Method for realizing osteoporosis screening of patients with spinal deformations by utilizing spiral CT (Computed Tomography) images

Abstract

The invention relates to the technical field of osteoporosis screening, in particular to a method for screening osteoporosis of patients with spine deformation by using spiral CT (computed tomography) image.The method comprises the steps that a plurality of patients with spine deformation are scanned through a spiral CT machine, and a coronal plane CT image and a sagittal plane CT image of the spine of each patient and a cross section CT image of each vertebra node in the spine are obtained; acquiring the bone mineral density excellence degree of each vertebra node in the spine of each patient; obtaining the abnormal degree of each gap distance in the gap distance sequence of each patient; obtaining the influence degree of osteoporosis on each gap distance in the gap distance sequence of each patient; according to the influence degree, the first influence degree and the bone mineral density rule damage degree, the osteoporosis risk degree of each vertebra node in the spine of each patient is obtained; and evaluating the osteoporosis condition of each patient. According to the invention, the screening accuracy for osteoporosis of patients with spinal deformations is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of osteoporosis screening, and in particular to a method for implementing osteoporosis screening for patients with spinal deformation using spiral CT images. Background Art

[0002] Spinal deformation is a clinical manifestation that may be caused by a variety of reasons, one of which is osteoporosis. When osteoporosis occurs, bone density and bone quality decrease, bones become fragile and brittle, and the vertebral bodies of the spine are prone to compression fractures with slight or even no obvious external force, leading to spinal deformation. Therefore, in medical applications, it is often necessary to combine spiral CT images for auxiliary analysis to achieve accurate screening of osteoporosis in patients with spinal deformation.

[0003] When screening patients with spinal deformity for osteoporosis, existing methods often perform threshold analysis on the bone density and intervertebral space of the vertebral section in the patient's spinal CT images. When both the bone density and intervertebral space meet the threshold requirements, the patient with spinal deformity is considered to have osteoporosis risk and a risk warning is required. However, due to the different biomechanics of different vertebral nodes in the spine, the bone density of different vertebral nodes in a normal spine is different. For example, the bone density of the lumbar spine is greater than that of the cervical spine, resulting in a low screening accuracy of the consistency threshold analysis of bone density in the traditional screening method. In addition to osteoporosis, spinal deformity itself may cause changes in the intervertebral space, further affecting the screening accuracy of the traditional method based on the analysis of the intervertebral space. Summary of the invention

[0004] To solve the above problems, the present invention provides a method for screening osteoporosis in patients with spinal deformation using spiral CT images.

[0005] The method of the present invention for realizing osteoporosis screening of patients with spinal deformation using spiral CT images adopts the following technical scheme: An embodiment of the present invention provides a method for screening osteoporosis in patients with spinal deformation using spiral CT images, the method comprising the following steps: Scanning several patients with spinal deformation using a spiral CT machine to obtain coronal CT images, sagittal CT images of the spine, and cross-sectional CT images of each vertebral node in the spine of each patient; The cross-sectional CT images are segmented to obtain the cancellous bone area in each cross-sectional CT image; the bone density of each vertebral node in the spine of each patient is obtained according to the gray value change of pixels in the cancellous bone area; the bone disorder degree of each vertebral node in the spine of each patient is obtained according to the gray value distribution of the local area in the cancellous bone area; the bone density excellence of each vertebral node in the spine of each patient is obtained according to the bone density and bone disorder; According to the difference in the bone density excellence of adjacent vertebral nodes, the degree of destruction of the bone density rule of each vertebral node in the spine of each patient is obtained; a number of vertebral node areas are obtained in each coronal CT image; the gap distances of adjacent vertebral node areas in the coronal CT image of the spine of each patient are obtained; the trend term curve of the gap distances of adjacent vertebral node areas in the coronal CT image of the spine of each patient is obtained; the gap distances of all adjacent vertebral node areas in the coronal CT image of the spine of each patient are arranged to obtain the gap distance sequence of each patient; the abnormal degree of each gap distance in the gap distance sequence of each patient is obtained according to the offset distance of the gap distance at the corresponding position in the trend term curve; According to the change of the area of ​​the adjacent vertebral node area corresponding to the gap distance, the edge deformation degree of the two adjacent vertebral node areas corresponding to each gap distance in the gap distance sequence of each patient is obtained; the curvature angle value corresponding to each gap distance in the gap distance sequence of each patient is obtained; according to the change of the curvature angle value, the edge deformation degree and the abnormality degree, the degree of influence of osteoporosis on each gap distance in the gap distance sequence of each patient is obtained; Acquire a number of first vertebral node areas in each sagittal CT image; acquire first gap distances between adjacent vertebral node areas in the sagittal CT image of the spine of each patient; arrange the first gap distances between all adjacent first vertebral node areas in the sagittal CT image of the spine of each patient to acquire a first gap distance sequence for each patient; acquire a first degree of influence of osteoporosis on each first gap distance in the first gap distance sequence for each patient; According to the degree of influence, the first degree of influence and the degree of destruction of bone density rules, the osteoporosis risk degree of each vertebral node in the spine of each patient is obtained; according to the osteoporosis risk degree, the osteoporosis status of each patient is evaluated.

