Method, device, equipment and storage medium for obtaining spinal scan parameters

Abstract

The present application relates to a method, apparatus, device and storage medium for obtaining spinal scan parameters. The method comprises: obtaining at least two positioning images of the spine to be scanned; performing splicing processing on the at least two positioning images of the spine to be scanned to determine the spliced ​​positioning image of the spine to be scanned; determining the corresponding scanning parameters of the spine to be scanned on the spliced ​​positioning image based on the spliced ​​positioning image of the spine to be scanned; mapping the corresponding scanning parameters of the spine to be scanned on the spliced ​​positioning image to each of the positioning images to determine the spinal scan parameters of the spine to be scanned on each of the positioning images. The use of this method can improve the accuracy of the obtained spinal scan parameters.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a method, apparatus, device and storage medium for acquiring spinal scan parameters. Background Art

[0002] With the continuous development of medical imaging technology, when patients go to the hospital for spinal examination, doctors will mostly ask patients to take medical images. Generally, in order to make the medical images taken more accurate, shorter scanning times are usually used to scan the patients to obtain positioning images of the patient's spine. After that, the doctor can set fine scanning parameters based on the positioning image and rescan the patient's spine using the set scanning parameters to obtain medical images of the patient's spine.

[0003] In related technologies, when setting scanning parameters through positioning images, the corresponding spinal scanning parameters are usually calculated on the captured single-segment spinal positioning image, and then the calculated single-segment spinal scanning parameters are used to rescan the patient's entire spinal area to obtain a medical image of the patient's entire spinal area.

[0004] However, the above technology has the problem that the accuracy of the determined spinal scan parameters is not high. Summary of the Invention

[0005] Based on this, it is necessary to provide a spinal scan parameter acquisition method, apparatus, device and storage medium that can improve the accuracy of determined spinal scan parameters in order to address the above technical problems.

[0006] A method for acquiring spinal scan parameters, the method comprising:

[0007] acquiring at least two positioning images of the spine to be scanned;

[0008] performing splicing processing on the at least two positioning images of the spine to be scanned to determine a spliced ​​positioning image of the spine to be scanned;

[0009] Determining scanning parameters corresponding to the spinal column to be scanned on the spliced ​​positioning image according to the spliced ​​positioning image of the spinal column to be scanned;

[0010] The scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image are mapped to each of the positioning images to determine the spine scanning parameters of the spine to be scanned on each of the positioning images.

[0011] In one embodiment, the determining of the scanning parameters corresponding to the spinal column to be scanned on the spliced ​​positioning image of the spinal column to be scanned includes:

[0012] Inputting the stitched positioning image of the spine to be scanned into a preset segmentation model for segmentation processing, and determining a segmentation result of the spine to be scanned on the stitched positioning image;

[0013] According to the segmentation result of the spine to be scanned on the spliced ​​positioning image, the corresponding scanning parameters of the spine to be scanned on the spliced ​​positioning image are determined.

[0014] In one embodiment, the determining of the corresponding scanning parameters of the spine to be scanned on the stitched positioning image based on the segmentation result of the spine to be scanned on the stitched positioning image includes:

[0015] Inputting the stitched positioning image of the spine to be scanned into a preset label marking model to determine the labels of each vertebra on the spine to be scanned in the stitched positioning image;

[0016] The scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image are determined according to the segmentation result of the spine to be scanned on the spliced ​​positioning image and the labels of the vertebrae on the spine to be scanned in the spliced ​​positioning image.

[0017] In one embodiment, determining the corresponding scanning parameters of the spine to be scanned on the stitched positioning image based on the segmentation result of the spine to be scanned on the stitched positioning image and the labels of each vertebra on the spine to be scanned in the stitched positioning image includes:

[0018] Determining the position information of the first key point of each vertebra based on the segmentation result of the spine to be scanned in the stitched positioning image and the label of each vertebra on the spine to be scanned in the stitched positioning image;

[0019] The scanning parameters corresponding to the spinal column to be scanned on the spliced ​​positioning image are determined according to the position information of the first key points of each vertebra.

[0020] In one embodiment, determining the corresponding scanning parameters of the spinal column to be scanned on the stitched positioning image based on the position information of the first key point of each vertebral body includes:

[0021] Performing surface or plane fitting processing on the position information of the first key point of each vertebra, and determining the fitted surface or plane as the coronal image or sagittal image corresponding to the spine to be scanned;

[0022] Acquiring position information of a second key point of each vertebra on the spinal column to be scanned on the coronal image or the sagittal image;

[0023] Performing curve or line fitting processing on the position information of the second key point of each vertebra on the spine to be scanned, and determining the direction perpendicular to the fitted curve or line as the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the spine to be scanned;

[0024] The scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image are determined according to the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the spine to be scanned.

[0025] In one embodiment, determining the scanning parameters corresponding to the spine to be scanned on the stitched positioning image according to the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the spine to be scanned includes:

[0026] Obtaining position information of a third key point of the curve or line obtained by fitting, and determining the position information of the third key point of the curve or line as a scanning position corresponding to the spine to be scanned;

[0027] The scanning position corresponding to the spine to be scanned and the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the spine to be scanned are determined as the scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image.

[0028] In one embodiment, mapping the scanning parameters corresponding to the spine to be scanned on the stitched positioning image to each of the positioning images to determine the spine scanning parameters of the spine to be scanned on each of the positioning images includes:

[0029] Mapping the labels of each vertebra on the spine to be scanned in the stitched positioning image onto each of the positioning images to obtain the labels of each vertebra on each of the positioning images;

[0030] Determining a segmentation result of the spine to be scanned on each of the positioning images according to the positioning images and the segmentation model;

[0031] The scanning parameters corresponding to the spine to be scanned on each of the positioning images are determined based on the segmentation results of the spine to be scanned on each of the positioning images and the labels of the vertebrae on each of the positioning images.

[0032] In one embodiment, mapping the scanning parameters corresponding to the spine to be scanned on the stitched positioning image to each of the positioning images to determine the spine scanning parameters of the spine to be scanned on each of the positioning images further includes:

[0033] Calculating the segmentation results of each vertebral disc on the spinal column to be scanned in the stitched positioning image, and mapping the segmentation results of each vertebral disc to each of the positioning images; the segmentation results of each vertebral disc include the position and label of each vertebral disc;

[0034] Performing principal component analysis on the segmentation results of the mapped vertebral discs, and determining the main direction of each vertebral disc obtained as the scanning direction of the transverse image corresponding to the spine to be scanned;

[0035] The position of the fourth key point of each vertebral disc is determined according to the segmentation result after mapping of each vertebral disc, and the position information of the fourth key point is determined as the scanning position corresponding to the spinal column to be scanned.

