Radiotherapy planning system, apparatus and computer device

Abstract

The application relates to a radiotherapy plan planning system, device and computer equipment. The radiotherapy plan planning system comprises at least one processor, which can realize the process of constructing a first medical image of a target object according to multiple local medical images of the target object, generating a target region radiotherapy plan of the target object based on the first medical image and a region of interest, and obtaining a local radiotherapy sub-plan corresponding to each local medical image of the target object based on the target region radiotherapy plan and the multiple local medical images. The method steps realized by the processor in the system can simplify the complexity of radiotherapy plan design and improve the accuracy of the designed radiotherapy plan.

Description

Technical Field

[0001] This application relates to the field of medical technology, and in particular to a radiotherapy planning system, apparatus, and computer equipment. Background Technology

[0002] Radiotherapy, or RT for short, is a treatment method that utilizes the biological effects of radiation energy on biological tissues as a clinical treatment approach. It is one of the three most important treatment methods in cancer treatment.

[0003] The target area varies depending on the location of the radiotherapy. For example, in treatments such as whole-brain and whole-spinal cord radiotherapy, whole-body radiotherapy, whole-bone marrow radiotherapy, and whole-skin radiotherapy, there are extremely large target areas. Typically, a radiotherapy plan needs to be designed in advance before performing radiotherapy on the lesion site, and this pre-designed plan serves as the guide for the radiotherapy procedure.

[0004] However, when radiotherapy is applied to lesions with a very large target area, the design of the radiotherapy plan is often complex and lacks precision. Summary of the Invention

[0005] This application provides a radiotherapy planning system, apparatus, and computer equipment that can simplify the design of radiotherapy plans and improve the accuracy of radiotherapy plan design for lesions with a very large target area.

[0006] In a first aspect, embodiments of this application provide a radiotherapy planning system, the system including at least one processor, the at least one processor being used to perform the following method steps:

[0007] Construct a first medical image of the target object based on multiple local medical images of the target object;

[0008] Based on the first medical image and the region of interest, a radiotherapy plan for the target area of ​​the target object is generated.

[0009] Based on the target area radiotherapy plan and multiple local medical images, local radiotherapy sub-plans corresponding to each local medical image of the target object are obtained.

[0010] In one embodiment, constructing a first medical image of the target object based on multiple local medical images of the target object includes:

[0011] Register multiple local medical images to obtain the first registration relationship between the multiple local medical images;

[0012] A first medical image of the target object is constructed based on multiple local medical images and the first registration relationship.

[0013] In one embodiment, the plurality of local medical images include upper body medical images and lower body medical images;

[0014] The first medical image is obtained by stitching together the upper body medical image and the lower body medical image based on the registration relationship.

[0015] In one embodiment, the above-mentioned generation of a target region radiotherapy plan based on a first medical image and a region of interest for radiotherapy includes:

[0016] At least one region of interest is obtained based on the first medical image;

[0017] Based on the isocenters corresponding to each region of interest, a target region radiotherapy plan is generated for the target object; the target region radiotherapy plan includes the planned dose information corresponding to each region of interest.

[0018] In one embodiment, the above-mentioned method of obtaining local radiotherapy sub-plans corresponding to each local medical image of the target object based on the target area radiotherapy plan and multiple local medical images includes:

[0019] Multiple local medical images are registered with the first medical image to obtain a second registration relationship between each local medical image and the first medical image; each local medical image corresponds to a second registration relationship.

[0020] Based on each second registration relationship, the radiotherapy plan for the target area is copied to each local medical image to obtain the local radiotherapy sub-plan corresponding to each local medical image of the target object.

[0021] In one embodiment, the processor is also used to perform the following steps:

[0022] Based on the isocenters of each region of interest in the radiotherapy plan for the target area, obtain the verification medical image of the target object at each isocenter.

[0023] Based on the verified medical images, obtain a second medical image of the target object;

[0024] Dose assessment results are obtained based on the second medical image and the radiotherapy plan for the target area.

[0025] In one embodiment, obtaining a second medical image of the target object based on each verified medical image includes:

[0026] Each verification medical image and the first medical image are registered separately to obtain a third registration relationship between each verification medical image and the first medical image; each verification medical image corresponds to a third registration relationship.

[0027] Based on the third registration relationships, the verification medical images are stitched together to form the second medical image.

[0028] In one embodiment, obtaining dose assessment results based on the second medical image and the target area radiotherapy plan includes:

[0029] The radiotherapy plan for the target area is copied into the second medical image to obtain the actual dose information in the second medical image.

[0030] The planned dose information in the radiotherapy plan for the target area is analyzed and compared with the actual dose information in the second medical image to obtain the dose assessment results.

[0031] Secondly, embodiments of this application provide a radiotherapy planning device, the device comprising:

[0032] The building module is used to construct the first medical image of the target object based on multiple local medical images of the target object;

[0033] The generation module is used to generate a target area radiotherapy plan for a target object based on a first medical image and a region of interest for radiotherapy.

[0034] The determination module is used to obtain local radiotherapy sub-plans corresponding to each local medical image of the target object based on the radiotherapy plan of the target area and multiple local medical images.

[0035] Thirdly, embodiments of this application provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method steps performed by the processor in the system described in the first aspect.

[0036] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the method steps executed by the processor in the system described in the first aspect.

