Tumor target volume segmentation method and device and storage medium

Abstract

The invention relates to a tumor target volume segmentation method and device and a storage medium. The method comprises the following steps: acquiring a medical image containing a target tumor; segmenting the target tumor in a spatial dimension according to the medical image to obtain a plurality of first target volumes which are located in the target tumor and are not overlapped; segmenting the plurality of first target volumes in a time dimension to obtain a plurality of target volume sets corresponding to different fractions; wherein the target volumes in the target volume set corresponding to at least one adjacent fraction are not completely the same. Through the tumor target volume segmentation method and device and the storage medium provided by the invention, accurate segmentation of the tumor target volume can be realized, and the pertinence of radiotherapy is improved, so that the damage to biological tissues around an irradiation area where a tumor is located in the radiotherapy process is reduced.

Description

[0001] This application claims priority to Chinese Patent Application No. 202511189177.5, filed on August 22, 2025, entitled "A Method, Apparatus and Storage Medium for Segmenting Tumor Target Volume", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of radiotherapy technology, and in particular to a method, apparatus and non-volatile computer-readable storage medium for tumor target volume segmentation. Background Technology

[0003] In conventional fractionation irradiation, each fractional irradiation area, such as at least one target volume, is exactly the same, and the irradiation dose for each fraction is the same. This results in greater damage to the biological tissues surrounding the irradiated area where the tumor is located between target volumes.

[0004] Therefore, it is necessary to improve one or more of the problems existing in the above-mentioned related technical solutions.

[0005] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this disclosure is to provide a method, apparatus, and non-volatile computer-readable storage medium for tumor target volume segmentation, thereby overcoming at least to some extent one or more problems caused by the limitations and defects of related technologies.

[0007] In a first aspect, this application provides a tumor target volume segmentation method, comprising: acquiring a medical image containing a target tumor; segmenting the target tumor in a spatial dimension based on the medical image to obtain a plurality of non-overlapping first target volumes located within the target tumor; segmenting the plurality of first target volumes in a temporal dimension to obtain a plurality of target volume sets corresponding to different segments; wherein, the target volumes in at least one adjacent segment target volume set are not completely identical.

[0008] This disclosure provides a method for segmenting tumor target volumes. First, a medical image containing the target tumor is acquired. Then, the target tumor is segmented spatially to obtain multiple non-overlapping first target volumes located within the tumor. Next, the multiple first target volumes are segmented temporally to obtain multiple target volume sets corresponding to different fractions, with at least one adjacent fraction's target volume set being different. Thus, by coordinating spatial and temporal segmentation of the target tumor, multiple target volume sets suitable for multiple fractions (radiotherapy) can be obtained, and the first target volumes in at least one adjacent fraction's target volume set are not completely identical. This ensures that when executing a treatment plan based on the multiple target volume sets obtained by this tumor target volume segmentation method, at least two fractions will irradiate different first target volumes. This is more conducive to the recovery of biological tissues surrounding the irradiated area of ​​the tumor among the multiple first target volumes, reducing damage to the biological tissues surrounding the irradiated area of ​​the tumor.

[0009] In a second aspect, this application provides a tumor target volume segmentation apparatus, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the instructions to implement the tumor target volume segmentation method as described in the first aspect and any possible implementation thereof.

[0010] Thirdly, this application provides a non-volatile computer-readable storage medium storing instructions that, when executed on a terminal, cause the terminal to perform the tumor target volume segmentation method as described in the first aspect and any possible implementation thereof.

[0011] Fourthly, this application provides a computer program product containing instructions that, when run on a tumor target volume segmentation device, cause the tumor target volume segmentation device to perform the tumor target volume segmentation method as described in the first aspect and any possible implementation thereof.

[0012] Fifthly, this application provides a chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run computer programs or instructions to implement the tumor target volume segmentation method as described in the first aspect and any possible implementation thereof.

[0013] Specifically, the chip provided in this application also includes a memory for storing computer programs or instructions.

[0014] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the processor of the device, or it may be packaged separately from the processor of the device; this application does not impose any limitation on this.

[0015] The descriptions of the second to fifth aspects in this application can be referenced to the detailed description of the first aspect; and the beneficial effects described in the second to fifth aspects can be referenced to the analysis of the beneficial effects of the first aspect, which will not be repeated here.

[0016] In this application, the name of the aforementioned tumor target volume segmentation device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear under other names. As long as the function of each device or functional module is similar to that of this application, it falls within the scope of the claims of this application and its equivalents. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0018] Figure 1 A schematic diagram illustrating the implementation environment of a tumor target volume segmentation method provided in this embodiment of the disclosure; Figure 2 A schematic flowchart of a tumor target volume segmentation method provided in this embodiment of the disclosure; Figure 3 A schematic diagram of a plurality of non-overlapping first target volumes provided for an embodiment of this disclosure; Figure 4A A schematic diagram of multiple target volume sets corresponding to different stages provided in this embodiment of the present disclosure. Figure 1 ; Figure 4B A schematic diagram of multiple target volume sets corresponding to different stages provided in this embodiment of the present disclosure. Figure 2 ; Figure 4C A schematic diagram of multiple target volume sets corresponding to different stages provided in this embodiment of the present disclosure. Figure 3 ; Figure 5 A schematic diagram of another non-overlapping plurality of target volumes provided for an embodiment of this disclosure; Figure 6 A schematic diagram of another set of multiple target volumes corresponding to different fractions provided in this embodiment of the present disclosure; Figure 7 This is a schematic diagram of the spatial and temporal segmentation process provided in the embodiments of this disclosure; Figure 8 This is a schematic diagram of a target volume group provided in an embodiment of the present disclosure; Figure 9A A schematic diagram of another target volume group corresponding to each segment provided in this embodiment of the present disclosure. Figure 1 ; Figure 9B A schematic diagram of another target volume group corresponding to each segment provided in this embodiment of the present disclosure. Figure 2 ; Figure 10 A schematic diagram of dynamically adjusting the target area according to an embodiment of this disclosure; Figure 11 A schematic diagram showing the radiation dose comparison for target volume segmentation of soft tissue sarcoma provided in this embodiment of the present disclosure; Figure 12 A schematic diagram showing the radiation dose comparison for lung cancer tumor target volume segmentation provided in an embodiment of this disclosure; Figure 13 This is a simplified schematic diagram of a tumor target volume segmentation device provided in an embodiment of the present disclosure; Figure 14 A schematic flowchart of another tumor target volume segmentation method provided in this embodiment of the present disclosure; Figure 15 A schematic flowchart of another tumor target volume segmentation method provided in this embodiment of the present disclosure; Figure 16 This is a schematic flowchart of another tumor target volume segmentation method provided in an embodiment of this disclosure. Detailed Implementation

[0019] In the embodiments of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first" and "second" may explicitly or implicitly include one or more of that feature.

[0020] In embodiments of this application, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0021] "A and / or B" includes the following three combinations: A only, B only, and a combination of A and B.

[0022] Taking traditional head radiotherapy (referred to as "head radiotherapy") as an example, before radiotherapy, invasive methods such as head pins and head frames are used to fix the patient's head, and then a single high-dose focused irradiation method is used to irradiate the irradiated area where the tumor is located.

[0023] With the accumulation of clinical experience, it has been found that for certain tumors such as gliomas, brain metastases, and malignant tumors, multifractionated radiotherapy is more effective than single-fractionated radiotherapy. Multifractionated radiotherapy (fractionated for short) divides the total radiation dose required to complete tumor radiotherapy into multiple independent single radiation doses (fractions), which are then applied to the irradiated area where the patient's tumor is located.

[0024] However, in conventional fractionation, the irradiated area of ​​the tumor is exactly the same in each fraction, and the irradiation dose to the irradiated area is the same in each fraction. The fraction irradiation dose is the prescription dose (total irradiation dose) divided by the number of fractions. Thus, the same irradiation dose is applied to the same irradiated area in each fraction of radiotherapy. This results in greater damage to the biological tissues surrounding the irradiated area of ​​the tumor, affecting the overall effect of radiotherapy.

[0025] Meanwhile, radiotherapy doses typically include low-dose radiotherapy (LD-RT), conventional fractionated radiotherapy, subablation dose, and ablation dose. Low-dose radiotherapy is usually 0.5-2 Gy × 4 fractions, used to normalize blood vessels / matrix, promote T cell and NK cell infiltration, downregulate TGF-β, and polarize the macrophage M2→M1 phenotype. Conventional fractionated radiotherapy is usually 2 Gy × 30 fractions, used to kill circulating immune cells, damage blood vessels, and chronically suppress interferon signaling through immunosuppressive mechanisms, and inhibit T cell activation through the negative effects of lymph node irradiation. Subablation dose is usually 8 Gy × 3 fractions, used to enhance MHC expression, activate the cGAS-STING pathway, promote antigen presentation, and induce ICAM-1 expression to promote CD8+ T cell infiltration. Ablation dose is usually 10-20 Gy × 1-5 fractions, used to induce immunogenic cell death (release HMGB1, ATP, calreticulin), and clear immunosuppressive cells (such as Tregs), but may damage blood vessels and limit immune infiltration.

[0026] Based on this, the present disclosure provides a tumor target volume segmentation method, which can first acquire a medical image containing the target tumor, segment multiple non-overlapping first target volumes within the tumor in the spatial dimension, and then segment them into target volume sets of different fractions in the temporal dimension, thereby reducing the damage to biological tissues around the irradiated area of ​​the tumor during radiotherapy.

[0027] First, the application scenarios involved in the embodiments of this disclosure are described. The tumor target volume segmentation method provided in the embodiments of this disclosure can be applied to the field of medical technology, especially the field of radiotherapy technology.

[0028] Figure 1 This is a schematic diagram illustrating the implementation environment of a tumor target volume segmentation method according to an embodiment of this disclosure. See also... Figure 1 The implementation environment includes: image acquisition equipment 101, treatment planning system equipment 102, and radiotherapy equipment 103.

[0029] The image acquisition device 101 is used to acquire medical images of a target object containing a target tumor. In this embodiment, the image acquisition device 101 can acquire medical images containing a target tumor. The medical images containing the target tumor will then be uploaded to the treatment planning system device 102, so that the treatment planning system device 102 can perform subsequent tumor target volume segmentation methods based on the medical images containing the target tumor.

[0030] The target object is used to refer to the user who is to receive radiation therapy, such as a patient, experimental subject, or a phantom used to simulate a patient.

[0031] In some embodiments, the image acquisition device 101 may be at least one of the following: 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.

[0032] The treatment planning system device 102 is a device for acquiring medical images containing a target tumor acquired by the image acquisition device 101, and for segmenting the target tumor into its target volume based on the medical images. Furthermore, it is also a device for developing, optimizing, and evaluating treatment plans based on the results of the tumor target volume segmentation.

[0033] Specifically, in this embodiment, the treatment planning system device 102 can acquire one or more optimization targets and receive medical images containing the target tumor acquired by the image acquisition device 101. Based on the medical images, the target tumor is segmented spatially to obtain multiple non-overlapping first target volumes within the target tumor. Subsequently, the treatment planning system device 102 can further segment the multiple first target volumes temporally to obtain multiple target volume sets corresponding to different segments, wherein the target volumes in at least one adjacent segment's target volume set are not completely identical. Further, a treatment plan is formulated, optimized, and evaluated based on the multiple target volume sets corresponding to different segments.

[0034] The treatment planning system device 102 can run a radiotherapy planning system (TPS) application that provides functions for creating, optimizing, and evaluating treatment plans. For example, the RT pro TPS system.

[0035] In some embodiments, the treatment planning system device 102 may include a TPS client and a TPS server.

[0036] The TPS client can be at least one of the following devices: smartphone, smartwatch, desktop computer, laptop, virtual reality terminal, augmented reality terminal, wireless terminal, and laptop computer. For example, in some embodiments, a user runs a 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 displaying the completed / optimized treatment plan. This effectively saves user time and provides a more intuitive presentation of the completed / optimized treatment plan, allowing users to evaluate it.

[0037] The TPS server can be a standalone physical server, a server cluster consisting of multiple physical servers, a distributed file system, or at least one of the following cloud servers providing basic cloud computing services: cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data or artificial intelligence platforms. This disclosure does not limit the specific type of TPS server. In some embodiments, the number of TPS servers can be more or less, and this disclosure does not limit the number of TPS servers. Of course, the TPS server can also include other functions to provide more comprehensive and diverse services. In some embodiments, the TPS server is used to provide background services for the TPS client, such as performing a treatment plan optimization process.

[0038] In some embodiments, the treatment planning system device 102 may be a computer device with a graphical user interface (GUI), which includes one or more processors, memory, and one or more applications. For example, the treatment planning system device 102 may include a treatment plan generation system application, the processor of which executes the application to implement the tumor target volume segmentation method provided in this disclosure.

[0039] Furthermore, in some embodiments, the treatment planning system device 102 may include a processor for implementing the tumor target volume segmentation method provided in embodiments of this disclosure.

[0040] The radiotherapy device 103 is a device for performing radiotherapy on a target subject. In one embodiment of this disclosure, the radiotherapy device 103 can acquire and execute a treatment plan for the target tumor generated by the treatment planning system device 102 based on the segmentation results of the tumor target volume segmentation plan.

[0041] In some embodiments, the radiotherapy device 103 may include a frame 1031, a treatment head 1032, and a support device 1033.

