquisition device 101 can be at least one of a computed tomography (CT) device, an emission computed tomography (ECT) device, a magnetic resonance imaging (MRI) device, a positron emission tomography (PET) device, and an ultrasound examination device.

[0038] The treatment plan generation device 102 is a device used to obtain images of the target object captured by the image acquisition device 101 in order to formulate, optimize, and evaluate a treatment plan. In the disclosed embodiment, the treatment plan generation device 102 can obtain a set of one or more optimization targets and receive an image of the target area captured by the image acquisition device 101, and then outline the image of the target area to obtain the outline of the target area (the outline of the target area can also be obtained using third-party outline software). Subsequently, the treatment plan generation device 102 can also formulate, optimize, and evaluate a treatment plan based on the image of the target area, the outline of the target area, and the set of one or more optimization targets.

[0039] The treatment plan generating device 102 may run a radiation treatment planning system (TPS), which provides functions of formulating, optimizing, and evaluating treatment plans, such as the RTpro TPS system.

[0040] In some embodiments, the treatment plan generating device 102 may include a TPS client and a TPS server.

[0041] The TPS client can be at least one of a smartphone, smartwatch, desktop computer, laptop, virtual reality terminal, augmented reality terminal, wireless terminal, and portable laptop. For example, in some embodiments, a user can run the treatment planning system on a TPS server through the TPS client, triggering the TPS server to execute the treatment plan creation and optimization process and display the completed / optimized treatment plan. This effectively saves user time and provides a more intuitive presentation of the completed / optimized treatment plan, facilitating user evaluation.

[0042] Among them, the TPS server can be an independent physical server, or a server cluster or distributed file system composed of multiple physical servers, or at least one of the cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data or artificial intelligence platforms, and the embodiments of the present disclosure are not limited to this. In some embodiments, the number of the above-mentioned TPS servers can be more or less, and the embodiments of the present disclosure are not limited to this. Of course, the TPS server can also include other functions to provide more comprehensive and diversified services. In some embodiments, the TPS server is used to provide background services for the above-mentioned TPS client, such as executing the treatment plan optimization process.

[0043] In some embodiments, the treatment plan generation device 102 may be a computer device with a graphical user interface (GUI), including one or more processors, memory, and one or more application programs. For example, the treatment plan generation device 102 may include a treatment plan generation system application, and the processor of the treatment plan generation device 102 executes the treatment plan generation system application to implement the treatment plan generation method provided in the embodiments of the present disclosure.

[0044] Furthermore, in some embodiments, the treatment plan generating device 102 may include a processor configured to implement the treatment plan generating method provided in the embodiments of the present disclosure.

[0045] The radiotherapy device 103 is a device for performing radiotherapy on a target object. In one embodiment of the present disclosure, the radiotherapy device 103 can obtain the treatment plan generated by the treatment plan generating device 102 and execute the treatment plan.

[0046] In some embodiments, the radiotherapy device 103 may include a gantry 1031 , a treatment head 1032 , and a support device 1033 .

[0047] The gantry 1031 can be a rotatable gantry. The treatment head 1032 can be mounted on the gantry and configured to emit radiation beams, such as gamma rays, MV-level X-rays, proton beams, etc., to perform radiotherapy on the target object. The support device 1033 is configured to support and move the target object and can be a treatment couch.

[0048] In some embodiments, when the target object is on the support device 1033 , the rotation of the gantry 1031 can drive the treatment head 1032 to perform 360-degree irradiation around the target object, thereby completing radiotherapy.

[0049] In the disclosed embodiment, the support device 1033 can move simultaneously with the rotation of the gantry 1031. That is, when the gantry 1031 rotates to emit a beam, the support device 1033 also moves along a predetermined trajectory, so that the focus of the radiation beam moves continuously within the target area, ultimately forming a dose field with the same shape as the target area at the target area, and the edge of the dose field is adapted to the edge contour of the target area.

[0050] The following is based on Figure 1 The scenario shown introduces the treatment plan generation method provided by the embodiment of the present disclosure.

[0051] The treatment plan generation method provided in the embodiment of the present disclosure is applied to Figure 1 The treatment plan generating device 102 in. Figure 2 FIG. 1 is a flow chart of a treatment plan generation method provided by an embodiment of the present disclosure. Figure 2 As shown, the treatment plan generation method includes:

[0052] S201: Acquire an image of a target area, a contour of the target area, and a set of one or more optimization targets.

[0053] The target area includes the area to be treated of the target object.

[0054] For example, the target object may be a phantom, a human body, an experimental subject, an animal, etc. The target volume may be a tumor region, an organ at risk region, etc. of the target object. It should be noted that the target volume may also be referred to as a planning target volume (PTV).

[0055] The image of the target area includes a multi-layer sub-image sequence of the target area acquired continuously along a certain anatomical direction.

[0056] Optionally, the aforementioned anatomical direction may be the head-to-foot direction of the target object, or the left-right direction of the target object.

[0057] like Figure 1 As can be seen from the description, the image acquisition device can acquire images of the target area of ​​the target object, and the treatment plan generation device obtains the images of the target area of ​​the target object acquired by the image acquisition device.

[0058] Optionally, the treatment plan generating device may also acquire an image of a target area of ​​the target object in response to a medical record import operation by a user (eg, a physician).

[0059] The contour of the target area is obtained by performing a contouring operation on the image of the target area. Since the image of the target area includes a multi-layer sub-image sequence of the target area acquired continuously along a certain anatomical direction, the contour of the target area also includes the contour of the target area slice of each sub-image layer in the multi-layer sub-image sequence. The contour of the target area slice of each sub-image layer can be obtained by performing a target area contouring operation on each sub-image layer in the multi-layer sub-image sequence included in the image of the target area.