[0037] This application provides a radiotherapy planning system, apparatus, and computer device. The radiotherapy planning system includes at least one processor, which can construct a first medical image of the target object based on multiple local medical images, generate a target region radiotherapy plan based on the first medical image and a region of interest, and then obtain local radiotherapy sub-plans corresponding to each local medical image of the target object based on the target region radiotherapy plan and multiple local medical images. Because this application, when designing radiotherapy plans for diseases with extremely large target areas, stitches together multiple acquired local medical images into a complete whole-body image and designs the radiotherapy plan on this whole-body image, it eliminates the need to develop separate plans for each local image, thus simplifying the complexity of radiotherapy plan design. Furthermore, designing the radiotherapy plan from a holistic whole-body perspective avoids the dose inhomogeneity problem that may occur in the transition areas between multiple local medical images, which could result from designing separate plans for multiple local medical images, thereby improving the accuracy of the radiotherapy plan design. Attached Figure Description

[0038] Figure 1 This is a block diagram of the application environment structure of the processor in a radiotherapy planning system in one embodiment;

[0039] Figure 2 This is a schematic diagram of the method steps executed by the processor of a radiotherapy planning system in one embodiment;

[0040] Figure 3 This is a schematic diagram of an upper body CT image and a lower body CT image in one embodiment;

[0041] Figure 4 This is a schematic diagram of the method steps executed by the processor of a radiotherapy planning system in another embodiment;

[0042] Figure 5 This is a schematic diagram of the method steps executed by the processor of a radiotherapy planning system in another embodiment;

[0043] Figure 6 This is a schematic diagram of the method steps executed by the processor of a radiotherapy planning system in another embodiment;

[0044] Figure 7 This is a schematic diagram of the method steps executed by the processor of a radiotherapy planning system in another embodiment;

[0045] Figure 8 This is a schematic diagram of the placement image in one embodiment;

[0046] Figure 9 This is a schematic diagram of a radiotherapy planning process in one embodiment;

[0047] Figure 10This is a schematic diagram of the method steps executed by the processor of a radiotherapy planning system in another embodiment;

[0048] Figure 11 This is a structural block diagram of a radiotherapy planning device in one embodiment;

[0049] Figure 12 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the embodiments of this application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely illustrative of the embodiments of this application and are not intended to limit the embodiments of this application.

[0051] The radiotherapy planning system provided in this application can be used in any type of computer device, server, or other medical device, and this application does not limit this. Taking a computer device as an example, such as... Figure 1 As shown, the processor in the radiotherapy planning system is used in this computer device to provide computational and control capabilities. The memory in this computer device includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores relevant data generated during the processor's execution of the process of obtaining local radiotherapy sub-plans corresponding to each local medical image of the target object based on multiple local medical images. When the computer program is executed by the processor, it implements the process of obtaining local radiotherapy sub-plans corresponding to each local medical image of the target object based on multiple local medical images. The network interface is used for communication with other external devices via a network connection.

[0052] This application provides a radiotherapy planning system, device, and computer equipment. It designs radiotherapy plans for a very large target area based on whole-body images. After the plan is made, it is split into upper body plans and lower body plans. Therefore, it can simplify the design of radiotherapy plans for lesions with a very large target area, avoid dose inhomogeneity that may occur in the transition area between upper and lower body images, and improve the accuracy of radiotherapy plan design.

[0053] The technical solutions of this application and how they solve the aforementioned technical problems will be described in detail below through embodiments and in conjunction with the accompanying drawings. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments.

[0054] In one embodiment, a radiotherapy planning system is provided, comprising at least one processor. This embodiment relates to the specific process by which the processor obtains local radiotherapy sub-plans corresponding to each local medical image of the target object based on multiple local medical images of the target object. Figure 2 As shown, the processor is used to execute the following method steps:

[0055] S101, construct the first medical image of the target object based on multiple local medical images of the target object.

[0056] The target object refers to any object. In the embodiments of this application, the local medical image of the target object can be obtained from a database, downloaded from a network platform, transmitted from other devices, or directly captured by an imaging device. The embodiments of this application do not limit this.

[0057] Specifically, taking the acquisition of images of a target object by an imaging device as an example, each local medical image is acquired by scanning at least a part of the target object's body area. Multiple local medical images can be obtained by scanning different parts of the target object's body area.

[0058] That is, the target object's whole body area is divided into at least two local body regions, for example, two, three, or even four local medical images. Each local medical image corresponds to one local body region. These multiple local medical images can then be used to construct a first medical image of the object, for example, a whole-body medical image, or a medical image that does not cover the head region, or does not cover the area below the ankles, etc. The specific coverage area of ​​the first medical image is not limited in this application embodiment and can be determined according to the actual target area required.

[0059] The medical images used in this application embodiment include, but are not limited to, computed tomography (CT) images, magnetic resonance (MR) images, positron emission tomography (PET) images, etc., or any combination of various types of medical images.

[0060] Based on this, after obtaining multiple local medical images of the target object, a first medical image of the target object can be constructed based on these multiple local medical images.

[0061] For example, such as Figure 3 As shown, multiple local medical images of a target object are illustrated as upper body electronic CT images and lower body CT images. A corresponding first medical image can be constructed based on the upper body CT images and lower body CT images.

[0062] CT images can be acquired through a CT and accelerator integrated system. This system can provide diagnostic-grade CT images for image guidance, and a single scan can cover a long area, thus providing local CT images of different parts of the body.

[0063] In one embodiment, the construction of the first medical image can be achieved using a pre-set stitching processing network model. For example, a stitching processing network model can be pre-trained, whose function is to stitch together multiple local images of the body into a complete full-body image. Thus, in this embodiment, when constructing the first medical image, the stitching processing network model can be directly invoked. The acquired upper-body CT image and lower-body CT image are input into the stitching processing network model, and the output is the desired first medical image. Therefore, by directly invoking a pre-trained stitching processing network model, the efficiency and accuracy of constructing the first medical image can be guaranteed.

[0064] In another embodiment, when constructing the first medical image, image registration techniques (e.g., registration based on image features or image intensity) can be used to combine multiple local medical images into a seamless, high-definition first medical image.

[0065] S102, based on the first medical image and the region of interest, generates a radiotherapy plan for the target area of ​​the target object.

[0066] After obtaining the first medical image of the target object, a radiotherapy plan for the target area is generated based on the first medical image and the pre-determined region of interest, such as a total marrow irradiation (TMI) plan.