[0042] The gantry 1031 can be a rotatable gantry. The treatment head 1032 can be mounted on the gantry and is used to emit radiation rays, such as at least one of gamma rays, X-rays, proton rays, neutron rays, and heavy ion rays, to perform radiotherapy on the target object. The support device 1033 is used to support and move the target object and can be a treatment bed.

[0043] 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 rotate and irradiate around the target object, thereby completing radiotherapy.

[0044] For example, the radiotherapy device 103 includes an X-ray treatment head and a gamma ray treatment head mounted on a gantry 1031. Driven by the gantry 1031, the emitted X-rays and gamma rays can rotate around the same axis of rotation and irradiate the target object located at the isocenter in a coplanar manner. The X-rays and gamma rays can irradiate simultaneously or switch rapidly, such as at the millisecond level, to ensure that even biological effects are avoided and tomography is prevented.

[0045] The following is based on Figure 1 The implementation environment shown will be used to describe the methods provided in the embodiments of this disclosure.

[0046] Figure 2A schematic flowchart of a tumor target volume segmentation method provided in this exemplary embodiment is shown. In some embodiments, the tumor target volume segmentation method is performed by a tumor target volume segmentation device. For example, the tumor target volume segmentation device may be the one described above. Figure 1 The treatment planning system equipment shown. (Reference) Figure 2 As shown, the method may include the following steps: Step S100: Obtain a medical image containing the target tumor.

[0047] Understandably, the medical image of the target tumor is a medical image of the target object acquired through the image acquisition device 101, and this medical image contains the target tumor. Here, "target object" refers to the user to be treated with radiotherapy, such as a patient, experimental subject, or a phantom used to simulate a patient, and the target tumor is a single solid tumor or one of multiple solid tumors within the target object.

[0048] The aforementioned medical images can be a single type of image (single modality image) such as computed tomography (CT) images, emission computed tomography (ECT) images, magnetic resonance imaging (MRI) images, or positron emission tomography (PET) images, or a fusion image of multiple modalities mentioned above.

[0049] Among these, CT images can clearly display the anatomical structure and density information of tumors, facilitating the determination of the spatial relationship between tumors and bone tissue, etc.; MRI images have high resolution for soft tissues and can better distinguish the boundaries between tumors and surrounding normal soft tissues, such as the brain and spinal cord; PET images can reflect the functional state of tumors through differences in metabolic activity, providing a basis for identifying active tumor areas. In practice, image fusion technology is often used to fuse or register and overlay multiple modalities of images to comprehensively utilize the advantages of different modalities and provide more comprehensive tumor information for subsequent precise segmentation of the target volume.

[0050] Step S200: Segment the target tumor in spatial dimension according to the medical image to obtain multiple non-overlapping first target volumes located within the target tumor.

[0051] In this context, the spatial dimension emphasizes the distinction of location in physical space. Segmentation involves dividing the target tumor as a whole and / or the tissue within the target tumor in a medical image in the spatial dimension to obtain multiple first target volumes, which are the volumes (regions) to be irradiated. From a physical space perspective, the multiple first target volumes obtained by segmentation are located within the target tumor and do not overlap.

[0052] It is understandable that the multiple non-overlapping first target volumes are spaced apart and are not closely distributed.

[0053] Segmentation can involve identifying the boundaries of a specific region, outlining the contours of a specific region, or placing a target volume of a pre-defined size in a specific region. After the identification, outlining, or placement operations, multiple first target volumes are obtained.

[0054] Segmentation can be done manually, semi-automatically, or fully automatically. Manual segmentation involves physicians manually identifying the boundaries of specific regions based on medical image features, manually outlining the contours of specific regions, or manually placing target volumes of a pre-defined size within specific regions. Similarly, semi-automatic segmentation can combine thresholding methods, region growing algorithms, and other techniques to assist physicians in segmenting target volumes. Fully automatic segmentation can be based on artificial intelligence algorithms such as deep learning, automatically identifying and segmenting various target volumes within the tumor through trained models.

[0055] Spatial segmentation can divide the target tumor into multiple non-overlapping target volumes, such as... Figure 3 As shown, the target tumor is segmented spatially based on medical images, resulting in 11 primary target volumes (AK) within the tumor. These primary target volumes (AK) are all located within the tumor, do not intersect, and are spaced apart. This provides a basis for developing differentiated irradiation parameters for different target volumes. For example, different doses and types of radiation can be applied to different primary target volumes, thereby achieving precise irradiation of different tumor target volumes.

[0056] Step S300: Divide the multiple first target volumes in the time dimension to obtain multiple target volume sets corresponding to different divisions; wherein, the target volumes in the target volume sets corresponding to at least one adjacent division are not completely the same.

[0057] The temporal dimension segmentation refers to dividing the multiple first target volumes obtained in step S200 (i.e., spatial segmentation) into different subdivisions in the temporal dimension, so that the target volumes in the target volume sets corresponding to different subdivisions are not completely the same.

[0058] It should be noted that there are at least two fractions for each fraction. The number of fractions can be obtained by the physician through the planned number of fractions set by the treatment planning system application, or by the prescription dose and fraction dose set by the physician. Here, the prescription dose is the dose that the target volume should receive as specified by the physician in the radiotherapy plan. Each fraction dose can be the same or different, and the sum of the fraction doses of each fraction is the prescription dose.

[0059] It is understandable that the target volume set is the collection of the first target volumes planned for irradiation within a single fraction of multiple fractions, that is, the combination of all the first target volumes that need to be irradiated by radiation during a certain fraction of radiotherapy.

[0060] In one embodiment, at least one target volume set in a plurality of target volume sets contains a number of first target volumes that are greater than or equal to 1 and less than the total number of the plurality of non-overlapping first target volumes, and the first target volumes contained in two adjacent target volume sets are different.

[0061] It should be noted that the difference in the first target volume included in two adjacent target volume sets can be due to differences in some of the first target volumes in the two adjacent target volume sets, or it can be that the first target volumes in the two adjacent target volume sets are completely different. However, the first target volumes included in two non-adjacent target volume sets can be completely different, partially the same, or completely the same.

[0062] Taking a planned irradiation session of 4 as an example, in Figure 3 See also: Figure 4A , Figure 4B and Figure 4C The four target volume sets, each irradiated in four separate sessions, are shown from left to right.

[0063] like Figure 4A As shown, the target volume set corresponding to the first division includes target volumes E and J, the target volume set corresponding to the second division includes target volumes B, G, and I, the target volume set corresponding to the third division includes target volumes A, C, and H, and the target volume set corresponding to the fourth division includes target volumes D, F, and K. It can be seen that the first target volume in the target volume sets corresponding to adjacent first and second divisions, second and third divisions, and third and fourth divisions is completely different, and the first target volume in the target volume sets corresponding to non-adjacent divisions is completely different.

[0064] like Figure 4B As shown, the target volume set corresponding to the 3rd division includes target volumes A, C, H, and I. It can be seen that the first target volumes in the target volume sets corresponding to adjacent 1st and 2nd divisions, and 3rd and 4th divisions are completely different. The first target volumes in the target volume sets corresponding to adjacent 2nd and 3rd divisions are partially different (e.g., target volumes A, C, and H). Furthermore, the first target volumes in the target volume sets corresponding to non-adjacent divisions are completely different.

[0065] like Figure 4C As shown, the first target volume A corresponding to non-adjacent subdivisions, such as subdivision 1 and subdivision 3, is the same target volume, but the first target volume in the target volume set corresponding to adjacent subdivisions is completely different.

[0066] In one embodiment, the first target volume in the target volume set is irradiated in the corresponding fraction. Correspondingly, the first target volumes in different target volume sets are not irradiated in the same fraction. It can be understood that each fraction, according to its corresponding target volume set, needs to irradiate all the first target volumes in the set to ensure the integrity of the fractionated radiotherapy.

[0067] It should be noted that if the target body includes multiple solid tumors, then at least one can be segmented in both spatial and temporal dimensions using the tumor target volume segmentation method in this embodiment. Other solid tumors can be segmented using other traditional temporal or spatial segmentation methods, or they can be segmented in both spatial and temporal dimensions using the tumor target volume segmentation method in this embodiment.

[0068] This disclosure provides a method for segmenting tumor target volumes. First, a medical image containing the target tumor is acquired. Then, the target tumor is segmented spatially to obtain multiple non-overlapping first target volumes located within the tumor. Next, these first target volumes are segmented temporally to obtain multiple target volume sets corresponding to different fractions, with at least one set of target volumes from adjacent fractions being different. Thus, by coordinating spatial and temporal segmentation of the target tumor, multiple target volume sets suitable for multiple fractions (radiotherapy) can be obtained, with at least one set of first target volumes from adjacent fractions being different. This ensures that when executing a treatment plan based on the multiple target volume sets obtained by this tumor target volume segmentation method, the first target volumes irradiated in at least two fractions are not completely identical. This allows for the recovery of biological tissues surrounding different irradiated areas within the target tumor during fraction intervals, reducing damage to these tissues. Simultaneously, the biological dose of each target volume (e.g., PTV) is relatively higher, while the biological dose to the surrounding biological tissues is lower, further reducing damage to these tissues.

[0069] like Figure 3 As shown, the multiple non-overlapping first target volumes are uniformly distributed in space. In one embodiment, the multiple non-overlapping first target volumes are non-uniformly distributed in space. That is, the arrangement of the multiple non-overlapping first target volumes in space is not regular. For example, as... Figure 5 As shown, the target volume within the target tumor is irregularly distributed.

[0070] It should be noted that non-uniform distribution can be designed based on the heterogeneity (biological heterogeneity) of the tumor and treatment needs, such as differences in cell activity, blood supply, and sensitivity to radiation in different regions. Specifically, the first target volume varies in size and distribution density at different locations. For example, in the tumor periphery or in areas of biological tissue or critical organs adjacent to the irradiated area of ​​the tumor, the first target volume may be smaller and more densely distributed to improve irradiation accuracy and reduce radiation to surrounding healthy tissues; while in the tumor core or areas with lower radiation sensitivity, the first target volume may be larger to accommodate higher cumulative irradiation doses and more accurately match the treatment needs of different tumor subregions.

[0071] In one embodiment, at least two of the plurality of non-overlapping first target volumes are different in at least one of the following aspects: Target volume size; planned radiation type; planned radiation dose (prescription dose); planned number of fractions; planned fraction sequence.

[0072] The target volume of the first target volume is the physical size or volume scale of the first target volume in the spatial dimension.

[0073] The planned irradiation type for the first target volume is the type of radiation rays planned to be used to irradiate the first target volume. It can be one or more types of irradiation rays, which may include X-rays, gamma rays, electron rays, proton rays, neutron rays, heavy ion rays, etc.

[0074] The planned irradiation dose for the first target volume is the prescription dose, which is the total dose that the first target volume needs to receive.

[0075] The planned number of fractions for the first target volume refers to the planned number of fractions for irradiation of the first target volume; the planned fractionation order for the first target volume refers to the sequence of the first target volume within the entire fractionation radiotherapy regimen, such as... Figure 4B The first target volume I in the plan has 2 planned irradiations and a planned irradiation sequence of (2,3), indicating that it needs to be irradiated in the 2nd and 3rd irradiations, and not in the other irradiations.

[0076] The target volume size, planned radiation type, prescription dose, planned number of sessions, and planned session order mentioned above can all be obtained by the physician through settings or other means. This application embodiment does not specifically limit these settings.

[0077] It should be noted that the planned sequence of sub-sub ... Figure 4CIf the first target volume A is divided into two fractions, and the planned number of fractions is 2, with a planned interval of 2 days (i.e., once every 1 day), then the planned fraction sequence can be determined as (1,3), indicating that irradiation will be carried out in the first fraction (day 1) and the third fraction (day 3).

[0078] It should also be noted that the target volume size, planned irradiation type, planned irradiation dose (prescription dose), and planned number of fractions mentioned above are all relative to the first target volume, without considering the effects of fractions.

[0079] Taking as an example at least two of a plurality of non-overlapping first target volumes that differ in terms of planned irradiation dose: In one specific implementation, such as Figure 5 As shown, Figure 5 The target tumor shown is divided into multiple target volumes AD of different sizes and uneven distribution. The target volume B is different in size from the target volume A. The target volume A of the biological tissue near the irradiated area of ​​the tumor is smaller than the target volume B of the target tumor center. In this way, the damage to the biological tissue around the irradiated area of ​​the tumor can be reduced by using a smaller target volume. Furthermore, the planned irradiation types for the first target volume B and the first target volume A are different. For example, the target volume of the first target volume B is greater than 20 mm, while the target volume of the first target volume A is less than or equal to 20 mm. The planned irradiation type for the first target volume B is set to X-rays, and the planned irradiation type for the first target volume A is set to gamma rays, thereby leveraging the advantages of different types of radiation. In addition, the planned irradiation doses for the first target volume B and the first target volume A can also be different. The planned irradiation dose for the first target volume A is set to be greater than or equal to 18 Gy, while the planned irradiation dose for the first target volume B is set to be less than 18 Gy. In this way, high and low dose zones with different doses are formed within the target area. Through highly modulated dose distribution, high-dose radiation can be precisely irradiated to specific areas within the tumor. The highly non-uniform dose distribution stimulates different degrees of immune response mechanisms, resulting in better anti-tumor immune effects.

