Method for calculating total three-dimensional bone scanning index, and electronic device and storage medium

Abstract

The present application relates to the technical field of medical image processing. Specifically provided are a method for calculating a total three-dimensional bone scanning index, and an electronic device and a storage medium. The method comprises the steps of: S1, performing lesion segmentation on SPECT tomographic bone scanning data, so as to obtain several lesion regions, wherein each lesion region corresponds to one bone metastasis lesion; S2, performing bone segmentation and SPECT spatial transformation on CT tomographic data, so as to obtain a plurality of bone regions; and S3, on the basis of a proportional relationship between each lesion region and the bone region to which the lesion region belongs, calculating a three-dimensional bone scanning index of each bone metastasis lesion, and then calculating a total three-dimensional bone scanning index on the basis of all three-dimensional bone scanning indexes. The method can effectively solve the problem of low accuracy in acquiring a total area of a bone region to which a lesion belongs caused by insufficient segmentation precision of the bone region.

Description

A method for calculating the total index of a three-dimensional bone scan, an electronic device, and a storage medium. Technical Field

[0001] This application relates to the field of medical image processing technology, and more specifically, to a method for calculating the total index of a three-dimensional bone scan, an electronic device, and a storage medium. Background Technology

[0002] To monitor disease progression and treatment effectiveness in cancer patients, related technologies require the calculation of bone scan indices. Specifically, the calculation process involves: obtaining the lesion area and the total area of ​​the bone region to which the lesion belongs from a SPECT planar image; and calculating the bone scan index based on the lesion area, the total area of ​​the corresponding bone region, and a preset percentage of bone weight corresponding to the bone region to which the lesion belongs. However, these technologies rely on SPECT planar images for bone scan index calculations. SPECT planar images suffer from insufficient bone region segmentation accuracy; for example, the sternum and spine overlap in SPECT planar images, making it difficult to accurately distinguish between them. Therefore, the accuracy of obtaining the total area of ​​the bone region to which the lesion belongs is low due to insufficient bone region segmentation accuracy, resulting in inaccurate bone scan index calculations. Furthermore, existing bone scan index calculations are only applicable to SPECT planar images.

[0003] There is currently no effective technical solution to the above problems. Summary of the Invention

[0004] The purpose of this application is to provide a method, electronic device and storage medium for calculating the total index of three-dimensional bone scans, which can effectively solve the problem of low accuracy in obtaining the total area of ​​the bone region to which the lesion belongs due to insufficient bone region segmentation accuracy.

[0005] In a first aspect, this application provides a method for calculating the total index of a three-dimensional bone scan, which includes the following steps:

[0006] S1. Segment the SPECT tomographic bone scan data to obtain several lesion regions, each of which corresponds to a bone metastasis lesion.

[0007] S2. Perform bone segmentation and SPECT spatial transformation on CT tomographic data to obtain multiple bone regions;

[0008] S3. Calculate the three-dimensional bone scan index of each bone metastasis based on the ratio between the lesion area and the bone region to which the lesion area belongs, and then calculate the total three-dimensional bone scan index based on all the three-dimensional bone scan indices.

[0009] This application provides a method for calculating the total index of a three-dimensional bone scan. This method can obtain the lesion region of bone metastases by segmenting SPECT tomographic bone scan data and obtain multiple bone regions by segmenting CT tomographic data and performing SPECT spatial transformation. Since CT tomographic data can clearly display bone structures, this application can accurately divide bone regions by segmenting CT tomographic data. Compared to segmenting bone regions based on SPECT planar images, this application can effectively improve the accuracy of bone region segmentation, thereby effectively solving the problem of low accuracy in obtaining the total area of ​​the bone region to which the lesion belongs due to insufficient bone region segmentation accuracy. This effectively improves the accuracy of the bone scan index. Furthermore, this method for calculating the total index of a three-dimensional bone scan is applicable to both SPECT planar images and SPECT three-dimensional images.