[0060] In some embodiments, combined Figure 1 When the treatment plan generation device obtains the image of the target area captured by the image acquisition device, the treatment plan generation device can outline the target area contour for each layer of sub-image in the multi-layer sub-image sequence included in the image of the target area to obtain the contour of the target area slice of each layer of sub-image.

[0061] In some embodiments, the treatment plan generating device may be further connected to a third-party software program for delineating the target area contour for each layer of sub-images to obtain the contour of the target area slice of each layer of sub-images.

[0062] Optionally, the aforementioned third-party software program may also be deployed in the treatment plan generating device.

[0063] Optionally, when delineating the target area for each layer of sub-image, the physician may perform the delineation operation on the treatment plan generating device. The treatment plan generating device may obtain the contour of the target area slice of each layer of sub-image in response to the physician's delineation operation.

[0064] Alternatively, the treatment plan generating device may also automatically outline the target area for each layer of sub-image using contouring software.

[0065] Optionally, the contouring software may be installed in a contouring device within a contouring system connected to a treatment plan generator. The contouring device uses the contouring software to delineate the target area for each sub-image layer to obtain the contours of the target area slices for each sub-image layer. The contours of the target area slices for each sub-image layer may then be sent to the treatment plan generator.

[0066] Optionally, the above-mentioned contouring software may also be deployed in a treatment plan generating device.

[0067] A set of one or more optimization objectives includes a desired dose distribution for a target volume.

[0068] Optionally, a desired dose distribution can be constructed using a prescription dose. A prescription is a specific radiation dose requirement developed by a physician based on the tumor type, anatomical location, and individual circumstances of the target area. It aims to ensure that the target area receives an adequate dose to kill cancer cells while maximizing the protection of surrounding normal tissue. It is the core basis for treatment planning.

[0069] Optionally, a set of one or more optimization objectives may further include a minimum dose limit that the target volume needs to receive and a maximum dose limit that organs at risk around the target volume can receive.

[0070] In some embodiments, the treatment plan generating device may receive a set of one or more optimization goals for a target object input by a physician.

[0071] S202 : For the target area slice of each layer of sub-image, determine the signed distance map of the target area slice according to the contour of the target area slice.

[0072] Among them, the signed distance map (SDM), also known as the signed distance function, is a way to describe the distance relationship between each pixel in the image and the target boundary (such as the outline of an object). The signed distance map can assign a signed distance value to each pixel in the image, and the signed distance value represents the signed distance between the corresponding pixel and the target boundary. When the signed distance value is positive, it means that the pixel is outside the target boundary. Correspondingly, when the signed distance value is negative, it means that the pixel is inside the target boundary. Correspondingly, when the signed distance value is zero, it means that the pixel is on the target boundary.

[0073] In the disclosed embodiment, the signed distance map is used to represent the distance between each voxel point in the target slice and the contour boundary of the target slice. Therefore, the signed distance map of the target slice can well reflect the distance relationship between each voxel point in the target slice and the edge of the target area (i.e., the contour boundary of the target slice).

[0074] Optionally, the treatment plan generating device may utilize a grassfire algorithm to determine a signed distance map of the target slice based on the contour of the target slice.

[0075] For example, Figure 3 A schematic diagram of a symbol distance diagram provided by an embodiment of the present disclosure. Figure 3As shown, taking a target slice of a sub-image layer as an example, the treatment plan generation device can first determine the contour boundary of the target slice and set the signed distance value of the voxel points on the contour boundary to 0. Accordingly, the signed distance value of the voxel points within the contour boundary can be set to a negative value, and the smaller the negative value, the farther the voxel point is from the contour boundary of the target slice. Correspondingly, the signed distance value of the voxel points outside the contour boundary can be set to a positive value, and the larger the positive value, the farther the voxel point is from the contour boundary of the target slice.

[0076] S203 : Determine, based on the signed distance map of the target area slice of each layer of the sub-image, a treatment couch control point set corresponding to the target area and one or more radiation delivery parameters associated with each treatment couch control point in the treatment couch control point set.

[0077] The treatment couch control point set involves the relative continuous movement between the treatment couch and the radiation beam focus point.

[0078] Specifically, in radiotherapy, to irradiate the entire target area as closely as possible, it is desirable for the treatment couch control point set corresponding to the target area to best describe the shape (i.e., outline) of the target area. Therefore, the treatment plan generator can first determine the outline characteristics of each target slice based on the signed distance map of the target slices in each sub-image layer. Subsequently, based on the outline characteristics of each target slice, the treatment plan generator can determine the treatment couch control point set corresponding to the target area and one or more radiation delivery parameters associated with each treatment couch control point in the treatment couch control point set.

[0079] In some embodiments, for each target slice in each sub-image layer, the treatment plan generation device may select key points from the signed distance map of the target slice that characterize the target slice's contour features and determine the couch motion sub-trajectory for the target slice based on these key points. Subsequently, the treatment plan generation device may determine the couch control point set corresponding to the target region based on the couch motion sub-trajectory for each target slice in each sub-image layer.

[0080] Specifically, since the treatment head on the radiotherapy device rotates 360° with the gantry and emits a beam toward the patient on the treatment couch during this rotation, the focus of the beam emitted by the treatment head is fixed during this process. To achieve continuous relative movement between the treatment couch and the focal point of the radiation beam, the treatment couch needs to move continuously relative to the focal point of the radiation beam while the treatment head is emitting the beam. Therefore, to achieve movement control of the treatment couch, the treatment plan generation device can process (e.g., discretize) the treatment couch motion sub-trajectory for each target volume slice to obtain a set of treatment couch control points. Of course, the treatment plan generation device can also first determine the treatment couch motion trajectory of the target target area based on the treatment couch motion sub-trajectory for each target volume slice, and then process (e.g., discretize) the treatment couch motion trajectory for the target target area to obtain a set of treatment couch control points.

