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; grouping the plurality of first target volumes to obtain a plurality of target volume groups; wherein each target volume group comprises at least one first target volume, and the adjacent first target volumes in the plurality of first target volumes are located in different target volume groups. According to the tumor target volume segmentation method and device and the storage medium provided by the invention, continuous irradiation of adjacent areas can be avoided through differential irradiation of different target volume groups, so that accumulated damage to surrounding normal tissues is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of radiotherapy technology, and in particular to a tumor target volume segmentation method and device and a nonvolatile computer readable storage medium. BACKGROUND

[0002] Conventional fractionated radiotherapy irradiates each fraction region completely identically and each fraction dose identically, which results in limited tumor killing effect and greater damage to biological tissues between irradiation regions, which is not conducive to the recovery of biological tissues.

[0003] Therefore, it is necessary to improve one or more problems in the above-mentioned related technical solutions.

[0004] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0005] The purpose of the embodiments of the present disclosure is to provide a tumor target volume segmentation method, device and storage medium, thereby at least partially overcoming one or more problems caused by the limitations and defects of the related art.

[0006] In a first aspect, the present application provides a tumor target volume segmentation method, comprising:

[0007] obtaining a medical image containing a target tumor;

[0008] segmenting the target tumor in a spatial dimension according to the medical image to obtain a plurality of first target volumes that do not overlap within the target tumor;

[0009] grouping a plurality of the first target volumes to obtain a plurality of target volume groups;

[0010] Each of the target volume groups includes at least one of the first target volumes, and adjacent first target volumes in the plurality of first target volumes are located in different target volume groups.

[0011] The embodiments of the present disclosure provide a tumor target volume segmentation method, which segments a target tumor into a plurality of first target volumes that do not overlap in a spatial dimension, and groups them into a plurality of target volume groups based on spatial position relationships, so that adjacent first target volumes belong to different groups. In this way, the difference between different target volume groups can be used to avoid continuous irradiation of adjacent regions, thereby reducing the cumulative damage to surrounding normal tissues.

[0012] In a second aspect, the present 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 of the first aspect.

[0013] In a third aspect, the present application provides a non-volatile computer readable storage medium, which stores instructions, when the instructions run on a terminal, cause the terminal to execute the tumor target volume segmentation method as described in the first aspect and any possible implementation of the first aspect.

[0014] In a fourth aspect, the present application provides a computer program product comprising instructions, when the computer program product runs on a tumor target volume segmentation apparatus, cause the tumor target volume segmentation apparatus to execute the tumor target volume segmentation method as described in the first aspect and any possible implementation of the first aspect.

[0015] In a fifth aspect, the present application provides a chip, which comprises a processor and a communication interface, the communication interface and the processor are coupled, and the processor is configured to run a computer program or instructions to implement the tumor target volume segmentation method as described in the first aspect and any possible implementation of the first aspect.

[0016] Specifically, the chip provided in the present application further comprises a memory for storing the computer program or instructions.

[0017] It should be noted that the above computer instructions can be stored on the computer readable storage medium in whole or in part. The computer readable storage medium can be packaged together with the processor of the apparatus or packaged separately from the processor of the apparatus, and the present application does not limit this.

[0018] The description of the second aspect to the fifth aspect in the present application can refer to the detailed description of the first aspect; and the beneficial effects of the description of the second aspect to the fifth aspect can refer to the beneficial effect analysis of the first aspect, which will not be repeated here.

[0019] In the present application, the name of the tumor target volume segmentation apparatus does not constitute a limitation on the device or functional module itself, and in actual implementation, these devices or functional modules can appear with other names. As long as the functions of each device or functional module are similar to those of the present application, they belong to the scope of the claims of the present application and equivalent technologies. BRIEF DESCRIPTION OF DRAWINGS

[0020] The accompanying drawings, which are incorporated herein and constitute part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, further serve to explain the principles of the present disclosure. It is to be understood that the drawings are only schematic, and that they do not purport to be to scale with respect to one another. The embodiments will be described with reference to the drawings in conjunction with a detailed description as follows.

[0021] Figure 1 An implementation environment schematic diagram of a tumor target volume segmentation method provided by an embodiment of the present disclosure;

[0022] Figure 2 A flowchart schematic diagram of a tumor target volume segmentation method provided by an embodiment of the present disclosure;

[0023] Figure 3 A schematic diagram of a plurality of first target volumes without overlap provided by an embodiment of the present disclosure;

[0024] Figure 4 A schematic diagram of a plurality of first target volumes without overlap and uneven provided by an embodiment of the present disclosure;

[0025] Figure 5 A schematic diagram of a plurality of target volume groups provided by an embodiment of the present disclosure Figure 1 ;

[0026] Figure 6 A schematic diagram of a plurality of target volume groups provided by an embodiment of the present disclosure Figure 2 ;

[0027] Figure 7 Another schematic diagram of a plurality of target volume groups provided by an embodiment of the present disclosure;

[0028] FIG. 8 is a schematic diagram of a first target volume of different target volume groups corresponding to each fraction provided by an embodiment of the present disclosure;

[0029] Figure 9 A simplified schematic diagram of a tumor target volume segmentation device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] In the embodiments of the present application, the terms "first", "second" are only used for description purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features.

[0031] In the embodiments of the present application, the terms "comprising", "containing" or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements not only includes those elements, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without more limitations, the element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0032] "A and / or B" includes the following three combinations: only A, only B, and a combination of A and B.

[0033] For example, in traditional head radiotherapy (referred to as radiotherapy), the patient's head is fixed by invasive methods such as head pins and head frames before radiotherapy, and then a single large dose of focused irradiation is used to irradiate the irradiation area where the tumor is located.

[0034] With the accumulation of clinical experience, it is found that for some specific tumors such as brain glioma, brain metastasis, and malignant tumors, the radiotherapy effect of multiple fraction radiotherapy is better than that of single fraction radiotherapy. The multiple fraction radiotherapy (referred to as fraction) divides the total irradiation dose required for tumor radiotherapy into multiple independent single irradiation doses (fractions) and applies the fractions to the irradiation area where the tumor is located.