[0010] Optionally, the proportional relationship includes volume ratio and weight ratio, and the total index of three-dimensional bone scan includes volume bone scan index and weight bone scan index. Step S3 includes:

[0011] S31. Obtain the lesion volume and weight information of each bone metastasis lesion according to the lesion area, and obtain the bone volume and weight information corresponding to each bone area.

[0012] S32. Calculate the volume bone scan index of each bone metastasis lesion based on the lesion volume information and bone volume information, and calculate the total volume bone scan index based on all volume bone scan indices. The volume bone scan index is the ratio of the lesion volume information corresponding to the lesion area to the bone volume information corresponding to the bone area to which the lesion area belongs.

[0013] S33. Calculate the weight bone scan index of each bone metastasis based on the lesion weight information and bone weight information, and calculate the total weight bone scan index based on all weight bone scan indices. The weight bone scan index is the ratio of the lesion weight information corresponding to the lesion area to the bone weight information corresponding to the bone area to which the lesion area belongs.

[0014] Optionally, the lesion volume information is the product of the total number of pixels occupied by the lesion region in each slice and the volume per unit pixel; the lesion weight information is the product of the average number of photons per unit volume in the lesion region and the lesion volume information; the bone volume information is the product of the total number of voxels in the bone region and the volume per unit voxel; and the bone weight information is the product of the average linear absorption coefficient of the bone region and the bone volume information.

[0015] Optionally, the formula for calculating bone volume information is shown in equation (1):

[0016] (1);

[0017] Among them, V bone N represents bone volume information. label V represents the total number of voxels in the skeletal region. voxel Represents the volume of a unit voxel;

[0018] The formula for calculating bone weight information is shown in equation (2):

[0019] (2);

[0020] Among them, W bone HU represents the weight and volume information of the skeletal region. bone This represents the average linear absorption coefficient of the corresponding skeletal region.

[0021] Optionally, the formula for calculating the total index of volumetric bone scan is shown in equation (3):

[0022] (3);

[0023] Among them, VSBI 总 VSBI represents the total index of bone scan volume, n represents the total number of bone metastases, and VSBI represents the total index of bone scan volume. i This represents the volumetric bone scan index corresponding to the i-th bone metastasis lesion;

[0024] The formula for calculating the volume bone scan index is shown in equation (4):

[0025] (4);

[0026] Among them, V lessioni V represents the lesion volume information of the lesion region corresponding to the i-th bone metastasis lesion. totalbonei This represents the bone volume information of the bone region corresponding to the i-th bone metastasis lesion.

[0027] Optionally, the formula for calculating the total index of weight bone scan is shown in equation (5):

[0028] (5);

[0029] Among them, WSBI 总 WSBI represents the total weight bone scan index, where n represents the total number of bone metastases. i This represents the weight bone scan index corresponding to the i-th bone metastasis lesion;

[0030] The formula for calculating the weight bone scan index is shown in equation (6):

[0031] (6);

[0032] Among them, W lessioniW represents the weight information of the lesion region corresponding to the i-th bone metastasis lesion. totalbonei This represents the bone weight information of the bone region corresponding to the i-th bone metastasis lesion.

[0033] Optionally, step S2 includes:

[0034] S21. Perform bone segmentation on CT tomographic data based on the pre-trained first segmentation network to obtain multiple bone segmentation results;

[0035] S22. Convert all bone segmentation results to SPECT space to obtain multiple bone regions.

[0036] Optionally, step S1 includes:

[0037] S11. Based on the pre-trained second segmentation network, several lesion regions are obtained from the SPECT tomographic bone scan data.

[0038] Secondly, this application provides an electronic device, including a processor and a memory, the memory storing computer-readable instructions, which, when executed by the processor, perform the steps in the three-dimensional bone scan total index calculation method provided in the first aspect above.

[0039] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps in the three-dimensional bone scan total index calculation method provided in the first aspect above.