[0067] When determining the target region radiotherapy plan based on the defined region of interest, isocenters (or isocenter locations) are determined for each region of interest. The radiotherapy plan for each region of interest in the first medical image of the target object is generated based on the isocenters, thus forming the target region radiotherapy plan for the target object.

[0068] For example, the radiotherapy plan for the target area can be automatically generated using radiotherapy planning software. When generating the radiotherapy plan for the target area using radiotherapy planning software, relevant parameters need to be set, such as isocentric position and dose restrictions for the region of interest. For example, taking whole-body bone marrow as an example, relevant parameters include the dose that organs around the isocentric point of the region of interest can be irradiated, as well as the dose restrictions for the region of interest. These relevant parameters, the first medical image of the target object, and information such as the region of interest are uploaded to the radiotherapy planning software, which can then automatically output the radiotherapy plan for the target area.

[0069] S103, based on the radiotherapy plan for the target area and multiple local medical images, obtain the local radiotherapy sub-plans corresponding to each local medical image of the target object.

[0070] In practical applications, radiotherapy plans need to be designed for different CT images. Similarly, the embodiments of this application initially obtain multiple local medical images of the target object. Therefore, when designing a radiotherapy plan, the final requirement is also the radiotherapy plan for each of these multiple local medical images, that is, the local radiotherapy sub-plan corresponding to each local medical image needs to be obtained.

[0071] Therefore, based on the above process, the target area radiotherapy plan and multiple local images of the target object are obtained. Further processing can then be performed to obtain the local radiotherapy sub-plans corresponding to each local medical image of the target object. For example, the target area radiotherapy plan of the target object can be used as a reference, and the radiotherapy plan for each region of the target area radiotherapy plan can be copied to the local medical images to obtain the local radiotherapy sub-plan corresponding to each local medical image. Alternatively, a target area radiotherapy plan of the target object can be split, and the split target area radiotherapy plan of the target object can be used to obtain an image whose range, region, specifications, and other information are completely consistent with each local medical image of the target object, thereby obtaining the local radiotherapy sub-plan corresponding to each local medical image.

[0072] The copying and splitting process described above can be implemented manually or automatically through algorithm models, automated software, etc. This application does not limit the implementation of this process.

[0073] This application provides a radiotherapy planning system, which includes a processor. The processor can construct a first medical image of the target object based on multiple local medical images, generate a target region radiotherapy plan based on the first medical image and a region of interest, and then obtain local radiotherapy sub-plans corresponding to each local medical image based on the target region radiotherapy plan and multiple local medical images. Because this application, when designing radiotherapy plans for diseases with extremely large target areas, stitches together multiple acquired local medical images into a complete whole-body image and formulates the radiotherapy plan on this whole-body image, it eliminates the need to formulate plans for each local image separately, thus simplifying the complexity of radiotherapy plan design. Furthermore, designing the radiotherapy plan from a holistic whole-body perspective avoids the dose inhomogeneity problem that may occur in the transition areas between multiple local medical images, which could result from designing plans separately for multiple local medical images, thereby improving the accuracy of the radiotherapy plan design.

[0074] Based on the above embodiments, the following embodiment illustrates the process of constructing a first medical image of a target object from multiple local medical images of the target object. Figure 4 As shown, in one embodiment, S101 includes the following steps:

[0075] S201, Register multiple local medical images to obtain the first registration relationship between the multiple local medical images.

[0076] In this embodiment, the first medical image of the target object is constructed using image registration technology. Specifically, multiple local medical images are first registered to obtain the registration relationship between these multiple local images, which is called the first registration relationship.

[0077] It should be noted that the first registration relationship between multiple local medical images can include a registration relationship based on every two local images, or a registration relationship based on the multiple local medical images as a whole. For example, if the multiple local medical images include upper body CT images and lower body CT images, then the first registration relationship is the registration relationship between the upper body CT images and the lower body CT images; however, if the multiple local medical images include CT images of the upper chest region, CT images of the waist and abdomen region, and CT images of the legs and feet region, then the first registration relationship can be the registration relationship between the CT images of the upper chest region and the CT images of the waist and abdomen region, the registration relationship between the CT images of the waist and abdomen region and the CT images of the legs and feet region, and the registration relationship between the CT images of the upper chest region and the CT images of the legs and feet region; of course, the first registration relationship can also be the registration relationship between the CT images of the upper chest region, the CT images of the waist and abdomen region, and the CT images of the legs and feet region.

[0078] Of course, the first registration relationship between the multiple local medical images can be obtained by registering the overlapping areas of the multiple local medical images.

[0079] For example, when obtaining the first registration relationship between the multiple local medical images, a mapping model between the multiple local medical images can be obtained first. After determining the mapping model, the parameters in the mapping model need to be further determined. The parameters that make the registration degree between the multiple local medical images the best are the parameters required in the mapping model. For example, the parameters of the mapping model can be determined by using genetic algorithms, particle swarm optimization algorithms, etc., so that the set of parameters with the highest registration degree judged according to the similarity measure criterion is used as the parameters of the mapping model. Then the functional relationship corresponding to the mapping model can be determined as the first registration relationship between the multiple local medical images.

[0080] S202, construct the first medical image of the target object based on multiple local medical images and the first registration relationship.

[0081] Multiple local medical images and a first registration relationship are obtained. The multiple local medical images are then stitched together using the first registration relationship. That is, the multiple local medical images are registered according to the first registration relationship to obtain the first medical image of the target object.

[0082] In one embodiment, taking multiple local medical images including upper body medical images and lower body medical images as an example, the first medical image is obtained by stitching together based on the registration relationship between the upper body medical images and the lower body medical images.

