SPECT bone scanning image restoration method, electronic equipment and storage medium

Abstract

The invention relates to the technical field of medical image processing, and particularly provides an SPECT bone scanning image restoration method, electronic equipment and a storage medium, and the method comprises the steps: S1, carrying out the skeleton segmentation of an SPECT bone scanning image, so as to obtain a plurality of skeleton regions; s2, segmenting the SPECT bone scanning image in each bone region into a first foreground and a first background, and then obtaining first foreground feature value information according to the first foreground; s3, according to the first foreground feature value information and a preset feature value of the corresponding skeleton region, analyzing whether there is an artifact in the skeleton region; s4, when artifacts exist in the bone area, acquiring a supplementary scanning image, and repairing the SPECT bone scanning image based on the supplementary scanning image; according to the method, the imaging quality of the SPECT bone scanning image and the diagnosis accuracy of the bone metastasis cancer can be effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of medical image processing, and in particular to a SPECT bone scan image repair method, electronic equipment and storage medium. Background Art

[0002] SPECT (Single Photon Emission Computed Tomography) technology is a commonly used imaging technology for diagnosing bone metastasis cancer. The related technology obtains SPECT bone scan images by scanning patients with SPECT equipment. If improper operation, patient movement, or urine spillage occurs during the scanning process, artifacts may exist in the final SPECT bone scan image, which will affect the imaging quality of the SPECT bone scan image and the diagnosis of bone metastasis cancer, thereby reducing the imaging quality of the SPECT bone scan image and the diagnostic accuracy of bone metastasis cancer.

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

[0004] The purpose of the present application is to provide a SPECT bone scan image repair method, electronic device and storage medium, which can effectively improve the imaging quality of SPECT bone scan images and the diagnostic accuracy of bone metastasis cancer.

[0005] In a first aspect, the present application provides a SPECT bone scan image repair method, which comprises the following steps: S1, performing bone segmentation on the SPECT bone scan image to obtain multiple bone regions; S2, segmenting the SPECT bone scan image in each bone region into a first foreground and a first background, and then acquiring first foreground feature value information according to the first foreground; S3, analyzing whether there is an artifact in the bone region according to the first foreground feature value information and the preset feature value of the corresponding bone region; S4. When artifacts exist in the bone region, a supplementary scan image is acquired, and the SPECT bone scan image is repaired based on the supplementary scan image.

[0006] The present application provides a SPECT bone scan image repair method, which can automatically analyze whether there are artifacts in the bone area based on the SPECT bone scan image, and use the supplementary scan image to repair the SPECT bone scan image when there are artifacts in the bone area. That is, the present application can eliminate artifacts in the bone area. Therefore, the present application can effectively improve the imaging quality of SPECT bone scan images and the diagnostic accuracy of bone metastasis cancer.

[0007] Optionally, the first foreground feature value information includes the actual pixel value sum and the actual maximum pixel value, the preset feature value includes the preset pixel value sum and the preset maximum pixel value, and step S3 includes: S31, if the actual maximum pixel value is greater than the preset maximum pixel value and / or the sum of the actual pixel values ​​is greater than the sum of the preset pixel values, it is considered that there is an artifact in the bone region; S32: If the actual maximum pixel value is less than or equal to the preset maximum pixel value and the total of the actual pixel values ​​is less than or equal to the total of the preset pixel values, it is considered that there is no artifact in the bone region.

[0008] Optionally, the SPECT bone scan image restoration method further includes the following steps performed after step S1 and before step S3: S5. Obtain preset feature values ​​of each bone region according to the type of the bone region and the preset conversion relationship.

[0009] Optionally, step S4 includes: S41, when there is an artifact in the bone region, obtaining a supplementary scan image of the bone region to which the artifact belongs; S42, aligning the bone region in the supplementary scan image with the corresponding bone region in the SPECT bone scan image; S43. Use the supplementary scan image to replace the SPECT bone scan image in the artifact.

[0010] Optionally, step S4 further includes the following steps performed between step S41 and step S42: S44, dividing the supplementary scanned image into a second foreground and a second background, and then acquiring feature information of the second foreground; S45, analyzing whether there are artifacts in the supplementary scanned image according to the second foreground feature information and the preset feature value, if not, executing step S42.