[0080] In one embodiment, the planned irradiation dose for multiple first target volumes is higher than the planned irradiation dose for non-target volume regions; wherein, as... Figure 3 As shown, the non-target volume region is the region outside of multiple first target volumes.

[0081] In this way, on the one hand, it ensures that the radiation energy is mainly concentrated in the primary target volume region where the tumor is located, effectively irradiating the primary target volume with a high dose of radiation, while providing appropriate low-dose radiation to non-target volume regions. This achieves effective radiation irradiation while reducing damage to biological tissues around the irradiated area of ​​the tumor. On the other hand, it can create different dose zones within the tumor, such as a high-dose zone (target volume region), a medium-dose zone (low-dose zone around the target volume region), and a low-dose zone (unirradiated area). Different dose zones are conducive to activating immunity and achieving a better anti-tumor immune effect.

[0082] For example, the combined irradiation of low-dose radiotherapy and ablation radiotherapy can achieve the superposition of the effects of "alteration of the immune microenvironment + immune regulation / activation". The low-dose radiotherapy consists of 4 fractions of 0.5 Gy; the ablation radiotherapy is performed via image-guided adaptive radiotherapy (IART) or ablation-guided radiotherapy (SRS / SABR). IART uses three doses: low, medium, and high, such as one fraction of 34 Gy, three fractions of 18 Gy, and five fractions of 10 Gy. SRS / SABR uses a high dose to induce direct tumor necrosis, suitable for early-stage, localized tumors.

[0083] In one embodiment, when the target volume set contains a plurality of first target volumes, at least two first target volumes in the target volume set are the same or different in at least one of the following aspects: Target volume size; planned radiation type; planned radiation dose (fractionated dose).

[0084] It should be noted that the planned irradiation dose of the first target volume in the target volume concentration is the dose of the first target volume in the corresponding fraction, that is, the fraction dose, and the fraction dose is less than or equal to the prescription dose of the first target volume.

[0085] For example, the target volume set in the same fraction can simultaneously include a first target volume of "small volume + high dose + gamma rays" and a first target volume of "large volume + low dose + X-rays". This setting enables precise radiotherapy to different tumor target volumes in a single irradiation, improving treatment efficiency. In other words, in the spatial dimension, by considering the biological differences and structural dynamic changes in different regions within the tumor, a more comprehensive radiotherapy dose strategy combining X-rays and gamma rays is formulated through zonal processing, achieving precise treatment of the symptom location in a single irradiation based on the specific region. In the temporal dimension, sequential dose sculpting between fractions, simultaneous multi-target region combination within a single fraction, and large-fraction bioequivalence acceleration precisely match the spatiotemporal evolution trajectory of the tumor. At the same time, X-rays and gamma rays are deeply synergistic, coaxial, coplanar, and of equal center, with rapid response of dual rays and real-time optimization of biological effects.

[0086] In one embodiment, at least two target volume sets from a plurality of target volume sets are the same or different in at least one of the following aspects: The number of first target volumes included; the size of the target volumes included; the planned radiation type of the first target volumes included; the planned radiation dose (fractionated dose) of the first target volumes included.

[0087] Among them, the number of first target volumes included in the target volume set is the number of first target volumes in the target volume set, the target volume size of the first target volumes included in the target volume set is the physical size or volume scale of each first target volume in the spatial dimension, the planned irradiation type of the first target volumes included in the target volume set is the planned irradiation type used to irradiate each first target volume in the target volume set, and the planned irradiation dose of the first target volumes included in the target volume set is the dose of each first target volume in the corresponding fraction.

[0088] In one embodiment, the first target volume, which is larger than a preset value, belongs to at least two or more target volume sets. This avoids irreversible damage to the biological tissues surrounding the irradiated area where the tumor is located by a single high-dose irradiation, while accumulating sufficient dose through multiple irradiations to achieve a better radiotherapy effect, thereby balancing the dose requirements of the large-volume target area with the protection requirements of the surrounding tissues.

[0089] Optionally, this preset value can be 20mm. For the first target volume with a target volume size of 20mm or less, a planned irradiation dose of 18-24Gy can be used. For the first target volume with a target volume size greater than 20mm, it is divided into multiple target volume clusters in the time dimension, and irradiation is performed in different fractions.

[0090] For example, such as Figure 5 As shown, the first target volume B is a target volume with a size greater than 20 mm, and the first target volumes A, C, and D are target volumes with a size less than 20 mm. Figure 6 As can be seen from the data, the first target volume B belongs to the target volume set corresponding to the second division and the target volume set corresponding to the third division, respectively, while the first target volumes A, C, and D belong to the target volume set of the first division.

[0091] In one embodiment, the tumor target volume segmentation method proposed in this embodiment further includes: Step S400: The target tumor is segmented in the spatial dimension according to the medical image, and a second target volume corresponding to the outline of the target tumor is obtained. Multiple non-overlapping first target volumes are all located within the second target volume.

[0092] It is understandable that the second target volume is the region where the entire target tumor is located. It can be the tumor target volume (GTV) or a target volume that includes the GTV, such as the clinical target volume (CTV) or the planning target volume (PTV). Multiple first target volumes are located within the second target volume of the target tumor. The second target volume covering the entire tumor can further improve the irradiation effect, and it can also work in synergy with the first target volume to further improve the irradiation effect.

[0093] Accordingly, in step S300, the multiple first target volumes are segmented along the time dimension to obtain multiple target volume sets corresponding to different segments, including: Step S310: Divide the second target volume and multiple first target volumes in the time dimension to obtain multiple target volume sets corresponding to different divisions, wherein at least one target volume set in the multiple target volume sets includes the second target volume, and the target volumes in at least one adjacent target volume set are not completely the same.

[0094] For example, the second target volume is as follows Figure 5 The shaded area shown contains multiple first target volumes within the second target volume.

[0095] Understandably, the target tumor is segmented along a time dimension to divide the second target volume and multiple first target volumes into different fractions, for example, such as... Figure 6 As shown, a second target volume is added to the target volume concentration corresponding to the first fraction to enhance the therapeutic effect, while the second target volume is not irradiated in the second and third fractions to reduce damage to biological tissues around the irradiated area of ​​the tumor.

[0096] It should be noted that the first target volume can be a high-dose region, and the second target volume can be a low-dose region. The high-dose region is usually referred to as the "peak" region, used to induce tumor cell death, release immunogenic molecules, expose antigens, clear immunosuppressive cells, and activate innate inflammatory signals. The low-dose region is usually referred to as the "trough" region, used to promote apoptosis, upregulate DNA repair genes, remodel matrix, normalize angiogenesis, downregulate transforming growth factor B, and promote giant cell polarization and immune cell infiltration through the bystander effect. Simultaneously, the immune system can be activated by combining high and low doses, i.e., combining high-dose radiotherapy to enhance the efficacy of immune checkpoint inhibitors.

[0097] Optionally, the second target volume differs from at least one of the plurality of first target volumes in at least one of the following aspects: planned irradiation type; planned irradiation dose (prescription dose); planned number of fractions; planned fractionation order.

[0098] Among them, the planned irradiation type is the type of irradiation line planned to be used to irradiate the first target volume / second target volume, the planned irradiation dose is the total dose that the first target volume / second target volume is planned to receive, the planned number of irradiations is the number of planned irradiations of the first target volume / second target volume, and the planned irradiation order is the order of the planned irradiations of the first target volume / second target volume.

[0099] Optionally, the number of target volume sets including the second target volume is less than the total number of multiple target volume sets.

[0100] It is understandable that the second target volume is not in the target volume set corresponding to all fractions, that is, there are fractions that do not contain the second target volume. For example, the second target volume is not irradiated in the third fraction to reduce damage to biological tissues around the irradiated area where the tumor is located.

[0101] Optionally, the first and second target volumes in the target volume concentration are both irradiated in the corresponding fractions.

[0102] Optionally, the second target volume in the target volume set differs from at least one of the plurality of first target volumes in at least one of the following aspects: Planned radiation type; planned radiation dose (fractionated dose).

[0103] The planned irradiation type refers to the type of irradiation to be used to irradiate the first target volume / second target volume of the target volume set. The irradiation type can include X-rays, gamma rays, electron beams, proton beams, neutron beams, heavy ion beams, etc. For example, the second target volume uses low-dose X-rays, and the first target volume uses high-dose gamma rays. The planned irradiation dose is the dose required for the first target volume / second target volume of the target volume set in the fractional irradiation, i.e., the fractional dose.

[0104] It should be noted that X / γ rays can be fused with multiple target volumes obtained by this target volume segmentation method to provide a higher peak-to-trough ratio, higher peak dose, and lower organ at risk (OAR) dose.

[0105] In one embodiment, the tumor target volume segmentation method proposed in this embodiment further includes: Step S500: Group the multiple first target volumes to obtain multiple target volume groups, each target volume group including at least one first target volume; Accordingly, in step S300, the multiple first target volumes are segmented along the time dimension to obtain multiple target volume sets corresponding to different segments, including: Step S320: Based on multiple target volume groups, the multiple first target volumes are segmented in the time dimension to obtain multiple target volume sets corresponding to different segments; wherein, the target volume set includes at least one target volume group, and the target volume groups in the target volume sets corresponding to at least one adjacent segment are not completely the same.

[0106] It should be noted that group management enables the orderly allocation and dynamic adjustment of the first target volume over time. Specifically, firstly, grouping the first target volume allows target volumes with similar treatment needs to be grouped together for intensive irradiation planning, reducing the complexity of each individual operation. For example, multiple first target volumes within a tumor with the same radiation sensitivity can be grouped together, allowing for standardized irradiation parameters and improved planning efficiency. Secondly, segmenting the time dimension based on target volume groups ensures that the target volume sets for each fraction are composed of target volume groups as the basic unit, rather than individual first target volumes. This allows for more systematic differentiation between fractions: target volume groups in adjacent fractions are not entirely identical, and the irradiation group combinations can be flexibly adjusted according to dynamic changes in the tumor. Through the combination and fractional allocation of target volume groups, it is ensured that all first target volumes are fully covered, and the accuracy and adaptability of radiotherapy planning can be improved through dynamic adjustment of groups.

[0107] Optionally, adjacent first target volumes among a plurality of first target volumes may be located in different target volume groups.

[0108] It should be noted that adjacent first target volumes may be irradiated in different fractions or in the same fraction; this application does not impose specific limitations on this.

[0109] It should be noted that by allowing adjacent first target volumes to be irradiated in different fractions, the risk of dose superposition between adjacent regions can be reduced by avoiding simultaneous irradiation of adjacent first target volumes in the same fraction. Since adjacent first target volumes are spatially close, irradiating them in the same group and fraction could lead to excessively high doses to the biological tissues surrounding the tumor at the irradiation zone. Dividing them into different target volume groups allows for staggered irradiation over time, such as separate fractions, reducing the possibility of localized dose concentration and protecting the biological tissues surrounding the tumor at the irradiation zone.

[0110] For example, such as Figure 7Taking a large tumor (dark red) as an example, the target tumor is first spatially segmented to obtain multiple first target volumes (red target volumes) and one second target volume (green target volume). Then, the multiple first target volumes are grouped (target area grouping) to obtain multiple target volume groups (target volumes of the same color are grouped together, for a total of four groups). Finally, the multiple target volume groups and the second target volume are time-segmented to obtain four sessions (numbered ①-④). Each session includes one target volume group and a second target volume. Among them, the first target volume in the target volume group is irradiated by local ablation (high dose) gamma rays, and the second target volume is irradiated by conventional / low dose X-rays, thereby achieving deep synergy of X-ray and gamma rays.

[0111] Figure 8 This diagram illustrates multiple target volume groups provided in embodiments of the present disclosure, wherein the first target volumes with the same reference numerals belong to the same target volume group, i.e. Figure 8 The diagram shows four target volume groups. The three first target volumes labeled 1 belong to the same target volume group and are all the same size. The three first target volumes labeled 2 belong to the same target volume group, and the other target volumes are also the same size, but all are larger than the first target volume labeled 1. The three first target volumes labeled 3 belong to the same target volume group, and the other target volumes are also the same size, but all are smaller than the first target volume labeled 2. The two first target volumes labeled 4 belong to the same target volume group, and the other target volumes are also the same size. Figure 8 It can be seen that among multiple first target volumes, adjacent first target volumes are located in different target volume groups.

[0112] at the same time, Figure 9A A schematic diagram of multiple target volume groups in the target volume sets corresponding to each segment provided in the embodiments of this disclosure is shown. The diagram schematically shows four target volume sets corresponding to four different segments. Each target volume set includes a corresponding target volume group, and the target volume groups included in two adjacent segments are different. According to... Figure 9A The four different fractions in the process enable irradiation of all first target volumes, and different groups of first target volumes can be irradiated in different fractions, while two adjacent first target volumes are not in the same fraction.

[0113] Figure 9B This illustration shows a schematic diagram of a target volume group corresponding to another set of target volumes in each segment, provided by an embodiment of this disclosure. It schematically shows three target volume sets corresponding to three different segments, each target volume set including a corresponding target volume group, and the target volume groups included in two adjacent target volume sets are different. According to... Figure 9BThe four different irradiation sessions enabled the irradiation of all first target volumes, and the same first target volume group could be irradiated in different sessions. For example, target volume group 2 was irradiated in the second and third sessions, and two adjacent first target volumes could be irradiated in the same session.