[0083] For example, please continue to see the above. Figure 3 The upper body medical image is an upper body CT image, and the lower body medical image is a lower body CT image. First, the first registration relationship between the upper body CT image and the lower body CT image is obtained. Then, the first registration relationship is used to align and register the upper body CT image and the lower body CT image to form the first medical image.

[0084] Of course, multiple local medical images can also include three, four, or even more local medical images. Taking three as an example, including: a medical image of the chest region, a medical image of the waist and abdomen region, and a medical image of the leg region, then the first medical image is constructed based on the medical images of the chest region, the medical images of the waist and abdomen region, and the medical images of the leg region. The construction process is the same as the process of constructing the upper body CT image and the lower body CT image mentioned above, and will not be repeated here.

[0085] This embodiment provides a radiotherapy planning system. When the processor of this system constructs a first medical image of a target object based on multiple local medical images, it does so by registering the multiple local medical images to obtain a first registration relationship between them, and then constructing the first medical image of the target object based on the multiple local medical images and the first registration relationship. In constructing the first medical image, each local medical image is registered and aligned based on the registration relationship between them to form a complete stitched image. This complete stitched image is the first medical image, ensuring the accuracy and completeness of the constructed first medical image.

[0086] Based on any of the above embodiments, after obtaining the first medical image of the target object, it is necessary to further determine the radiotherapy plan for the target area of ​​the target object based on the first medical image.

[0087] In one embodiment, a target region radiotherapy plan for the target object can be generated based on the first medical image and the region of interest for radiotherapy, such as... Figure 5 As shown, this embodiment includes:

[0088] S301, acquire at least one region of interest based on the first medical image.

[0089] There can be multiple regions of interest or just one region of interest. Based on this, each region of interest can be delineated in whole-body medical imaging.

[0090] In one embodiment, each region of interest (ROI) in the first medical image can be manually delineated using a delineation tool in software combined with the doctor's experience. In another embodiment, automatic delineation can be performed using deep learning methods. For example, a deep learning-based method for delineating radiotherapy target areas might involve image registration, data preprocessing, and data normalization, followed by inputting the processed data into a neural network for inference, thereby obtaining multiple delineated ROIs. This application does not limit the method of delineating ROIs in the first medical image. Regardless of the delineation method, doctors can adjust the automatically delineated results based on experience to ensure more accurate delineation of ROIs.

[0091] S302, Generate a target region radiotherapy plan for the target object based on the isocenters corresponding to each region of interest; wherein, the target region radiotherapy plan includes the planned dose information corresponding to each region of interest.

[0092] After obtaining the region of interest (ROI), isocenters within the ROI can be determined. Using these isocenters, a target area radiotherapy plan for the target patient can be designed. This design can be implemented using radiotherapy planning software or a radiotherapy-assisted design network model; this embodiment does not limit the specific implementation.

[0093] The target region radiotherapy plan includes planned dose information for each region of interest (ROI), which includes specific dose data and distribution. Naturally, it can be understood that when designing a target region radiotherapy plan, it is necessary to first determine the planned dose information for each ROI, using the isocenter point as the center. In this way, the planned dose information for each ROI in the entire first medical image can be determined using this method. The resulting image includes the planned dose information for each ROI, thus obtaining the target region radiotherapy plan for the target object.

[0094] In the radiotherapy planning system provided in this embodiment, after acquiring a first medical image of the target object, the processor needs to further determine the radiotherapy plan for the target region based on the first medical image. The processor can obtain at least one region of interest (ROI) based on the first medical image and generate the target region radiotherapy plan based on the isocenters corresponding to each ROI. Since each ROI is delineated in the first medical image, and each ROI corresponds to an isocenter, the planned dose information for each ROI is determined using this isocenter as the center, thus obtaining the target region radiotherapy plan. In this way, by designing the planned dose information based on each delineated ROI, each isocenter, and related parameters, the planned dose information for each ROI is more accurate, resulting in a more accurate target region radiotherapy plan.

[0095] Based on the target area radiotherapy plan obtained in any of the above embodiments, in order to obtain radiotherapy sub-plans for each local medical image of the target object, the processor needs to perform further processing. In one embodiment, the specific processing steps are as follows: Figure 6 As shown, the above S103 includes the following steps:

[0096] S401, register multiple local medical images and the first medical image respectively to obtain a second registration relationship between each local medical image and the first medical image; each local medical image corresponds to a second registration relationship.

[0097] When obtaining local radiotherapy sub-plans corresponding to each local medical image of the target object based on the radiotherapy plan of the target area and multiple local medical images, some embodiments can be implemented by copying or duplicating. Whether copying or duplicating, it is necessary to ensure that the multiple local medical images of the target object are completely aligned with the first medical image of the target object in order to avoid errors after copying or duplicating and to ensure the accuracy of the radiotherapy sub-plan of the local medical images.

[0098] Based on this, the effect of achieving complete alignment between multiple local medical images and the first medical image of the target object can be achieved by obtaining the registration relationship between each of the multiple local medical images and the first medical image.

[0099] Specifically, multiple local medical images are registered with the first medical image to obtain a second registration relationship between each local medical image and the first medical image, with each local medical image corresponding to one second registration relationship. That is, each local medical image and the first medical image can obtain a registration relationship, and these registration relationships are all called second registration relationships.

[0100] For example, if multiple local medical images include an upper body CT image and a lower body CT image, then the registration relationship between the upper body CT image and the first medical image, as well as the registration relationship between the lower body CT image and the first medical image, are both referred to as the second registration relationship.

[0101] The method of obtaining the second registration relationship is the same as or different from the method of obtaining the first registration relationship in the previous embodiments. This application does not limit this.