[0040] As can be seen from the above, the three-dimensional bone scan total index calculation method, electronic device, and storage medium provided in this application can obtain the lesion area of ​​bone metastasis by segmenting the lesion in SPECT tomographic bone scan data, and obtain multiple bone regions by segmenting the bone in CT tomographic data and SPECT spatial transformation. Since CT tomographic data can clearly display the bone structure, this application can accurately divide the bone region by segmenting the bone in CT tomographic data. That is, compared with dividing the bone region according to SPECT planar images, this application can effectively improve the bone region segmentation accuracy, thereby effectively solving the problem of low accuracy in obtaining the total area of ​​the bone region to which the lesion belongs due to insufficient bone region segmentation accuracy, and thus effectively improving the accuracy of bone scan index. Moreover, the three-dimensional bone scan total index calculation method of this application can be applied to SPECT planar images and SPECT three-dimensional images. Attached Figure Description

[0041] Figure 1 is a flowchart of a three-dimensional bone scan total index calculation method provided in an embodiment of this application.

[0042] Figure 2 is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0043] Reference numerals: 101, processor; 102, memory; 103, communication bus. Detailed Implementation

[0044] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0045] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0046] Firstly, as shown in Figure 1, this application provides a method for calculating the total index of a three-dimensional bone scan, which includes the following steps:

[0047] S1. Segment the SPECT tomographic bone scan data to obtain several lesion regions, each of which corresponds to a bone metastasis lesion.

[0048] S2. Perform bone segmentation and SPECT spatial transformation on CT tomographic data to obtain multiple bone regions;

[0049] S3. Calculate the three-dimensional bone scan index of each bone metastasis based on the ratio between the lesion area and the bone region to which the lesion area belongs, and then calculate the total three-dimensional bone scan index based on all the three-dimensional bone scan indices.

[0050] The SPECT bone scan data in step S1 is preferably data obtained after scanning the patient using a single-photon emission computed tomography (SPECT) device. This SPECT bone scan data is about bone metastatic lesions, that is, the SPECT bone scan data can accurately reflect the relevant information of bone metastatic lesions (such as the location and size of bone metastatic lesions). In step S1, the SPECT bone scan data can be manually segmented to obtain several lesion regions, each of which corresponds to a bone metastatic lesion.

[0051] The CT tomographic data used in step S2 is preferably data obtained after scanning the patient using an X-ray scanning imaging device. Because CT equipment has the advantages of high resolution and the ability to clearly display bone structures, step S2 can precisely divide the bone regions in the CT tomographic data by performing bone segmentation. Since the size of CT tomographic data is typically 512×512×N, while the size of SPECT bone scan data is typically 128×128×N, in order to make the data obtained after bone segmentation of the CT tomographic data applicable to SPECT bone scan data, step S2 needs to perform SPECT spatial transformation on the data obtained after bone segmentation of the CT tomographic data, thereby obtaining multiple bone regions suitable for SPECT bone scan data. It should be understood that the bone regions in this embodiment are CT data with the same resolution as the SPECT bone scan data. Since the SPECT spatial transformation in this embodiment is equivalent to adjusting the resolution of the data obtained after bone segmentation of the CT tomographic data to be consistent with the resolution of the SPECT bone scan data, the bone regions in this embodiment can match the bone regions in the SPECT bone scan data.

[0052] Step S3 can analyze which bone region the lesion region belongs to by analyzing which bone region it intersects with. Alternatively, this embodiment can first obtain the location of the lesion region and then analyze which bone region it belongs to. The total three-dimensional bone scan index in step S3 reflects the percentage of all bone metastases in the bone. Therefore, step S3 can first calculate the three-dimensional bone scan index of each bone metastasis based on the proportional relationship between the lesion region and the bone region to which it belongs, and then calculate the total three-dimensional bone scan index based on all the three-dimensional bone scan indices. Specifically, step S3 can obtain the total three-dimensional bone scan index by summing all the three-dimensional bone scan indices. It should be understood that since SPECT tomographic bone scan data can accurately reflect the relevant information of bone metastases, and CT tomographic data can accurately reflect bone structure, and this application obtains the lesion region based on SPECT tomographic bone scan data and the bone region based on CT tomographic data, this application is equivalent to utilizing the respective advantages of SPECT tomographic bone scan data and CT tomographic data to calculate an accurate total three-dimensional bone scan index.