[0035] However, in conventional fractions, the irradiation area where the tumor is located in each fraction is completely the same and the irradiation dose of each fraction to the irradiation area is the same. The fraction irradiation dose is the prescription dose (total irradiation dose) divided by the number of fractions. Therefore, the same irradiation dose is applied to the same irradiation area in each fraction radiotherapy, which causes greater damage to the biological tissues around the irradiation area where the tumor is located and affects the overall radiotherapy effect.

[0036] Based on this, the tumor target volume segmentation method provided in the embodiments of the present application can first segment the target tumor into multiple first target volumes that do not overlap in space, and then divide them into different target volume groups according to the spatial position relationship, thereby reducing the damage to normal tissues during radiotherapy.

[0037] First, the application scenario related to the embodiments of the present application is described. The tumor target volume segmentation method provided by the embodiments of the present application can be applied in the field of medical technology, especially in the field of radiotherapy technology.

[0038] Figure 1 is a schematic diagram of an implementation environment of a tumor target volume segmentation method according to an embodiment of the present application. Referring to Figure 1 , the implementation environment includes an image acquisition device 101, a treatment planning system device 102, and a radiotherapy device 103.

[0039] The image acquisition device 101 is a device for acquiring a medical image containing a target tumor. In the embodiments of the present disclosure, the image acquisition device 101 can acquire a medical image containing a target tumor. The subsequent medical image containing the target tumor will be uploaded to the treatment planning system device 102, so that the treatment planning system device 102 performs a subsequent tumor target volume segmentation method based on the medical image containing the target tumor.

[0040] In some embodiments, the image acquisition device 101 can be at least one of a computed tomography (CT) device, an emission computed tomography (ECT) device, a magnetic resonance imaging (MRI) device, a positron emission tomography (PET) device, and an ultrasonic examination device.

[0041] The treatment planning system device 102 is a device for obtaining a medical image containing a target tumor acquired by the image acquisition device 101, and performing tumor target volume segmentation on the target tumor according to the medical image. Further, it is also a device for formulating, optimizing and evaluating a treatment plan based on the result of tumor target volume segmentation.

[0042] Specifically, in the embodiments of the present disclosure, the treatment planning system device 102 can obtain a set of one or more optimization objectives and receive a medical image containing a target tumor acquired by the image acquisition device 101, and segment the target tumor in the spatial dimension according to the medical image to obtain a plurality of first target volumes that do not overlap in the target tumor. Subsequently, the treatment planning system device 102 can also group a plurality of first target volumes to obtain a plurality of target volume groups. Each of the target volume groups includes at least one of the first target volumes, and adjacent first target volumes in the plurality of first target volumes are located in different target volume groups; further, a treatment plan is formulated, optimized and evaluated based on the plurality of target volume groups.

[0043] The treatment planning system device 102 can run a radiotherapy planning system (TPS) application, which provides functions of formulating, optimizing and evaluating a treatment plan. For example, an RT pro TPS system.

[0044] In some embodiments, the treatment planning system device 102 can include a TPS client and a TPS server.

[0045] The TPS client can be at least one of a smart phone, a smart watch, a desktop computer, a laptop computer, a virtual reality terminal, an augmented reality terminal, a wireless terminal, and a laptop computer, etc. For example, in some embodiments, a user can trigger the TPS server to perform a treatment planning process and display the completed / optimized treatment plan by running a treatment planning system on the TPS server through the TPS client. In this way, the user's time can be effectively saved, and the completed / optimized treatment plan can be more intuitively presented to the user for evaluation.

[0046] The TPS server can be at least one of a standalone physical server, a server cluster or a distributed file system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content distribution networks, and big data or artificial intelligence platforms, etc. The number of TPS servers can be more or less in some embodiments, and the present disclosure is not limited thereto. Of course, the TPS server can also include other functions to provide more comprehensive and diversified services. In some embodiments, the TPS server is used to provide background services for the TPS client, such as performing a treatment plan optimization process.

[0047] In some embodiments, the treatment planning system device 102 can be a computer device with a graphical user interface (GUI), which includes one or more processors, memories, and one or more application programs. For example, the treatment planning system device 102 can include a treatment planning generation system application program, and the processor of the treatment planning system device 102 executes the treatment planning generation system application program to implement the treatment planning generation method provided by the present disclosure.

[0048] Further, in some embodiments, the treatment planning system device 102 can include a processor for implementing the treatment planning generation method provided by the present disclosure.

[0049] The radiotherapy device 103 is a device for performing radiotherapy on a target object. In one embodiment of the present disclosure, the radiotherapy device 103 can obtain and execute a treatment plan for a target tumor generated by the treatment planning system device 102 based on the segmentation result of the tumor target volume segmentation plan.

[0050] In some embodiments, the radiotherapy device 103 can include a gantry 1031, a treatment head 1032, and a support device 1033.

[0051] The gantry 1031 can be a rotatable gantry. The treatment head 1032 can be disposed on the gantry and configured to emit at least one of a gamma ray, an X-ray, a proton ray, a neutron ray, a heavy ion ray, or the like, to perform radiotherapy on a target object. The support device 1033 can be a treatment bed and configured to support and move the target object.

[0052] In some embodiments, the rotation of the gantry 1031 can drive the treatment head 1032 to rotate around the target object to perform radiotherapy, when the target object is on the support device 1033.

[0053] For example, the radiotherapy device 103 can include an X-ray treatment head and a gamma ray treatment head disposed on the gantry 1031. The X-ray and the gamma ray can be emitted to rotate around the same rotation axis and to irradiate the target object at the isocenter, when the gantry 1031 is driven to rotate. The X-ray and the gamma ray can be irradiated simultaneously or switched rapidly, for example, in a millisecond level, to ensure the biological effect and to reject the dose tomography.