[0102] Taking the above method of obtaining the first registration relationship as an example, for a single local medical image, the mapping model between a certain local medical image and the first medical image is first obtained. This mapping model can be a rigid body transformation model or a nonlinear transformation model. After determining the mapping model, the parameters in the mapping model are further determined. These parameters are the parameters that make the registration degree between multiple local medical images the best. For example, the parameters of the mapping model can be determined by using genetic algorithms, particle swarm optimization algorithms, etc., so that the set of parameters with the highest registration degree judged according to the similarity measure criterion is used as the parameters of the mapping model. Then the functional relationship corresponding to the mapping model can be determined as the second registration relationship between multiple local medical images.

[0103] S402, based on each second registration relationship, the radiotherapy plan for the target area is copied to each local medical image to obtain the local radiotherapy sub-plan corresponding to each local medical image of the target object.

[0104] Based on the second registration relationship described above, and using the target region radiotherapy plan of the target object as a reference, the radiotherapy plan for each region of the target region radiotherapy plan is copied into the local medical image. Because the second registration relationship can accurately determine the correspondence between each local medical image and the first medical image, the radiotherapy plan for the corresponding region in the target region radiotherapy plan can be copied into each local medical image, thereby obtaining the local radiotherapy sub-plan corresponding to each local medical image.

[0105] It should be noted that, in order to save computing resources, in some scenarios, the first registration relationship in the above embodiments can be directly used to copy the target area radiotherapy plan to each local medical image. That is, based on the registration relationship between each local medical image, the target area radiotherapy plan is copied to each local medical image. This application embodiment does not limit this.

[0106] In practical applications, when acquiring medical images of the human body, such as CT images, if a local medical image is acquired, the body position in that local medical image is scanned starting from the top. For example, please refer to the above. Figure 3 In an upper-body CT image, the patient's position is head-up, and in a lower-body CT image, the patient's position is feet-up. Based on this, an embodiment is provided that the radiotherapy plan for the target region can be adjusted according to each second registration relationship, and local radiotherapy sub-plans corresponding to each local medical image of the target subject can be obtained based on the adjusted target-region radiotherapy plan. This embodiment includes adjusting the position of the radiotherapy plan corresponding to each local medical image in each target-region radiotherapy plan based on the target subject's position information when acquiring each local medical image; and copying the target-region radiotherapy plan to each local medical image according to the adjusted target-region radiotherapy plan and each second registration relationship.

[0107] Specifically, based on the isocenter and second registration relationship of the treatment plan, it can be determined whether the sub-treatment plan corresponding to the isocenter needs adjustment. If adjustment is required, the adjustment process is carried out. Here, the information to be adjusted refers to the relevant dose information of the corresponding position in the target area radiotherapy plan. For example, by rotating the beam, the head-first-supine (HFS) position in the target area radiotherapy plan can be adjusted to the feet-first-supine (FFS) position. In this way, the relevant dose information of the plan before and after the adjustment is consistent. After copying the radiotherapy plan of the corresponding area in the target area radiotherapy plan to each local medical image, a precise local radiotherapy sub-plan for each local medical image can be obtained.

[0108] It should be noted that the above adjustment process is carried out during the replication process of the radiotherapy plan. However, in some scenarios, the adjustment process can also be applied to the acquisition process of the second registration relationship and the first registration relationship. That is, before acquiring the first registration relationship and the second registration relationship, the positions of each local medical image can be adjusted to a uniform position before registration. This can facilitate and accurately acquire the first registration relationship and the second registration relationship. This application does not limit this aspect.

[0109] In this embodiment, multiple local medical images are registered with a first medical image to obtain a second registration relationship between each local medical image and the first medical image. Based on this second registration relationship, the radiotherapy plan for the target area is copied to each local medical image, resulting in a local radiotherapy sub-plan corresponding to each local medical image of the target object. In this embodiment, the radiotherapy plan copying is based on the registration relationship between each local medical image and the first medical image, and the target area radiotherapy plan is generated from the first medical image. Therefore, each local medical image can be more accurately mapped to the corresponding area of ​​the target area radiotherapy plan, thereby ensuring the accuracy of the local radiotherapy sub-plan corresponding to each local medical image.

[0110] In addition, the processor in the radiotherapy planning system provided in this application embodiment, while implementing the above-mentioned local radiotherapy sub-plan corresponding to the local medical image of the target object, is also used to implement the step of obtaining dose evaluation results.

[0111] Generally, when performing radiotherapy on a very large target area, the patient's position needs to be precisely adjusted. After the position is adjusted, the patient's own positioning changes. Therefore, in some scenarios, there may be errors between the designed radiotherapy plan and the actual radiotherapy. Based on this, it is necessary to verify the above-mentioned radiotherapy plan in order to evaluate its rationality.

[0112] like Figure 7 As shown, in one embodiment, the processor is further configured to perform the following steps:

[0113] S501, based on the isocenters corresponding to each region of interest in the radiotherapy plan for the target area, obtain the verification medical image of the target object at each isocenter.

[0114] The radiotherapy plan for the target area mentioned above contains at least one region of interest, and each region of interest corresponds to an isocenter. Based on each isocenter, the patient is positioned by moving the bed, for example, positioning the patient at the corresponding isocenter for imaging, thereby obtaining a verification medical image of each isocenter.

[0115] The target object can be the same object as the previous target object, or it can be a different object.

[0116] For example, see Figure 8 As shown, taking four isocentric points as an example, four verification medical images of the target object can be obtained, namely: four verification medical images including the head, chest, waist and abdomen, and legs and feet.

[0117] The process of obtaining the verification medical image of the target object at each isocenter point can be achieved by scanning the fabricated simulation model as the target object in real time using medical equipment; it can also be achieved by simulating the verification medical image of the target object using simulation software; or it can be achieved by scanning the target object in real time, etc. The embodiments of this application do not limit this process.

[0118] Taking a simulation phantom as an example, the verification medical images of the simulation phantom can be obtained by scanning with an integrated CT and accelerator system. The integrated CT and accelerator system can provide diagnostic-grade CT images for image guidance, and a single scan can cover a long range, thus obtaining positioning images at different isocenter points.