[0011] Since this technical solution will perform image alignment and image replacement only when it is analyzed that there are no artifacts in the supplementary scan image, this technical solution can effectively avoid the situation where the artifacts in the bone area of ​​the SPECT bone scan image cannot be repaired by image alignment and image replacement due to the presence of artifacts in the supplementary scan image.

[0012] Optionally, step S4 includes: S41', when there are artifacts in the skeleton region, generate prompt information, and then obtain a supplementary scan image of the artifact region in the skeleton region manually determined based on the prompt information; S42', after manually aligning the supplementary scan image with the corresponding artifact region in the SPECT bone scan image, the SPECT bone scan image in the artifact region is replaced with the supplementary scan image.

[0013] Optionally, the patient adopts a standard body position when obtaining both the SPECT bone scan image and the supplemental scan image.

[0014] Since the patient in this technical solution adopts a standard body position when obtaining the SPECT bone scan image and the supplementary scan image, this technical solution can effectively avoid the situation where the supplementary scan image and the SPECT bone scan image where the artifact is located cannot correspond due to the inconsistent body position of the patient when obtaining the SPECT bone scan image and the supplementary scan image, making it difficult to repair the artifact in the bone area based on the supplementary scan image.

[0015] Optionally, step S2 includes: S21, obtaining the minimum bounding rectangle of the skeleton area; S22, segmenting the minimum circumscribed rectangle based on the OTSU segmentation algorithm to segment the SPECT bone scan image in the bone region into a first foreground and a first background; S23. Obtain first foreground feature value information according to the first foreground.

[0016] In a second aspect, the present application provides an electronic device, including a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the method provided in the first aspect are performed.

[0017] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the method provided in the first aspect are performed.

[0018] From the above, it can be seen that the SPECT bone scan image repair method, electronic device and storage medium provided by the present application can automatically analyze whether there are artifacts in the bone area based on the SPECT bone scan image, and use the supplementary scan image to repair the SPECT bone scan image when there are artifacts in the bone area. That is, the present application can eliminate artifacts in the bone area. Therefore, the present application can effectively improve the imaging quality of SPECT bone scan images and the diagnostic accuracy of bone metastasis cancer. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flowchart of a SPECT bone scan image repair method provided in an embodiment of the present application.

[0020] Figure 2 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0021] Reference numerals: 101, processor; 102, memory; 103, communication bus. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0023] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0024] First, as Figure 1 As shown, the present application provides a SPECT bone scan image repair method, which includes the following steps: S1, performing bone segmentation on the SPECT bone scan image to obtain multiple bone regions; S2, segmenting the SPECT bone scan image in each bone region into a first foreground and a first background, and then acquiring first foreground feature value information according to the first foreground; S3, analyzing whether there is an artifact in the bone region according to the first foreground feature value information and the preset feature value of the corresponding bone region; S4. When artifacts exist in the bone region, a supplementary scan image is acquired, and the SPECT bone scan image is repaired based on the supplementary scan image.

[0025] The SPECT bone scan image of step S1 is preferably an image obtained by scanning a patient using a SPECT device. Step S1 can use a pre-trained bone segmentation model to perform bone segmentation on the bone scan image. The architecture of the bone segmentation model is preferably nnUNet.

[0026] Step S2 can use the existing image segmentation algorithm or image segmentation model to segment the SPECT bone scan image in the bone region into a first foreground and a first background. After segmenting the SPECT bone scan image in the bone region, the artifact can be unified with the bone region as the first foreground, that is, this embodiment is equivalent to merging the artifact with the bone region by segmenting the SPECT bone scan image. After completing the segmentation of the first foreground and the second foreground, step S2 can obtain the first foreground feature value information by means of data statistics. The first foreground feature value information is the feature value of the first foreground, and each bone region corresponds to a first foreground feature value information. It should be understood that since the SPECT bone scan image of this embodiment is used for the diagnosis of bone metastasis lesions, and the bone metastasis lesions grow on the bones, that is, only the artifacts located in the bone region will affect the diagnosis of the bone metastasis lesions, so this embodiment only needs to pay attention to whether there are artifacts in the bone region, and step S2 only needs to segment the SPECT bone scan image in the bone region, and there is no need to segment the SPECT bone scan image outside the bone region.