[0036] A device for acquiring spinal scan parameters, comprising:

[0037] an acquisition module, configured to acquire at least two positioning images of the spine to be scanned;

[0038] a splicing module, configured to splice the at least two positioning images of the spine to be scanned to determine a spliced ​​positioning image of the spine to be scanned;

[0039] A splicing scanning parameter determination module, configured to determine the corresponding scanning parameters of the spine to be scanned on the splicing positioning image according to the splicing positioning image of the spine to be scanned;

[0040] The single-segment scanning parameter determination module is used to map the scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image to each of the positioning images, and determine the spine scanning parameters of the spine to be scanned on each of the positioning images.

[0041] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0042] acquiring at least two positioning images of the spine to be scanned;

[0043] performing splicing processing on the at least two positioning images of the spine to be scanned to determine a spliced ​​positioning image of the spine to be scanned;

[0044] Determining scanning parameters corresponding to the spinal column to be scanned on the spliced ​​positioning image according to the spliced ​​positioning image of the spinal column to be scanned;

[0045] The scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image are mapped to each of the positioning images to determine the spine scanning parameters of the spine to be scanned on each of the positioning images.

[0046] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0047] acquiring at least two positioning images of the spine to be scanned;

[0048] performing splicing processing on the at least two positioning images of the spine to be scanned to determine a spliced ​​positioning image of the spine to be scanned;

[0049] Determining scanning parameters corresponding to the spinal column to be scanned on the spliced ​​positioning image according to the spliced ​​positioning image of the spinal column to be scanned;

[0050] The scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image are mapped to each of the positioning images to determine the spine scanning parameters of the spine to be scanned on each of the positioning images.

[0051] The above-mentioned spinal scan parameter acquisition method, apparatus, device, and storage medium splice at least two acquired positioning images of the spine to be scanned to determine a spliced ​​positioning image of the spine to be scanned, determine the scanning parameters of the spine to be scanned on the spliced ​​positioning image based on the spliced ​​positioning image, and map the scanning parameters on the spliced ​​positioning image to each positioning image to determine the spinal scan parameters of the spine to be scanned on each positioning image. In this method, since the overall scanning parameters of the spine to be scanned can be determined by the spliced ​​positioning image obtained by splicing multiple positioning images, the image information of the multiple positioning images can be effectively utilized to calculate the parameters of the entire spine to be scanned. The overall scanning parameters can then be mapped to each single-segment positioning image for accurate calculation to determine the spinal scan parameters on the single-segment image, thereby improving the accuracy of the scanning parameters determined for the single-segment positioning image. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a diagram of the internal structure of a computer device in one embodiment;

[0053] Figure 2 1 is a flow chart of a method for acquiring spinal scan parameters in one embodiment;

[0054] Figure 3 A schematic flow chart of the steps for obtaining spinal scan parameters in another embodiment;

[0055] Figure 4 is a flowchart of a method for acquiring spinal scan parameters in another embodiment;

[0056] Figure 5 is a flowchart of a method for acquiring spinal scan parameters in another embodiment;

[0057] Figure 6FIG. 1 is a structural block diagram of a device for acquiring spinal scan parameters in an embodiment. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0059] The spine scanning parameter acquisition method provided in the embodiment of the present application can be applied to a computer device, which can be a terminal. The internal structure diagram thereof can be as shown in FIG. Figure 1 As shown. The computer device includes a processor, memory, communication interface, display screen and input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for obtaining spinal scanning parameters is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0060] Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0061] It should be noted that the execution subject of the embodiment of the present application can be a spinal scanning parameter acquisition device or a computer device. The following describes the solution of the embodiment of the present application in detail with the computer device as the execution subject.

[0062] In one embodiment, a method for obtaining spinal column scanning parameters is provided. This embodiment relates to a specific process of obtaining spinal column scanning parameters of a single segment positioning image using the spinal column scanning parameters of multiple positioning images. Figure 2 As shown, the method may include the following steps:

[0063] S202: Acquire at least two positioning images of the spine to be scanned.

[0064] The spine to be scanned refers to the spine of the subject, which may be a human or animal, living or non-living. The spine to be scanned may be a single part of the subject's spine, multiple parts of the spine, or all parts of the subject's spine.

[0065] In addition, the positioning image of the spine to be scanned refers to an image obtained by quickly scanning the spine to be scanned in a short time using a scanning device and reconstructing the data obtained by the quick scan.

[0066] Specifically, the at least two positioning images of the spine to be scanned herein refer to the situation where, when scanning the spine to be scanned, the field of view of the positioning image of a single scan cannot cover a large area of ​​the spine to be scanned. Therefore, multiple scans of the spine with overlapping areas are performed, thereby obtaining at least two positioning images of the spine to be scanned. Each positioning image herein can be considered to be obtained by scanning a single segment of the spine.

[0067] S204: performing splicing processing on the at least two positioning images of the spine to be scanned to determine a spliced ​​positioning image of the spine to be scanned.

[0068] Specifically, after obtaining at least two positioning images of the spine to be scanned, typically multiple positioning images, the order in which these positioning images were obtained, as well as the position and size of the overlapping region between each two adjacent positioning images, are also typically determined. Subsequently, the positioning images can be stitched together in the order in which they were obtained based on the position and size of the overlapping region between each two adjacent positioning images, resulting in a stitched image, which is recorded as the stitched positioning image of the spine to be scanned.

[0069] Among them, when obtaining the position and size of the overlapping area between each two adjacent positioning images, the positioning images can be arranged according to the acquisition order of each positioning image and the position coordinates of each positioning image, and the overlapping area between each two adjacent positioning images can be determined. The overlapping area between the two positioning images is interpolated to obtain the image in the overlapping area as well as the position and size of the overlapping area.

[0070] S206 , determining scanning parameters corresponding to the spinal column to be scanned on the spliced ​​positioning image according to the spliced ​​positioning image of the spinal column to be scanned.

[0071] The scanning parameters of the spine to be scanned may include the scanning direction, scanning position, scanning orientation, etc. of the spine.