[0119] S502, based on each verified medical image, obtain a second medical image of the target object.

[0120] After obtaining multiple verification medical images of the target object, these multiple verification medical images are stitched together to obtain a full-body positioning medical image of the target object.

[0121] In one embodiment, when obtaining a second medical image of the target object based on each verification medical image, it can be achieved by a preset network model, for example, by pre-training a network model, the function of which is to stitch multiple verification medical images into a second medical image.

[0122] Based on this, the network model can be directly invoked, and the verification medical images of the target object obtained above can be input into the network model. The output is the second medical image of the target object. In this way, by directly invoking the pre-trained network model, the efficiency and accuracy of constructing the second medical image can be guaranteed.

[0123] In another embodiment, the second medical image of the target object is obtained based on each verification medical image by: registering each verification medical image and the first medical image respectively to obtain a third registration relationship between each verification medical image and the first medical image; stitching each verification medical image into a second medical image based on each third registration relationship; each verification medical image corresponds to a third registration relationship.

[0124] Each verification medical image and the first medical image are registered separately to obtain a third registration relationship between each verification medical image and the first medical image, with each verification medical image corresponding to one third registration relationship. That is, each verification medical image and the first medical image can obtain a registration relationship, and these registration relationships are all called third registration relationships.

[0125] The method of obtaining the third registration relationship is the same as, or different from, the method of obtaining the first registration relationship and the method of obtaining the second registration relationship in the previous embodiments. This application does not limit this.

[0126] Each verification medical image and a third registration relationship were obtained. Multiple verification medical images were stitched together using the third registration relationship. Each verification medical image was registered with the overlapping area in the first medical image using the third registration relationship. After the overlapping area was aligned and registered, the complete image was obtained, which is the second medical image of the target object.

[0127] For example, please see the above. Figure 8 The four verification medical images are used to first obtain the third registration relationship between the four verification medical images and the first medical image. Based on the third registration relationship, the four verification medical images are stitched together to form a complete second medical image.

[0128] Of course, when acquiring the second medical image, the body position adjustment steps in the foregoing embodiments can also be performed. The execution method and purpose are the same as in the foregoing embodiments, and will not be repeated here.

[0129] S503, based on the second medical image and the radiotherapy plan for the target area, obtains dose assessment results.

[0130] Dose assessment results can be used to characterize the rationality of local radiotherapy sub-plans corresponding to each local medical image. This indicates whether the determined local radiotherapy sub-plans for each local medical image are accurate, whether the radiotherapy effect meets requirements, etc. Therefore, these dose assessment results can identify problems in the radiotherapy plan designed for the target patient, preventing the same problems from occurring in subsequent radiotherapy plans designed for other patients. They can also provide reference opinions for the design and modification of radiotherapy plans for other patients. Furthermore, they can serve as experimental data for some studies, such as investigating the impact of actual treatment dose distribution on patient survival rate, target area treatment effect, etc. The embodiments of this application do not limit the use of dose assessment results; they can be selected according to actual circumstances.

[0131] In this embodiment of the application, the dose assessment result is obtained by analyzing and comparing the second medical image and the radiotherapy plan of the target area. The result of the analysis and comparison is the dose assessment result.

[0132] In one embodiment, the dose assessment result is obtained based on the second medical image and the radiotherapy plan for the target area by: copying the radiotherapy plan for the target area into the second medical image to obtain the actual dose information in the second medical image; and analyzing and comparing the planned dose information in the radiotherapy plan for the target area with the actual dose information in the second medical image to obtain the dose assessment result.

[0133] The dose distribution in the radiotherapy plan for the target area is the planned data, i.e., the planned dose information. During analysis and comparison, this planned dose information needs to be compared with the actual dose information to accurately identify which parts of the planned dose information are flawed. The actual dose information needs to be calculated using actual positioning images. Therefore, based on the second medical image obtained in the preceding steps, the radiotherapy plan for the target area needs to be copied into the second medical image to calculate the dose distribution in the second medical image as the actual dose information.

[0134] When the processor performs the task of copying the radiotherapy plan of the target area into the second medical image, it may first calculate the registration relationship between the radiotherapy plan of the target area and the second medical image. Based on the registration relationship between the two, the correspondence between each pixel in the second medical image and each pixel in the radiotherapy plan of the target area can be accurately determined. With this correspondence, the planned dose information in the radiotherapy plan of the target area is copied into the second medical image.

[0135] The actual dose information in the second medical image is calculated based on the second medical image, which replicates the planned dose information.

[0136] When analyzing and comparing the actual dose information in the second medical image with the planned dose information in the radiotherapy plan for the target area, the dose assessment result can be obtained automatically through a preset algorithm model, that is, by using the actual dose information and the planned dose information as input to the algorithm model.

[0137] In addition, this application also provides a radiotherapy planning system, which takes a local medical image including an upper body CT image and a lower body CT image, with the first medical image being a whole-body CT image, as an example. Figure 9 and Figure 10 As shown, the processor in this system is used to implement the following steps:

[0138] S1, Patient localization: Acquire upper body CT and lower body CT images, and register the upper body CT images with the lower body CT images to obtain the first registration relationship.

[0139] S2, Whole-body image stitching: Using the first registration relationship between the upper body CT image and the lower body CT image, the two sets of CT images are stitched together to form a complete body image.

[0140] S3 delineates regions of interest, such as the target area, based on a full-body image.

[0141] S4, the TMI program designed based on full-body imaging.

[0142] S5, Image Registration: Register the upper body CT image, lower body CT image and whole body CT image respectively to obtain the second registration relationship.

[0143] S6, Plan Copy: Rotate the beam to adjust the leg plan from HFS position to FFS position, and use the second registration relationship to copy the TMI plan designed for the whole body image to the upper body CT image and the lower body CT image respectively.