[0053] This application provides a method for calculating the total index of a three-dimensional bone scan. This method can obtain the lesion region of bone metastases by segmenting SPECT tomographic bone scan data and obtain multiple bone regions by segmenting CT tomographic data and performing SPECT spatial transformation. Since CT tomographic data can clearly display bone structures, this application can accurately divide bone regions by segmenting CT tomographic data. Compared to segmenting bone regions based on SPECT planar images, this application can effectively improve the accuracy of bone region segmentation, thereby effectively solving the problem of low accuracy in obtaining the total area of ​​the bone region to which the lesion belongs due to insufficient bone region segmentation accuracy. This effectively improves the accuracy of the bone scan index. Furthermore, this method for calculating the total index of a three-dimensional bone scan is applicable to both SPECT planar images and SPECT three-dimensional images. Furthermore, existing technologies require the use of a preset bone weight percentage to calculate the bone scan index. This preset bone weight percentage is the percentage of the weight of a certain bone region relative to the total weight of all bones. This preset bone weight percentage is obtained by comprehensively considering the bone weight ratios of multiple patients collected in advance. Therefore, this preset bone weight percentage may not accurately reflect the actual situation of the patient who needs to have their bone scan index calculated. However, since this application obtains multiple bone regions based on CT tomographic data, it can obtain an accurate bone weight percentage based on the patient's own multiple bone regions. That is, the bone weight percentage of this application can accurately reflect the actual situation of the patient who needs to have their bone scan index calculated, thereby effectively avoiding the situation where the preset bone weight percentage may not accurately reflect the actual situation of the patient who needs to have their bone scan index calculated.

[0054] In some preferred embodiments, the proportional relationship includes volume ratio and weight ratio, the three-dimensional bone scan total index includes volume bone scan total index and weight bone scan total index, and step S3 includes:

[0055] S31. Obtain the lesion volume and weight information of each bone metastasis lesion according to the lesion area, and obtain the bone volume and weight information corresponding to each bone area.

[0056] S32. Calculate the volume bone scan index of each bone metastasis lesion based on the lesion volume information and bone volume information, and calculate the total volume bone scan index based on all volume bone scan indices. The volume bone scan index is the ratio of the lesion volume information corresponding to the lesion area to the bone volume information corresponding to the bone area to which the lesion area belongs.

[0057] S33. Calculate the weight bone scan index of each bone metastasis based on the lesion weight information and bone weight information, and calculate the total weight bone scan index based on all weight bone scan indices. The weight bone scan index is the ratio of the lesion weight information corresponding to the lesion area to the bone weight information corresponding to the bone area to which the lesion area belongs.

[0058] Since each bone metastasis corresponds to a lesion volume and a lesion weight, and each bone region corresponds to a bone volume and a bone weight, and each bone metastasis corresponds to a bone region, after executing step S31, each lesion volume corresponds to a bone volume, each lesion weight corresponds to a bone weight, and the bone weight is the relative weight of the bone region. Step S32 can calculate the volume bone scan index by summing all volume bone scan indices, and step S33 can calculate the total weight bone scan index by summing all weight bone scan indices.

[0059] In some preferred embodiments, the lesion volume information is the product of the total number of pixels occupied by the lesion region in each slice and the volume per unit pixel; the lesion weight information is the product of the average number of photons per unit volume in the lesion region and the lesion volume information; the bone volume information is the product of the total number of voxels in the bone region and the volume per unit voxel; and the bone weight information is the product of the average linear absorption coefficient of the bone region and the bone volume information. It should be understood that, since the average number of photons per unit volume in the lesion region is affected by the tissue density of the bone metastasis, this embodiment can use the product of the average number of photons per unit volume in the lesion region and the lesion volume information as the lesion weight information. Similarly, since the average linear absorption coefficient is affected by the bone density of the bone region, this embodiment can use the product of the average linear absorption coefficient of the bone region and the bone volume information as the bone weight information. It should also be understood that, since patients are injected with a contrast agent containing a radioactive isotope before SPECT bone scan data is obtained, and the radioactive isotope emits photons during decay, these photons are captured by the SPECT device, this embodiment can use the SPECT device to obtain the total number of photons in a certain area. That is, this embodiment can obtain the average number of photons per unit volume in the lesion area by dividing the total number of photons in a certain area of ​​the lesion area by the volume of that area.