[0114] Of course, the number of first target volumes in the target volume group, the size of the first target volume, the planned irradiation type of the first target volume, the planned irradiation dose of the first target volume, and the planned number of fractions of the first target volume can be planned for the target volume group of each target volume set based on the dose peak-to-valley ratio.

[0115] Optionally, multiple target volume groups within a target volume cluster may be irradiated in the corresponding fractions.

[0116] Optionally, when the target volume group contains multiple first target volumes, the multiple first target volumes are identical in at least one of the following aspects: Target volume size; planned radiation type; planned radiation dose (fraction dose); planned number of fractions.

[0117] Among them, the target volume size is the physical size or volume scale of the first target volume in the target volume group in the spatial dimension; the planned irradiation line type is the type of irradiation line planned to be used to irradiate multiple first target volumes in the target volume group; the planned irradiation dose is the dose required for the first target volume in the target volume group corresponding to the target volume set, i.e., the fractional dose; and the planned number of fractions is the number of fractions of planned irradiation for the first target volume in the target volume group.

[0118] It should be noted that grouping primary target volumes with consistent key treatment parameters together allows for standardized irradiation protocols for that group, reducing the complexity of treatment planning and improving efficiency. For example, grouping multiple small primary target volumes requiring gamma-ray irradiation together allows for one-time planning of their irradiation parameters, eliminating the need for individual settings.

[0119] Optionally, at least two of the multiple target volume groups are different in at least one of the following aspects: The number of first target volumes included; the size of the first target volumes included; the planned radiation type of the first target volumes included; the planned radiation dose (prescription dose) of the first target volumes included; the planned number of fractions of the first target volumes included; the planned fraction order of the first target volumes included.

[0120] Wherein, the number of first target volumes included refers to the number of first target volumes in the target volume group; the target volume size of the included first target volumes refers to the physical dimensions or volume scale of the first target volumes in the target volume group in the spatial dimension; the planned irradiation type of the included first target volumes refers to the type of irradiation to be used to irradiate the first target volumes in the target volume group; the planned irradiation dose of the included first target volumes refers to the prescription dose of the first target volumes in the target volume group, that is, the total dose that the first target volumes need to receive; the planned number of fractions of the included first target volumes refers to the number of fractions of the planned irradiation of the first target volumes in the target volume group; and the planned fraction order of the included first target volumes refers to the order in which the first target volumes in the target volume group are irradiated throughout the entire fractionated radiotherapy.

[0121] Optionally, at least two target volume groups in the target volume set are different in at least one of the following aspects: The number of first target volumes included; the size of the target volumes included; the planned radiation type of the first target volumes included; the planned radiation dose (fractionated dose) of the first target volumes included.

[0122] Wherein, the number of first target volumes included is the number of first target volumes in the target volume group of the target volume set; the target volume size of the included first target volumes is the physical size or volume scale of the first target volumes in the target volume group of the target volume set in the spatial dimension; the planned irradiation type of the included first target volumes is the type of irradiation line planned to be used to irradiate the first target volumes in the target volume group of the target volume set; and the planned irradiation dose of the included first target volumes is the dose required for the first target volumes in the target volume group of the target volume set in the corresponding fraction of the target volume set, i.e., the fractional dose.

[0123] For example, a target volume set includes a target volume group of "5 small volumes + gamma rays + high dose" and a target volume group of "1 large volume + X-ray + low dose". By differentiating the irradiation within a single session, both local enhancement and overall coverage are taken into account, thereby improving the accuracy and comprehensiveness of a single treatment.

[0124] Optionally, at least two target volume sets are different in at least one of the following ways: The number of target volume groups included; the size of the target volume within each target volume group; the planned radiation type for each target volume group; and the planned radiation dose (fractionated dose) for each target volume group.

[0125] The number of target volume groups included refers to the number of target volume groups in the target volume set; the target volume size of the included target volume group refers to the physical size or volume scale of the volume in the spatial dimension within the target volume set; the planned irradiation type of the included target volume group refers to the type of radiation planned to be used to irradiate the target volume set; and the planned irradiation dose of the included target volume group refers to the required dose for the target volume set corresponding to the fractional dose of the target volume set, i.e., the fractional dose.

[0126] It should be noted that in other embodiments, other numbers of multiple divisions can be designed to make different plans for the first target volume of the target volume group included in each target volume set. This embodiment does not limit this.

[0127] In one embodiment, step S200, segmenting the target tumor spatially based on the medical image, includes: Based on tumor heterogeneity (biological heterogeneity), the target tumor is segmented in spatial dimensions according to medical images.

[0128] Tumor specificity is used to indicate biological differences within a tumor, which can be reflected in tumor cell proliferation activity, metabolic levels, gene expression, and sensitivity to radiation. These differences can be identified and quantified through medical imaging.

[0129] Based on the tumor heterogeneity (biological heterogeneity) of the target tumor, different temporal segmentation methods are used to irradiate different spatial regions of the target tumor. This means that during spatial segmentation, the target tumor is divided into multiple regions with different biological differences, i.e., multiple first target volumes, according to the biological differences within the tumor reflected in medical images. In this way, different radiotherapy dosage strategies can be formulated for different first target volumes, and different irradiations can be applied to different first target volumes within the target tumor to achieve precise radiotherapy based on the specific region.

[0130] For example, high-metabolic regions of a tumor identified through PET images are segmented into one or more primary target volumes, while low-metabolic regions are segmented into other primary target volumes. This segmentation method can accurately match the heterogeneity (biological heterogeneity) characteristics within the tumor, providing a basis for developing differentiated radiotherapy plans for different primary target volumes, such as different irradiation doses, radiation types, and fractionation times. This enables enhanced treatment of high-risk areas and reasonable control of low-risk areas, improving the precision and effectiveness of radiotherapy.

[0131] Furthermore, after step S200, the method further includes: Based on the tumor heterogeneity (biological heterogeneity) of multiple first target volumes, a radiotherapy strategy for multiple first target volumes is developed.

[0132] The radiotherapy strategy for the first target volume may include at least one of the following: the prescribed dose of the first target volume, the target volume size, the planned radiation type, the planned number of fractions, the fraction dose, and the planned fraction sequence.

[0133] It should be noted that if radiotherapy is not fractionated, a one-target-volume radiotherapy strategy may not include the planned number of fractions, fraction dose, and planned fractionation order.

[0134] In one embodiment, when the target tumor is located in the head, the total number of target volumes is less than or equal to 5.

[0135] It is important to note that the head region contains a large number of biological tissues surrounding the irradiation area of ​​critical tumors that are highly sensitive to radiation, such as the cerebral cortex, brainstem, optic nerve, and cochlea. These tissues have low radiation tolerance doses, and excessive irradiation can easily lead to serious complications, such as cognitive impairment, vision loss, and hearing impairment. Limiting the total number of target volumes corresponding to head tumors to no more than 5, i.e., controlling the total number of radiotherapy fractions, can reduce the cumulative radiation exposure of biological tissues surrounding the irradiation area of ​​the head tumor, thereby reducing the risk of radiation damage. Simultaneously, the anatomical location of head tumors is relatively fixed, and the tumor morphology and boundaries are usually well-defined. By rationally designing target volumes of no more than 5 fractions, complete coverage and precise irradiation of the tumor can be achieved, balancing treatment needs with the protection of biological tissues surrounding the irradiation area of ​​the tumor while ensuring therapeutic efficacy.

[0136] In one embodiment, the tumor target volume segmentation method proposed in this embodiment further includes: Step S410: Before the i-th fraction, acquire an image containing the target tumor, where i is greater than 1 and less than or equal to the planned number of fractions.

[0137] Here, "before the i-th fraction" can refer to the period before the i-th fraction irradiation, or between the (i-1)-th fraction and the i-th fraction, where i is greater than 1 and less than or equal to the planned number of fractions. Imaging containing the target tumor can indicate the biological differences within the target tumor and the dynamic changes in the target tumor structure. This imaging can be an image scanned before the i-th fraction, or an image predicted before the i-th fraction based on medical images or other images before the i-th fraction.

[0138] It should be noted that this step dynamically monitors the biological differences within the tumor and the dynamic changes in the tumor structure by acquiring images containing the target tumor before the i-th fraction. This provides a real-time basis for adjusting the radiotherapy strategy for the first target volume in the i-th fraction, ensuring that the radiotherapy strategy is always based on the latest state of the tumor, thus demonstrating the flexibility of adaptive radiotherapy.

[0139] Step S420: Adjust at least one aspect of the first target volume and / or the second target volume within the i-th segment based on the imaging prior to the i-th segment: Target volume distribution; target volume size; planned irradiation type; planned irradiation dose (fractionated dose).

[0140] The target volume distribution refers to the spatial distribution of the first target volume / second target volume within the i-th fraction, which can be a regular or irregular distribution. The target volume size refers to the physical dimensions or volume scale of the first target volume / second target volume within the i-th fraction in the spatial dimension. The planned irradiation type refers to the type of irradiation line planned to be used to irradiate the first target volume / second target volume within the i-th fraction. The planned irradiation dose refers to the dose required for the first target volume / second target volume in the i-th fraction.

[0141] Understandably, based on the imaging results before the i-th fraction, if the tumor volume is found to have shrunk, the distribution and / or size of the first and / or second target volumes can be adjusted accordingly to avoid ineffective irradiation of the already diminished areas. If the sensitivity of a certain area of ​​the tumor to the current radiation type decreases, the planned irradiation type can be changed to improve efficacy. If imaging shows that the cumulative dose in a certain area is insufficient or excessive, the planned irradiation dose (fraction dose) can be adjusted to balance treatment efficacy and safety. Through this targeted adjustment, the irradiation plan for each fraction is ensured to be precisely matched with the real-time status of the tumor, reducing the risk of treatment deficiencies or damage to biological tissues around the irradiated area of ​​the tumor caused by deviations.

[0142] Furthermore, it enables precise spatial segmentation of the tumor interior, ensuring that irradiation rays reach the first target volume without overlap. This allows the radiotherapy plan to be adjusted according to the dynamic changes of the tumor during treatment, avoiding irradiation deviations that may occur with fixed plans. Ultimately, through the coordinated segmentation of spatial and temporal dimensions, the adaptability and precision of the tumor target volume are improved, thereby enhancing radiotherapy efficacy and reducing damage to biological tissues surrounding the irradiated area of ​​the tumor. Based on the tumor's biological and immune characteristics, it can precisely irradiate specific areas within the tumor with high-dose radiation from multi-source focused gamma rays through highly modulated dose distribution, while simultaneously adapting low-dose X-ray intensity-modulated irradiation to irregular tumors. This highly uneven dose distribution stimulates different immune response mechanisms, resulting in better therapeutic effects.

[0143] Furthermore, the imaging is functional imaging, which can be one or more of the following: positron emission tomography (PET), functional magnetic resonance imaging (fMRI), and stereotactic image-guided cyberknife therapy (SICT).

[0144] It is important to note that, compared to conventional anatomical imaging, functional imaging not only displays the anatomical morphology of tumors but also reflects their biological activity, such as metabolic levels, blood perfusion, and cell proliferation activity. For example, PET can identify hypermetabolic active areas within a tumor based on tracer uptake, while functional MRI can reflect the microcirculatory status of tumor tissue. Using functional imaging allows for more precise localization of active residual tumor areas, recurrence risk areas, or areas of differential response to treatment. This provides a more biologically meaningful basis for adjusting target volume, radiation type, and dose, enabling adjustments to better align with the functional characteristics of the tumor and further improving the precision and targeting of radiotherapy.

[0145] Based on the biological differences within the target tumor and the dynamic changes in the target tumor structure reflected in the imaging of the target tumor acquired before the i-th fraction, optimization is performed in the spatial dimension, such as adjusting the distribution and / or size of the target volume, and in the radiation type and / or dose, such as adjusting the planned radiation type and / or fraction dose. In this way, while accurately optimizing the spatial segmentation within the target tumor, different radiotherapy dose strategies can be formulated for different regions based on their biological and structural differences. Different radiation irradiation and / or fraction doses can be applied to the optimized first target volume within the target tumor in a targeted manner, achieving precision radiotherapy "tailored to the region". This concept of "tailored to the region" is called adaptive biological therapy (ATB).

[0146] For example, such as Figure 10 As shown, for the target tumor region (gray area), before the first fraction, one or more imaging methods such as PET, fMRI, and SICT are acquired. Based on the heterogeneity of the tumor reflected by the imaging, spatial segmentation is performed within the target tumor to obtain two first target volumes, namely target volume A (red) and target volume B (orange), and a second target volume, namely target volume C (yellow area). In the first fraction, the planned irradiation type for target volume A is gamma rays, and the planned irradiation type for target volume C is X-rays.

[0147] If, after the first fraction, the target tumor region, i.e. the target volume C, has shrunk, for example, if the target volume C has shrunk based on imaging obtained before the second fraction, or if the target volume C has shrunk based on one or more imaging methods such as PET, fMRI, and SICT, then the irradiation field of the second target volume (i.e., modified field) is modified. In the second fraction, the planned irradiation type for the target volume B is gamma rays, and the planned irradiation type for the target volume C is X-rays. If, after the second fraction, it is determined / predicted that the target volume has changed, for example, target volume A has disappeared, target volume B has expanded, and target volume C has not shrunk, then, for example, if the target volume change is determined based on the imaging obtained before the second fraction, or if the target volume change is predicted based on one or more imaging methods such as PET, fMRI, and SICT, then the irradiation peak region of target volume B is modified. In the third fraction, the planned irradiation type for target volume B is gamma rays, and the planned irradiation type for target volume C is X-rays. After the third fraction, the same process is followed. If the target tumor area, i.e. the target volume C, is determined / predicted to have shrunk, the irradiation field of the target volume C is modified. In the fourth fraction, the planned irradiation type for the target volume B is gamma rays, and the planned irradiation type for the target volume C is X-rays. Similarly, after the fourth irradiation, if the target tumor region (target volume C) is determined / predicted to have shrunk and is very close to the shape of the target volume B, the irradiation peak area of ​​the first target volume is modified to cover the entire tumor region. In the fifth irradiation, the entire tumor region (target volume C) is irradiated with gamma rays. This completes the entire ATB procedure.