[0144] S7, Patient Positioning Verification: Obtain CT verification images at different isocenters in the region of interest, and register the CT images at different isocenters with the whole-body images designed with the TMI plan to obtain the third registration relationship.

[0145] S8, Whole-body image stitching: Using the third registration relationship, CT verification images with different isocenter points are stitched together into a complete verification body image.

[0146] S9, Plan Copy: Copy the designed TMI plan from the whole-body image to the stitched validation body image, and calculate the actual dose information in the validation body image.

[0147] S10, Dose Comparison: The actual dose information in the validated body images is compared and analyzed with the planned dose information in the designed TMI plan in the whole-body images to obtain the dose assessment results.

[0148] The radiotherapy planning system provided in this application designs radiotherapy plans for extremely large target areas based on whole-body images. After the plan is created, it is split into upper body and lower body plans. Therefore, it can simplify the design of radiotherapy plans for lesions with extremely large target areas, avoid dose inhomogeneity that may occur in the transition area between upper and lower body images, and improve the accuracy of radiotherapy plan design. Furthermore, after obtaining the registration relationship between CT positioning images at different isocenters and the planned CT images, this registration relationship is used to stitch the CT positioning images at different isocenters into a complete body positioning image. Then, the designed radiotherapy plan is copied onto the complete body positioning image, and the actual dose in the body positioning image is recalculated to obtain actual dose information. This actual dose information is then compared with the planned dose to obtain dose evaluation results, providing more accurate data for patient radiotherapy planning and clinical research.

[0149] It should be understood that although the steps in the flowcharts attached to the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the figures attached to the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps.

[0150] In one embodiment, such as Figure 11 As shown in the illustration, this application also provides a radiotherapy planning device, comprising: a construction module 10, a generation module 11, and a determination module 12, wherein:

[0151] Module 10 is used to construct a first medical image of the target object based on multiple local medical images of the target object;

[0152] Generation module 11 is used to generate a target area radiotherapy plan for the target object based on the first medical image and the radiotherapy region of interest;

[0153] The determination module 12 is used to obtain the local radiotherapy sub-plans corresponding to each local medical image of the target object based on the radiotherapy plan of the target area and multiple local medical images.

[0154] In one embodiment, the above-mentioned building module 10 includes:

[0155] The first registration unit is used to register multiple local medical images and obtain the first registration relationship between the multiple local medical images;

[0156] The construction unit is used to construct a first medical image of the target object based on multiple local medical images and a first registration relationship.

[0157] In one embodiment, the aforementioned plurality of local medical images include an upper body medical image and a lower body medical image; then the first medical image is obtained by stitching together the upper body medical image and the lower body medical image based on the registration relationship between them.

[0158] In one embodiment, the generation module 11 includes:

[0159] A delineation unit is used to acquire at least one region of interest based on a first medical image;

[0160] The generation unit is used to generate a target region radiotherapy plan for the target object based on the isocenters corresponding to each region of interest; wherein, the target region radiotherapy plan includes the planned dose information corresponding to each region of interest.

[0161] In one embodiment, the determining module 12 includes:

[0162] The second registration unit is used to register multiple local medical images and the first medical image respectively, to obtain a second registration relationship between each local medical image and the first medical image; each local medical image corresponds to a second registration relationship.

[0163] The determination unit is used to copy the target region radiotherapy plan to each local medical image according to each second registration relationship, so as to obtain the local radiotherapy sub-plan corresponding to each local medical image of the target object.

[0164] In one embodiment, the radiotherapy planning device further includes:

[0165] The first acquisition module is used to acquire the verification medical image of the target object at each isocenter point based on the isocenter points corresponding to each region of interest in the radiotherapy plan of the target area.

[0166] The second acquisition module is used to acquire a second medical image of the target object based on each verified medical image;

[0167] The assessment module is used to obtain dose assessment results based on the second medical image and the radiotherapy plan for the target area.

[0168] In one embodiment, the second acquisition module includes:

[0169] The third registration unit is used to register each verification medical image and the first medical image respectively, to obtain the third registration relationship between each verification medical image and the first medical image; each verification medical image corresponds to a third registration relationship.

[0170] The stitching unit is used to stitch together the verification medical images into a second medical image according to the third registration relationship.

[0171] In one embodiment, the evaluation module includes:

[0172] The acquisition unit is used to copy the radiotherapy plan of the target area into the second medical image and acquire the actual dose information in the second medical image.

[0173] The evaluation unit is used to analyze and compare the planned dose information in the radiotherapy plan for the target area with the actual dose information in the second medical image to obtain the dose evaluation result.

[0174] Specific limitations regarding the radiotherapy planning device can be found in the above description of the limitations on the steps executed by the processor in the radiotherapy planning system, and will not be repeated here. Each module in the aforementioned radiotherapy planning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in the radiotherapy planning system, or stored in software within the memory of the radiotherapy planning system, so that the processor in the radiotherapy planning system can call and execute the corresponding operations of each module.

[0175] In one embodiment, a computer device is provided, the internal structure of which can be shown in the following diagram. Figure 12 As shown. The computer device includes a processor, memory, communication interface, display screen, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it represents the method steps performed by the processor in any of the above embodiments of the radiotherapy planning system. The display screen can be a liquid crystal display (LCD) or an e-ink display. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0176] Those skilled in the art will understand that Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0177] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps performed by the processor in the above-described radiotherapy planning system:

[0178] Construct a first medical image of the target object based on multiple local medical images of the target object;

[0179] Based on the first medical image and the region of interest, a radiotherapy plan for the target area of ​​the target object is generated.

[0180] Based on the target area radiotherapy plan and multiple local medical images, local radiotherapy sub-plans corresponding to each local medical image of the target object are obtained.

[0181] The computer device provided in the above embodiments, when implementing the above steps, has a similar implementation principle and technical effect to the method steps executed by the processor in the above radiotherapy planning system, and will not be described again here.