[0027] The preset characteristic value of step S3 is equivalent to the ideal characteristic value of the first foreground corresponding to the skeleton area. Since the characteristic value of the artifact is greater than the characteristic value of the non-artifact, step S2 can unify the artifact and the skeleton area as the first foreground and obtain the characteristic value of the first foreground, that is, when there is an artifact in the skeleton area, the artifact will cause the first foreground characteristic value information corresponding to the skeleton area to which it belongs to increase. Therefore, if there is an artifact in the skeleton area, the first foreground characteristic value information corresponding to the skeleton area will be greater than the preset characteristic value. If there is no artifact in the skeleton area, the first foreground characteristic value information corresponding to the skeleton area will be less than or equal to the preset characteristic value. That is, step S3 can analyze whether there is an artifact in the skeleton area by analyzing whether the first foreground characteristic value information is greater than or equal to the preset characteristic value. Since different bone regions usually present different colors in the SPECT bone scan image (for example, the color of the bone region corresponding to the calf is dark green, and the color of the bone region corresponding to the rib is gray or red), there are differences in the sum of pixel values ​​and the maximum pixel value corresponding to different bone regions, that is, even if there are no artifacts in all bone regions, the first foreground feature value information corresponding to different bone regions is different. Since this embodiment analyzes whether there are artifacts in the bone region according to the first foreground feature value information and the preset feature value of the corresponding bone region, this embodiment is equivalent to using the judgment standard corresponding to the bone region to analyze whether there are artifacts in the bone region, thereby effectively avoiding the situation where the bone region with artifacts is misjudged as not having artifacts and the misjudged artifacts are not repaired due to the use of the same judgment standard for artifact analysis, thereby effectively improving the imaging quality of the SPECT bone scan image and the diagnostic accuracy of bone metastasis cancer. It should be understood that the coverage range of the artifact in this embodiment is less than or equal to the coverage range of the bone region to which the artifact belongs.

[0028] When it is analyzed that there are artifacts in the bone area, step S4 can obtain a supplementary scan image by performing a supplementary scan on the patient using the SPECT device. Since improper operation, patient movement, and urine spillage can be avoided in the process of obtaining the supplementary scan image, that is, step S4 can obtain a supplementary scan image without artifacts, so step S4 can repair the SPECT bone scan image based on the supplementary scan image, that is, the supplementary scan image of step S4 is equivalent to the reference image used when repairing the SPECT bone scan image. It should be understood that when it is analyzed that there are no artifacts in the bone area, the present application does not need to repair the SPECT bone scan image, that is, when it is analyzed that there are no artifacts in the bone area, the SPECT bone scan image repair method provided by the present application ends.

[0029] The present application provides a SPECT bone scan image repair method, which can automatically analyze whether there are artifacts in the bone area based on the SPECT bone scan image, and use the supplementary scan image to repair the SPECT bone scan image when there are artifacts in the bone area. That is, the present application can eliminate artifacts in the bone area. Therefore, the present application can effectively improve the imaging quality of SPECT bone scan images and the diagnostic accuracy of bone metastasis cancer.

[0030] In some preferred embodiments, the first foreground feature value information includes the actual pixel value sum and the actual maximum pixel value, the preset feature value includes the preset pixel value sum and the preset maximum pixel value, and step S3 includes: S31, if the actual maximum pixel value is greater than the preset maximum pixel value and / or the sum of the actual pixel values ​​is greater than the sum of the preset pixel values, it is considered that there is an artifact in the bone region; S32: If the actual maximum pixel value is less than or equal to the preset maximum pixel value and the total of the actual pixel values ​​is less than or equal to the total of the preset pixel values, it is considered that there is no artifact in the bone region.