[0006] Furthermore, the bone density of each vertebral node in the spine of each patient is obtained according to the change of the gray value of the pixels in the cancellous bone area, and the specific steps include the following: ; In the formula, Indicates The patient's spine The number of pixels in the cancellous bone area of ​​the cross-sectional CT image of the vertebral node; Indicates The patient's spine The first vertebral node in the cross-sectional CT image of the cancellous bone area The gray value of pixels; Indicates The patient's spine The mean grayscale value of all pixels in the cancellous bone area in the cross-sectional CT image of the vertebral node; Indicates taking the absolute value; Indicates The patient's spine The density of bone at each vertebral node; The first hyperparameter to prevent the denominator from being zero.

[0007] Furthermore, the bone disorder degree of each vertebral node in the spine of each patient is obtained according to the gray value distribution of the local area in the cancellous bone area, and the specific steps include the following: For The patient's spine K-means clustering was performed on all pixels in the cancellous bone region of the cross-sectional CT images of the vertebral nodes. The distance metric was the absolute difference in grayscale values ​​between pixels. The patient's spine Several clusters within the cancellous bone region in the cross-sectional CT image of the vertebral node; ; In the formula, Indicates The patient's spine The number of clusters in the cancellous bone area of ​​the cross-sectional CT images of the vertebral nodes; Indicates The patient's spine The first vertebral node in the cross-sectional CT image of the cancellous bone area The area of ​​each cluster; Indicates The patient's spine The mean area of ​​all clusters in the cancellous bone region of the cross-sectional CT images of the vertebral nodes; Indicates The patient's spine The degree of bone disorder at the nodes of the vertebrae.

[0008] Furthermore, the bone density excellence of each vertebral node in the spine of each patient is obtained according to the degree of bone density and the degree of bone disorder, and the specific steps include the following: For The patient's spine The bone density of the first vertebrae The patient's spine The ratio of the bone disorder degree of the two vertebrae nodes is normalized, and the result of the normalization is used as the first The patient's spine The bone density of each vertebra is excellent.

[0009] Furthermore, the method of obtaining the degree of destruction of the bone density rule of each vertebral node in the spine of each patient based on the difference in the bone density excellence of adjacent vertebral nodes includes the following specific steps: For The patient's spine The bone density of the first vertebrae is excellent The spine of the patient The difference in the mean values ​​of the bone density excellence of adjacent vertebral nodes of the first vertebral node was normalized, and the result obtained by the normalization was used as the The patient's spine The degree of destruction of the bone density pattern of the vertebral nodes.

[0010] Furthermore, the step of obtaining the trend curve of the gap distance between adjacent vertebral node regions in the coronal CT image of the spine of each patient includes the following specific steps: For The gap distances of all adjacent vertebral node areas in the coronal CT image of the spine of each patient are obtained, and a two-dimensional rectangular coordinate system is constructed with the order value of the gap distance from top to bottom in the spine as the horizontal axis and the gap distance as the vertical axis; the point corresponding to the gap distance in the two-dimensional rectangular coordinate system is obtained according to the first order value and the gap distance corresponding to the first order value; the points corresponding to all gap distances in the two-dimensional rectangular coordinate system are obtained, and the first The distribution scatter plot of the gap distance between adjacent vertebral nodes in the coronal CT image of the spine of the patient was obtained by performing STL trend decomposition on the distribution scatter plot. A trend term curve of gap distances between adjacent vertebral node regions in a coronal CT image of a patient's spine is provided, wherein the trend term curve includes several standard gap distances.