[0182] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, performs the following steps performed by the processor in the radiotherapy planning system described above:

[0183] Construct a first medical image of the target object based on multiple local medical images of the target object;

[0184] Based on the first medical image and the region of interest, a radiotherapy plan for the target area of ​​the target object is generated.

[0185] Based on the target area radiotherapy plan and multiple local medical images, local radiotherapy sub-plans corresponding to each local medical image of the target object are obtained.

[0186] The implementation principle and technical effect of the computer-readable storage medium provided in the above embodiments are similar to the principle of the method steps executed by the processor in the above radiotherapy planning system, and will not be repeated here.

[0187] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0188] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0189] The above-described embodiments are merely illustrative of several implementation methods of the embodiments of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the embodiments of this application, and these all fall within the protection scope of the embodiments of this application. Therefore, the protection scope of the patent for the embodiments of this application should be determined by the appended claims.

Claims

1. A radiotherapy planning system, characterized in that, The system includes at least one processor, the at least one processor being configured to perform the following steps: A first medical image of the target object is constructed based on multiple different local medical images of the target object; At least one region of interest is obtained based on the first medical image; a target region radiotherapy plan is generated for the target object according to the isocenters corresponding to each region of interest; wherein, the target region radiotherapy plan includes planned dose information corresponding to each region of interest; Based on the radiotherapy plan for the target area, the radiotherapy plan for each region of the target area is copied to the local medical image to obtain the local radiotherapy sub-plan corresponding to each local medical image of the target object, or the radiotherapy plan for the target area is split to obtain the local radiotherapy sub-plan corresponding to each local medical image of the target object.

2. The system according to claim 1, characterized in that, The step of constructing a first medical image of the target object based on multiple different local medical images of the target object includes: The plurality of local medical images are registered to obtain a first registration relationship among the plurality of local medical images; Based on the plurality of local medical images and the first registration relationship, a first medical image of the target object is constructed.

3. The system according to claim 2, characterized in that, The multiple local medical images include upper body medical images and lower body medical images; The first medical image is obtained by stitching together the upper body medical image and the lower body medical image based on the registration relationship between them.

4. The system according to any one of claims 1-3, characterized in that, The step of copying the radiotherapy plan for each region of the target region to a local medical image, based on the radiotherapy plan for the target region, to obtain local radiotherapy sub-plans corresponding to each local medical image of the target object, includes: The plurality of local medical images and the first medical image are registered respectively to obtain a second registration relationship between each local medical image and the first medical image; each local medical image corresponds to a second registration relationship; According to each of the second registration relationships, the radiotherapy plan for the target area is copied to each of the local medical images to obtain the local radiotherapy sub-plans corresponding to each local medical image of the target object.

5. The system according to claim 4, characterized in that, The step of copying the radiotherapy plan for the target region to each of the local medical images according to each of the second registration relationships includes: Based on the body position information of the target object when acquiring each of the local medical images, the body position is adjusted for the radiotherapy plan corresponding to each local medical image in the radiotherapy plan of each target region. Based on the adjusted target area radiotherapy plan and each of the second registration relationships, the target area radiotherapy plan is copied to each of the local medical images.

6. The system according to any one of claims 1-3, characterized in that, The processor is also used to perform the following steps: Based on the isocenters corresponding to each region of interest in the radiotherapy plan for the target area, obtain verification medical images by locating the target object at each of the isocenters and taking pictures. Based on the aforementioned verification medical images, a second medical image of the target object is obtained; Dose assessment results are obtained based on the second medical image and the radiotherapy plan for the target area.

7. The system according to claim 6, characterized in that, The step of obtaining dose assessment results based on the second medical image and the radiotherapy plan for the target area includes: The radiotherapy plan for the target area is copied into the second medical image to obtain the actual dose information in the second medical image. The planned dose information in the radiotherapy plan for the target area is analyzed and compared with the actual dose information in the second medical image to obtain the dose assessment result.

8. A radiotherapy planning device, characterized in that, The device includes: A construction module is used to construct a first medical image of the target object based on multiple different local medical images of the target object; A generation module is configured to acquire at least one region of interest based on the first medical image; and generate a target region radiotherapy plan for the target object based on the isocenters corresponding to each region of interest; wherein the target region radiotherapy plan includes planned dose information corresponding to each region of interest; The determination module is used to copy the radiotherapy plan of each region of the target region to the local medical image based on the radiotherapy plan of the target region, so as to obtain the local radiotherapy sub-plan corresponding to each local medical image of the target object, or to split the radiotherapy plan of the target region to obtain the local radiotherapy sub-plan corresponding to each local medical image of the target object.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it performs the following steps: A first medical image of the target object is constructed based on multiple different local medical images of the target object; At least one region of interest is obtained based on the first medical image; a target region radiotherapy plan is generated for the target object according to the isocenters corresponding to each region of interest; wherein, the target region radiotherapy plan includes planned dose information corresponding to each region of interest; Based on the radiotherapy plan for the target area, the radiotherapy plan for each region of the target area is copied to the local medical image to obtain the local radiotherapy sub-plan corresponding to each local medical image of the target object, or the radiotherapy plan for the target area is split to obtain the local radiotherapy sub-plan corresponding to each local medical image of the target object.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it performs the following steps: A first medical image of the target object is constructed based on multiple different local medical images of the target object; At least one region of interest is obtained based on the first medical image; a target region radiotherapy plan is generated for the target object according to the isocenters corresponding to each region of interest; wherein, the target region radiotherapy plan includes planned dose information corresponding to each region of interest; Based on the radiotherapy plan for the target area, the radiotherapy plan for each region of the target area is copied to the local medical image to obtain the local radiotherapy sub-plan corresponding to each local medical image of the target object, or the radiotherapy plan for the target area is split to obtain the local radiotherapy sub-plan corresponding to each local medical image of the target object.

Images