[0060] In some preferred embodiments, the formula for calculating bone volume information is shown in equation (1):

[0061] (1);

[0062] Among them, V bone N represents bone volume information. label V represents the total number of voxels in the skeletal region. voxel Represents the volume of a unit voxel;

[0063] The formula for calculating bone weight information is shown in equation (2):

[0064] (2);

[0065] Among them, W bone HU represents the weight and volume information of the skeletal region. bone This represents the average linear absorption coefficient of the corresponding skeletal region.

[0066] This embodiment can also first calculate the product of each voxel in the skeletal region and its corresponding linear absorption coefficient to obtain the weight of each voxel in the skeletal region, and then sum the weights of all voxels to obtain the bone weight information.

[0067] In some preferred embodiments, the formula for calculating the total index of volumetric bone scan is shown in equation (3):

[0068] (3);

[0069] Among them, VSBI 总 VSBI represents the total index of bone scan volume, n represents the total number of bone metastases, and VSBI represents the total index of bone scan volume. i This represents the volumetric bone scan index corresponding to the i-th bone metastasis lesion;

[0070] The formula for calculating the volume bone scan index is shown in equation (4):

[0071] (4);

[0072] Among them, V lessioni V represents the lesion volume information of the lesion region corresponding to the i-th bone metastasis lesion. totalbonei This represents the bone volume information of the bone region corresponding to the i-th bone metastasis lesion. V in this embodiment... totalbonei V represents the bone region corresponding to the i-th bone metastasis lesion. bone .

[0073] In some preferred embodiments, the formula for calculating the total index of weight bone scan is shown in equation (5):

[0074] (5);

[0075] Among them, WSBI 总 WSBI represents the total weight bone scan index, where n represents the total number of bone metastases. i This represents the weight bone scan index corresponding to the i-th bone metastasis lesion;

[0076] The formula for calculating the weight bone scan index is shown in equation (6):

[0077] (6);

[0078] Among them, W lessioni W represents the weight information of the lesion region corresponding to the i-th bone metastasis lesion. totalbonei This represents the bone weight information of the bone region corresponding to the i-th bone metastasis lesion. W in this embodiment... totalbonei W is the bone region corresponding to the i-th bone metastasis lesion. bone .

[0079] In some preferred embodiments, step S2 includes:

[0080] S21. Perform bone segmentation on CT tomographic data based on the pre-trained first segmentation network to obtain multiple bone segmentation results;

[0081] S22. Convert all bone segmentation results to SPECT space to obtain multiple bone regions.

[0082] The first segmentation network in this embodiment is preferably the existing open-source segmentation algorithm nnUNet. This first segmentation network can perform bone segmentation on CT tomographic data to accurately divide the bones in the CT tomographic data into regions. The difference between the bone segmentation result and the bone region in this embodiment is that the two have different resolutions.

[0083] In some preferred embodiments, step S22 includes:

[0084] S221. Based on the registration algorithm and CT data resampling technology, all bone segmentation results are converted to SPECT space to obtain multiple bone regions.

[0085] The registration algorithm of this embodiment can align data in CT space with SPECT space, and the CT data resampling technology of this embodiment can adjust the resolution of bone segmentation results to match SPECT space.

[0086] In some preferred embodiments, step S1 includes:

[0087] S11. Based on the pre-trained second segmentation network, the SPECT tomographic bone scan data is segmented into lesions to obtain several lesion regions.

[0088] The second segmentation network in this embodiment is preferably the existing open-source segmentation algorithm nnUNet. The difference between the second segmentation network in this embodiment and the first segmentation network in the above embodiment lies in their different network parameters. Since this embodiment obtains several lesion regions by segmenting SPECT tomographic bone scan data based on a pre-trained second segmentation network, it can effectively avoid the high labor intensity and low calculation efficiency of bone scan index caused by manually segmenting SPECT tomographic bone scan data.