[0011] Furthermore, the abnormality degree of each gap distance in the gap distance sequence of each patient is obtained according to the offset distance of the gap distance at the corresponding position in the trend item curve, and the specific steps include the following: The first The gap distance sequence of the patient The absolute difference between the gap distance and the standard gap distance at the corresponding position in the trend item curve is taken as the The offset distance of the gap distance; For The gap distance sequence of the patient The offset distance of the first gap distance is The absolute difference of the mean of the offset distances of all gap distances in the gap distance sequence of each patient is normalized, and the result of the normalization is used as the The gap distance sequence of the patient The abnormality of the gap distance.

[0012] Furthermore, the step of obtaining the edge deformation degree of two adjacent vertebral node regions corresponding to each gap distance in the gap distance sequence of each patient according to the area change of the adjacent vertebral node regions corresponding to the gap distance includes the following specific steps: The first The gap distance sequence of the patient The average convex hull area of ​​the two adjacent vertebral nodes corresponding to the gap distance is The gap distance sequence of the patient The gap distance corresponds to the ratio of the mean area of ​​the two adjacent vertebral node regions, which is taken as the The gap distance sequence of the patient The gap distance corresponds to the edge deformation of the node area of ​​two adjacent vertebrae.

[0013] Furthermore, the degree to which each gap distance in the gap distance sequence of each patient is affected by osteoporosis is obtained according to the change of the curvature angle value, the edge deformation degree and the abnormality degree, and the specific steps include the following: ; In the formula, Indicates The gap distance sequence of the patient The gap distance corresponds to the edge deformation of the node area of ​​two adjacent vertebrae; Indicates The gap distance sequence of the patient The degree of abnormality of the gap distance; Indicates The gap distance sequence of the patient The curvature angle value corresponding to the gap distance; Indicates The standard curvature angle value corresponding to the gap distance is a preset value; Indicates taking the absolute value; represents the linear normalization function; Indicates The gap distance sequence of the patient The degree to which the gap distance is affected by osteoporosis; represents a hyperparameter that prevents the denominator from being zero.

[0014] Furthermore, the step of obtaining the osteoporosis risk level of each vertebral node in the spine of each patient according to the impact level, the first impact level and the degree of destruction of the bone density rule includes the following specific steps: ; Indicates The patient's spine The degree of disruption of the bone density pattern of the vertebral nodes; Indicates The patient's spine The average value of the distance between two adjacent gaps corresponding to the vertebral nodes affected by osteoporosis; Indicates The patient's spine The average value of the first influence degree of osteoporosis on the distance between two adjacent first gaps corresponding to the vertebral nodes; represents the linear normalization function; Indicates The patient's spine The risk of osteoporosis in each vertebral node.

[0015] The beneficial effect of the technical solution of the present invention is that the present invention can analyze the difference in the influence of different vertebral nodes in the spine, spinal deformity and osteoporosis on the intervertebral space, thereby improving the screening accuracy of osteoporosis for patients with spinal deformation. When determining the excellent degree of bone density of each vertebral node in the patient's spine, the excellent degree of bone density is determined by analyzing the bone density of the vertebral node and the bone disorder of the vertebral node, thereby improving the scientificity, accuracy and objectivity of the excellent degree of bone density. When determining the abnormality of each gap distance in the gap distance sequence of the patient, the abnormality is determined by analyzing the offset distance of the gap distance at the corresponding position in the trend term curve, accurately describing the influence of the offset of the gap distance on the gap abnormality. When determining the degree of influence of osteoporosis on each gap distance in the gap distance sequence of the patient, the degree of influence is determined by analyzing the change of the curvature angle value, the edge deformation degree and the abnormality, thereby improving the accuracy, scientificity and objectivity of the influence. When determining the osteoporosis risk level of each vertebral node in the patient's spine, a comprehensive and comprehensive analysis is performed by combining sagittal CT images and coronal CT images to determine the osteoporosis risk level, thereby improving the scientificity, accuracy and objectivity of the osteoporosis risk level. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A flowchart of the steps of a method for screening osteoporosis in patients with spinal deformation using spiral CT images provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the method for screening osteoporosis in patients with spinal deformity using spiral CT images according to the present invention, its specific implementation method, structure, characteristics and effects, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0020] The specific scheme of the method for screening osteoporosis in patients with spinal deformation using spiral CT images provided by the present invention is described in detail below with reference to the accompanying drawings.