[0072] In this step, the stitched positioning image can be directly processed using a pre-trained scanning parameter model to obtain the scanning parameters of the spine to be scanned on the stitched positioning image. The scanning parameter model can be trained based on multiple spine training stitched images and the annotated scanning parameters corresponding to each spine training stitched image.

[0073] Of course, the scanning parameters of the spine to be scanned on the spliced ​​positioning image can also be obtained by segmenting the spine in the spliced ​​positioning image and performing scanning parameter analysis and calculation on the obtained spine segmentation result.

[0074] Of course, it is also possible to obtain the scanning parameters of the spine to be scanned on the spliced ​​positioning image by directly analyzing and calculating the scanning parameters of the spine in the spliced ​​positioning image.

[0075] Of course, other scanning parameter acquisition methods are also possible and are not specifically limited here.

[0076] S208 , mapping the scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image to each of the positioning images, and determining the spine scanning parameters of the spine to be scanned on each of the positioning images.

[0077] Specifically, after obtaining the scanning parameters of the spine to be scanned on the stitched positioning image, since each positioning image is obtained by scanning a single segment of the spine, there is a certain positional correspondence between it and the stitched positioning image. Therefore, the scanning parameters of the spine to be scanned on the stitched positioning image can be directly mapped to each corresponding single segment positioning image according to the positional correspondence between each positioning image and the stitched positioning image, and the scanning parameters of the spine to be scanned on each positioning image are obtained, which are recorded as spine scanning parameters.

[0078] Of course, it is also possible to map the scanning parameters of the spine to be scanned on the spliced ​​positioning image to each corresponding single-segment positioning image according to the positional correspondence between each positioning image and the spliced ​​positioning image, combined with the spinal segmentation results and scanning parameters of each positioning image itself, to obtain the spinal scanning parameters of the spine to be scanned on each positioning image.

[0079] In the above-mentioned method for obtaining spinal scan parameters, at least two acquired positioning images of the spine to be scanned are spliced ​​together to determine a spliced ​​positioning image of the spine to be scanned. Scan parameters of the spine to be scanned in the spliced ​​positioning image are determined based on the spliced ​​positioning image. The scanning parameters in the spliced ​​positioning image are then mapped onto each positioning image to determine the spinal scan parameters for each positioning image. In this method, since the overall scanning parameters of the spine to be scanned can be determined using the spliced ​​positioning image obtained by splicing together multiple positioning images, the image information of the multiple positioning images can be effectively utilized to calculate parameters for the entire spine to be scanned. The overall scanning parameters can then be mapped to each single-segment positioning image for precise calculation to determine the spinal scan parameters on the single-segment image, thereby improving the accuracy of the scan parameters determined for the single-segment positioning image.

[0080] In another embodiment, another method for obtaining spinal scan parameters is provided. This embodiment involves a specific process of determining spinal scan parameters on a spliced ​​image by splicing multiple positioning images. Figure 3 As shown, the above S206 may include the following steps:

[0081] S302: Input the spliced ​​positioning image of the spine to be scanned into a preset segmentation model for segmentation processing, and determine the segmentation result of the spine to be scanned on the spliced ​​positioning image.

[0082] In this step, the segmentation model here is obtained by training based on a spinal training image set, which includes multiple spinal training images and standard segmentation results corresponding to each spinal training image; wherein, the standard segmentation results of the spinal training image may include the standard position of the spine on the spinal training image, the mask image of the spine, etc.

[0083] In addition, the segmentation model here can not only perform spinal segmentation on the above-mentioned spliced ​​positioning images, but also perform segmentation on single-segment positioning images.

[0084] Specifically, before segmenting the spliced ​​positioning image, the segmentation model can be trained in advance. After obtaining the trained segmentation model, the spliced ​​positioning image can be input into the trained segmentation model for spinal segmentation processing to obtain the segmentation result of the spine to be scanned on the spliced ​​positioning image.

[0085] S304: Determine scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image according to the segmentation result of the spine to be scanned on the spliced ​​positioning image.

[0086] In this step, optionally, the following steps A1 and A2 may be included:

[0087] Step A1: input the spliced ​​positioning image of the spine to be scanned into a preset label marking model to determine the label of each vertebra on the spine to be scanned in the spliced ​​positioning image.

[0088] In this step, the label marking model is trained based on the spine training image set, which includes multiple spine training images and the labeling labels of each vertebra on the spine in each spine training image; wherein the spine training image here is a spine training image including the spine segmentation result; in addition, for example, assuming that the spine includes the cervical vertebra, the labeling labels of each vertebra on the cervical vertebra may include C1, C2, C3...C6, C7 and so on.

[0089] Specifically, when determining the labels of each vertebra, the label marking model can be trained in advance. After obtaining the trained label marking model, the segmentation results of the spine to be scanned on the spliced ​​positioning image can be input into the label marking model to obtain the labels of each vertebra on the spine to be scanned in the spliced ​​positioning image.

[0090] Step A2: determining the corresponding scanning parameters of the spine to be scanned on the spliced ​​positioning image according to the segmentation result of the spine to be scanned on the spliced ​​positioning image and the labels of each vertebra on the spine to be scanned in the spliced ​​positioning image.

[0091] In this step, after obtaining the segmentation results of the spine to be scanned on the stitched positioning image and the labels of each vertebra on the spine to be scanned, the labels of each vertebra can be used to perform parameter analysis and calculation on the segmentation results of the spine to be scanned corresponding to the labels of each vertebra, so as to obtain the scanning parameters of the spine to be scanned on the stitched positioning image.

[0092] The spinal scan parameter acquisition method of this embodiment performs spinal segmentation processing on the spliced ​​positioning image to obtain a segmentation result of the spine to be scanned, and then determines the scanning parameters on the spliced ​​positioning image based on the segmentation result of the spine to be scanned. In this embodiment, since the spinal scan parameters can be determined based on the segmentation result of the spine to be scanned, the spinal scan parameter acquisition process is gradually refined, thereby making the obtained spinal scan parameters more accurate. Furthermore, by combining the segmentation result of the spine to be scanned with the labels of each vertebra, the spinal scan parameter acquisition process considers more parameters, resulting in more refined and accurate spinal scan parameters.

[0093] In another embodiment, another method for obtaining spinal scan parameters is provided. This embodiment involves a specific process of determining the spinal scan parameters on a spliced ​​image using the spinal segmentation results and the labels of each vertebra on the spliced ​​image. Figure 4As shown, the above step A2 may include the following steps:

[0094] S402 : Determine the position information of the first key point of each vertebra according to the segmentation result of the spine to be scanned in the stitched positioning image and the label of each vertebra on the spine to be scanned in the stitched positioning image.