[0081] The specific process of the treatment plan generation device determining the treatment bed control point set corresponding to the target area can be referred to below. Figure 5 The detailed description is omitted here.

[0082] As can be seen above, because the treatment couch needs to continuously move relative to the radiation beam focal point, each couch control point corresponds to a beam angle and position. The number of couch control points in the couch control point set corresponding to the target area is related to the number of beam angles of the treatment head. Furthermore, for each target area slice, the number of couch control points in the target area slice is also related to the number of beam angles of the treatment head.

[0083] For example, Figure 4 Schematic diagram of a coordinate system for determining a control point set of a treatment bed provided in an embodiment of the present disclosure. Figure 4 As shown, for each target slice, the treatment plan generation device can establish a coordinate system with the center point O(X, Y) of the target slice as the origin, with the X-axis pointing left and the Y-axis pointing upward. The X-axis coordinate of the center point is the sum of the maximum and minimum values ​​of the target in the horizontal direction divided by 2, and the Y-axis coordinate is the sum of the maximum and minimum values ​​of the target in the vertical direction divided by 2.

[0084] Next, the treatment plan generation device can select the angle θ in the interval [0°, 360°] at intervals of 6°, that is, the values ​​of the angle θ can be 0°, 6°, ..., 357°. Next, the treatment plan generation device can extend a ray along the direction with an angle θ with the positive direction of the X-axis from the origin as the starting point, and determine the point where the ray intersects with the boundary of the treatment bed motion sub-trajectory of the target area slice as the treatment bed control point, and the gantry angle corresponding to the treatment bed control point is θ, and the control point sequence is θ / 6° (for example Figure 4 The control point of the treatment bed corresponding to 0° and the control point of the treatment bed corresponding to 144°).

[0085] After determining the set of treatment couch control points corresponding to the target area, the treatment plan generating device also needs to determine one or more radiation delivery parameters associated with each treatment couch control point.

[0086] In some embodiments, radiation delivery parameters include target size, target weight, couch control point position, and beam angle, among others.

[0087] The target size can be set by the collimator model. Commonly used collimator models include 4mm, 8mm, 14mm, 18mm, etc.

[0088] In some embodiments, the preferred approach for radiotherapy planning requires that the irradiation field fill the entire target volume as closely as possible, and that the irradiation fields of different targets minimize repetitions within the target volume to achieve the best therapeutic effect. In other words, when emitting a beam, the radiotherapy device must irradiate from the first to the last couch control point using the collimator's aperture, ultimately producing a dose field that approximates the target volume's shape. In this case, the "target size" should be similar to or slightly larger than the "distance between the couch control point and the target slice's outline."

[0089] In some embodiments, when the radiotherapy plan requires high conformality, the "target size" can be set to be similar to the "distance between the couch control point and the outline of the target slice." In this case, the target size of the couch control point can be determined by the distance between the couch control point and the outline of the target slice to which it belongs. Within the target slices configured in this manner, the target sizes associated with the couch control point may vary.

[0090] For example, a target slice includes couch control point 1 and couch control point 2. According to the signed distance map for this target slice, the distance between couch control point 1 and the target slice's outline is 4 mm. Therefore, the target size for couch control point 1 is set to 4 mm, meaning a 4 mm collimator is selected. The distance between couch control point 2 and the target slice's outline is 7 mm. Therefore, the target size for couch control point 2 is set to 8 mm, meaning an 8 mm collimator is selected.

[0091] In some embodiments, when a radiotherapy plan requires a shorter treatment duration, the "target size" can be set slightly larger than the "distance between the couch control point and the target slice's outline." In this case, the target size of the couch control point can be determined by using the minimum signed distance value in the signed distance map for the target slice to which the couch control point belongs. In this way, all target sizes associated with the couch control point remain the same across all target slices.

[0092] For example, when the minimum signed distance value in the signed distance map of a target slice is -4, the target point size of the treatment bed control point corresponding to the target slice is set to 4 mm, that is, a 4 mm collimator model is selected.

[0093] The beam angle refers to the angle at which the treatment head on the radiotherapy device emits rays toward the target object within a 360-degree range, that is, from which angles within the 360-degree range the treatment head should emit rays toward the target object.

[0094] For example, the beam angle resolution can be 6°, which can be set by default or to another value (e.g., 12°). However, in practical applications, it is not recommended to set this value too small or too large. Setting it too small increases the burden of dose calculation and the complexity of control, while setting it too large can lead to dose calculation errors and affect the accuracy of radiotherapy.

[0095] After determining each couch control point in the couch control point set corresponding to the target area, a beam angle can be assigned to each couch control point. Angle assignment starts at 0° and continues with 6°, 12°, 18°, and so on until the last couch control point is assigned.

[0096] After determining the beam angle and target size, the final dose field of the target area is obtained by weighted superposition of the dose fields at all treatment couch control points. Therefore, the initial target weight of each treatment couch control point can be set to a default value (e.g., 1).

[0097] S204: Based on a set of one or more optimization objectives, optimize the radiation delivery parameters associated with the treatment couch control points in the target area to generate a treatment plan.

[0098] Specifically, after determining the treatment couch control point set corresponding to the target area and one or more radiation delivery parameters associated with each treatment couch control point in the treatment couch control point set, since the final dose field of the target area is obtained by weighted superposition of the dose fields at all treatment couch control points, the weighted superposition of the dose fields at each treatment couch control point may not meet the desired dose distribution of the target area. Therefore, the treatment plan generation device can optimize all treatment couch control points and the associated radiation delivery parameters in the target area based on a set of one or more optimization objectives, that is, optimize the dose distribution of the target area, thereby generating a higher quality treatment plan.