[0054] The method provided by the embodiments of the present disclosure will be described below based on the implementation environment shown in Figure 1 The method provided by the embodiments of the present disclosure will be described below based on the implementation environment shown in

[0055] Figure 2 A flowchart of a tumor target volume segmentation method provided by the embodiments of the present disclosure 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 can be the treatment planning system device shown in the above Figure 1 The method can include the following steps: Figure 2

[0056] Step S100: Obtain a medical image containing a target tumor.

[0057] It can be understood that the medical image of the target tumor is obtained by the image acquisition device 101. The medical image contains a target tumor of a target object. The target object refers to a user to be treated, such as a patient, an experimental object, or a phantom simulating a patient. The target tumor is a single solid tumor or one of multiple solid tumors in the target object.

[0058] The medical image can be a computed tomography (CT) image, an emission computed tomography (ECT) image, a magnetic resonance imaging (MRI) image, a positron emission tomography (PET) image, or the like, or a fusion image of the above-mentioned multiple modal images.

[0059] ​The CT image can clearly show the anatomical structure and density information of the tumor, which is beneficial to determine the spatial relationship between the tumor and bone tissue and the like; the MRI image has high resolution for soft tissue, which can better distinguish the boundary between the tumor and the surrounding normal soft tissue, such as brain, spinal cord and the like; and the PET image can reflect the functional state of the tumor through metabolic activity difference, and provide a basis for identifying the active area of the tumor. In actual operation, the image fusion technology is often used to fuse or register and superimpose multiple modal images, so as to comprehensively utilize the advantages of different modal images, and provide more comprehensive tumor information for subsequent accurate segmentation of the target volume.

[0060] Step S200: Segmentation of the target tumor in the spatial dimension according to the medical image, to obtain a plurality of first target volumes located in the target tumor and not overlapping.

[0061] The spatial dimension emphasizes the distinction of the position in the physical space, the segmentation is to segment the target tumor as a whole and / or the tissue in the target tumor in the spatial dimension according to the medical image, to obtain a plurality of first target volumes, and the first target volume is a volume (region) to be irradiated. The plurality of first target volumes obtained by segmentation are located in the target tumor and not overlapping in the physical space.

[0062] It can be understood that the first target volumes of the plurality of first target volumes not overlapping are spaced apart, and are not closely distributed.

[0063] The segmentation can be to identify the boundary of a specific region, to outline the contour of a specific region, or to place a target volume with a set size in a specific region. After the identification, the outlining or the placing, the plurality of first target volumes are obtained.

[0064] The segmentation can be manual segmentation, semi-automatic segmentation or automatic segmentation. The manual segmentation is to manually identify the boundary of a specific region, to manually outline the contour of a specific region, or to manually place a target volume with a set size in a specific region according to the characteristics of the medical image; similarly, the semi-automatic segmentation can assist the physician to complete the segmentation of the target volume by combining threshold method, region growing algorithm and the like; and the automatic segmentation can automatically identify and segment each target volume in the tumor based on deep learning and other artificial intelligence algorithms.

[0065] Through the spatial segmentation, a plurality of target volumes not overlapping in the target tumor can be segmented, such as Figure 3 As shown in FIG. 1, the target tumor is segmented in the spatial dimension according to the medical image, to obtain a total of 11 first target volumes A-K located in the target tumor, wherein the first target volumes A-K are located in the target tumor and do not intersect with each other and have a certain interval distance therebetween. In this way, a basis can be provided for subsequent grouping of different target volumes, so as to reduce the damage to the normal tissue.

[0066] Step S300: grouping the plurality of first target volumes to obtain a plurality of target volume groups. Each target volume group includes at least one first target volume, and adjacent first target volumes in the plurality of first target volumes are located in different target volume groups.

[0067] The grouping of the plurality of first target volumes refers to grouping the plurality of first target volumes obtained in step S200 (i.e., spatial segmentation) based on the positional relationship of each first target volume in the spatial dimension, so that any two spatially adjacent first target volumes are divided into different target volume groups, thereby forming a plurality of target volume groups satisfying the adjacent constraint condition.

[0068] It can be understood that the target volume group is a group including first target volumes formed based on the spatial positional relationship of the first target volumes, and the first target volumes in each group are not adjacent in space, while any two spatially adjacent first target volumes necessarily belong to different groups.

[0069] In one embodiment, the number of first target volumes included in each target volume group is greater than or equal to 1 and less than the total number of the plurality of first target volumes, and the first target volumes included in each target volume group are not adjacent.

[0070] It should be noted that the first target volumes included in different target volume groups are completely different.

[0071] For example, Figure 4 A schematic diagram of the plurality of target volume groups provided by the embodiments of the present disclosure is shown, which shows Figure 3 The plurality of target volumes A-K shown in FIG. 1 are grouped, wherein first target volumes with the same label belong to the same target volume group, i.e., the first target volume A1 and the first target volume A2 belong to the same target volume group, the first target volume B1 and the first target volume B2 belong to the same target volume group, the first target volume C1 and the first target volume C2 belong to the same target volume group, the first target volume D1 and the first target volume D2 belong to the same target volume group, and the first target volume E1 and the first target volume E2 belong to the same target volume group. Figure 4 As shown in FIG. 2, four target volume groups are shown, three first target volumes with label 1 belong to the same target volume group, three first target volumes with label 2 belong to the same target volume group, three first target volumes with label 3 belong to the same target volume group, and two first target volumes with label 4 belong to the same target volume group, from which it can be seen that adjacent first target volumes in the plurality of first target volumes are located in different target volume groups. Figure 4 As shown in FIG. 2, four target volume groups are shown, three first target volumes with label 1 belong to the same target volume group, three first target volumes with label 2 belong to the same target volume group, three first target volumes with label 3 belong to the same target volume group, and two first target volumes with label 4 belong to the same target volume group, from which it can be seen that adjacent first target volumes in the plurality of first target volumes are located in different target volume groups.