[0021] See also Figure 1 , which shows a flowchart of a method for implementing osteoporosis screening for patients with spinal deformation using spiral CT images provided by an embodiment of the present invention, the method comprising the following steps: Step S001: Scanning a number of patients with spinal deformation by a spiral CT machine to obtain a coronal CT image, a sagittal CT image, and a cross-sectional CT image of each vertebral node in the spine of each patient.

[0022] It should be noted that the main purpose of this embodiment is to evaluate and screen the osteoporosis risk of patients with spinal deformation. Before starting the analysis, relevant data is first obtained.

[0023] It should be noted that osteoporosis is one of the factors affecting spinal deformity in patients with spinal deformity. Screening for osteoporosis in patients with spinal deformity is often achieved by analyzing the spiral CT images of patients with spinal deformity. For a normal spine, there is no osteoporosis inside the bones, and there is no abnormal curvature deformation on the surface.

[0024] Specifically, a number of patients with spinal deformation are scanned by a spiral CT machine to obtain a coronal CT image of the spine, a sagittal CT image, and a cross-sectional CT image of each vertebral node in the spine of each patient.

[0025] It should be noted that scanning patients with spinal deformation using a spiral CT machine to obtain coronal CT images, sagittal CT images of the patient's spine, and cross-sectional CT images of each vertebral node in the spine is an existing method and will not be repeated in this embodiment.

[0026] At this point, the coronal CT images, sagittal CT images of the spine and the cross-sectional CT images of each vertebral node in the spine of each patient were obtained.

[0027] Step S002, segment the cross-sectional CT images to obtain the cancellous bone area in each cross-sectional CT image; obtain the bone density of each vertebral node in the spine of each patient based on the change of the gray value of the pixels in the cancellous bone area; obtain the bone disorder degree of each vertebral node in the spine of each patient based on the gray value distribution of the local area in the cancellous bone area; obtain the bone density excellence of each vertebral node in the spine of each patient based on the bone density and the bone disorder.

[0028] It should be noted that the spine is composed of vertebral nodes. When patients with spinal deformation develop osteoporosis, the bone mineral in the vertebrae will decrease, causing the bone lining of the vertebrae to become sparse and disordered. Therefore, the bone density excellence of each vertebral node is evaluated based on the bone density characteristics in the cross-sectional CT images of each vertebral node.

[0029] Specifically, the cross-sectional CT images are segmented to obtain the cancellous bone area in each cross-sectional CT image, as follows: Any cross-sectional CT image of a vertebral node is recorded as a target cross-sectional CT image; semantic segmentation is performed on the target cross-sectional CT image to obtain the cancellous bone area in the target cross-sectional CT image.

[0030] It should be noted that the semantic segmentation network used in this embodiment is the DeepLabV3 network, which is a well-known technology, and the specific results and training methods of the network are not described in detail in this embodiment. The main target of osteoporosis is the bone in the spongy bone area.

[0031] Furthermore, according to the change of the gray value of the pixels in the cancellous bone area, the bone density of each vertebral node in the spine of each patient is obtained, as follows: ; In the formula, Indicates The patient's spine The number of pixels in the cancellous bone area of ​​the cross-sectional CT image of the vertebral node; Indicates The patient's spine The first vertebral node in the cross-sectional CT image of the cancellous bone area The gray value of pixels; Indicates The patient's spine The mean grayscale value of all pixels in the cancellous bone area in the cross-sectional CT image of the vertebral node; Indicates taking the absolute value; Indicates The patient's spine The density of bone at each vertebral node; To prevent the first hyperparameter from having a denominator of 0, this embodiment uses Give a narrative.

[0032] Specifically, the degree of bone disorder of each vertebral node in the spine of each patient is obtained according to the gray value distribution of the local area in the cancellous bone area, including the following steps: First, the pixels in the cancellous bone region are clustered to obtain several clusters in the cancellous bone region of the cross-sectional CT image of each vertebral node in the spine of each patient.