[0099] The specific process of the treatment plan generating device optimizing the radiation delivery parameters associated with the treatment bed control points in the target area based on a set of one or more optimization objectives can be referred to below regarding Figure 6 The detailed description is omitted here.

[0100] As can be seen from the above, the set of couch control points corresponding to the target area determined in this disclosure involves the continuous relative movement between the couch and the focal point of the radiation beam. Therefore, when the gantry of the radiotherapy device rotates to emit the radiation beam, the couch also moves synchronously, similar to scanning the target area with the radiation beam, thereby shortening treatment time. Furthermore, because the couch control point set is determined based on the signed distance map of the target area slices of each sub-image of the target area, and the signed distance map of the target area slices of each sub-image is derived based on the contours of each target area slice in the target area, the radiation beam can form a dose field that is consistent with the contour of the target area. In other words, the radiation beam can form a dose field that is more conformal to the target area, thereby improving the quality of the treatment plan.

[0101] The following combination Figure 2 , the process of determining the treatment bed control point set corresponding to the target area provided by the embodiment of the present disclosure is described in detail. Figure 2 ,like Figure 5 As shown, in the above S203, the method in which the treatment plan generating device determines the treatment bed control point set corresponding to the target area according to the signed distance map of the target area slice of each layer of the sub-image specifically includes:

[0102] S501 : For a target area slice of each layer of sub-image, determine a plurality of key points of the target area slice according to a signed distance map of the target area slice.

[0103] Among them, multiple key points are used to characterize the contour features of the target slice.

[0104] Specifically, because multiple key points are used to characterize the contour features of a target slice, these key points can be connected within the target slice to describe the target contour. Furthermore, during treatment, radiotherapy equipment typically uses collimators of varying sizes to conform radiation arriving at different locations within the target into approximate "spheres" of varying diameters. This means that radiation emitted by the radiotherapy equipment has a specific irradiation range. Therefore, these key points can be located deeper within the target slice.

[0105] In some embodiments, in the signed distance map, the signed distance value of the key point is smaller than the signed distance value of the voxel points adjacent to the key point. In other words, the plurality of key points may be voxel points whose signed distance values ​​are local minimums in the signed distance map of the target slice.

[0106] Among them, the voxel point of the local minimum value is the voxel point in the 4-domain (i.e., above, below, left, and right of the voxel point) where there is no voxel point with a smaller signed distance value than the voxel point, for example Figure 3 The 5 circled voxel points.

[0107] S502: Determine the convex hull of multiple key points to obtain a treatment couch motion sub-trajectory of a target area slice.

[0108] Specifically, for the extracted key points, the convex hull solution algorithm can be used to determine the convex hull of multiple key points. The convex hull of multiple key points can be used to obtain the motion sub-trajectory of the treatment bed of the target area slice. For example Figure 3 The motion subtrajectories of the treatment bed are connected by dotted lines.

[0109] S503: Determine a set of control points of the treatment couch corresponding to the target area according to the movement sub-trajectory of the treatment couch of the target area slice of each layer of the sub-image.

[0110] In some embodiments, the method for the treatment plan generating device to determine the treatment couch control point set corresponding to the target area based on the treatment couch motion sub-trajectory of the target area slice of each sub-image layer specifically includes:

[0111] The treatment couch motion subtrajectory of the target area slice of each layer of sub-image is discretized to obtain a subset of treatment couch control points corresponding to the target area slice of each layer of sub-image. Control points are then selected from the subset of treatment couch control points corresponding to the target area slice of each layer of sub-image to obtain a treatment couch control point set corresponding to the target area.

[0112] Specifically, after obtaining the couch motion subtrajectory for the target slice of each sub-image layer, the treatment plan generation device can discretize the couch motion subtrajectory for each target slice of the sub-image layer to facilitate dose calculation. Each discretized point serves as a couch control point, thereby obtaining a subset of couch control points corresponding to the target slice of each sub-image layer. To avoid the increased difficulty of dose calculation due to an excessive number of control points, the treatment plan generation device selects control points from the subset of couch control points corresponding to the target slice of each sub-image layer to obtain the couch control point set corresponding to the target area.

[0113] Optionally, the treatment plan generation device can number the subset of treatment bed control points corresponding to the target area slices of each sub-image. Assuming that the subset of treatment bed control points corresponding to the target area slices of each sub-image includes 60 control points, the treatment plan generation device can start from control point 1 of the first target area slice and intercept control points within a 90° range for each target area slice, that is, 15 control points: control points 1-15 for the first target area slice, control points 16-30 for the second target area slice, and so on. After obtaining the treatment bed control point set corresponding to the target target area, the treatment plan generation device can assign serial numbers to the control points one by one in the order from the first target area slice to the last layer, with serial numbers being 1, 2, ..., N.

[0114] In some embodiments, the method for the treatment plan generating device to determine the treatment couch control point set corresponding to the target area based on the treatment couch motion sub-trajectory of the target area slice of each sub-image layer specifically includes:

[0115] Within the target slices of each sub-image layer, trajectory segments are selected from the couch motion sub-trajectory. These segments are then sequentially connected to obtain the couch motion trajectory for the target area. Subsequently, the couch motion trajectory is discretized to obtain the couch control point set corresponding to the target area.

[0116] Specifically, after obtaining the couch motion subtrajectory for the target area slice in each sub-image layer, the treatment plan generation device may further determine the couch motion trajectory for the target area based on the couch motion subtrajectory for the target area slice in each sub-image layer. In this case, the treatment plan generation device may select trajectory segments from the couch motion subtrajectory for the target area slice in each sub-image layer.