[0072] It should be noted that in Figure 3 and Figure 5 In FIG. 1, the first target volume A1 and the first target volume A2 are adjacent in space, and the first target volume B1 and the first target volume B2 are adjacent in space. Figure 5In the direction indicated by the two dashed lines, the two first target volumes with the smallest distance are considered adjacent. For example, taking the first target volume C with the upper right corner number 2 as an example, the first target volume E with the lower left corner number 4 and the first target volume F with the lower right corner number 3 are considered adjacent to it, while the first target volume I with the number 1 below it is not considered adjacent, because the distance between the first target volume I with the number 1 is greater than the distance between the first target volume E with the lower left corner number 4 or the first target volume F with the lower right corner number 3.

[0073] It should be noted that if the target body includes multiple solid tumors, at least one can be segmented using the tumor target volume segmentation method in this embodiment of the present disclosure, while other solid tumors can be segmented using other traditional time or space segmentation methods, or they can be segmented using the tumor target volume segmentation method in this embodiment of the present disclosure.

[0074] This disclosure provides a method for tumor target volume segmentation. 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, based on spatial location, the first target volumes are divided into different target volume groups, resulting in multiple target volume groups, where the first target volumes within each group are not adjacent. Thus, by segmenting and grouping the target tumor based on spatial location, it avoids the cumulative damage to normal tissues caused by continuous irradiation of the same area in conventional radiotherapy, providing repair time for adjacent normal tissues. Simultaneously, it ensures the killing effect on the tumor through comprehensive irradiation, thereby improving treatment effectiveness while reducing damage to surrounding healthy tissues.

[0075] like Figure 3 As shown, the multiple non-overlapping first target volumes can be uniformly distributed in space. However, 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 6 and Figure 7 As shown, the target volume within the target tumor is irregularly distributed.

[0076] It should be noted that the non-uniform distribution can be designed based on the heterogeneity characteristics of the tumor and the treatment needs, such as the cell activity, blood supply, and sensitivity difference to the rays of different regions. Specifically, the first target volumes at different positions have differences in size and distribution density, for example, the first target volume at the tumor edge region or the region adjacent to the normal tissue or the key organ can be smaller and more densely distributed to improve the irradiation accuracy and reduce the radiation to the surrounding healthy tissue; and the first target volume at the tumor core region or the region with lower sensitivity to the rays can be larger to adapt to the cumulative irradiation requirement of a higher dose and more accurately match the treatment needs of different sub-regions of the tumor.

[0077] In one embodiment, the plurality of first target volumes in the same target volume group are identical in at least one of the following aspects:

[0078] Target volume size; planned fraction number; planned fraction order; planned irradiation ray type; planned irradiation dose (prescription dose).

[0079] The target volume size of the first target volume is the physical size or volume scale of the first target volume in the spatial dimension.

[0080] The planned fraction number of the first target volume is the number of fractions of the planned irradiation of the first target volume; the planned fraction order of the first target volume is the sequence of the first target volume in the whole fraction radiotherapy, such as Figure 8A The first target volume in the target volume group 2 in the embodiment of the application has a planned fraction number of 2 and a planned fraction order of (1, 3), which indicates that it needs to be irradiated at the 1st fraction and the 3rd fraction and not irradiated at other fractions.

[0081] The planned irradiation ray type of the first target volume is the irradiation ray type planned to be used to irradiate the first target volume, which can be one or more irradiation ray types, and the irradiation ray type can include X-rays, gamma rays, electron rays, proton rays, neutron rays, heavy ion rays, etc.

[0082] The planned irradiation dose of the first target volume is the prescription dose, that is, the total dose that the first target volume needs to receive.

[0083] The target volume size, the planned irradiation ray type, the prescription dose, the planned fraction number, and the planned fraction order can be obtained by setting by a physician or by other means, and the embodiments of the application do not make specific limitations thereto.

[0084] It should be noted that the planned fraction order can also be determined by the planned fraction interval, the planned fraction number, and the start fraction, wherein the start fraction is the fraction from which the plurality of fractions starts, and the planned fraction interval is the time interval between adjacent fractions of the first target volume, such as Figure 8AThe first target volume in the target volume group 2, which starts from the first fraction, has a planned fraction number of 2 and a planned fraction interval of 2 days (i.e. once every other day), so the planned fraction order can be determined as (1, 3), indicating that the irradiation is performed at the first fraction (the first day) and the third fraction (the third day).

[0085] It should be further noted that the target volume size, the planned irradiation beam type, the planned irradiation dose (prescription dose), and the planned fraction number are all for the first target volume in the target volume group, without considering the fraction effect.

[0086] Taking at least two of the non-overlapping first target volumes as an example, the planned irradiation dose is different:

[0087] In a specific embodiment, as shown in Figure 6 The target volume size of the first target volume B is different from that of the first target volume A, and the target volume of the first target volume A near the normal tissue is smaller than that of the first target volume B located at the center of the target tumor, so that the damage to the normal tissue can be reduced by a smaller target volume size. In addition, the planned irradiation beam type of the first target volume B is different from that of the first target volume A, for example, the target volume size of the first target volume B is greater than 20 mm, and the target volume size of the first target volume A is less than or equal to 20 mm, the planned irradiation beam type of the first target volume B is set to X-ray, and the planned irradiation beam type of the first target volume A is set to γ-ray, so as to exert the advantages of different types of radiation beams; in addition, the planned irradiation dose of the first target volume B can also be different from that of the first target volume A, the planned irradiation dose of the first target volume A is set to be greater than or equal to 18 Gy, and the planned irradiation dose of the first target volume B is set to be less than 18 Gy, so that different dose areas of high and low doses are formed in the target region, which can activate the immune response in the patient's body and obtain a better anti-tumor immune effect.

[0088] In one embodiment, at least two of the target volume groups are different in at least one of the following aspects: the number of contained first target volumes; the target volume size of the contained first target volumes; the planned fraction number of the contained first target volumes; the planned fraction order of the contained first target volumes; the planned irradiation beam type of the contained first target volumes; and the planned irradiation dose (fraction dose) of the contained first target volumes.