[0095] The first key points of the vertebra include the center of mass, center of gravity, left edge point, right edge point, etc. of the vertebra.

[0096] In this step, after obtaining the labels of each vertebra and the segmentation results of the spine to be scanned, the position information of each point within each vertebra on the spine to be scanned can be obtained. By performing edge search based on the position information of each point within each vertebra, the position information of the left and right edges of each vertebra can be obtained. Subsequently, the center of gravity or center of mass of each vertebra can be calculated by calculating the center of gravity or center of mass of each vertebra.

[0097] S404: Determine scanning parameters corresponding to the spinal column to be scanned on the spliced ​​positioning image according to the position information of the first key point of each vertebral body.

[0098] In this step, optionally, this step may include the following steps B1-B4:

[0099] Step B1: performing surface or plane fitting processing on the position information of the first key point of each vertebral body, and determining the fitted surface or plane as the coronal image or sagittal image corresponding to the spine to be scanned.

[0100] Here, after obtaining the position information of the first key point of each vertebra, a fitting method such as the least squares method can be used to perform plane or surface fitting processing on the position information of the center of mass or center of gravity of each vertebra to obtain a fitted plane or curve; alternatively, the position information of the left edge point and the position information of the right edge point of each vertebra can be subjected to plane or surface fitting processing to obtain a fitted plane or curve; alternatively, the position information of the center of mass or center of gravity of each vertebra, and the position information of the left edge point and the position information of the right edge point of each vertebra can be subjected to plane or surface fitting processing to obtain a fitted plane or curve.

[0101] After the fitted plane or curved surface is obtained, the fitted plane or curved surface can be used as the coronal image corresponding to the spine to be scanned.

[0102] Likewise, the sagittal image corresponding to the spine to be scanned can be determined in this manner.

[0103] Step B2: acquiring position information of the second key point of each vertebra on the spinal column to be scanned on the coronal image or the sagittal image.

[0104] The second key point of the vertebral body may include the center of mass, center of gravity, etc. of the vertebral body.

[0105] After obtaining the coronal image corresponding to the spine to be scanned as mentioned above, the position information of each point in each vertebra on the coronal image can also be obtained. Usually, the coronal image is a two-dimensional image, so the position information of the points on the coronal image is generally two-dimensional; and the position information of the first key point of the vertebra used in fitting the coronal image is three-dimensional coordinate information. Therefore, here, the position information of the second key point of each vertebra can be calculated through the position information of each point in each vertebra in the fitted coronal image.

[0106] Step B3: Perform curve or straight line fitting processing on the position information of the second key points of each vertebra on the spine to be scanned, and determine the direction perpendicular to the fitted curve or straight line as the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the spine to be scanned.

[0107] In this step, a fitting method such as the least squares method can also be used to perform curve or straight line fitting on the positional information of the center of mass or center of gravity of each vertebra to obtain a fitted curve or straight line, which can generally be a line segment. Subsequently, any direction of a line segment perpendicular to the fitted line segment can be used as the scanning direction for the sagittal image corresponding to the spine to be scanned. For example, if the two endpoints of the line segment perpendicular to the fitted line segment include point A and point B, the direction from point A to point B can be used as the scanning direction for the sagittal image corresponding to the spine to be scanned, or the direction from point B to point A can be used as the scanning direction for the sagittal image corresponding to the spine to be scanned.

[0108] Likewise, the scanning direction of the coronal image corresponding to the spine to be scanned can be determined in this manner.

[0109] Step B4: determining the scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image according to the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the spine to be scanned.

[0110] In this step, optionally, the step may include: obtaining the position information of the third key point of the curve or straight line obtained by the above fitting, and determining the position information of the third key point of the above curve or straight line as the scanning position corresponding to the above spine to be scanned; determining the scanning position corresponding to the above spine to be scanned and the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the above spine to be scanned as the scanning parameters corresponding to the above spine to be scanned on the above spliced ​​positioning image.

[0111] The third key point may be the midpoint of the fitted line segment, or the point on the line segment that is closest to a specific vertebra.

[0112] Here, the midpoint of the segment can be calculated using the position information of each point on the fitted segment. Alternatively, the position information of each point on the fitted segment can be combined with information such as the distance from each point on the segment to each vertebra to obtain the point on the segment closest to a specific vertebra and its position information. In short, the position information of the third key point can be obtained, which can then be used as the scanning position of the spine to be scanned on the stitched positioning image.

[0113] Afterwards, the above-determined scanning direction and the scanning position here can be used together as scanning parameters of the spine to be scanned on the spliced ​​positioning image.

[0114] Furthermore, the sagittal image corresponding to the spine to be scanned can also be obtained by adopting the above-mentioned S402-S404 method. The specific process can be the same as the above-mentioned S402-S404, and will not be repeated here.

[0115] The spinal scan parameter acquisition method of this embodiment can determine the position information of the first key point of each vertebra using the segmentation results of the spine to be scanned and the labels of each vertebra. The scanning parameters of the spine to be scanned on the spliced ​​positioning image are then determined based on the position information of the first key point of each vertebra. In this embodiment, since the position information of the first key point of each vertebra can be determined by combining the segmentation results of the spine to be scanned and the labels of each vertebra, the scanning parameters of the spine to be scanned can be determined step by step. This allows the scanning parameter acquisition process to be refined step by step, resulting in more detailed and accurate scanning parameters ultimately obtained.

[0116] In another embodiment, another method for obtaining spinal scan parameters is provided. This embodiment relates to a specific process of determining the corresponding scanning parameters of the spinal column to be scanned on the stitched positioning image in a transverse position. Based on the above embodiment, the above S206 and S208 may further include the following steps C1-C3:

[0117] Step C1, calculating the segmentation results of each vertebral disc on the spine to be scanned in the spliced ​​positioning image, and mapping the segmentation results of each vertebral disc to each of the positioning images; the segmentation results of each vertebral disc include the position and label of each vertebral disc.

[0118] In this step, a segmentation model can be used to segment each vertebral disc in the spliced ​​localization image, obtaining a segmentation result that includes the location of each vertebral disc. Simultaneously, a labeling model can be used to label the vertebral discs in the segmentation result, obtaining labels for each vertebral disc. The segmentation result and labeling model can be found in the explanations of S302-S304 above and will not be further elaborated here.