[0148] Furthermore, the effectiveness of the tumor target volume segmentation method of this application is compared with that of traditional tumor target volume segmentation methods, as follows: like Figure 11 As shown, for target volume segmentation of soft tissue sarcoma, X-rays are used to cover a second target volume, such as a PTV, and the edges of the second target volume are conformally sized. Multiple spherical high-dose points (i.e., the first target volume) are arranged inside the second target volume using gamma rays. The areas enclosed by green, yellow, and red in the figure represent the cumulative radiation dose. Figure 10 As can be seen from the diagram, the tumor target volume segmentation method of this application on the left has a higher peak-to-trough ratio compared with the existing tumor target volume segmentation method on the right. With a higher dose at the second target volume apex, the dose to organs at risk is lower, and the protection of normal organs is better.

[0149] like Figure 12As shown, this illustrates target volume segmentation for soft tissue lung cancer tumors. A large second target volume is covered with low-dose X-rays with conformal edge treatment. Multiple high-dose spherical irradiations (first target volumes) are then performed within the large second target volume. The areas enclosed by green, yellow, and red in the figure also represent the cumulative radiation dose. Figure 11 As can be seen from the image, the tumor target volume segmentation method of this application on the left, compared with the existing tumor target volume segmentation method on the right, significantly increases the dose of the second target volume, such as the GTV apex, by X / γ irradiation, while greatly reducing the dose of the GTV edge and organs at risk (OARS), resulting in a higher peak-to-trough ratio.

[0150] The tumor target volume segmentation method provided in the above-disclosed embodiments segments the tumor from both spatial and temporal dimensions to reduce damage to biological tissues surrounding the irradiated area of ​​the tumor during radiotherapy. The following three disclosed embodiments segment the tumor target volume from other dimensions. Before explaining these three embodiments in detail, some concepts related to volume in the above-disclosed embodiments are summarized to avoid repeating these concepts in subsequent embodiments. Alternatively, the concepts described in the foregoing disclosed embodiments can be referred to.

[0151] Target volume distribution: The distribution of the target volume in the spatial dimension. The distribution can be regular or irregular.

[0152] Target volume size: The physical dimensions or volume scale of the target in spatial dimensions.

[0153] Planned irradiation type: The type of irradiation to be used to irradiate the target volume. It can be one or more types of irradiation, including X-rays, gamma rays, electron beams, proton beams, neutron beams, heavy ion beams, or other rays.

[0154] Fractionation: Also known as fractionated radiotherapy, this involves dividing the total radiation dose (e.g., the prescribed dose) required for radiotherapy into multiple doses and applying them to the target subject in fractions.

[0155] Planned number of irradiations: The planned number of irradiations of the target volume.

[0156] Fractional dose: The dose that the target volume should receive within a fraction.

[0157] Subsequent number: Indicates which subsequent number it is in, for example, the subsequent number of the 2nd subsequent is 2; Planned fractionation sequence: The order in which the volume is divided into fractions within the entire fractionated radiotherapy treatment can be represented by the set of fractionation sequence numbers.

[0158] It should be noted that the planned irradiation sequence can also be determined by the planned number of irradiations, the planned irradiation interval, and the starting irradiation. The starting irradiation refers to which irradiation among multiple irradiations begins, which can be indicated by the irradiation sequence number. The planned irradiation interval is the time interval between adjacent irradiations of the target volume; for example, a 1-day interval indicates daily irradiation, a 2-day interval indicates irradiation once a day, and so on. Thus, based on the planned number of irradiations, the planned irradiation interval in days, and the starting irradiation sequence number, the planned irradiation sequence can be determined.

[0159] It should be noted that the target volume size, planned radiation type, planned number of fractions, and planned fraction order mentioned above can all be obtained by manual setting by the physician or by automatic determination using algorithms based on medical images, or by other means. This application embodiment does not specifically limit these parameters.

[0160] Furthermore, it should be noted that the wording in the method steps of the following three disclosed embodiments that is identical to certain method steps or static limitations in the above disclosed embodiments can be explained by referring to the descriptions in the above embodiments, and will not be explained in detail in the following disclosed embodiments. Of course, the wording in the method steps or static limitations described in the above disclosed embodiments can also be explained by referring to the specific explanations in the following disclosed embodiments.

[0161] The following disclosed embodiments (i.e., disclosed embodiment one) address the technical problem of how to synergistically combine high and low doses to achieve a better anti-tumor immune response. To this end, a target volume segmentation method is proposed, which constrains (sculpts) the prescribed dose based on the segmentation results of the tumor in the spatial dimension, forming heterogeneity (different doses) of irradiation dose within the tumor to enhance the anti-tumor immune response.

[0162] The following is based on Figure 1 The scenario shown illustrates the tumor target volume segmentation method provided in this disclosure.

[0163] The tumor target volume segmentation method provided in this disclosure is applied to a tumor target volume segmentation device, which can be... Figure 1 Treatment planning system equipment 102 in the middle. Figure 14 A schematic flowchart of a tumor target volume segmentation method provided in an embodiment of this disclosure is shown. Figure 14 As shown, the tumor target volume segmentation method includes: Step S1401: Obtain a medical image containing the target tumor.

[0164] The medical image of the target tumor is acquired by the image acquisition device 101, which contains the target tumor. The target object refers to the user undergoing radiotherapy, such as a patient, experimental subject, or a phantom used to simulate a patient. The target tumor is a single solid tumor or one of multiple solid tumors within the target object.

[0165] The aforementioned medical images can be a single image (single modality image) such as CT image, ECT image, MRI image, or PET image, or a fusion image of multiple modalities of the above.

[0166] Step S1402: Segment the target tumor in spatial dimension according to the medical image to obtain multiple non-overlapping first target volumes located within the target tumor; wherein, at least two first target volumes have different prescription doses.

[0167] In this context, the spatial dimension emphasizes the distinction of location in physical space. Segmentation involves dividing the target tumor as a whole and / or the tissue within the target tumor in a medical image in the spatial dimension to obtain multiple first target volumes, which are the volumes (regions) to be irradiated. From a physical space perspective, the multiple first target volumes obtained by segmentation are located within the target tumor and do not overlap.

[0168] It should be noted that the multiple non-overlapping first target volumes are spaced apart and are not closely distributed.

[0169] It should be understood that segmentation can involve identifying the boundaries of a specific region, outlining the contours of a specific region, or placing a target volume of a predetermined size within a specific region. After identification, outlining, or placement, multiple first target volumes are obtained. Segmentation can be done manually, semi-automatically, or fully automatically. Manual segmentation involves physicians manually identifying the boundaries of a specific region, manually outlining the contours of a specific region, or manually placing a target volume of a predetermined size within a specific region based on medical image features. Similarly, semi-automatic segmentation can combine thresholding methods, region growing algorithms, etc., to assist physicians in segmenting target volumes. Fully automatic segmentation can be based on artificial intelligence algorithms such as deep learning, automatically identifying and segmenting various target volumes within the tumor through trained models.

[0170] In addition, the prescribed dose is the total dose that should be received by the target volume (tumor and high-risk areas that may be invaded) as specified by the physician in the treatment plan. Specifically, physicians can set corresponding prescribed doses for different first target volumes through the treatment planning system.

[0171] In the embodiments of this disclosure, the prescription doses of at least two first target volumes are different, that is, the prescription dose of one of the at least two first target volumes is higher than the prescription dose of the other target volume. Specifically, the prescription doses of at least two first target volumes being different can mean that one first target volume has a different prescription dose than the other first volumes, while the prescription doses of the other first volumes are the same; it can also mean that some (more than one) of the first target volumes have a different prescription dose than the other first target volumes, while the prescription doses of the other first volumes are the same; of course, it can also mean that the prescription doses of each first target volume are different, and the embodiments of this disclosure do not specifically limit this.

[0172] It should be noted that if the target body includes multiple solid tumors, then at least one or each solid tumor can be segmented using the tumor target volume segmentation method in this disclosure embodiment, while other solid tumors can be segmented using other conventional time or space segmentation methods or the segmentation method of this disclosure.

[0173] The technical solution provided in this disclosure, after acquiring a medical image containing a target tumor, segments the target tumor in the medical image spatially to obtain multiple non-overlapping first target volumes within the target tumor, wherein at least two of the first target volumes have different prescription doses. This allows the formation of dose zones with different doses within the tumor, such as high-dose zones (the first target volume corresponding to the higher dose among the different dose first target volumes), medium-dose zones (the first target volume corresponding to the lower dose among the different dose first target volumes), and low-dose zones (the area within the target tumor and surrounding the first target volumes). Through highly modulated dose distribution, high-dose radiation can be precisely irradiated to specific areas (multiple first target volumes) within the tumor. Simultaneously, the highly non-uniform dose distribution (i.e., radiotherapy dose heterogeneity) can stimulate different degrees of activation response, achieving a better anti-tumor immune response effect.

[0174] In some embodiments, the plurality of non-overlapping first target volumes within the target tumor may be uniformly distributed in the spatial dimension, that is, the distribution of the plurality of non-overlapping first target volumes in the spatial dimension is regular. Of course, the plurality of non-overlapping first target volumes within the target tumor may also be non-uniformly distributed in the spatial dimension, that is, the distribution of the plurality of non-overlapping first target volumes in the spatial dimension is not regular, and the embodiments of this disclosure do not specifically limit this.

[0175] In some embodiments, at least two of the plurality of first target volumes are the same or different in at least one aspect of the target volume size, planned irradiation type, planned number of fractions, or planned fractionation order.

[0176] It should be noted that the objects of comparison here are at least two of the multiple first target volumes. Each first target volume can obtain at least one of the following: target volume size, planned irradiation type, planned number of fractions, or planned fractionation order.

[0177] For example, the planned number of fractions for dividing one first target volume and another first target volume within the target tumor can be the same, such as 3 times for both. Of course, they can also be different, such as 1 fraction for some target volumes and 2 fractions for others.

[0178] In some embodiments, the planned irradiation dose of each of the plurality of first target volumes is higher than the planned irradiation dose of the non-target volume region; wherein, the non-target volume region is the region outside the plurality of first target volumes.

[0179] In some embodiments, the method may further include the following steps: Step S1403: Group the multiple first target volumes to obtain multiple target volume groups, each target volume group including at least one first target volume. The first target volumes with different planned irradiation doses may be located in different target volume groups.

[0180] This step can be performed after step S1402 to group multiple first target volumes. After grouping, the planned irradiation dose of the first target volumes within a group can be set to be the same, which can improve the efficiency of developing radiotherapy plans.

[0181] In some embodiments, when the target volume group includes a plurality of first target volumes, the plurality of first target volumes are identical in at least one of the following aspects: Target volume size; planned radiation type; planned radiation dose; planned number of fractions; planned fraction sequence.

[0182] In some embodiments, at least two of the multiple target volume groups are different in at least one of the following aspects: The number of first target volumes included; the size of the target volumes included; the planned radiation type of the first target volumes included; the planned radiation dose of the first target volumes included; the planned number of fractions of the first target volumes included; the planned fraction order of the first target volumes included.

[0183] In some embodiments, the method may further include the following steps: Step S1404: Divide the multiple first target volumes along the time dimension to obtain multiple target volume sets corresponding to different divisions. The target volumes in the target volume sets corresponding to different divisions can be completely identical. Of course, as in the above-disclosed embodiment, the target volumes in the target volume sets corresponding to different divisions can not be completely identical.

[0184] This step can be performed after step S1402 or after step 1403. It is used to segment multiple first target volumes in the time dimension to obtain multiple target volume sets corresponding to different fractions. In this way, under different fractions, the target volumes in the target volume sets corresponding to different fractions are exactly the same, but the prescription dose (i.e., planned irradiation dose) of at least two first target volumes are different. Regardless of whether the first target volumes with different planned irradiation doses belong to the same fraction, from the perspective of the entire radiotherapy process (dose accumulation), it is still possible to form dose zones with different doses inside the tumor. Different dose zones are conducive to activating immunity and can still achieve a better anti-tumor immune response.

[0185] Based on step S1403, step S1404 specifically includes: Based on multiple target volume groups, the first target volume is segmented in the time dimension to obtain multiple target volume sets corresponding to different segments; wherein, the target volume set includes at least one target volume group, and the target volume groups in the target volume set are completely identical.

[0186] It should be understood that the number of fractions and / or the order of fractions for multiple first target volumes can be set by the physician or automatically generated by the algorithm.