[0031] The sum of the actual pixel values ​​of this embodiment is the sum of all pixel values ​​in the first foreground corresponding to the skeleton area. The actual maximum pixel value of this embodiment is the maximum value of all pixel values ​​in the first foreground corresponding to the skeleton area. Since artifacts will cause the pixel values ​​of pixels in the artifacts to increase, that is, when there are artifacts in the skeleton area, the sum of the pixel values ​​in the first foreground where the artifacts are located will increase, and the pixel value of a certain pixel in the first foreground may be too large. Therefore, when the actual maximum pixel value is greater than the preset maximum pixel value and / or the sum of the actual pixel values ​​is greater than the preset sum of the pixel values, this embodiment can consider that there are artifacts in the skeleton area. When the actual maximum pixel value is less than or equal to the preset maximum pixel value and the sum of the actual pixel values ​​is less than or equal to the preset sum of the pixel values, this embodiment can consider that there are no artifacts in the skeleton area.

[0032] In some preferred embodiments, the SPECT bone scan image restoration method further includes the following steps performed after step S1 and before step S3: S5. Obtain preset feature values ​​of each bone region according to the type of the bone region and the preset conversion relationship.

[0033] The preset conversion relationship of this embodiment is a mapping relationship table between the bone region type and the characteristic value. This embodiment can extract the corresponding preset characteristic value from the preset conversion relationship according to the type of the bone region by means of data extraction.

[0034] In some preferred embodiments, step S4 comprises: S41, when there is an artifact in the bone region, obtaining a supplementary scan image of the bone region to which the artifact belongs; S42, aligning the bone region in the supplementary scan image with the corresponding bone region in the SPECT bone scan image; S43. Use the supplementary scan image to replace the SPECT bone scan image in the artifact.

[0035] Step S41 can obtain a supplementary scan image of the area where the artifact is located by using a SPECT scanner to perform a supplementary scan on only the area corresponding to the artifact in the patient's body. Step S41 can also obtain a supplementary scan image of the area where the artifact is located by using a SPECT scanner to perform a supplementary scan on the bone area to which the artifact belongs. Step S42 can align the area corresponding to the artifact in the supplementary scan image with the corresponding artifact in the SPECT bone scan image by manually adjusting the image size, manually translating, and determining by human eye vision. Step S42 can also align the area corresponding to the artifact in the supplementary scan image with the corresponding artifact in the SPECT bone scan image using existing image registration technology. Step S43 can replace the SPECT bone scan image in the artifact with the supplementary scan image using an existing image fusion algorithm or image stitching algorithm.

[0036] In some preferred embodiments, step S4 comprises: S41', when there are artifacts in the skeleton region, generate prompt information, and then obtain a supplementary scan image of the artifact region in the skeleton region manually determined based on the prompt information; S42', after manually aligning the supplementary scan image with the corresponding artifact region in the SPECT bone scan image, the SPECT bone scan image in the artifact region is replaced with the supplementary scan image.

[0037] The prompt information of step S41' is used to remind the medical staff that there are artifacts in the bone area. After receiving the prompt information, the medical staff first manually determines the artifact area in the bone area based on the SPECT bone scan image. The artifact area is the area where the artifacts in the bone area are located, and then uses the SPECT scanner to perform a supplementary scan on the area in the patient's body corresponding to the artifact area to obtain a supplementary scan image of the area where the artifact area is located. It should be understood that since this embodiment only performs a supplementary scan on the area corresponding to the artifact area, and the above embodiment performs a supplementary scan on the bone area to which the artifacts belong, the coverage range of the supplementary scan image of this embodiment is smaller than the coverage range of the supplementary scan image of the above embodiment. The process of step S42' replacing the SPECT bone scan image in the artifact area with the supplementary scan image is preferably similar to step S43. Preferably, the process of replacing the SPECT bone scan image in the artifact area with the supplementary scan image in step S42' is: replacing the artifact area with the supplementary scan image by image mean normalization based on an adaptive fusion algorithm, so that the average brightness value of the supplementary scan image is the same as the average brightness value of the non-artifact area in the corresponding bone area in the SPECT bone scan image. Since this embodiment can make the average brightness value of the supplementary scan image the same as the average brightness value of the non-artifact area in the corresponding bone area in the SPECT bone scan image, that is, this embodiment is equivalent to making the brightness of the bone area consistent with the brightness of the non-artifact after image replacement, this embodiment can effectively avoid the situation of subjective visual inconsistency caused by the brightness of the area where the artifact is located being inconsistent with the brightness of the non-artifact after image replacement.