[0119] Afterwards, based on the scanning order of each positioning image (or the order when splicing) and the positional correspondence between each positioning image and the spliced ​​positioning image, the labels and positions of each vertebral disc on the spine to be scanned in the spliced ​​positioning image can be matched with the vertebral discs in each positioning image to obtain the labels and positions of the vertebral bodies of each vertebral disc in each positioning image.

[0120] Step C2: performing principal component analysis on the segmentation results of each vertebral disc after mapping, and determining the main direction of each vertebral disc obtained as the scanning direction of the transverse image corresponding to the spine to be scanned.

[0121] Here, principal component analysis can be performed using the principal component analysis method. By performing principal component analysis on the segmentation results of each vertebral disc after mapping, the main direction of each vertebral disc can be obtained, and the main direction of each vertebral disc can be used as the scanning direction of the corresponding transverse image of the spine to be scanned on each positioning image.

[0122] Step C3: determining the position of the fourth key point of each vertebral disc according to the segmentation result after mapping of each vertebral disc, and determining the position information of the fourth key point as the scanning position corresponding to the spine to be scanned.

[0123] The fourth key point here can be the posterior edge point of the vertebral disc. After obtaining the segmentation results of each vertebral disc after mapping, the posterior edge point of each vertebral disc can be found out, the position of the posterior edge point of each vertebral disc can be obtained, and the position of the posterior edge point of each vertebral disc can be used as the corresponding scanning position of the spine to be scanned on each positioning image.

[0124] Afterwards, the scanning direction of the transverse image corresponding to the spine to be scanned on each positioning image and the scanning position corresponding to the spine to be scanned on each positioning image can be used as the scanning parameters corresponding to the spine to be scanned on each positioning image.

[0125] In this embodiment, by calculating the segmentation results of each vertebral disc on the spine to be scanned in the spliced ​​positioning image and performing principal component analysis on the segmentation results of each disc, the main direction of each disc obtained is determined as the scanning direction of the corresponding transverse image of the spine to be scanned. The position of the fourth key point of each disc is determined based on the segmentation results of each disc, and the position information of the fourth key point is determined as the scanning position corresponding to the spine to be scanned. Here, because the position information of the fourth key point of each disc can be determined by combining the segmentation results of the spine to be scanned and the labels of each disc, the scanning parameters of the spine to be scanned can be determined. This allows the scanning parameter acquisition process to be refined step by step, resulting in more detailed and accurate scanning parameters.

[0126] In another embodiment, another method for obtaining spinal scan parameters is provided. This embodiment involves a specific process of mapping the spinal scan parameters on the spliced ​​image to the spinal scan parameters on each single segment image. Figure 5 As shown, the above S208 may include the following steps:

[0127] S502 : Mapping the labels of each vertebra on the spinal column to be scanned in the spliced ​​positioning image onto each of the positioning images to obtain the labels of each vertebra on each of the positioning images.

[0128] In this step, based on the scanning order of each positioning image (or the order when splicing) and the positional correspondence between each positioning image and the spliced ​​positioning image, the labels of each vertebra on the spine to be scanned in the spliced ​​positioning image can be matched with the vertebra in each positioning image to obtain the vertebral labels of each vertebra in each positioning image.

[0129] Similarly, based on the scanning order of each positioning image (or the order when splicing) and the positional correspondence between each positioning image and the spliced ​​positioning image, the labels and positions of each vertebral disc on the spine to be scanned in the spliced ​​positioning image can be matched with the vertebral discs in each positioning image to obtain the labels and positions of each vertebral disc in each positioning image.

[0130] S504: Determine the segmentation result of the spine to be scanned on each of the positioning images according to the positioning images and the segmentation model.

[0131] In this step, after the segmentation model is trained, each positioning image may be input into the trained segmentation model to perform spinal segmentation, thereby obtaining a spinal segmentation result in each positioning image.

[0132] S506 , determining scanning parameters corresponding to the spine to be scanned on each positioning image according to the segmentation results of the spine to be scanned on each positioning image and the labels of each vertebra on each positioning image.

[0133] In this step, after obtaining the segmentation results of the spine in each positioning image, the scanning parameters of the spine on each positioning image can be obtained in the same manner as S402-S404 above, and combined with the labels of each vertebra mapped here, the scanning parameters corresponding to the spine to be scanned on each positioning image can be obtained.

[0134] Of course, the labels of each vertebra mapped in each positioning image, and / or the position and label of each vertebral disc can also be used as initialization results, and the scanning parameters of the spine in each positioning image can be iteratively calculated to obtain the scanning parameters corresponding to the spine to be scanned on each positioning image.

[0135] The spinal scan parameter acquisition method in this embodiment maps the labels of each vertebra in the spliced ​​positioning image onto each positioning image to obtain the labels of each vertebra in each positioning image. This method also combines the spinal segmentation results from each positioning image to determine the scanning parameters of the spine to be scanned in each positioning image. In this embodiment, since the mapping results of the spliced ​​positioning image and the segmentation results of the single-segment positioning image can be combined to obtain the scanning parameters for the single-segment positioning image, parameter errors caused by image splicing can be minimized, thereby making the final determined scanning parameters of the spine to be scanned in each positioning image more accurate.

[0136] It should be understood that although Figure 2-5 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 2-5 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The order of execution of these steps or stages is not necessarily one by one, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0137] In one embodiment, Figure 6 As shown, a spinal column scanning parameter acquisition device is provided, comprising: an acquisition module 10, a splicing module 11, a splicing scanning parameter determination module 12 and a single-segment scanning parameter determination module 13, wherein:

[0138] An acquisition module 10 is used to acquire at least two positioning images of the spine to be scanned;

[0139] A stitching module 11 is configured to stitch at least two positioning images of the spine to be scanned to determine a stitched positioning image of the spine to be scanned;

[0140] A splicing scanning parameter determination module 12 is used to determine the scanning parameters corresponding to the splicing positioning image of the spine to be scanned based on the splicing positioning image of the spine to be scanned;

[0141] The single-segment scanning parameter determination module 13 is used to map the scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image to each of the positioning images, and determine the spine scanning parameters of the spine to be scanned on each of the positioning images.

[0142] The specific definition of the spinal column scanning parameter acquisition device can be found in the above definition of the spinal column scanning parameter acquisition method, which will not be repeated here.