[0117] Optionally, the treatment plan generation device may divide the treatment couch motion sub-trajectory corresponding to the target area slice of each layer of sub-image into trajectory segments. Assuming that the treatment couch motion sub-trajectory corresponding to the target area slice of each layer of sub-image includes four trajectory segments (each trajectory segment is a trajectory segment within a 90° range), the treatment plan generation device may select the first trajectory segment from the first layer of target area slices (for example, a trajectory segment within a 0° to 90° range), select the second trajectory segment from the second layer of target area slices (for example, a trajectory segment within a 90° to 180° range), and so on, until the trajectory segments of the target area slices of each layer of sub-image are obtained.

[0118] The treatment plan generator then sequentially connects the selected trajectory segments to derive the couch's trajectory for the target area. To facilitate dose calculation, the treatment plan generator discretizes the couch's trajectory for the target area, using each discretized point as a couch control point to generate the couch's control point set for the target area.

[0119] The following combination Figure 2 The process for optimizing radiation delivery parameters associated with couch control points within a target volume, as provided in embodiments of the present disclosure, is described in detail. Specifically, to ensure that the treatment plan's dose field more closely matches the desired dose requirements, the treatment plan generator can optimize the target size, couch control point position, and target volume weighting of the couch control points.

[0120] In the embodiment of the present disclosure, the treatment plan generating device can optimize the target size and the position of the treatment bed control point based on the same optimization goal. That is, when the radiation delivery parameters include the target size and the position of the treatment bed control point, the treatment plan generating device can optimize the target size and the position of the treatment bed control point based on the same optimization goal. Figure 2 ,like Figure 6 As shown, in the above S204, the treatment plan generating device optimizes the radiation delivery parameters associated with the treatment couch control points in the target area based on a set of one or more optimization objectives to generate a treatment plan, specifically including:

[0121] S601. Obtain an average dose of voxel points within the current target volume that are less than the prescribed dose, and optimize the target point size and the position of the treatment couch control point associated with the current treatment couch control point in the target volume based on a set of one or more optimization objectives to obtain an optimized average dose of voxel points within the target volume that are less than the prescribed dose.

[0122] In the disclosed embodiment, during the optimization of the target size and position associated with the couch control points, the same optimization objective can be set. For example, after optimization, the average dose of voxels within the target volume that are below the prescribed dose is less than the average dose of voxels within the current target volume that are below the prescribed dose. In this case, the target size and position associated with the couch control points can be optimized based on this optimization objective.

[0123] It should be noted that although the optimization objectives for the target size and the position of the treatment couch control point associated with the treatment couch control point are the same, the treatment plan generating device may optimize the target size and the position of the treatment couch control point separately or simultaneously, and the embodiments of the present disclosure are not limited to this.

[0124] In the process of optimizing the target size, considering that the shape of the target area is usually large in the middle and small on both sides, the treatment plan generation device can first optimize the target size of the treatment bed control point of the target area slice in the middle layer of the target area, and then optimize the target size of the treatment bed control point of the target area slice on both sides of the target area to protect the normal tissue around the target area.

[0125] Specifically, the treatment plan generating device can optimize the target size by selecting the treatment bed control points in descending order according to the normal distribution probability (the probability of the treatment bed control points in the target slices in the middle layer of the target area is the highest, and the probability of the treatment bed control points in the target slices on both sides of the target area is the lowest).

[0126] Optionally, when optimizing the target size of the treatment couch control point, the optimization may be performed by adjusting the unit of the target size of the treatment couch control point, for example, increasing the target size of the treatment couch control point by one unit.

[0127] In the process of optimizing the positions of the treatment couch control points, the positions of the treatment couch control points may be optimized in sequence according to the order of the treatment couch control points.

[0128] Optionally, when optimizing the position of the treatment bed control point, the optimization can be performed by adjusting the direction and step size of the treatment bed control point, for example, moving the treatment bed control point position of the treatment bed control point along a random direction and a preset step size (generally set to 2 mm).

[0129] S602: If the average dose of the voxels in the optimized target volume that are less than the prescribed dose is less than the average dose of the voxels in the current target volume that are less than the prescribed dose, optimize the target size and position of the next couch control point until the target sizes and positions of all couch control points are optimized to obtain a treatment plan.

[0130] Specifically, in order to make the dose field of the target area meet the expected dose requirements as much as possible, in the process of optimizing the target point size and the position of the treatment bed control point associated with the treatment bed control point, the optimization goal is that the average dose of the voxel points in the optimized target area that are less than the prescribed dose is less than the average dose of the voxel points in the current target area that are less than the prescribed dose, that is, the dose of each voxel point is close to or greater than the prescribed dose, so that the generated treatment plan can achieve the best treatment effect.

[0131] The above average dose satisfies the following formula:

[0132]

[0133] Where n is the number of voxels in the target area that are less than the prescribed dose.

[0134] As can be seen from the above step S601, when optimizing the target size of the treatment couch control point, the target size of the treatment couch control point can be increased by one unit. If the average dose of voxels within the target area that are less than the prescribed dose after the one-unit increase is less than the average dose of voxels within the target area that are less than the prescribed dose before the one-unit increase, the optimization process is retained. Otherwise, the optimization process is ignored.

[0135] Repeat the above steps until the target sizes of all the control points of the treatment bed are optimized.

[0136] Accordingly, as can be seen from the above step S601, when optimizing the position of the couch control point, the couch control point can be moved. If the average dose of the voxels within the target volume that are below the prescribed dose after the movement is less than the average dose of the voxels within the target volume that are below the prescribed dose before the movement, the optimization process is retained. Otherwise, the optimization process is ignored.