[0187] In some embodiments, for a first target volume with a planned number of fractions greater than or equal to 2, the irradiation dose (i.e., fractional irradiation dose) for each fraction may be the same or different. For example, if the first target volume is configured with 3 fractions and the prescribed dose (planned total irradiation dose) is 30 Gy, the irradiation dose for the three fractions of the first target volume may all be the same, 10 Gy, or the irradiation dose for the first fraction may be 15 Gy, the irradiation dose for the second fraction may be 10 Gy, and the irradiation dose for the third fraction may be 5 Gy.

[0188] In some embodiments, when the target volume set includes a plurality of first target volumes, at least two first target volumes in the target volume set are the same or different in at least one of the following aspects: Target volume size; planned radiation type; planned radiation dose.

[0189] In some embodiments, the first target volume in the target volume set is irradiated in the corresponding fractions.

[0190] In some embodiments, at least two target volume sets among a plurality of target volume sets are the same or different in at least one of the following aspects: The number of first target volumes included; the size of the target volumes included; the planned radiation type of the first target volumes included; the planned radiation dose of the first target volumes included.

[0191] In some embodiments, at least two target volume groups within the target volume set are different in at least one of the following aspects: The number of first target volumes included; the size of the target volumes included; the planned radiation type of the first target volumes included; the planned radiation dose of the first target volumes included.

[0192] In some embodiments, at least two of the plurality of target volume sets are different in at least one of the following aspects: The number of target volume groups included; the size of the target volume within each target volume group included; the planned radiation type for each target volume group included; and the planned radiation dose for each target volume group included.

[0193] In some embodiments, the first target volume whose target volume is larger than a preset value belongs to at least two or more target volume sets.

[0194] In some embodiments, the method may further include the following steps: Step S1405: The target tumor is segmented in spatial dimension according to the medical image, and a second target volume corresponding to the contour of the target tumor is obtained. Multiple non-overlapping first target volumes are all located within the second target volume.

[0195] Accordingly, step S1402 specifically includes: The multiple first target volumes and second target volumes are segmented along the time dimension to obtain multiple target volume sets corresponding to different segments, and at least one target volume set in the multiple target volume sets includes the second target volume.

[0196] In some embodiments, the second target volume differs from at least one of the plurality of first target volumes in at least one of the following aspects: Planned radiation type; planned radiation dose; planned number of fractions; planned fraction sequence.

[0197] In some embodiments, the number of target volume sets including the second target volume is less than the total number of multiple target volume sets.

[0198] In some embodiments, the first target volume and the second target volume in the target volume set are both irradiated in the corresponding fractions.

[0199] In some embodiments, the second target volume in the target volume set differs from at least one of the plurality of first target volumes in at least one of the following aspects: Planned radiation type; planned radiation dose.

[0200] In some embodiments, step S1402 specifically includes: Step S14021: Based on tumor heterogeneity, segment the target tumor in the medical image in the spatial dimension.

[0201] Tumor specificity is used to indicate biological differences within a tumor, which can be reflected in tumor cell proliferation activity, metabolic levels, gene expression, and sensitivity to radiation. These differences can be identified and quantified through medical imaging.

[0202] Spatial segmentation of the target tumor based on its heterogeneity means that, during the segmentation process, the target tumor is divided into multiple regions with different biological differences, i.e., multiple primary target volumes, based on the biological differences within the tumor reflected in medical images. This allows for the development of different radiotherapy dosage strategies for different primary target volumes, enabling targeted irradiation of different primary target volumes within the target tumor, achieving precise radiotherapy tailored to specific regions.

[0203] Furthermore, after step S1402, the method further includes: Step S1406: Based on the tumor heterogeneity of multiple first target volumes, formulate a radiotherapy strategy for multiple first target volumes.

[0204] The radiotherapy strategy for the first target volume may include at least one of the following: the prescribed dose of the first target volume, the target volume size, the planned radiation type, the planned number of fractions, the fraction dose, and the planned fraction sequence.

[0205] It should be noted that if radiotherapy is not fractionated, a one-target-volume radiotherapy strategy may not include the planned number of fractions, fraction dose, and planned fractionation order.

[0206] In the case where the radiotherapy for the target tumor is fractionated, in one embodiment, the tumor target volume segmentation method proposed in this embodiment further includes: Step S1407: Before the i-th fraction, acquire an image containing the target tumor.

[0207] Here, "before the i-th fraction" can refer to the period before the i-th fraction irradiation, or between the (i-1)-th fraction and the i-th fraction, where i is greater than 1 and less than or equal to the planned number of fractions. Imaging containing the target tumor can indicate the biological differences within the target tumor and the dynamic changes in the target tumor structure. This imaging can be an image scanned before the i-th fraction, or an image predicted before the i-th fraction based on medical images or other images before the i-th fraction.

[0208] It should be noted that this step dynamically monitors the biological differences within the tumor and the dynamic changes in the tumor structure by acquiring images containing the target tumor before the i-th fraction. This provides a real-time basis for adjusting the radiotherapy strategy for the first target volume in the i-th fraction, ensuring that the radiotherapy strategy is always based on the latest state of the tumor, thus demonstrating the flexibility of adaptive radiotherapy.

[0209] Step S1408: Adjust at least one aspect of the first target volume and / or the second target volume within the i-th segment based on the imaging prior to the i-th segment: Target volume distribution; target volume size; planned radiation type; fractionated dose.

[0210] Understandably, based on the imaging results before the i-th fraction, if the tumor volume is found to have shrunk, the distribution and / or size of the first and / or second target volumes can be adjusted accordingly to avoid ineffective irradiation of the already diminished areas. If the sensitivity of a certain area of ​​the tumor to the current radiation type decreases, the planned irradiation type can be changed to improve efficacy. If imaging shows that the cumulative dose in a certain area is insufficient or excessive, the fraction dose can be adjusted to balance treatment effectiveness and safety. Through this targeted adjustment, the irradiation plan for each fraction is ensured to be precisely matched with the real-time status of the tumor, reducing the risk of undertreatment or damage to normal tissue caused by deviations.

[0211] Furthermore, the above imaging is functional imaging.

[0212] It is important to note that, compared to conventional anatomical imaging, functional imaging not only reveals changes in the anatomical structure of tumors but also reflects their biological activity, such as metabolic levels, blood perfusion, and cell proliferation activity. For example, PET can identify highly metabolically active areas within a tumor based on tracer uptake, while functional MRI can reflect the microcirculatory status of tumor tissue. Using functional imaging allows for more precise localization of active residual tumor areas, recurrence risk areas, or areas of differential response to treatment. This provides a more biologically meaningful basis for adjusting target volume, radiation type, and dose, enabling adjustments to better align with the functional characteristics of the tumor and further improving the precision and targeting of radiotherapy.

[0213] Based on the biological differences within the tumor and the dynamic changes in the target tumor structure reflected in the imaging of the target tumor obtained before the i-th fraction, optimization is performed in the spatial dimension, such as adjusting the distribution and / or size of the target volume, and in terms of radiation type and / or dose, such as adjusting the planned radiation type and / or fraction dose. In this way, while accurately optimizing the spatial segmentation within the target tumor, different radiotherapy dose strategies can be formulated for different regions based on the biological and structural differences of different regions. Different radiation irradiation and / or fraction doses can be applied to the optimized first target volume within the target tumor in a targeted manner, achieving precise radiotherapy based on the region.

[0214] The following disclosed embodiments (i.e., disclosed embodiment two) also address the technical problem of how to synergistically combine high and low doses to obtain a better anti-tumor immune response. To this end, a target volume segmentation method is proposed, which constrains (sculpts) the segmentation results of the tumor in spatial dimensions on the fractional doses, forming heterogeneity (different doses) of irradiation dose within the tumor to enhance the anti-tumor immune response.

[0215] The following is based on Figure 1 The scenario shown illustrates the tumor target volume segmentation method provided in this disclosure.

[0216] The tumor target volume segmentation method provided in this disclosure is applied to a tumor target volume segmentation device, which can be... Figure 1 Treatment planning system equipment 102 in the middle. Figure 15 A schematic flowchart of a tumor target volume segmentation method provided in an embodiment of this disclosure is shown. Figure 15 As shown, the tumor target volume segmentation method includes: Step S1501: Obtain a medical image containing the target tumor.

[0217] The medical image of the target tumor is acquired by the image acquisition device 101, which contains the target tumor. The target object refers to the user undergoing radiotherapy, such as a patient, experimental subject, or a phantom used to simulate a patient. The target tumor is a single solid tumor or one of multiple solid tumors within the target object.

[0218] The aforementioned medical images can be a single image (single modality image) such as CT image, ECT image, MRI image, or PET image, or a fusion image of multiple modalities of the above.

[0219] Step S1502: Segment the target tumor in spatial dimension according to the medical image to obtain multiple non-overlapping first target volumes located within the target tumor.

[0220] In this context, the spatial dimension emphasizes the distinction of location in physical space. Segmentation involves dividing the target tumor as a whole and / or the tissue within the target tumor in a medical image in the spatial dimension to obtain multiple first target volumes, which are the volumes (regions) to be irradiated. From a physical space perspective, the multiple first target volumes obtained by segmentation are located within the target tumor and do not overlap.

[0221] It is understandable that the multiple non-overlapping first target volumes are spaced apart and are not closely distributed.

[0222] Segmentation can involve identifying the boundaries of a specific region, outlining the contours of a specific region, or placing a target volume of a pre-defined size in a specific region. After the identification, outlining, or placement operations, multiple first target volumes are obtained.

[0223] The segmentation method can be manual, semi-automatic, or fully automatic.

[0224] Step S1503: Obtain fractionated doses of multiple first target volumes in different fractions, wherein at least two fractionated doses of the first target volumes are configured as different doses in at least one fraction.

[0225] Fractionated dose is the dose that a target volume should receive in different fractions, as specified by the physician in the radiotherapy plan. Specifically, physicians can use the treatment planning system to set corresponding fractionated doses for different first target volumes, or they can determine the fractionated dose based on the prescription dose and the number of fractions set by the physician. The total fractionated dose of all fractions for the first target volume equals the prescription dose.

[0226] Here, the prescribed doses of multiple first target agents can be the same or different; the number of fractions of multiple first target volumes can be the same or different, but there must be at least one fraction in which the fraction doses of at least two first target volumes are different.

[0227] For example, each first target volume may be divided into 3 fractions, or some first target volumes may be divided into 1 fraction, some first target volumes may be divided into 2 fractions, and some first target volumes may be divided into 3 fractions. If multiple first target volumes are divided into 1 fraction, then at least two first target volumes in that 1 fraction have different doses.

[0228] For example, the prescription dose for a target volume M with 1 fraction is 30 Gy, and the corresponding fraction order is the second fraction; the prescription dose for a first target volume N with 3 fractions is 30 Gy, which can be 15 Gy for the first fraction, 10 Gy for the second fraction, and 5 Gy for the third fraction; then in the second fraction, the fraction doses for the first target volume M and the first target volume N are different.

[0229] The technical solution provided in this disclosure, after acquiring a medical image containing a target tumor, segments the target tumor in the medical image spatially to obtain multiple non-overlapping first target volumes within the target tumor. Then, it acquires fractional doses for different fractions of the multiple first target volumes, wherein at least two first target volumes in at least one fraction are configured with different doses. This allows the formation of different dose zones within the tumor within each fraction, such as a high-dose zone (the first target volume corresponding to the higher fractional dose among the different fractional doses), a medium-dose zone (the first target volume corresponding to the lower fractional dose among the different fractional doses), and a low-dose zone (the area within the target tumor and surrounding the first target volumes). Through highly modulated dose distribution, high-dose radiation can be precisely irradiated to specific areas (multiple first target volumes) within the tumor. Simultaneously, the highly non-uniform dose distribution (i.e., radiotherapy dose heterogeneity) can stimulate different degrees of activation response, achieving a better anti-tumor immune response effect.

[0230] In some embodiments, the number of times at least one of the plurality of first target volumes is divided is configured to be greater than or equal to 2.

[0231] In some embodiments, after step S1502 and before step S1503, the method further includes: Step S1504: Divide the multiple first target volumes in the time dimension to obtain multiple target volume sets corresponding to different divisions. The target volume set includes at least one first target volume.

[0232] The temporal segmentation refers to dividing the multiple first target volumes obtained in step S1502 (i.e., spatial segmentation) into different target volume sets corresponding to different fractions in the temporal dimension. In this way, at least one target volume in the target volume set corresponding to different fractions has a different fractional dose, which can form a dose zone with different doses within the tumor. Different dose zones are conducive to activating immunity and can still achieve a good anti-tumor immune response.

[0233] In one embodiment, the number of first target volumes contained in at least one target volume set within a plurality of target volume sets is greater than or equal to 1 and less than or equal to the total number of non-overlapping first target volumes. Alternatively, in the foregoing disclosed embodiments, the number of first target volumes contained in at least one target volume set within a plurality of target volume sets may be greater than or equal to 1 and less than the total number of non-overlapping first target volumes.

[0234] In one embodiment, the target volumes in the target volume sets corresponding to different fractions can be exactly the same, or they can be different.

[0235] It is understandable that the target volume set is the collection of the first target volumes planned for irradiation within a single fraction of multiple fractions, that is, the combination of all the first target volumes that need to be irradiated by radiation during a certain fraction of radiotherapy.

[0236] In one embodiment, the first target volume in the target volume cluster is irradiated in the corresponding fraction, and correspondingly, the first target volumes in different target volume clusters are not irradiated in the same fraction.

[0237] In some embodiments, the multiple non-overlapping first target volumes within the target tumor are non-uniformly distributed in space. Of course, the multiple first target volumes can also be uniformly distributed in space.