[0089] As can be seen from the above, the three-dimensional bone scan total index calculation method provided in this application can obtain the lesion area of ​​bone metastasis by segmenting the lesion in SPECT tomographic bone scan data, and obtain multiple bone regions by segmenting the bone in CT tomographic data and SPECT spatial transformation. Since CT tomographic data can clearly display the bone structure, this application can accurately divide the bone region by segmenting the bone in CT tomographic data. That is, compared with dividing the bone region according to SPECT planar images, this application can effectively improve the bone region segmentation accuracy, thereby effectively solving the problem of low accuracy in obtaining the total area of ​​the bone region to which the lesion belongs due to insufficient bone region segmentation accuracy, and thus effectively improving the accuracy of bone scan index. Moreover, the three-dimensional bone scan total index calculation method of this application can be applied to SPECT planar images and SPECT three-dimensional images.

[0090] Please refer to Figure 2, which is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. This application provides an electronic device including: a processor 101 and a memory 102. The processor 101 and the memory 102 are interconnected and communicate with each other through a communication bus 103 and / or other forms of connection mechanism (not shown). The memory 102 stores computer-readable instructions executable by the processor 101. When the electronic device is running, the processor 101 executes the computer-readable instructions to execute the method in any optional implementation of the above embodiments to achieve the following functions: Step S1: Segment the SPECT tomographic bone scan data to obtain several lesion regions, each lesion region corresponding to a bone metastasis lesion; Step S2: Segment the CT tomographic data into bones and perform SPECT spatial transformation to obtain multiple bone regions; Step S3: Calculate the three-dimensional bone scan index of each bone metastasis lesion according to the proportional relationship between the lesion region and the bone region to which the lesion region belongs, and then calculate the total three-dimensional bone scan index based on all three-dimensional bone scan indices.

[0091] This application embodiment also provides a computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it performs the method in any optional implementation of the above embodiments to achieve the following functions: Step S1, segmenting the SPECT tomographic bone scan data to obtain several lesion regions, each lesion region corresponding to a bone metastasis lesion; Step S2, segmenting the CT tomographic data into bones and performing SPECT spatial transformation to obtain multiple bone regions; Step S3, calculating the three-dimensional bone scan index of each bone metastasis lesion based on the proportional relationship between the lesion region and the bone region to which the lesion region belongs, and then calculating the total three-dimensional bone scan index based on all three-dimensional bone scan indices. The computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0092] As can be seen from the above, the three-dimensional bone scan total index calculation method, electronic device, and storage medium provided in this application can obtain the lesion area of ​​bone metastasis by segmenting the lesion in SPECT tomographic bone scan data, and obtain multiple bone regions by segmenting the bone in CT tomographic data and SPECT spatial transformation. Since CT tomographic data can clearly display the bone structure, this application can accurately divide the bone region by segmenting the bone in CT tomographic data. That is, compared with dividing the bone region according to SPECT planar images, this application can effectively improve the bone region segmentation accuracy, thereby effectively solving the problem of low accuracy in obtaining the total area of ​​the bone region to which the lesion belongs due to insufficient bone region segmentation accuracy, and thus effectively improving the accuracy of bone scan index. Moreover, the three-dimensional bone scan total index calculation method of this application can be applied to SPECT planar images and SPECT three-dimensional images.

[0093] In the embodiments provided in this application, it should be understood that relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0094] The above description is merely an embodiment of this application and is not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for calculating the total index of a three-dimensional bone scan, characterized in that, The method for calculating the total index of three-dimensional bone scan includes the following steps: S1. The SPECT tomographic bone scan data is segmented to obtain several lesion regions, each of which corresponds to a bone metastasis lesion; S2. Perform bone segmentation and SPECT spatial transformation on CT tomographic data to obtain multiple bone regions; S3. Calculate the three-dimensional bone scan index of each bone metastasis lesion based on the ratio between the lesion area and the bone region to which the lesion area belongs, and then calculate the total three-dimensional bone scan index based on all the three-dimensional bone scan indices.