[0089] It should be noted that the number of first target volumes included in the target volume group is the number of first target volumes in the target volume group; the target volume size of the first target volumes included in the target volume group is the physical size or volume scale of each first target volume in the target volume group in the spatial dimension; the planned number of fractions of the first target volumes included in the target volume group is the planned number of fractions of irradiation for each first target volume in the target volume group; the planned fraction order of the first target volumes included in the target volume group is the order in which each of the first target volumes in the target volume group is irradiated throughout the entire fractionated radiotherapy; the planned radiation type of the first target volumes included in the target volume group is the radiation type planned to be used to irradiate each first target volume in the target volume group; and the planned radiation dose of the first target volumes included in the target volume group is the fractional dose, that is, the dose that the first target volume in the target volume group needs to receive in the corresponding fraction.

[0090] Example, reference Figure 8A As shown in the diagram, the first target volume corresponding to four different fractions of irradiation is schematically illustrated. According to... Figure 8A The four different fractions irradiated the first target volume in all target volume groups, and the first target volume irradiated in each fraction was not adjacent.

[0091] In one embodiment, the first target volume of the same fraction is at least one first target volume in the same group of target volumes.

[0092] It is understandable that the first target volume in the same fraction all comes from the same group of target volumes, and these first target volumes are not spatially adjacent to each other. This ensures that the first target volumes irradiated within the same fraction will not cause continuous and concentrated radiation damage to surrounding normal tissues in a single irradiation due to spatial adjacency.

[0093] Example, reference Figure 8B As shown, in the fourth subdivision, the corresponding first target volume is at least one first target volume in the same target volume group, which is two first target volumes in group 3. The other target volume in group 3 is in the first subdivision.

[0094] Furthermore, at least one first target volume in the same target volume group is all the first target volumes in the same target volume group.

[0095] It is understandable that within the same radiotherapy fraction, all first target volumes within the same target volume group are irradiated, and since all first target volumes within this target volume group are not spatially adjacent, concentrated damage to surrounding normal tissues caused by simultaneous irradiation of adjacent target volumes in a single fraction can be avoided.

[0096] Example, reference Figure 8B As shown, in the second division, the corresponding first target volume is all the first target volumes in the same target volume group, which is all the first target volumes in the fourth group.

[0097] Optionally, the multiple first target volumes of the same fraction are identical in at least one of the following aspects: target volume size; planned irradiation type; planned irradiation dose (fraction dose); planned number of fractions.

[0098] The planned irradiation dose is the dose corresponding to the first target volume in the fraction, that is, the fraction dose, and the fraction dose is less than or equal to the prescription dose of the first target volume.

[0099] It should be noted that multiple first target volumes in the same fraction can maintain consistency in at least one of the following: target volume size, planned type of irradiation, planned irradiation dose, or planned total number of fractions. This facilitates standardized execution of the treatment plan, reducing operational complexity and dosage error risks caused by parameter differences. Furthermore, since the first target volumes in the same fraction are not spatially adjacent, unifying some parameters can better adapt to the common biological characteristics of that batch of target volumes, thereby ensuring the treatment efficacy while further improving the precision and safety of the treatment.

[0100] In one embodiment, the first target volume of the same division is a plurality of non-adjacent first target volumes in at least two target volume groups.

[0101] It should be noted that in a single fraction, the first target volume is selected from multiple target volume groups for irradiation, and these first target volumes are not adjacent to each other. This can both expand the coverage of the tumor and avoid concentrated damage to normal tissues caused by simultaneous irradiation of adjacent target volumes.

[0102] Optionally, the plurality of non-adjacent first target volumes are a portion of the first target volumes in the at least two groups of target volumes.

[0103] It should be noted that it is not necessary to select all the first target volumes from multiple target volume groups. Instead, a portion of the target volume is selected based on the characteristics of different regions of the tumor to achieve more refined and differentiated treatment.

[0104] Example, reference Figure 8B As shown, in the first and third subdivisions, the corresponding first target volume is a plurality of non-adjacent first target volumes in two target volume groups. In the third subdivision, it is composed of all the first target volumes of one of the two target volume groups and a portion of the first target volumes of the other group. In the first subdivision, it is composed of a portion of the first target volumes of one of the two target volume groups and a portion of the first target volumes of the other group.

[0105] Optionally, multiple first target volumes in different target volume groups within the same fraction are identical in at least one of the following aspects: target volume size; planned irradiation type; planned irradiation dose (fraction dose); planned number of fractions.

[0106] wherein the target volume size is a physical dimension or a volume scale of the first target volume in a spatial dimension; the planned irradiation beam type is a type of irradiation beam planned for irradiating the first target volume; the planned irradiation dose is a fraction dose, i.e. a dose that the first target volume needs to receive within a fraction; and the planned fraction number is a number of fractions of the planned irradiation of the first target volume.

[0107] Optionally, at least two of the first target volumes in the same fraction are identical or different in at least one of the following aspects: the target volume size; the planned irradiation beam type; the planned irradiation dose; and the planned fraction number.

[0108] Optionally, at least two of the first target volumes in the same fraction are different in at least one of the following aspects:

[0109] the target volume size; the planned irradiation beam type; the planned irradiation dose; and the planned fraction number.

[0110] In an embodiment, at least two of the first target volumes in different fractions are first target volumes in the same target volume group.

[0111] It can be understood that some of the first target volumes in the same target volume group can be repeatedly selected for irradiation in different fractions. Since the first target volumes in the same target volume group are not adjacent to each other in space, and adjacent first target volumes belong to different groups, such cross-fraction irradiation arrangement can ensure that the tumor regions in the target volume group obtain sufficient cumulative dose through multiple irradiations to achieve a killing effect, and at the same time, provide repair time for the surrounding normal tissues through fraction intervals to avoid irreversible damage caused by continuous irradiation.