[0137] Repeat the above steps until the positions of all the treatment bed control points are optimized.

[0138] Subsequently, after the positions of all the treatment couch control points are optimized, in order to ensure smoothness of the treatment couch movement process, the treatment plan generating device may perform Gaussian smoothing on the optimized positions of the treatment couch control points.

[0139] In some embodiments, the treatment plan generating device also needs to optimize the target area weights of the treatment couch control points.

[0140] Optionally, the treatment plan generating device can optimize the target weights of the treatment bed control points using a weight optimization algorithm. The weight optimization algorithm can be a simulated annealing algorithm, a genetic algorithm, a linear programming algorithm, a particle swarm algorithm, a gradient descent algorithm, or the like.

[0141] In the embodiment of the present disclosure, the treatment plan generating device can also use the stochastic gradient descent algorithm to optimize the target weights of the treatment bed control points. That is, when the radiation delivery parameters include target weights, combined with Figure 2 ,like Figure 6 As shown, in the above S204, the treatment plan generating device optimizes the radiation delivery parameters associated with the treatment couch control points in the target area based on a set of one or more optimization objectives to generate a treatment plan, specifically including:

[0142] S603: Based on a set of one or more optimization objectives, optimize the target point weights associated with the treatment couch control points in the target area until the target optimization function reaches the target value, thereby obtaining a treatment plan.

[0143] The objective optimization function can represent the optimization objective for the desired dose distribution of the target volume. Optimizing the target weights associated with the couch control points in a direction that decreases the objective function indicates that the dose to the target volume is as close to the desired dose distribution as possible. In this case, the objective optimization function is constructed based on the target volume dose, the tissue dose to the surrounding tissues, and the prescription dose.

[0144] In some embodiments, the objective optimization function satisfies the following formula:

[0145] F=min(a1f1+a2f2+a3f3+a4f4+a5f5+a6f6);

[0146] f1=∑ i∈T Dose of the first voxel = ∑ i∈T max(0,[prescribe-Dose(i)]) 2 ;

[0147] f2=∑ i∈T The dose of the second voxel = ∑ i∈T max(0,[prescribe-2*Dose(i)]) 2 ;

[0148] f3=∑ i∈Ring1 The dose of the third voxel = ∑ i∈Ring1max(0,[Dose(i)-prescribe]) 2 ;

[0149] f4=∑ i∈Ring2 The dose of the fourth voxel = ∑ i∈Ring2 max(0,[Dose(i)-0.9*prescribe]) 2 ;

[0150] f5=∑ i∈Ring3 Dose of the fifth voxel = ∑ i∈Ring3 max(0,[Dose(i)-0.8*prescribe]) 2 ;

[0151] f6=∑ i∈Ring4 Dose of the sixth voxel = ∑ i∈Ring4 max(0,[Dose(i)-0.7*prescribe]) 2 ;

[0152]

[0153] Among them, a1, a2, a3, a4, a5, and a6 are weights, the default value is 1, and they can be flexibly set according to needs.

[0154] The first voxel point is the voxel point in the target area that is lower than the prescribed dose, i is the voxel point i, T is the number of voxels in the target area, prescribe is the prescribed dose, and Dose(i) is the dose of the i-th voxel point.

[0155] The second voxel point is the voxel point within the target area that is higher than 2 times the prescription dose.

[0156] The third voxel point is the voxel point that exceeds the prescribed dose within the ring between the target area contour line and the contour line obtained by expanding the target area contour by 0.5 cm. Ring1 is the number of voxel points that exceed the prescribed dose within the ring between the target area contour line and the contour line obtained by expanding the target area contour by 0.5 cm.

[0157] The fourth voxel point is the voxel point that exceeds 0.9 times the prescription dose within the ring between the contour line obtained by expanding the target area contour by 0.5 cm and the contour line obtained by expanding the target area contour by 1 cm. Ring2 is the number of voxel points that exceed 0.9 times the prescription dose within the ring between the contour line obtained by expanding the target area contour by 0.5 cm and the contour line obtained by expanding the target area contour by 1 cm.

[0158] The fifth voxel point is the voxel point that exceeds 0.8 times the prescription dose within the ring between the contour line obtained by expanding the target area contour by 1 cm and the contour line obtained by expanding the target area contour by 1.5 cm. Ring3 is the number of voxel points that exceed 0.8 times the prescription dose within the ring between the contour line obtained by expanding the target area contour by 1 cm and the contour line obtained by expanding the target area contour by 1.5 cm.

[0159] The sixth voxel point is the voxel point located outside the contour line obtained by expanding the target area contour by 1.5 cm and exceeding 0.7 times the prescription dose. Ring4 is the number of voxel points outside the contour line obtained by expanding the target area contour by 1.5 cm and exceeding 0.7 times the prescription dose.

[0160] j is the jth treatment couch control point, K is the number of treatment couch control points, wj is the target weight of the jth treatment couch control point, and dij is the dose contribution of the target weight of the jth control point to the i-th voxel point.

[0161] After the target weights of all the treatment couch control points are optimized, in order to ensure the smoothness of the treatment couch's beam output process, the treatment plan generation device may perform Gaussian smoothing on the optimized target weights.

[0162] The above mainly introduces the scheme of the embodiment of the present disclosure from the perspective of method. It can be understood that in order to achieve the above functions, the treatment plan generation device and the radiotherapy device include hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiment disclosed herein, the embodiment of the present disclosure can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiment of the present disclosure.

[0163] In the embodiments of the present disclosure, the treatment plan generation device and the radiotherapy device can be divided into functional units according to the above-described method examples. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into a single processing unit. The above-mentioned integrated units can be implemented in the form of hardware or software functional units. It should be noted that the division of units in the embodiments of the present disclosure is illustrative and is merely a logical functional division. In actual implementation, other division methods may be used.