[0038] In some preferred embodiments, step S4 further includes the following steps performed between step S41 and step S42: S44, dividing the supplementary scanned image into a second foreground and a second background, and then acquiring feature information of the second foreground; S45, analyzing whether there are artifacts in the supplementary scanned image according to the second foreground feature information and the preset feature value, if not, executing step S42.

[0039] Since this embodiment will only perform image alignment and image replacement when it is analyzed that there are no artifacts in the supplementary scan image, this embodiment can effectively avoid the situation where the artifacts in the bone area of ​​the SPECT bone scan image cannot be repaired by image alignment and image replacement due to the presence of artifacts in the supplementary scan image (that is, artifacts still exist in the bone area of ​​the SPECT bone scan image after repair).

[0040] In some preferred embodiments, the patient adopts a standard body position when acquiring the SPECT bone scan image and the supplementary scan image. Specifically, the standard body position of this embodiment is: the patient lies flat, the patient's hands are placed flat on both sides of the body, and the patient's toes are aligned inward. Since the patient of this embodiment adopts a standard body position when acquiring the SPECT bone scan image and the supplementary scan image, this embodiment can effectively avoid the situation where the supplementary scan image cannot correspond to the SPECT bone scan image where the artifact is located due to the inconsistent body position of the patient when acquiring the SPECT bone scan image and the supplementary scan image, and it is difficult to repair the artifact in the bone area based on the supplementary scan image.

[0041] In some preferred embodiments, step S2 comprises: S21, obtaining the minimum bounding rectangle of the skeleton area; S22, segmenting the minimum circumscribed rectangle based on the OTSU segmentation algorithm to segment the SPECT bone scan image in the bone region into a first foreground and a first background; S23. Obtain first foreground feature value information according to the first foreground.

[0042] Step S21 can use the existing minimum bounding rectangle generation method to obtain the minimum bounding rectangle of the skeleton area. The OTSU segmentation algorithm (also known as the maximum inter-class variance method) of step S22 is an existing technology. The OTSU algorithm can adaptively select a threshold and divide the image into foreground and background based on the threshold.

[0043] From the above, it can be seen that the SPECT bone scan image repair method provided by the present application can automatically analyze whether there are artifacts in the bone area based on the SPECT bone scan image, and use the supplementary scan image to repair the SPECT bone scan image when there are artifacts in the bone area. That is, the present application can eliminate artifacts in the bone area. Therefore, the present application can effectively improve the imaging quality of SPECT bone scan images and the diagnostic accuracy of bone metastasis cancer.

[0044] Please refer to Figure 2 , Figure 2The present invention provides a structural schematic diagram of an electronic device provided in an embodiment of the present application. The present 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 mechanisms (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 embodiment to achieve the following functions: step S1, performing bone segmentation on a SPECT bone scan image to obtain multiple bone regions; step S2, segmenting the SPECT bone scan image in each bone region into a first foreground and a first background, and then obtaining first foreground feature value information according to the first foreground; step S3, analyzing whether there is an artifact in the bone region according to the first foreground feature value information and the preset feature value of the corresponding bone region; step S4, when there is an artifact in the bone region, obtaining a supplementary scan image, and repairing the SPECT bone scan image based on the supplementary scan image.

[0045] The embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method in any optional implementation of the above embodiment is executed to achieve the following functions: step S1, performing bone segmentation on the SPECT bone scan image to obtain multiple bone regions; step S2, segmenting the SPECT bone scan image in each bone region into a first foreground and a first background, and then obtaining first foreground feature value information based on the first foreground; step S3, analyzing whether there is an artifact in the bone region based on the first foreground feature value information and a preset feature value of the corresponding bone region; step S4, when there is an artifact in the bone region, obtaining a supplementary scan image, and repairing the SPECT bone scan image based on the supplementary scan image. Among them, 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.