[0112] For example, referring to FIG. 2, the target volume group 2 has at least two first target volumes in the first fraction and the third fraction. Figure 8A

[0113] Optionally, at least two of the first target volumes in different fractions are identical in at least one of the following aspects:

[0114] the target volume size; the planned irradiation beam type; the planned irradiation dose; and the planned fraction number.

[0115] In an embodiment, the planned fraction number of the first target volume with a target volume size greater than a preset value is greater than or equal to 2.

[0116] It should be noted that the preset value can be 20 mm, and for the first target volume with a target volume size less than or equal to 20 mm, a planned fraction number of 1 can be used; and for the first target volume with a target volume size greater than or equal to 20 mm, a planned fraction number of 2 or more can be used.​

[0117] As shown in FIG. 2, the size of the first target volume of the target volume group 2 located at the center of the target tumor is greater than 20mm, so the planned fraction number is two, and the first target volume of the target volume group 2 located at the center of the target tumor is irradiated in the first fraction and the third fraction. Figure 8C

[0118] In one embodiment, the tumor target volume segmentation method further comprises:

[0119] Step S400: segmenting the target tumor in a spatial dimension according to a medical image, and obtaining a second target volume corresponding to a target tumor contour, to plan a fraction order of the second target volume in multiple fractions; wherein the multiple non-overlapping first target volumes are located in the second target volume.

[0120] It can be understood that the area of the second target volume is the area of the whole target tumor, which can be a tumor target volume (Gross Target Volume, GTV), and can be a target volume containing the GTV, such as a clinical target volume (Clinical Target Volume, CTV) or a planning target volume (Planning Target Volume, PTV), and the multiple first target volumes are located in the second target volume of the target tumor; covering the whole tumor in the second target volume can further improve the irradiation effect, and can also cooperate with the first target volume for irradiation, further improving the irradiation effect.

[0121] Further, the second target volume and at least one of the multiple first target volumes are different in at least one of the following aspects:

[0122] a planned irradiation beam type, a planned irradiation dose (a prescription dose), a planned fraction number, and a planned fraction order.

[0123] The planned irradiation beam type is a planned irradiation beam type for irradiating the first target volume / second target volume, the planned irradiation dose is a total dose planned to be received by the first target volume / second target volume, the planned fraction number is the number of fractions of the planned irradiation of the first target volume / second target volume, and the planned fraction order is the order of the fractions of the planned irradiation of the first target volume / second target volume.

[0124] Optionally, the planned fraction number of the second target volume is less than the maximum value of the planned fraction order of at least one of the first target volumes.

[0125] It can be understood that the second target volume is not in all fractions, that is, there are fractions that do not contain the second target volume, for example, as shown in FIG. 2, the second target volume is not irradiated in the third fraction, reducing damage to normal tissues. Figure 8B It can be understood that the second target volume is not in all fractions, that is, there are fractions that do not contain the second target volume, for example, as shown in FIG. 2, the second target volume is not irradiated in the third fraction, reducing damage to normal tissues.​

[0126] Optionally, the first target volume and the second target volume with the same fraction order are irradiated in the corresponding fraction.

[0127] For example, as shown in FIG. 8, Figure 8A In the embodiment, the second target volume and the first target volume are irradiated in the first fraction and the third fraction. Figure 8B In the embodiment, the second target volume and the first target volume are irradiated in the first fraction and the fourth fraction. Figure 8C In the embodiment, the second target volume and the first target volume are irradiated in the first fraction and the third fraction.

[0128] In one embodiment, the second target volume and at least one of the first target volumes with the same irradiation order are different in at least one of the following aspects:

[0129] Planning irradiation ray type; planning irradiation dose (fraction dose).

[0130] The planning irradiation ray type is the irradiation ray type planned for irradiating the first target volume / second target volume in the target volume set. The irradiation ray type can include X-ray, gamma ray, electron ray, proton ray, neutron ray, heavy ion ray, etc. For example, the second target volume uses low irradiation dose X-ray, and the first target volume uses high irradiation dose gamma ray. The planning irradiation dose is the dose required by the first target volume / second target volume in the corresponding fraction of the target volume set, i.e., the fraction dose.

[0131] In one embodiment, the segmentation of the target tumor in the spatial dimension according to the medical image further includes:

[0132] Step S210: based on tumor heterogeneity, segmenting the target tumor in the spatial dimension according to the medical image.

[0133] It should be noted that tumor heterogeneity refers to the differences in biological characteristics, such as cell proliferation activity, metabolic level, gene expression, sensitivity to radiation, etc., between different regions inside the tumor; these differences can be identified and quantified through medical images. Based on tumor heterogeneity for spatial dimension segmentation, it means that in the segmentation process, the target tumor will be divided into multiple first target volumes with different biological characteristics according to the differences reflected by the medical image.

[0134] For example, the high-metabolism region of the tumor identified by the PET image is segmented into one or more first target volumes, while the lower-metabolism region is segmented into other first target volumes. This segmentation method can accurately match the heterogeneity characteristics within the tumor, providing a basis for subsequent development of differentiated radiotherapy plans for different first target volumes, such as different irradiation doses, ray types, and fraction numbers, etc.; thereby achieving the reinforcement treatment of high-risk regions and the reasonable control of low-risk regions of the tumor, and improving the accuracy and effectiveness of radiotherapy.

[0135] In one embodiment, when the target tumor is located in the head, the total number of the target volume set is less than or equal to 5.

[0136] It should be noted that the head region concentrates a large number of key normal tissues that are highly sensitive to radiation rays, such as the cerebral cortex, brainstem, optic nerve, cochlea, etc. The radiation tolerance dose of these tissues is low, and excessive irradiation is easy to cause serious complications, such as cognitive impairment, vision loss, hearing impairment, etc. Limiting the total number of the target volume set corresponding to the head tumor to within 5, i.e., controlling the total fraction number of radiotherapy, can reduce the cumulative radiation exposure of the normal tissues in the head and reduce the risk of radioactivity damage. At the same time, the anatomical position of the head tumor is relatively fixed, and the tumor shape and boundary are usually clear. By reasonably designing the target volume set within 5 times, complete coverage and accurate irradiation of the tumor can be achieved, balancing the treatment needs and normal tissue protection on the premise of ensuring the treatment effect.