[0164] like Figure 7As shown, the embodiment of the present disclosure provides a treatment plan generating apparatus, which is applied to the above-mentioned treatment plan generating device, including: a communication unit 701 and a processing unit 702;

[0165] A communication unit 701 is configured to acquire an image of a target region, an outline of the target region, and a set of one or more optimization targets, wherein the set of one or more optimization targets includes a desired dose distribution of the target region; the image of the target region includes a sequence of multi-layer sub-images of the target region acquired continuously along a certain anatomical direction; and the outline of the target region includes an outline of a target region slice of each sub-image in the sequence of multi-layer sub-images.

[0166] The processing unit 702 is configured to determine a signed distance map of the target slice according to the contour of the target slice for each layer of the sub-image; the signed distance map is used to represent the distance between each voxel point in the target slice and the contour boundary of the target slice;

[0167] The processing unit 702 is further configured to determine, based on the signed distance map of the target slice of each sub-image layer, a treatment couch control point set corresponding to the target region and one or more radiation delivery parameters associated with each treatment couch control point in the treatment couch control point set, wherein the treatment couch control point set relates to the relative continuous movement between the treatment couch and the focus of the radiation beam;

[0168] The processing unit 702 is further configured to optimize radiation delivery parameters associated with the treatment couch control points in the target area based on a set of one or more optimization objectives, and generate a treatment plan.

[0169] In some embodiments, the processing unit 702 is specifically configured to:

[0170] For the target area slice of each layer of sub-image, multiple key points of the target area slice are determined according to the signed distance map of the target area slice; the multiple key points are used to characterize the contour features of the target area slice;

[0171] Determine the convex hull of multiple key points to obtain the motion sub-trajectory of the treatment bed of the target slice;

[0172] According to the treatment bed motion sub-trajectory of the target area slice of each layer of sub-image, the treatment bed control point set corresponding to the target area is determined.

[0173] In some embodiments, in the signed distance map, the signed distance value of a keypoint is smaller than the signed distance value of a voxel point adjacent to the keypoint.

[0174] In some embodiments, the processing unit 702 is specifically configured to:

[0175] Discretizing the treatment bed motion sub-trajectory of the target area slice of each layer of sub-image to obtain a subset of treatment bed control points corresponding to the target area slice of each layer of sub-image;

[0176] Control points are selected from the treatment bed control point subset corresponding to the target area slice of each layer of sub-image to obtain a treatment bed control point set corresponding to the target area.

[0177] In some embodiments, the processing unit 702 is specifically configured to:

[0178] Selecting trajectory segments from the treatment couch motion subtrajectory of the target area slice of each layer of sub-image, and sequentially connecting the selected trajectory segments to obtain the treatment couch motion trajectory of the target area;

[0179] The motion trajectory of the treatment bed is discretized to obtain the control point set of the treatment bed corresponding to the target area.

[0180] In some embodiments, radiation delivery parameters include target size, target weight, couch control point position, and beam angle.

[0181] In some embodiments, the target size of the couch control point is determined by:

[0182] Determine the target size of the treatment bed control point based on the distance between the treatment bed control point and the contour boundary of the target area slice to which the treatment bed control point belongs;

[0183] Alternatively, the target point size of the treatment couch control point is determined according to the minimum signed distance value in the signed distance map of the target volume slice to which the treatment couch control point belongs.

[0184] In some embodiments, when the radiation delivery parameters include target size and couch control point positions, the processing unit 702 is specifically configured to:

[0185] Obtain the average dose of voxel points within the current target area that are less than the prescribed dose;

[0186] Based on a set of one or more optimization objectives, optimizing the target point size and the position of the treatment couch control point associated with the current treatment couch control point in the target volume to obtain an average dose of voxels within the target volume that are less than the prescribed dose after optimization;

[0187] When the average dose of the voxel points in the optimized target area that are less than the prescribed dose is less than the average dose of the voxel points in the current target area that are less than the prescribed dose, the target size and position of the next treatment couch control point are optimized until the target sizes and positions of all treatment couch control points are optimized to obtain a treatment plan.

[0188] In some embodiments, when the radiation delivery parameters include target weights, the processing unit 702 is specifically configured to:

[0189] Based on a set of one or more optimization objectives, the target weights associated with the treatment bed control points in the target area are optimized until the target optimization function reaches the target value, thereby obtaining a treatment plan; the target optimization function is constructed based on the target dose of the target area, the tissue dose of the tissue surrounding the target area, and the prescription dose.

[0190] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, comprising at least one processor; and a memory communicatively connected to 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 execute the treatment plan generation method or the treatment plan execution method provided by the present disclosure.

[0191] According to an embodiment of the present disclosure, the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable an electronic device to execute the treatment plan generating method or the treatment plan executing method provided by the present disclosure.

[0192] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product, including a computer program, which, when executed by a processor, implements the treatment plan generating method or the treatment plan executing method provided by the present disclosure.

[0193] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein. In some embodiments, the electronic device can be the above-mentioned Figure 1 The treatment plan generating device or radiotherapy device shown in .

[0194] like Figure 8As shown, the electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory 802 or a computer program loaded from a storage unit 808 into a random access memory 803. In the random access memory (RAM) 803, various programs and data required for the operation of the electronic device 800 can also be stored. The computing unit 801, the read-only memory (ROM) 802 and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0195] Multiple components in the electronic device 800 are connected to the input / output interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0196] The computing unit 801 can be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit, a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors, and any appropriate processors, controllers, microcontrollers, etc. The computing unit 801 performs the various methods and processes described above, such as the data matching method. For example, in one embodiment, the data matching method can be implemented as a computer software program that is tangibly included in a machine-readable medium, such as a storage unit 808. In one embodiment, part or all of the computer program can be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the data matching method described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the data matching method in any other appropriate manner (e.g., by means of firmware).