[0143] In another embodiment, another spinal column scanning parameter acquisition device is provided. Based on the above embodiment, the above-mentioned splicing scanning parameter determination module 12 may include a spinal column segmentation unit and a splicing scanning parameter determination unit, wherein:

[0144] A spine segmentation unit, configured to input the spliced ​​positioning image of the spine to be scanned into a preset segmentation model for segmentation processing, and determine a segmentation result of the spine to be scanned on the spliced ​​positioning image;

[0145] The splicing scanning parameter determination unit is used to determine the corresponding scanning parameters of the spine to be scanned on the splicing positioning image according to the segmentation result of the spine to be scanned on the splicing positioning image.

[0146] Optionally, the stitching scan parameter determination unit may include a label determination subunit and a stitching scan parameter determination subunit, wherein:

[0147] a label determination subunit, configured to input the spliced ​​positioning image of the spine to be scanned into a preset label marking model, and determine the label of each vertebra on the spine to be scanned in the spliced ​​positioning image;

[0148] The splicing scanning parameter determination subunit is used to determine the corresponding scanning parameters of the spine to be scanned on the splicing positioning image according to the segmentation result of the spine to be scanned on the splicing positioning image and the labels of each vertebra on the spine to be scanned in the splicing positioning image.

[0149] In another embodiment, another spinal scanning parameter acquisition device is provided. Based on the above embodiment, the above-mentioned splicing scanning parameter determination subunit is specifically used to determine the position information of the first key point of each of the above-mentioned vertebrae based on the segmentation result of the spine to be scanned on the above-mentioned splicing positioning image and the label of each vertebra on the spine to be scanned in the above-mentioned splicing positioning image; based on the position information of the first key point of each of the above-mentioned vertebrae, determine the corresponding scanning parameters of the above-mentioned spine to be scanned on the above-mentioned splicing positioning image.

[0150] Optionally, the above-mentioned splicing scanning parameter determination subunit is specifically used to perform surface or plane fitting processing on the position information of the first key points of each of the above-mentioned vertebrae, and determine the fitted surface or plane as the coronal image or sagittal image corresponding to the above-mentioned spine to be scanned; obtain the position information of the second key points of each vertebra on the above-mentioned spine to be scanned on the above-mentioned coronal image or sagittal image; perform curve or straight line fitting processing on the position information of the second key points of each vertebra on the above-mentioned spine to be scanned, and determine the direction perpendicular to the fitted curve or straight line as the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the above-mentioned spine to be scanned; according to the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the above-mentioned spine to be scanned, determine the scanning parameters corresponding to the above-mentioned spine to be scanned on the above-mentioned splicing positioning image.

[0151] Optionally, the above-mentioned stitching scanning parameter determination subunit is specifically used to obtain the position information of the third key point of the curve or straight line obtained by the above-mentioned fitting, and determine the position information of the third key point of the above-mentioned curve or straight line as the scanning position corresponding to the above-mentioned spine to be scanned; the scanning position corresponding to the above-mentioned spine to be scanned and the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the above-mentioned spine to be scanned are determined as the scanning parameters corresponding to the above-mentioned spine to be scanned on the above-mentioned stitching positioning image.

[0152] In another embodiment, another spinal scan parameter acquisition device is provided. Based on the above embodiment, the splicing scan parameter determination module 12 and the single-segment scan parameter determination module 13 may further include a calculation unit, an analysis unit, and a position determination unit, wherein:

[0153] a computing unit configured to compute segmentation results of each vertebral disc on the spinal column to be scanned in the stitched positioning image, and map the segmentation results of each vertebral disc to each of the positioning images; the segmentation results of each vertebral disc include the position and label of each vertebral disc;

[0154] an analyzing unit, configured to perform principal component analysis on the segmentation results of the mapped vertebral discs, and determine the main direction of each vertebral disc obtained as the scanning direction of the transverse image corresponding to the spinal column to be scanned;

[0155] The position determination unit is used to determine the position of the fourth key point of each vertebral disc according to the segmentation result after mapping of each vertebral disc, and determine the position information of the fourth key point as the scanning position corresponding to the spinal column to be scanned.

[0156] In another embodiment, another spinal scan parameter acquisition device is provided. Based on the above embodiment, the single-segment scan parameter determination module 13 may include a label mapping unit, a single-segment segmentation unit, and a single-segment scan parameter determination unit, wherein:

[0157] a label mapping unit, configured to map the labels of the vertebrae on the spinal column to be scanned in the stitched positioning image onto the positioning images to obtain the labels of the vertebrae on the positioning images;

[0158] a single segment segmentation unit, configured to determine a segmentation result of the spinal column to be scanned on each of the positioning images according to the positioning images and the segmentation model;

[0159] The single-segment scanning parameter determination unit is used to determine the scanning parameters corresponding to the spine to be scanned on each of the positioning images according to the segmentation results of the spine to be scanned on each of the positioning images and the labels of each vertebra on each of the positioning images.

[0160] The specific definition of the spinal column scanning parameter acquisition device can be found in the above definition of the spinal column scanning parameter acquisition method, which will not be repeated here.

[0161] Each module in the spinal scan parameter acquisition device described above may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a computer device memory in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0162] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0163] Acquire at least two positioning images of the spine to be scanned; perform stitching processing on the at least two positioning images of the spine to be scanned to determine the stitched positioning image of the spine to be scanned; determine the scanning parameters corresponding to the spine to be scanned on the stitched positioning image based on the stitched positioning image of the spine to be scanned; map the scanning parameters corresponding to the spine to be scanned on the stitched positioning image to each of the positioning images to determine the spine scanning parameters of the spine to be scanned on each of the positioning images.

[0164] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0165] The stitched positioning image of the spine to be scanned is input into a preset segmentation model for segmentation processing to determine the segmentation result of the spine to be scanned on the stitched positioning image; based on the segmentation result of the spine to be scanned on the stitched positioning image, the corresponding scanning parameters of the spine to be scanned on the stitched positioning image are determined.

[0166] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0167] The stitched positioning image of the spine to be scanned is input into a preset label marking model to determine the labels of each vertebra on the spine to be scanned in the stitched positioning image; based on the segmentation result of the spine to be scanned on the stitched positioning image and the labels of each vertebra on the spine to be scanned in the stitched positioning image, the corresponding scanning parameters of the spine to be scanned on the stitched positioning image are determined.

[0168] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0169] Based on the segmentation results of the spine to be scanned on the above-mentioned stitched positioning image and the labels of each vertebra on the spine to be scanned in the above-mentioned stitched positioning image, the position information of the first key point of each of the above-mentioned vertebrae is determined; based on the position information of the first key point of each of the above-mentioned vertebrae, the corresponding scanning parameters of the spine to be scanned on the above-mentioned stitched positioning image are determined.