[0137] In one embodiment, the tumor target volume segmentation method further comprises:

[0138] Step S510: acquiring imaging containing the target tumor before the i th fraction, where i is greater than 1 and less than or equal to the planned fraction number.

[0139] Wherein, before the i th fraction can be before the i th irradiation, or between the i-1 th fraction and the i th fraction, i is greater than 1 and less than or equal to the planned fraction number. The imaging containing the target tumor can indicate the biological differences within the target tumor and the dynamic changes of the target tumor structure. This imaging can be the imaging scanned before the i th fraction, or the imaging before the i th fraction predicted based on the medical image or other image before the i th fraction.

[0140] It should be noted that this step dynamically monitors the biological differences within the tumor and the dynamic changes of the tumor structure by acquiring the imaging containing the target tumor before the i th fraction, to provide real-time basis for adjusting the radiotherapy strategy of the first target volume in the i th fraction, ensuring that the radiotherapy strategy is always based on the latest state of the tumor, and embodying the flexibility of adaptive radiotherapy.

[0141] Step S520: adjusting at least one of the following aspects of the first target volume and / or the second target volume within the i-th fraction based on the imaging before the i-th fraction:

[0142] target volume size; planned irradiation beam type; planned irradiation dose (fraction dose).

[0143] wherein the target volume size is a physical size or volume scale of the first target volume / second target volume in the i-th fraction in a spatial dimension; the planned irradiation beam type is a type of irradiation beam planned to irradiate the first target volume / second target volume in the i-th fraction; and the planned irradiation dose is a dose required by the first target volume / second target volume in the i-th fraction.

[0144] It can be understood that, based on the imaging result before the i-th fraction, if it is found that the tumor volume is reduced, the size of the first target volume and / or the second target volume can be adjusted accordingly to avoid ineffective irradiation of the regressed area; if the sensitivity of a certain region of the tumor to the current beam type decreases, the planned irradiation beam type can be replaced to improve the therapeutic effect; if the imaging shows that a certain region has insufficient or excessive dose accumulation, the planned irradiation dose can be adjusted to balance the treatment effect and safety. Through such targeted adjustment, it is ensured that the irradiation scheme of each fraction is accurately matched with the real-time state of the tumor, and the risk of insufficient treatment or normal tissue damage caused by deviation is reduced.

[0145] Moreover, the fine division inside the tumor in space is realized, and it is ensured that the irradiation beams irradiate the first target volume without overlapping each other; so that the radiotherapy scheme can be adjusted according to the dynamic changes of the tumor during the treatment process, avoiding the irradiation deviation caused by the fixed scheme, and finally improving the adaptability and accuracy of the tumor target volume through the collaborative segmentation in the spatial and temporal dimensions, thereby improving the radiotherapy effect and reducing the damage to normal tissues. The precise and dynamic segmentation of the tumor target volume can be realized, and the pertinence and effectiveness of radiotherapy are improved.

[0146] Further, the imaging is functional imaging.

[0147] It should be noted that, compared with conventional anatomical imaging, functional imaging can not only show the anatomical morphology of the tumor, but also reflect the biological activity of the tumor, such as metabolic level, blood perfusion, and cell proliferation activity. For example, PET can identify the active region with high metabolism in the tumor through the amount of tracer uptake, and functional MRI can reflect the microcirculation state of the tumor tissue. The use of functional imaging can more accurately locate the active residual area, recurrence risk area, or poor response area to treatment of the tumor, provide a more biologically meaningful basis for adjusting the target volume size, beam type, and dose, make the adjustment more in line with the functional characteristics of the tumor, and further improve the accuracy and pertinence of radiotherapy.

[0148] It should be noted that, in the above case involving "fractions", the target volumes after grouping have actually been grouped in the time dimension, that is, the first target volumes and / or the second target volumes are divided in the time dimension based on the plurality of target volume groups to obtain a plurality of target volume sets corresponding to different fractions; wherein the target volume set includes at least one target volume group.

[0149] It should be noted that the ordered allocation and dynamic adjustment of the first target volumes in the time dimension are achieved through grouping management. Specifically, first, the first target volumes are grouped, and first target volumes with similar treatment needs can be grouped into the same target volume group for intensive planning and irradiation, thereby reducing the complexity of single operation. For example, a plurality of first target volumes with the same radiotherapy sensitivity in a tumor can be grouped into a group, and irradiation parameters can be uniformly formulated to improve planning efficiency. Second, the time dimension is divided based on the target volume groups, so that the target volume set of each fraction is formed as a basic unit of the target volume group rather than a single first target volume, which can more systematically realize the differentiation between fractions: the target volume groups of adjacent fractions are not completely the same, and the combination of irradiation can be flexibly adjusted according to the dynamic changes of the tumor. Through the combination of the target volume groups and the allocation of the fractions, all the first target volumes can be completely covered, and the accuracy and adaptability of the radiotherapy plan can be improved through the dynamic adjustment of the groups.

[0150] Optionally, adjacent first target volumes in the plurality of first target volumes are located in different target volume groups.

[0151] It should be noted that the adjacent first target volumes can be irradiated in the same fraction or can be irradiated in different fractions, and the embodiments of the present application are not limited in particular.

[0152] It should be noted that, by allowing the adjacent first target volumes to be irradiated in different fractions, the adjacent first target volumes can be irradiated simultaneously in the same fraction, thereby reducing the risk of dose superposition in the adjacent regions. Since the adjacent first target volumes are close in space, if they are irradiated in the same group and in the same fraction, the normal tissue at the junction may be exposed to a high dose; and by dividing them into different target volume groups, the irradiation can be staggered in the time dimension, such as irradiation in different fractions, thereby reducing the possibility of local dose concentration and protecting the normal tissue around the tumor.