[0238] In some embodiments, at least two of the plurality of first target volumes are the same or different in at least one aspect of target volume size, planned radiation type, prescribed dose, planned number of fractions, and planned fractionation order.

[0239] It should be understood that these references can be manually set by the doctor or automatically generated using algorithms based on medical images.

[0240] In some embodiments, the planned irradiation dose of each of the plurality of first target volumes is higher than the planned irradiation dose of the non-target volume region; wherein, the non-target volume region is the region outside the plurality of first target volumes.

[0241] In one embodiment, when the target volume set includes multiple first target volumes, the fractionated doses of at least two first target volumes in the target volume set are different, but are the same or different in at least one of the following aspects: Target size; planned radiation type.

[0242] In one embodiment, at least two target volume sets from a plurality of target volume sets are the same or different in at least one of the following aspects: The number of first target volumes included; the size of the target volumes included; the planned radiation type of the first target volumes included.

[0243] In one embodiment, the first target volume whose target volume is larger than a preset value belongs to at least two or more target volume sets.

[0244] In one embodiment, the tumor target volume segmentation method proposed in this embodiment further includes: Step S1505: The target tumor is segmented in the spatial dimension according to the medical image, and the second target volume corresponding to the contour of the target tumor is obtained. Multiple non-overlapping first target volumes are all located within the second target volume.

[0245] It is understandable that the region of the second target volume is the region where the target tumor is located. It can be the GTV, or a target volume that includes the GTV, such as CTV or PTV. Multiple first target volumes are located within the second target volume of the target tumor.

[0246] Accordingly, in step S1504, the multiple first target volumes are segmented along the time dimension to obtain multiple target volume sets corresponding to different segments, including: Step S15041: The second target volume and multiple first target volumes are segmented in the time dimension to obtain multiple target volume sets corresponding to different fractions, wherein at least one target volume set in the multiple target volume sets includes the second target volume, and the fraction doses of at least two first target volumes in the target volume sets are configured to be different.

[0247] It should be noted that in at least one target volume set including a second target volume, the fractional dose of the second target volume may be less than the fractional dose of all first target volumes in the target volume set, but may also be greater than or equal to the fractional dose of at least one first target volume in the target volume set.

[0248] Optionally, the second target volume is different from or the same as at least one of the plurality of first target volumes in at least one of the following aspects: planned radiation type; prescribed dose; fractionated dose; planned number of fractions; planned fractionation sequence.

[0249] Optionally, the number of target volume sets for the second target volume is less than the total number of multiple target volume sets.

[0250] Optionally, the first and second target volumes in the target volume concentration are both irradiated in the corresponding fractions.

[0251] Optionally, the second target volume in the target volume set differs from at least one of the plurality of first target volumes in at least one of the following aspects: Planned radiation type; fractionated dose.

[0252] In some embodiments, the method may further include the following steps: Step S1506: Group the multiple first target volumes to obtain multiple target volume groups, each target volume group including at least one first target volume.

[0253] Accordingly, in step S1504, the multiple first target volumes are segmented along the time dimension to obtain multiple target volume sets corresponding to different segments, including: Step S15042: Based on multiple target volume groups, the multiple first target volumes are segmented in the time dimension to obtain multiple target volume sets corresponding to different segments; wherein, the target volume set includes at least one target volume group, at least two target volumes in at least one target volume group have different prescription doses, or, the first target volumes with different prescription doses among the multiple first target volumes are located in different target volume groups.

[0254] Optionally, adjacent first target volumes among a plurality of first target volumes may be located in different target volume groups.

[0255] Optionally, multiple target volume groups within a target volume cluster may be irradiated in the corresponding fractions.

[0256] Optionally, when the target volume group contains multiple first target volumes, the multiple first target volumes are identical in at least one of the following aspects: Target size; planned type of radiation exposure; planned number of irradiations.

[0257] Optionally, at least two of the multiple target volume groups are different in at least one of the following aspects: The number of first target volumes included; the size of the target volumes included; the planned radiation type of the first target volumes included; the prescribed dose of the first target volumes included; the fraction dose of the first target volumes included; the planned number of fractions of the first target volumes included; the planned fraction order of the first target volumes included.

[0258] Optionally, at least two target volume groups in the target volume set are different in at least one of the following aspects: The number of first target volumes included; the size of the target volumes included; the planned radiation type of the first target volumes included; the fractionated dose of the first target volumes included.

[0259] Optionally, at least two target volume sets are different in at least one of the following ways: The number of target volume groups included; the size of the target volume within each target volume group included; the planned radiation type for each target volume group included; and the fractionated dose for each target volume group included.

[0260] In some embodiments, step S1502 specifically includes: Based on tumor heterogeneity, the target tumor is segmented in spatial dimension according to medical images.

[0261] Furthermore, after step S1502, the method further includes: Based on the tumor heterogeneity of multiple first target volumes, a radiotherapy strategy with multiple first target volumes is developed.

[0262] The radiotherapy strategy for the first target volume may include at least one of the following: the prescribed dose of the first target volume, the target volume size, the planned radiation type, the planned number of fractions, the fraction dose, and the planned fraction sequence.

[0263] In one embodiment, when the target tumor is located in the head, the total number of target volumes is less than or equal to 5.

[0264] In one embodiment, the tumor target volume segmentation method proposed in this embodiment further includes: Step S1507: Before the i-th fraction, acquire an image containing the target tumor, where i is greater than 1 and less than or equal to the planned number of fractions.

[0265] Here, "before the i-th fraction" can refer to the period before the i-th fraction irradiation, or between the (i-1)-th fraction and the i-th fraction, where i is greater than 1 and less than or equal to the planned number of fractions. Imaging containing the target tumor can indicate the biological differences within the target tumor and the dynamic changes in the target tumor structure. This imaging can be an image scanned before the i-th fraction, or an image predicted before the i-th fraction based on medical images or other images before the i-th fraction.

[0266] Step S1508: Adjust at least one aspect of the first target volume and / or the second target volume within the i-th fraction based on the imaging prior to the i-th fraction: Target volume distribution; target volume size; planned radiation type; fractionated dose.

[0267] Furthermore, the imaging is functional imaging.

[0268] The following disclosed embodiments (i.e., disclosed embodiment three) address the technical problem of achieving a higher peak-to-valley ratio. To this end, a target volume segmentation method is proposed. Based on the segmentation results of the tumor in spatial dimensions, the characteristics of different radiation rays are utilized to achieve a higher peak-to-valley ratio within the tumor's target volume, thereby resulting in a higher target volume dose within the tumor while a lower dose to normal tissues.

[0269] The following is based on Figure 1 The scenario shown illustrates the tumor target volume segmentation method provided in this disclosure.

[0270] The tumor target volume segmentation method provided in this disclosure is applied to a tumor target volume segmentation device, which can be... Figure 1 Treatment planning system equipment 102 in the middle. Figure 16 A schematic flowchart of a tumor target volume segmentation method provided in an embodiment of this disclosure is shown. Figure 16 As shown, the tumor target volume segmentation method includes: Step S1601: Obtain a medical image of the target object containing the target tumor.

[0271] The medical image of the target tumor is acquired by the image acquisition device 101, which contains the target tumor. The target object refers to the user undergoing radiotherapy, such as a patient, experimental subject, or a phantom used to simulate a patient. The target tumor is a single solid tumor or one of multiple solid tumors within the target object.

[0272] The aforementioned medical images can be a single image (single modality image) such as CT image, ECT image, MRI image, or PET image, or a fusion image of multiple modalities of the above.

[0273] Step S1602: Segment the target tumor in the spatial dimension according to the medical image to obtain multiple non-overlapping first target volumes located within the target tumor; wherein, at least two of the multiple first target volumes are configured with different types of radiation.

[0274] In this context, the spatial dimension emphasizes the distinction of location in physical space. Segmentation involves dividing the target tumor as a whole and / or the tissue within the target tumor in a medical image in the spatial dimension to obtain multiple first target volumes, which are the volumes (regions) to be irradiated. From a physical space perspective, the multiple first target volumes obtained by segmentation are located within the target tumor and do not overlap.

[0275] It should be noted that the multiple non-overlapping first target volumes are spaced apart and are not closely distributed.

[0276] It should be understood that segmentation can involve identifying the boundaries of a specific region, outlining the contours of a specific region, or placing a target volume of a predetermined size within a specific region. After identification, outlining, or placement, multiple first target volumes are obtained. Segmentation can be done manually, semi-automatically, or fully automatically. Manual segmentation involves physicians manually identifying the boundaries of a specific region, manually outlining the contours of a specific region, or manually placing a target volume of a predetermined size within a specific region based on medical image features. Similarly, semi-automatic segmentation can combine thresholding methods, region growing algorithms, etc., to assist physicians in segmenting target volumes. Fully automatic segmentation can be based on artificial intelligence algorithms such as deep learning, automatically identifying and segmenting various target volumes within the tumor through trained models.

[0277] The types of radiation can include X-rays, gamma rays, electron beams, proton beams, neutron beams, heavy ion beams, and other types of radiation.

[0278] Due to the differences in the physical properties of different radiation beams, this technical solution can target at least two target volumes within a tumor with different radiation beams, resulting in a higher peak-to-valley ratio within the tumor target volume. This enables precise radiotherapy, improves treatment efficacy, and reduces damage to normal tissues.

[0279] In some embodiments, when the target volume size of the first target volume is greater than or equal to a preset value (e.g., 20 mm), the radiation type of the first target volume is configured as a first ray, such as an X-ray.

[0280] In some embodiments, when the target volume of the first target volume is smaller than a preset value (e.g., 20 mm), the radiation type of the first target volume is configured as a second ray, such as gamma rays.

[0281] In some embodiments, the prescription dose of the first target volume is configured to be greater than or equal to 18 Gy, and the irradiation type is gamma rays.

[0282] In some embodiments, the method further includes: S1603. Based on the distance between the first target volume and the surface of the target object and / or the shape and / or the size of the first target volume, determine the radiation type of multiple first target volumes.

[0283] Here, the distance between the first target volume and the surface of the target object can be the distance between the center of the target volume and the surface of the target object.

[0284] In one example, if a first type of target volume among a plurality of first target volumes is determined to be within a first preset value (e.g., 3 cm, 5 cm) of the distance from the patient's skin surface, it indicates that the first type of target volume is a superficial target volume. Therefore, the radiation type of the first type of target volume is determined to be a first type of radiation, such as electron beam. Because electron beams have the characteristics of high surface dose and rapid dose decay at depth, they are suitable for treating superficial target volumes in the skin or subcutaneous tissue, avoiding excessive irradiation of deep normal tissue. Here, the first type of target volume is the first target volume whose distance from the patient's skin surface is less than or equal to the first preset value.

[0285] If, among multiple first target volumes, a second-type target volume is determined to be located at a distance greater than a first preset value from the body surface (e.g., 3 cm, 5 cm), it indicates that the second-type target volume is a deep target volume. Therefore, the radiation type of the second-type target volume is determined to be second-type radiation, such as proton rays, gamma rays, or X-rays. The "Bragg peak" characteristics of these rays allow for the release of maximum dose at a specific depth with extremely low output dose, making them suitable for deep target volumes and significantly reducing the radiation dose to normal tissues. Here, the second-type target volume is the first target volume located at a distance greater than the first preset value from the patient's skin surface.

[0286] In another example, if a third type of target volume among multiple first target volumes is determined to be larger than a second preset value (e.g., 3 cm, 5 cm, or 6 cm, or other values) or has an irregular shape, indicating that the third type of target volume is large or has a complex structure, then the radiation type of the third type of target volume is determined to be third-type radiation, such as X-rays. High-energy X-rays (e.g., 6-18 MV) can be adapted to the shape of the third type of target area using intensity-modulated field radiotherapy (IMRT) or volumetric modulated arc therapy (VMAT) techniques, and the dose distribution can be flexibly adjusted to cover larger or irregular target volumes. Here, the third type of target volume is a first target volume whose distance from the patient's skin surface is greater than the second preset value or whose target volume is administratively irregular.

[0287] In some embodiments, at least two target volumes may be irradiated with different types of radiation. For example, at least a portion of the first target volumes may be configured to be irradiated with a first ray, and at least a portion of the first target volumes may be configured to be irradiated with a second ray.

[0288] It should be noted that at least some can be at least one, and the first ray and the second ray refer to different types of radiation, rather than limiting it to only two types of radiation.

[0289] Here, the first ray and the second ray are different types of rays, which can be different rays such as X-rays, gamma rays, electron beams, proton beams, neutron beams, heavy ion beams, etc. For example, the first ray and the second ray are X-rays and gamma rays, respectively.

[0290] In some embodiments, at least one of the plurality of first target volumes can be configured to have at least two irradiation types, thereby enabling the at least one target volume to be irradiated with at least two or more irradiation rays to optimize the dose gradient.

[0291] For example, as described above, in addition to irradiating the first target volume with X-rays, electron beams, gamma rays, or proton beams can be used as supplementary irradiation of the first target volume, thereby optimizing the dose gradient in the region where the first target volume is located.

[0292] In some embodiments, the method further includes: Step S1604: Divide the multiple first target volumes in the time dimension to obtain multiple target volume sets corresponding to different divisions. Each target volume set includes at least one target volume.