[0170] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0171] The position information of the first key point of each of the above-mentioned vertebrae is subjected to surface or plane fitting processing, and the fitted surface or plane is determined as the coronal image or sagittal image corresponding to the above-mentioned spine to be scanned; the position information of the second key point of each of the vertebrae on the above-mentioned spine to be scanned is obtained on the above-mentioned coronal image or sagittal image; the position information of the second key point of each of the vertebrae on the above-mentioned spine to be scanned is subjected to curve or straight line fitting processing, and the direction perpendicular to the fitted curve or straight line is determined as the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the above-mentioned spine to be scanned; according to the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the above-mentioned spine to be scanned, the scanning parameters corresponding to the above-mentioned spine to be scanned on the above-mentioned spliced ​​positioning image are determined.

[0172] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0173] Obtain the position information of the third key point of the curve or straight line obtained by the above fitting, and determine the position information of the third key point of the above curve or straight line as the scanning position corresponding to the above spine to be scanned; determine the scanning position corresponding to the above spine to be scanned and the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the above spine to be scanned as the corresponding scanning parameters of the above spine to be scanned on the above spliced ​​positioning image.

[0174] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0175] Calculate the segmentation results of each vertebral disc on the spine to be scanned in the above-mentioned spliced ​​positioning image, and map the segmentation results of each vertebral disc to each of the above-mentioned positioning images; the segmentation results of each vertebral disc include the position and label of each vertebral disc; perform principal component analysis on the segmentation results after mapping of each vertebral disc, and determine the main direction of each vertebral disc obtained as the scanning direction of the transverse image corresponding to the spine to be scanned; determine the position of the fourth key point of each vertebral disc according to the segmentation results after mapping of each vertebral disc, and determine the position information of the fourth key point as the scanning position corresponding to the spine to be scanned.

[0176] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0177] The labels of each vertebra on the spine to be scanned in the above-mentioned spliced ​​positioning image are mapped to each of the above-mentioned positioning images to obtain the labels of each vertebra on each of the above-mentioned positioning images; based on each of the above-mentioned positioning images and the above-mentioned segmentation model, the segmentation results of the spine to be scanned on each of the above-mentioned positioning images are determined; based on the segmentation results of the spine to be scanned on each of the above-mentioned positioning images and the labels of each vertebra on each of the above-mentioned positioning images, the scanning parameters corresponding to the spine to be scanned on each of the above-mentioned positioning images are determined.

[0178] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0179] Acquire at least two positioning images of the spine to be scanned; perform stitching processing on the at least two positioning images of the spine to be scanned to determine the stitched positioning image of the spine to be scanned; determine the scanning parameters corresponding to the spine to be scanned on the stitched positioning image based on the stitched positioning image of the spine to be scanned; map the scanning parameters corresponding to the spine to be scanned on the stitched positioning image to each of the positioning images to determine the spine scanning parameters of the spine to be scanned on each of the positioning images.

[0180] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0181] The stitched positioning image of the spine to be scanned is input into a preset segmentation model for segmentation processing to determine the segmentation result of the spine to be scanned on the stitched positioning image; based on the segmentation result of the spine to be scanned on the stitched positioning image, the corresponding scanning parameters of the spine to be scanned on the stitched positioning image are determined.

[0182] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0183] The stitched positioning image of the spine to be scanned is input into a preset label marking model to determine the labels of each vertebra on the spine to be scanned in the stitched positioning image; based on the segmentation result of the spine to be scanned on the stitched positioning image and the labels of each vertebra on the spine to be scanned in the stitched positioning image, the corresponding scanning parameters of the spine to be scanned on the stitched positioning image are determined.

[0184] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0185] Based on the segmentation results of the spine to be scanned on the above-mentioned stitched positioning image and the labels of each vertebra on the spine to be scanned in the above-mentioned stitched positioning image, the position information of the first key point of each of the above-mentioned vertebrae is determined; based on the position information of the first key point of each of the above-mentioned vertebrae, the corresponding scanning parameters of the spine to be scanned on the above-mentioned stitched positioning image are determined.

[0186] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0187] The position information of the first key point of each of the above-mentioned vertebrae is subjected to surface or plane fitting processing, and the fitted surface or plane is determined as the coronal image or sagittal image corresponding to the above-mentioned spine to be scanned; the position information of the second key point of each of the vertebrae on the above-mentioned spine to be scanned is obtained on the above-mentioned coronal image or sagittal image; the position information of the second key point of each of the vertebrae on the above-mentioned spine to be scanned is subjected to curve or straight line fitting processing, and the direction perpendicular to the fitted curve or straight line is determined as the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the above-mentioned spine to be scanned; according to the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the above-mentioned spine to be scanned, the scanning parameters corresponding to the above-mentioned spine to be scanned on the above-mentioned spliced ​​positioning image are determined.

[0188] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0189] Obtain the position information of the third key point of the curve or straight line obtained by the above fitting, and determine the position information of the third key point of the above curve or straight line as the scanning position corresponding to the above spine to be scanned; determine the scanning position corresponding to the above spine to be scanned and the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the above spine to be scanned as the corresponding scanning parameters of the above spine to be scanned on the above spliced ​​positioning image.

[0190] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0191] Calculate the segmentation results of each vertebral disc on the spine to be scanned in the above-mentioned spliced ​​positioning image, and map the segmentation results of each vertebral disc to each of the above-mentioned positioning images; the segmentation results of each vertebral disc include the position and label of each vertebral disc; perform principal component analysis on the segmentation results after mapping of each vertebral disc, and determine the main direction of each vertebral disc obtained as the scanning direction of the transverse image corresponding to the spine to be scanned; determine the position of the fourth key point of each vertebral disc according to the segmentation results after mapping of each vertebral disc, and determine the position information of the fourth key point as the scanning position corresponding to the spine to be scanned.

[0192] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0193] The labels of each vertebra on the spine to be scanned in the above-mentioned spliced ​​positioning image are mapped to each of the above-mentioned positioning images to obtain the labels of each vertebra on each of the above-mentioned positioning images; based on each of the above-mentioned positioning images and the above-mentioned segmentation model, the segmentation results of the spine to be scanned on each of the above-mentioned positioning images are determined; based on the segmentation results of the spine to be scanned on each of the above-mentioned positioning images and the labels of each vertebra on each of the above-mentioned positioning images, the scanning parameters corresponding to the spine to be scanned on each of the above-mentioned positioning images are determined.