[0153] According to an embodiment of the present disclosure, the present disclosure also provides a tumor target volume segmentation device, 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, and the instructions are executed by the at least one processor to enable the at least one processor to execute the tumor target volume segmentation method provided by the present disclosure.

[0154] According to an embodiment of the present disclosure, the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to make a tumor target volume segmentation device execute the tumor target volume segmentation method provided by the present disclosure.

[0155] According to an embodiment of the present disclosure, the present disclosure further provides a computer program product comprising a computer program which, when executed by a processor, implements the tumor target volume segmentation method provided by the present disclosure.

[0156] Figure 9 A schematic block diagram of an example tumor target volume segmentation device 800 that can be used to implement embodiments of the present disclosure is shown. The tumor target volume segmentation device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The tumor target volume segmentation device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document. In some embodiments, the tumor target volume segmentation device can be a treatment planning system device or a radiotherapy device as shown in Figure 1 the above.

[0157] As shown in Figure 9 , the tumor target volume segmentation device 900 includes a computing unit 901 that can perform various appropriate actions and processes according to a computer program stored in a read-only memory 902 or a computer program loaded into a random access memory 903 from a storage unit 908. In the random access memory (RAM) 903, various programs and data required for the operation of the tumor target volume segmentation device 900 can also be stored. The computing unit 901, the read-only memory (ROM) 902, and the RAM 903 are connected to each other through a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0158] The plurality of components in the tumor target volume segmentation apparatus 900 are connected to the input / output interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a magnetic disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the tumor target volume segmentation apparatus 900 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0159] The computing unit 901 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 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, a digital signal processor, and any appropriate processor, controller, microcontroller, etc. The computing unit 901 performs various methods and processes described above, such as the data matching method. For example, in an embodiment, the data matching method can be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as the storage unit 908. In an embodiment, part or all of the computer program can be loaded and / or installed on the tumor target volume segmentation apparatus 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded to the RAM 903 and executed by the computing unit 901, one or more steps of the data matching method described above can be performed. Alternatively, in other embodiments, the computing unit 901 can be configured to perform the data matching method by any other appropriate means, such as by means of firmware.

[0160] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, specially designed application specific integrated circuits, application specific standard products (ASSPs), system on a chip (SOCs), complex programmable logic devices (CPLDs), computers hardware, firmware, software, and / or combinations of them. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0161] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / operations specified in the flowchart and / or block diagram block or blocks. The program code can be retrieved from storage and / or memory and / or can be executed by a processor or controller. The program code can be executed completely on a machine, partially on a machine, as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0162] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact discs read-only memories, optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0163] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a Cathode Ray Tube (CRT) or Liquid Crystal Display (LCD) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; 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 acoustic, speech, or tactile input.

[0164] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a Local Area Network (LAN), a Wide Area Network (WAN), and the Internet.

[0165] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server can arise by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0166] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, in series, or in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0167] The above detailed description does not limit the scope of the disclosure. Various modifications, combinations, sub-combinations and alternatives can be made to the detailed description. Any modification, equivalent replacement and improvement etc. made within the spirit and principle of the disclosure shall be included in the scope of the 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; The multiple first target volumes are grouped to obtain multiple target volume groups; wherein each target volume group includes at least one first target volume, and adjacent first target volumes among the multiple first target volumes are located in different target volume groups.

2. The tumor target volume segmentation method according to claim 1, characterized in that, The multiple non-overlapping first target volumes are non-uniformly distributed in the spatial dimension.

3. The tumor target volume segmentation method according to claim 1, characterized in that, Multiple first target volumes in the same target volume group are identical in at least one of the following aspects: Target volume size; Planned number of sessions; The plan is divided into stages and sequences; Planned radiation type; Planned irradiation dose.

4. The tumor target volume segmentation method according to claim 1, characterized in that, 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 target volume size including the first target volume; The planned number of times the first target volume is included; The planned sequence of the first target volume included; The planned radiation type of the first target volume included; The planned irradiation dose for the first target volume contained therein.

5. The tumor target volume segmentation method according to claim 1, characterized in that, The first target volume of the same division is at least one first target volume in the same group of target volumes.

6. The tumor target volume segmentation method according to claim 1, characterized in that, The first target volume of the same division is a plurality of non-adjacent first target volumes in at least two groups of said target volumes.

7. The tumor target volume segmentation method according to claim 1, characterized in that, At least two of the multiple first target volumes in different fractions are first target volumes in the same target volume group.

8. The tumor target volume segmentation method according to claim 1, characterized in that, The planned number of rounds corresponding to the first target volume whose target volume is greater than the preset value is greater than or equal to 2.

9. The tumor target volume segmentation method according to claim 1, characterized in that, The method further includes: The target tumor is segmented in the spatial dimension based on the medical image, and a second target volume corresponding to the outline of the target tumor is obtained, so as to plan the order of the second target volume in multiple subdivisions. In this configuration, the multiple non-overlapping first target volumes are all located within the second target volume.

10. The tumor target volume segmentation method according to claim 9, characterized in that, 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 irradiation dose; Planned number of sessions; The plan is to proceed in stages and in sequence.

11. The tumor target volume segmentation method according to claim 9, characterized in that, The number of planned subdivisions for the second target volume is less than the maximum value of at least one planned subdivision sequence for the first target volume.

12. The tumor target volume segmentation method according to claim 1, characterized in that, The step of segmenting the target tumor in the spatial dimension based on the medical image further includes: Based on tumor heterogeneity, the target tumor is segmented in spatial dimension according to the medical image.

13. The tumor target volume segmentation method according to claim 1, characterized in that, The method further includes: 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; Based on the imaging prior to the i-th fraction, adjust at least one of the following aspects of the first target volume and / or the second target volume within the i-th fraction: Target size; Planned radiation type; Planned irradiation dose.

14. A tumor target volume segmentation device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the instructions to implement the tumor target volume segmentation method as described in any one of claims 1 to 13.

15. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the tumor target volume segmentation method as described in any one of claims 1 to 13.

Images