[0197] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays, application specific integrated circuits, application specific standard parts (ASSPs), system on chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0198] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0199] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or apparatus, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical fiber, a portable compact disk read-only memory, an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0200] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user, such as a cathode ray tube (CRT) or a liquid crystal display (LCD) monitor; and a keyboard and pointing device (such as a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (such as visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0201] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0202] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0203] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions of this disclosure can be achieved. This is not a limitation herein.

[0204] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for generating a treatment plan, characterized in that: include: Acquiring an image of a target region, an outline of the target region, and a set of one or more optimization targets, wherein the set of one or more optimization targets includes a desired dose distribution of the target region; the image of the target region includes a sequence of multi-layer sub-images of the target region continuously acquired along a certain anatomical direction; and the outline of the target region includes an outline of a target region slice of each sub-image in the sequence of multi-layer sub-images; For the target area slice of each layer of the sub-image, a signed distance map of the target area slice is determined according to the contour of the target area slice; the signed distance map is used to represent the distance between each voxel point in the target area slice and the contour boundary of the target area slice; determining, based on the signed distance map of the target slice of each layer of the sub-image, a treatment couch control point set corresponding to the target area and one or more radiation delivery parameters associated with each treatment couch control point in the treatment couch control point set, wherein the treatment couch control point set relates to continuous relative movement between the treatment couch and a focal point of the radiation beam; Based on the set of one or more optimization objectives, radiation delivery parameters associated with the treatment couch control points in the target volume are optimized to generate a treatment plan.

2. The method according to claim 1, characterized in that Determining a treatment bed control point set corresponding to the target area according to the signed distance map of the target area slice of each layer of the sub-image includes: For the target area slice of each layer of sub-image, a plurality of key points of the target area slice are determined according to the signed distance map of the target area slice; the plurality of key points are used to characterize the contour features of the target area slice; determining a convex hull of the plurality of key points to obtain a treatment couch motion sub-trajectory of the target slice; According to the treatment couch motion sub-trajectory of the target area slice of each layer of sub-image, a treatment couch control point set corresponding to the target area is determined.

3. The method according to claim 2, characterized in that In the signed distance map, the signed distance value of the key point is smaller than the signed distance value of the voxel point adjacent to the key point.

4. The method according to claim 2, characterized in that The step of determining a set of control points of the treatment couch corresponding to the target area according to the treatment couch motion sub-trajectory of the target area slice of each layer of the sub-image comprises: Discretizing the treatment bed motion sub-trajectory of the target area slice of each layer of sub-image to obtain a subset of treatment bed control points corresponding to the target area slice of each layer of sub-image; Control points are selected from a subset of treatment couch control points corresponding to the target area slice of each layer of sub-image to obtain a treatment couch control point set corresponding to the target area.

5. The method according to claim 2, characterized in that The step of determining a set of control points of the treatment couch corresponding to the target area according to the treatment couch motion sub-trajectory of the target area slice of each layer of the sub-image comprises: Selecting trajectory segments from the treatment couch motion subtrajectory of the target area slice of each layer of sub-image, and sequentially connecting the selected trajectory segments to obtain the treatment couch motion trajectory of the target area; The motion trajectory of the treatment couch is discretized to obtain a set of control points of the treatment couch corresponding to the target area.

6. The method according to claim 1, wherein The radiation delivery parameters include target size, target weight, couch control point position, and beam angle.

7. The method according to claim 6, characterized in that The target size of the treatment bed control point is determined by the following method: determining a target point size of the treatment couch control point according to a distance between the treatment couch control point and a contour boundary of a target area slice to which the treatment couch control point belongs; Alternatively, the target point size of the treatment couch control point is determined according to the minimum signed distance value in the signed distance map of the target volume slice to which the treatment couch control point belongs.

8. The method according to claim 6, characterized in that In a case where the radiation delivery parameters include the target size and the position of the treatment couch control point, optimizing the radiation delivery parameters associated with the treatment couch control point in the target volume based on the set of one or more optimization objectives to generate a treatment plan includes: Obtaining the average dose of voxel points within the current target area that are less than the prescribed dose; optimizing, based on the set of one or more optimization objectives, target point sizes and positions of the current couch control points in the target volume to obtain an optimized average dose of voxels within the target volume that are less than the prescribed dose; If the average dose of the voxel points in the target area that are less than the prescribed dose after the optimization is less than the average dose of the voxel points in the current target area that are less than the prescribed dose, the target point size and the position of the treatment couch control point associated with the next treatment couch control point are optimized until the target sizes and positions of all treatment couch control points are optimized to obtain the treatment plan.

9. The method according to claim 6, characterized in that In a case where the radiation delivery parameters include the target point weights, optimizing the radiation delivery parameters associated with the treatment couch control points in the target volume based on the set of one or more optimization objectives to generate a treatment plan includes: Based on the set of one or more optimization objectives, target point weights associated with treatment couch control points in the target area are optimized until a target optimization function reaches a target value, thereby obtaining the treatment plan; the target optimization function is constructed based on a target dose of the target area, a tissue dose of tissue surrounding the target area, and a prescription dose.

10. An electronic device, characterized in that: The electronic device comprises: processor; a memory configured to store instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 9.

11. A non-volatile storage medium, characterized in that: The storage medium stores a computer program, which, when read and executed, implements the method according to any one of claims 1 to 9.

Images