2. The method for calculating the total index of three-dimensional bone scans according to claim 1, characterized in that, The proportional relationship includes volume ratio and weight ratio, and the total index of the three-dimensional bone scan includes the total index of volume bone scan and the total index of weight bone scan. Step S3 includes: S31. Obtain the lesion volume information and lesion weight information of each bone metastasis lesion according to the lesion area, and obtain the bone volume information and bone weight information corresponding to each bone area. S32. Calculate the volume bone scan index of each bone metastasis lesion based on the lesion volume information and the bone volume information, and calculate the total volume bone scan index based on all the volume bone scan indices. The volume bone scan index is the ratio of the lesion volume information corresponding to the lesion area to the bone volume information corresponding to the bone area to which the lesion area belongs. S33. Calculate the weight bone scan index of each bone metastasis lesion based on the lesion weight information and the bone weight information, and calculate the total weight bone scan index based on all the weight bone scan indices. The weight bone scan index is the ratio of the lesion weight information corresponding to the lesion area to the bone weight information corresponding to the bone area to which the lesion area belongs.

3. The method for calculating the total index of three-dimensional bone scans according to claim 2, characterized in that, The lesion volume information is the product of the total number of pixels occupied by the lesion region in each slice and the volume per unit pixel. The lesion weight information is the product of the average number of photons per unit volume in the lesion region and the lesion volume information. The bone volume information is the product of the total number of voxels in the bone region and the volume per unit voxel. The bone weight information is the product of the average linear absorption coefficient of the bone region and the bone volume information.

4. The method for calculating the total index of three-dimensional bone scans according to claim 3, characterized in that, The formula for calculating the bone volume information is as follows: ； Among them, V bone N represents bone volume information. label V represents the total number of voxels in the skeletal region. voxel Represents the volume of a unit voxel; The formula for calculating the bone weight information is as follows: ； Among them, W bone HU represents the weight and volume information of the skeletal region. bone This represents the average linear absorption coefficient of the corresponding skeletal region.

5. The method for calculating the total index of three-dimensional bone scans according to claim 2, characterized in that, The formula for calculating the total index of the volumetric bone scan is as follows: ； Among them, VSBI 总 VSBI represents the total index of bone scan volume, n represents the total number of bone metastases, and VSBI represents the total index of bone scan volume. i This represents the volumetric bone scan index corresponding to the i-th bone metastasis lesion; The formula for calculating the volume bone scan index is as follows: ； Among them, V lessioni V represents the lesion volume information of the lesion region corresponding to the i-th bone metastasis lesion. totalbonei This represents the bone volume information of the bone region corresponding to the i-th bone metastasis lesion.

6. The method for calculating the total index of three-dimensional bone scans according to claim 2, characterized in that, The formula for calculating the total index of the weight bone scan is as follows: ； Among them, WSBI 总 WSBI represents the total weight bone scan index, where n represents the total number of bone metastases. i This represents the weight bone scan index corresponding to the i-th bone metastasis lesion; The formula for calculating the weight bone scan index is as follows: ； Among them, W lessioni W represents the weight information of the lesion region corresponding to the i-th bone metastasis lesion. totalbonei This represents the bone weight information of the bone region corresponding to the i-th bone metastasis lesion.

7. The method for calculating the total index of three-dimensional bone scans according to claim 5, characterized in that, Step S2 includes: S21. Perform bone segmentation on CT tomographic data based on the pre-trained first segmentation network to obtain multiple bone segmentation results; S22. Convert all the bone segmentation results to SPECT space to obtain multiple bone regions.

8. The method for calculating the total index of three-dimensional bone scans according to claim 1, characterized in that, Step S1 includes: S11. Based on the pre-trained second segmentation network, several lesion regions are obtained from the SPECT tomographic bone scan data.

9. An electronic device, characterized in that, It includes a processor and a memory, the memory storing computer-readable instructions that, when executed by the processor, perform the steps of the method as described in any one of claims 1-8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it performs the steps of the method as described in any one of claims 1-8.

Images