[0046] From the above, it can be seen that the SPECT bone scan image repair method, electronic device and storage medium provided by the present application can automatically analyze whether there are artifacts in the bone area based on the SPECT bone scan image, and use the supplementary scan image to repair the SPECT bone scan image when there are artifacts in the bone area. That is, the present application can eliminate artifacts in the bone area. Therefore, the present application can effectively improve the imaging quality of SPECT bone scan images and the diagnostic accuracy of bone metastasis cancer.

[0047] In the embodiments provided in the present application, it should be understood that, herein, relational terms such as first and second, etc. are merely used 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.

[0048] The above description is only an embodiment of the present application and is not intended to limit the protection scope of the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for repairing a SPECT bone scan image, characterized in that: The SPECT bone scan image repair method comprises the following steps: S1, performing bone segmentation on the SPECT bone scan image to obtain multiple bone regions; S2, segmenting the SPECT bone scan image in each of the bone regions into a first foreground and a first background, and then acquiring first foreground feature value information according to the first foreground; S3, analyzing whether there is an artifact in the bone area according to the first foreground feature value information and a preset feature value corresponding to the bone area; S4. When the artifact exists in the bone region, a supplementary scan image is acquired, and the SPECT bone scan image is repaired based on the supplementary scan image.

2. The SPECT bone scan image restoration method according to claim 1, characterized in that: The first foreground feature value information includes the actual pixel value sum and the actual maximum pixel value, the preset feature value includes the preset pixel value sum and the preset maximum pixel value, and step S3 includes: S31, if the actual maximum pixel value is greater than the preset maximum pixel value and / or the sum of the actual pixel values ​​is greater than the sum of the preset pixel values, it is considered that there is an artifact in the bone region; S32: If the actual maximum pixel value is less than or equal to the preset maximum pixel value and the total of the actual pixel values ​​is less than or equal to the total of the preset pixel values, it is considered that the artifact does not exist in the skeleton area.

3. The SPECT bone scan image restoration method according to claim 1, characterized in that: The SPECT bone scan image repair method further includes the following steps performed after step S1 and before step S3: S5. Obtain preset feature values ​​of each of the skeleton regions according to the type of the skeleton region and the preset conversion relationship.

4. The SPECT bone scan image restoration method according to claim 1, characterized in that: Step S4 includes: S41, when the artifact exists in the bone region, obtaining a supplementary scan image of the bone region to which the artifact belongs; S42, aligning the bone region in the supplementary scan image with the corresponding bone region in the SPECT bone scan image; S43: Use the supplementary scan image to replace the SPECT bone scan image in the bone region.

5. The SPECT bone scan image restoration method according to claim 4, characterized in that: Step S4 also includes the following steps performed between step S41 and step S42: S44, dividing the supplementary scanned image into a second foreground and a second background, and then acquiring feature information of the second foreground; S45. Analyze whether there are artifacts in the supplementary scanned image according to the second foreground feature information and the preset feature value; if not, execute step S42.

6. The SPECT bone scan image restoration method according to claim 1, characterized in that: Step S4 includes: S41', when the artifact exists in the bone region, generating prompt information, and then obtaining a supplementary scan image of the artifact region in the bone region manually determined based on the prompt information; S42', after manually aligning the supplementary scan image with the corresponding artifact region in the SPECT bone scan image, using the supplementary scan image to replace the SPECT bone scan image in the artifact region.

7. The SPECT bone scan image restoration method according to claim 1, characterized in that: The patient adopts a standard body position when acquiring the SPECT bone scan image and the supplementary scan image.

8. The SPECT bone scan image restoration method according to claim 1, characterized in that: Step S2 includes: S21, obtaining the minimum circumscribed rectangle of the skeleton area; S22, segmenting the minimum circumscribed rectangle based on the OTSU segmentation algorithm to segment the SPECT bone scan image in the bone region into a first foreground and a first background; S23: Acquire first foreground feature value information according to the first foreground.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the method according to any one of claims 1 to 8 are executed.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are executed.

Images