[0033] Secondly, the degree of bone disorder at each vertebral node in the spine of each patient was obtained based on the changes in cluster area.

[0034] Furthermore, the pixels in the cancellous bone region are clustered to obtain several clusters in the cancellous bone region of the cross-sectional CT image of each vertebral node in the spine of each patient, as follows: For The patient's spine K-means clustering was performed on all pixels in the cancellous bone region of the cross-sectional CT images of the vertebral nodes. The distance metric was the absolute difference in grayscale values ​​between pixels. The patient's spine Several clusters in the cancellous bone region in the cross-sectional CT image of the vertebral node. It should be noted that the K value of K-means clustering in this embodiment is determined by the elbow method.

[0035] Furthermore, according to the change in cluster area, the degree of bone disorder of each vertebral node in the spine of each patient is obtained, as follows: ; In the formula, Indicates The patient's spine The number of clusters in the cancellous bone area of ​​the cross-sectional CT images of the vertebral nodes; Indicates The patient's spine The first vertebral node in the cross-sectional CT image of the cancellous bone area The area of ​​each cluster; Indicates The patient's spine The mean area of ​​all clusters in the cancellous bone region of the cross-sectional CT images of the vertebral nodes; Indicates The patient's spine The degree of bone disorder at the nodes of the vertebrae.

[0036] It should be noted that the cluster area in this embodiment is represented by the number of pixels in the cluster; Furthermore, based on the degree of bone density and bone disorder, the bone density excellence of each vertebral node in the spine of each patient is obtained, as follows: ; In the formula, Indicates The patient's spine The density of bone at each vertebral node; Indicates The patient's spine The degree of bone disorder at the vertebral nodes; Represents a linear normalization function, used for normalization processing; Indicates The patient's spine The bone density of each vertebra is excellent.

[0037] Thus, the bone density excellence of each vertebral node in the spine of each patient is obtained.

[0038] Step S003, according to the difference in the bone density excellence of adjacent vertebral nodes, obtain the degree of destruction of the bone density rule of each vertebral node in the spine of each patient; obtain several vertebral node areas in each coronal CT image; obtain the gap distances of adjacent vertebral node areas in the coronal CT image of the spine of each patient; obtain the trend term curve of the gap distances of adjacent vertebral node areas in the coronal CT image of the spine of each patient; arrange the gap distances of all adjacent vertebral node areas in the coronal CT image of the spine of each patient to obtain the gap distance sequence of each patient; obtain the abnormality of each gap distance in the gap distance sequence of each patient according to the offset distance of the gap distance at the corresponding position in the trend term curve.

[0039] It should be noted that different vertebral nodes in the spine are subject to different biomechanics. For example, the lumbar vertebrae are subject to greater biomechanics than the cervical vertebrae, and the bone density of the vertebra is positively correlated with the biomechanics that the vertebrae can withstand. Therefore, normal spinal vertebrae should show increasing bone density from top to bottom. If osteoporosis exists at a certain vertebral node, it will disrupt the regular change of increasing vertebral density from top to bottom. Therefore, the degree of disruption of the bone density pattern of each vertebral node is evaluated.

[0040] It should be noted that, because the bone volume of the vertebral nodes closer to the coccyx is larger, the demand for gap connecting tissues such as tissue fluid and ligaments between the two vertebral nodes is higher, and the intervertebral space is larger. Therefore, the normal intervertebral space also shows a rule that the closer to the coccyx, the larger the space. Osteoporosis and spinal deformity will cause the intervertebral space to not meet the gap change rule. Therefore, the confidence of intervertebral osteoporosis is determined based on the degree of vertebral deformity and gap edge characteristics shown by coronal and sagittal CT, thereby calculating the osteoporosis risk level of each vertebral node.

[0041] Specifically, according to the difference in the bone density excellence of adjacent vertebral nodes, the degree of destruction of the bone density regularity of each vertebral node in the spine of each patient is obtained, as follows: ; In the formula, Indicates The patient's spine The bone density of the vertebral nodes is excellent; Indicates The spine of the patient The mean value of bone density excellence of adjacent vertebral nodes of a vertebral node; Indicates taking the absolute value; Represents a linear normalization function, used for normalization processing; Indicates The patient's spine The degree of destruction of the bone density pattern of the vertebral nodes.