[0293] The temporal dimension segmentation refers to dividing the multiple first target volumes obtained in step S1602 (i.e., spatial segmentation) into different subdivisions in the temporal dimension, so that the target volumes in the target volume sets corresponding to different subdivisions are not completely the same.

[0294] It is understandable that the target volume set is the collection of the first target volumes planned for irradiation within a single fraction of multiple fractions, that is, the combination of all the first target volumes that need to be irradiated by radiation during a certain fraction of radiotherapy.

[0295] In one embodiment, at least one target volume set in a plurality of target volume sets contains a number of first target volumes that are greater than or equal to 1 and less than the total number of a plurality of non-overlapping first target volumes.

[0296] In one embodiment, the first target volume in the target volume cluster is irradiated in the corresponding fraction, and correspondingly, the first target volumes in different target volume clusters are not irradiated in the same fraction.

[0297] In some embodiments, the target volumes in at least one adjacent set of target volumes may not be exactly the same; of course, the target volumes in at least one adjacent set of target volumes may also be exactly the same.

[0298] In some embodiments, the multiple non-overlapping first target volumes are non-uniformly distributed in the spatial dimension; of course, the multiple non-overlapping first target volumes can also be uniformly distributed in the spatial dimension.

[0299] In some embodiments, at least two of the plurality of non-overlapping first target volumes are different in at least one of the following aspects: Target volume size; planned radiation type; prescribed dose; planned number of fractions; planned fraction sequence.

[0300] For example, in the multiple first target volumes, at least one first target volume has a number of divisions greater than or equal to 2, wherein some first target volumes have a number of divisions of 1 and some first target volumes have a number of divisions greater than or equal to 2.

[0301] For example, the irradiation type of multiple target volumes in a fraction is either first-ray irradiation or second-ray irradiation. The first and / or second rays can be X-rays or gamma rays.

[0302] In some embodiments, the planned irradiation dose of each of the plurality of first target volumes is higher than the planned irradiation dose of the non-target volume region; wherein, the non-target volume region is the region outside the plurality of first target volumes.

[0303] In some embodiments, at least one of the target volume sets in the plurality of target volume sets contains a number of first target volumes that are greater than or equal to 1 and less than the total number of the plurality of non-overlapping first target volumes.

[0304] In some embodiments, when the target volume set includes a plurality of first target volumes, at least two first target volumes in the target volume set are the same or different in at least one of the following aspects: Target volume size; planned radiation type; fractionated dose.

[0305] In some embodiments, the first target volume in the target volume set is irradiated in each corresponding fraction.

[0306] In some embodiments, at least two target volume sets among the plurality of target volume sets are the same or different in at least one of the following aspects: The number of first target volumes included; the size of the target volumes included; the planned radiation type of the first target volumes included; the fractionated dose of the first target volumes included.

[0307] In some embodiments, a first target volume whose target volume is larger than a preset value (e.g., 20 mm) belongs to at least two or more target volume sets.

[0308] In some embodiments, the method further includes: Step S1605: The target tumor is segmented in spatial dimension according to the medical image, and a second target volume corresponding to the contour of the target tumor is obtained. Multiple non-overlapping first target volumes are all located within the second target volume.

[0309] It is understandable that the region of the second target volume is the region where the target tumor is located. It can be the GTV, or a target volume that includes the GTV, such as CTV or PTV. Multiple first target volumes are located within the second target volume of the target tumor.

[0310] Accordingly, in step S1604, the multiple first target volumes are segmented along the time dimension to obtain multiple target volume sets corresponding to different segments, including: Step S16041: Divide the second target volume and multiple first target volumes in the time dimension to obtain multiple target volume sets corresponding to different divisions, wherein at least one target volume set in the multiple target volume sets includes the second target volume.

[0311] In some embodiments, the target volumes in at least one adjacent set of target volumes are not exactly the same.

[0312] In some embodiments, the type of radiation emitted by the second target volume is configured as X-rays.

[0313] In some embodiments, the second target volume differs from at least one of the plurality of first target volumes in at least one of the following aspects: Planned radiation type; prescribed dose; planned number of fractions; planned fraction sequence.

[0314] In some embodiments, the number of target volume sets including the second target volume is less than the total number of the plurality of target volume sets.

[0315] In some embodiments, the first target volume and the second target volume in the target volume set are both irradiated in corresponding fractions.

[0316] In some embodiments, the second target volume in the target volume set differs from at least one first target volume among a plurality of first target volumes in at least one of the following aspects: Planned radiation type; fractionated dose.

[0317] In some embodiments, the method further includes: Step S1606: Group the multiple first target volumes to obtain multiple target volume groups, each target volume group including at least one first target volume; correspondingly, the step of segmenting the multiple first target volumes along the time dimension to obtain multiple target volume sets corresponding to different segments includes: Based on the multiple target volume groups, the multiple first target volumes are segmented in the time dimension to obtain multiple target volume sets corresponding to different segments; wherein, the target volume set includes at least one target volume group.

[0318] In some embodiments, the target volume groups in at least one adjacent target volume set are not completely identical.

[0319] In some embodiments, adjacent first target volumes among a plurality of first target volumes are located in different target volume groups.

[0320] In some embodiments, multiple target volume groups within the target volume set are irradiated in corresponding fractions.

[0321] In some embodiments, when the target volume group includes a plurality of first target volumes, the plurality of first target volumes are identical in at least one of the following aspects: Target volume size; planned radiation type; fraction dose; planned number of fractions; planned fraction sequence.

[0322] In some embodiments, at least two of the multiple target volume groups are different in at least one of the following aspects: The number of first target volumes included; the size of the first target volumes included; the planned radiation type of the first target volumes included; the prescribed dose of the first target volumes included; the planned number of fractions of the first target volumes included; the planned fractionation order of the first target volumes included.

[0323] In some embodiments, at least two target volume groups in the target volume set are different in at least one of the following aspects: The number of first target volumes included; the size of the target volumes included; the planned radiation type of the first target volumes included; the fractionated dose of the first target volumes included.

[0324] In some embodiments, at least two of the plurality of target volume sets are different in at least one of the following aspects: The number of target volume groups included; the size of the target volume within each target volume group included; the planned radiation type for each target volume group included; and the fractionated dose for each target volume group included.

[0325] In some embodiments, segmenting the target tumor in a spatial dimension based on the medical image includes: Based on tumor heterogeneity, the target tumor is segmented in spatial dimension according to the medical image.

[0326] Furthermore, after step S1602, the method further includes: Based on the tumor heterogeneity of multiple first target volumes, a radiotherapy strategy with multiple first target volumes is developed.

[0327] The radiotherapy strategy for the first target volume may include at least one of the following: the prescribed dose of the first target volume, the target volume size, the planned radiation type, the planned number of fractions, the fraction dose, and the planned fraction sequence.

[0328] In some embodiments, when the target tumor is located in the head, the total number of the target volume set is less than or equal to 5.

[0329] In some embodiments, the method further includes: Step S1607: Before the i-th fraction, acquire an image containing the target tumor, where i is greater than 1 and less than or equal to the planned number of fractions.

[0330] Here, "before the i-th fraction" can refer to the period before the i-th fraction irradiation, or between the (i-1)-th fraction and the i-th fraction, where i is greater than 1 and less than or equal to the planned number of fractions. Imaging containing the target tumor can indicate the biological differences within the target tumor and the dynamic changes in the target tumor structure. This imaging can be an image scanned before the i-th fraction, or an image predicted before the i-th fraction based on medical images or other images before the i-th fraction.

[0331] Step S1608: Adjust at least one aspect of the first target volume and / or the second target volume within the i-th fraction based on the imaging prior to the i-th fraction: Target volume distribution; target volume size; planned radiation type; fraction dose; planned number of fractions.

[0332] In some embodiments, the imaging is functional imaging.

[0333] According to embodiments of the present disclosure, the present disclosure also provides a tumor target volume segmentation apparatus, including 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, the instructions being executed by the at least one processor to enable the at least one processor to perform the tumor target volume segmentation method provided in the present disclosure.

[0334] According to embodiments of the present disclosure, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a tumor target volume segmentation device to perform the tumor target volume segmentation method provided in the present disclosure.

[0335] According to embodiments of this disclosure, this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the tumor target volume segmentation method provided in this disclosure.

[0336] Figure 13 A schematic block diagram of an example tumor target volume segmentation apparatus 900 that can be used to implement embodiments of the present disclosure is shown. The tumor target volume segmentation apparatus 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 tumor target volume segmentation apparatus can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein. In some embodiments, the tumor target volume segmentation apparatus can be the one described above. Figure 1 The treatment planning system or radiotherapy equipment shown is shown.

[0337] like Figure 13As shown, the tumor target volume segmentation device 1300 includes a computing unit 1301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory 1302 or a computer program loaded from a storage unit 1308 into a random access memory 1303. The random access memory (RAM) 1303 can also store various programs and data required for the operation of the tumor target volume segmentation device 1300. The computing unit 1301, the read-only memory (ROM) 1302, and the RAM 1303 are interconnected via a bus 1304. An input / output (I / O) interface 1305 is also connected to the bus 1304.

[0338] Multiple components in the tumor target volume segmentation device 1300 are connected to the input / output interface 1305, including: an input unit 1306, such as a keyboard, mouse, etc.; an output unit 1307, such as various types of displays, speakers, etc.; a storage unit 1308, such as a disk, optical disk, etc.; and a communication unit 1309, such as a network card, modem, wireless transceiver, etc. The communication unit 1309 allows the tumor target volume segmentation device 1300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0339] The computing unit 1301 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1301 include, but are not limited to, a central processing unit, a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors, and any suitable processor, controller, microcontroller, etc. The computing unit 1301 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, which is tangibly included in a machine-readable medium, such as storage unit 1308. In one embodiment, part or all of the computer program can be loaded and / or mounted on the tumor target volume segmentation device 1300 via ROM 1302 and / or communication unit 1309. When the computer program is loaded into RAM 1303 and executed by the computing unit 1301, one or more steps of the data matching method described above can be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to perform a data matching method by any other suitable means (e.g., by means of firmware).

[0340] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays, application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0341] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0342] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0343] 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 liquid crystal display (LCD) monitor; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0344] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0345] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0346] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this disclosure can be achieved, and this is not limited herein.

[0347] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for segmenting tumor target volume, characterized in that, include: Acquire medical images containing the target tumor; The target tumor is segmented in spatial dimension based on the medical image to obtain multiple non-overlapping first target volumes located within the target tumor; Obtain fractionated doses for different fractions of the plurality of first target volumes, wherein at least two fractionated doses of the first target volumes are configured to be different doses.

2. The tumor target volume segmentation method according to claim 1, characterized in that, The number of times at least one of the plurality of first target volumes is configured to be greater than or equal to 2.

3. The tumor target volume segmentation method according to claim 1, characterized in that, The method further includes: The multiple first target volumes are divided along the time dimension to obtain multiple target volume sets corresponding to different divisions; wherein, the target volume set includes at least one first target volume.

4. The tumor target volume segmentation method according to claim 3, characterized in that, The number of first target volumes contained in at least one of the multiple target volume sets is greater than or equal to 1 and less than the total number of multiple non-overlapping first target volumes.

5. The tumor target volume segmentation method according to claim 3, characterized in that, The target volumes in the target volume sets corresponding to different fractions may be completely the same or not completely the same.

6. The tumor target volume segmentation method according to claim 3, characterized in that, The first target volume in the target volume set is irradiated in the corresponding fraction, and correspondingly, the first target volumes in different target volume sets are not irradiated in the same fraction.

7. The tumor target volume segmentation method according to claim 3, characterized in that, The method further includes: Based on the medical image, the target tumor is segmented in the spatial dimension, and a second target volume corresponding to the contour of the target tumor is obtained. Multiple non-overlapping first target volumes are all located within the second target volume. Accordingly, the step of segmenting the multiple first target volumes along the time dimension to obtain multiple target volume sets corresponding to different segments includes: The second target volume and multiple first target volumes are segmented in the time dimension to obtain multiple target volume sets corresponding to different fractions, wherein at least one target volume set in the multiple target volume sets includes the second target volume, and the fraction doses of at least two first target volumes in the target volume sets are configured to be different.

8. The tumor target volume segmentation method according to claim 3, characterized in that, The method further includes: The multiple first target volumes are grouped to obtain multiple target volume groups, and each target volume group includes at least one first target volume. Accordingly, the segmentation of the multiple first target volumes along the time dimension to obtain multiple target volume sets corresponding to different segments includes: Based on multiple target volume groups, multiple first target volumes are segmented in the time dimension to obtain multiple target volume sets corresponding to different segments; wherein, the target volume set includes at least one target volume group, at least two target volumes in at least one target volume group have different prescription doses, or, the first target volumes with different prescription doses among the multiple first target volumes are located in different target volume groups.

9. The tumor target volume segmentation method according to claim 1, characterized in that, The method further includes: Based on the tumor heterogeneity of the multiple first targets, a radiotherapy strategy for multiple first target volumes is formulated. The radiotherapy strategy for the first target volume includes at least one of the following: the prescribed dose of the first target volume, the target volume size, the planned radiation type, the planned number of fractions, the fraction dose, and the planned fraction sequence.

10. A tumor target volume segmentation device, characterized in that, include: processor; and memory for storing the executable instructions of the processor; The processor is configured to execute the instructions to implement the steps of the tumor target volume segmentation method as described in any one of claims 1 to 25.

Images