[0194] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0195] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0196] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for obtaining spinal scan parameters, characterized in that: The method comprises: Acquire at least two positioning images of the spine to be scanned, and perform splicing processing on the at least two positioning images of the spine to be scanned to determine a spliced ​​positioning image of the spine to be scanned; Determining, based on the spliced ​​positioning image of the spine to be scanned, scanning parameters corresponding to the spliced ​​positioning image of the spine to be scanned; Mapping the scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image to each of the positioning images, and determining the spine scanning parameters of the spine to be scanned on each of the positioning images; The step of mapping the corresponding scanning parameters of the spine to be scanned on the spliced ​​positioning image to each positioning image and determining the spine scanning parameters of the spine to be scanned on each positioning image includes: Mapping the labels of each vertebra on the spinal column to be scanned in the spliced ​​positioning image onto each positioning image according to the scanning order of each positioning image and the positional correspondence between each positioning image and the spliced ​​positioning image, and determining the labels of each vertebra on each positioning image; Determining a segmentation result of the spine to be scanned on each positioning image according to each positioning image and a preset segmentation model; The scanning parameters corresponding to the spine to be scanned on each positioning image are determined according to the segmentation results of the spine to be scanned on each positioning image and the labels of each vertebra on each positioning image.

2. The method according to claim 1, characterized in that The method further comprises: According to the scanning order or splicing order of each of the positioning images, and the positional correspondence between each of the positioning images and the spliced ​​positioning image, the labels and positions of each vertebral disc on the spine to be scanned in the spliced ​​positioning image are matched with the vertebral discs in each of the positioning images to obtain the labels and positions of each vertebral disc in each of the positioning images.

3. The method according to claim 2, characterized in that Determining scanning parameters corresponding to the spine to be scanned on each positioning image according to the segmentation results of the spine to be scanned on each positioning image and the labels of each vertebra on each positioning image includes: The labels of each vertebra mapped in each positioning image, and / or the positions and labels of each vertebral disc are used as initialization results, and the scanning parameters of the spine to be scanned in each positioning image are iteratively calculated to obtain the scanning parameters corresponding to the spine to be scanned in each positioning image.

4. The method according to any one of claims 1 to 3, characterized in that The step of determining, based on the spliced ​​positioning image of the spine to be scanned, scanning parameters corresponding to the spliced ​​positioning image of the spine to be scanned includes: Inputting the spliced ​​positioning image of the spine to be scanned into the segmentation model for segmentation processing, and determining a segmentation result of the spine to be scanned on the spliced ​​positioning image; According to the segmentation result of the spine to be scanned on the spliced ​​positioning image, the scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image are determined.

5. The method according to claim 4, characterized in that The step of determining corresponding scanning parameters of the spine to be scanned on the spliced ​​positioning image based on the segmentation result of the spine to be scanned on the spliced ​​positioning image includes: Inputting the spliced ​​positioning image of the spine to be scanned into a preset label marking model to determine the label of each vertebra on the spine to be scanned in the spliced ​​positioning image; The scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image are determined according to the segmentation result of the spine to be scanned on the spliced ​​positioning image and the labels of each vertebra on the spine to be scanned in the spliced ​​positioning image.

6. The method according to claim 5, characterized in that The determining, based on the segmentation result of the spine to be scanned on the spliced ​​positioning image and the labels of each vertebra on the spine to be scanned in the spliced ​​positioning image, corresponding scanning parameters of the spine to be scanned on the spliced ​​positioning image includes: determining position information of a first key point of each vertebra according to a segmentation result of the spine to be scanned on the spliced ​​positioning image and a label of each vertebra on the spine to be scanned in the spliced ​​positioning image; The scanning parameters corresponding to the spinal column to be scanned on the spliced ​​positioning image are determined according to the position information of the first key point of each vertebral body.

7. The method according to claim 6, characterized in that Determining the scanning parameters corresponding to the spinal column to be scanned on the spliced ​​positioning image based on the position information of the first key point of each vertebral body includes: Performing surface or plane fitting processing on the position information of the first key point of each vertebra, and determining the fitted surface or plane as the coronal image or sagittal image corresponding to the spine to be scanned; Acquiring position information of a second key point of each vertebra on the spinal column to be scanned on the coronal image or the sagittal image; performing curve or line fitting processing on the position information of the second key points of each vertebra on the spine to be scanned, and determining the direction perpendicular to the fitted curve or line as the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the spine to be scanned; The scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image are determined according to the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the spine to be scanned.

8. The method according to claim 7, characterized in that Determining the scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image according to the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the spine to be scanned includes: Obtaining position information of a third key point of the fitted curve or straight line, and determining the position information of the third key point of the curve or straight line as a scanning position corresponding to the spine to be scanned; The scanning position corresponding to the spine to be scanned and the scanning direction of the sagittal image or the scanning direction of the coronal image corresponding to the spine to be scanned are determined as the scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image.

9. A device for acquiring spinal scan parameters, characterized in that: The device comprises: an acquisition module, configured to acquire at least two positioning images of the spine to be scanned, a splicing module, configured to splice at least two positioning images of the spine to be scanned to determine a spliced ​​positioning image of the spine to be scanned; a splicing scanning parameter determination module, configured to determine, based on the splicing positioning image of the spine to be scanned, the corresponding scanning parameters of the spine to be scanned on the splicing positioning image; a single-segment scanning parameter determination module, configured to map the scanning parameters corresponding to the spine to be scanned on the spliced ​​positioning image to each of the positioning images, and determine the spine scanning parameters of the spine to be scanned on each of the positioning images; The single-segment scanning parameter determination module includes: a label mapping unit, configured to map the labels of each vertebra on the spinal column to be scanned in the spliced ​​positioning image to each positioning image according to the scanning order of each positioning image and the positional correspondence between each positioning image and the spliced ​​positioning image, and determine the label of each vertebra on each positioning image; a single-segment segmentation unit, configured to determine a segmentation result of the spine to be scanned on each positioning image according to each positioning image and a preset segmentation model; The single-segment scanning parameter determination unit is used to determine the scanning parameters corresponding to the spine to be scanned on each positioning image according to the segmentation results of the spine to be scanned on each positioning image and the labels of each vertebra on each positioning image.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images