[0042] It should be noted that the greater the difference between the bone density excellence of a vertebral node in the spine and the average bone density excellence of adjacent vertebral nodes, the less the bone density of the vertebral node meets the law of increasing density from top to bottom of the vertebral nodes, and the greater the degree of destruction of the bone density law.

[0043] Specifically, several vertebral node regions in each coronal CT image are obtained, as follows: Any coronal CT image is recorded as a target coronal CT image; semantic segmentation is performed on the target coronal CT image to obtain all vertebral node regions in the target coronal CT image.

[0044] Furthermore, a plurality of vertebral node regions in each sagittal CT image are obtained. It should be noted that the specific method of obtaining the plurality of vertebral node regions in each coronal CT image is the same as that of obtaining the plurality of vertebral node regions in each coronal CT image, and will not be described in detail.

[0045] It should be noted that the gap value of a normal spine should be larger as it is closer to the coccyx. Osteoporosis will change the edge morphology of the vertebral nodes, causing abnormal changes in the gap between the vertebral nodes. Therefore, the degree of violation of the gap increment of the vertebral node gap is analyzed.

[0046] Specifically, the gap distance between adjacent vertebral node regions in the coronal CT image of the spine of each patient is obtained. It should be noted that obtaining the gap distance between two vertebral node regions is an existing method and will not be described in detail in this embodiment.

[0047] Furthermore, a trend curve of the gap distance between adjacent vertebral node regions in the coronal CT image of the spine of each patient is obtained, as follows: For The gap distances of all adjacent vertebral node areas in the coronal CT image of the spine of each patient are obtained, and a two-dimensional rectangular coordinate system is constructed with the order value of the gap distance from top to bottom in the spine as the horizontal axis and the gap distance as the vertical axis; the point corresponding to the gap distance in the two-dimensional rectangular coordinate system is obtained according to the first order value and the gap distance corresponding to the first order value; the points corresponding to all gap distances in the two-dimensional rectangular coordinate system are obtained, and the first The distribution scatter plot of the gap distance between adjacent vertebral nodes in the coronal CT image of the spine of the patient was obtained by performing STL trend decomposition on the distribution scatter plot. A trend term curve of gap distances between adjacent vertebral node regions in a coronal CT image of a patient's spine is provided, wherein the trend term curve includes several standard gap distances.

[0048] It should be noted that the distribution scatter plot is subjected to STL trend decomposition to obtain the The trend term curve of the gap distance between adjacent vertebral node areas in the coronal CT image of the spine of each patient is an existing method of STL trend decomposition, which will not be described in detail in this embodiment.

[0049] Furthermore, the gap distances of all adjacent vertebral node regions in the coronal CT image of each patient's spine are arranged to obtain a gap distance sequence for each patient, as follows: The first The gap distances of all adjacent vertebral node areas in the coronal CT image of the spine of each patient are arranged in order from top to bottom in the spine, and the obtained sequence is recorded as Gap distance sequence for each patient.

[0050] Furthermore, according to the offset distance of the gap distance at the corresponding position in the trend term curve, the abnormal degree of each gap distance in the gap distance sequence of each patient is obtained, as follows: The first The gap distance sequence of the patient The absolute difference between the gap distance and the standard gap distance at the corresponding position in the trend item curve is taken as the The offset distance of the gap distance.

[0051] ; In the formula, Indicates The gap distance sequence of the patient The offset distance of the gap distance; Indicates The mean of the offset distances of all gap distances in the gap distance sequence of each patient; Indicates taking the absolute value; Represents a linear normalization function, used for normalization processing; Indicates The gap distance sequence of the patient The abnormality of the gap distance.

[0052] It should be noted that The gap distance sequence of the patient The offset distance of the first gap distance is compared with the The larger the mean of the offset distances of all gap distances in the gap distance sequence of a patient, the greater the The gap distance sequence of the patient The more abnormal the gap distance is, the greater the degree of abnormality is.

[0053] At this point, the abnormality degree of each gap distance in the gap distance sequence of each patient is obtained.

[0054] Step S004, obtaining the edge deformation of two adjacent vertebral node areas corresponding to each gap distance in the gap distance sequence of each patient according to the change in area of ​​the gap distance corresponding to the adjacent vertebral node areas; obtaining the curvature angle value corresponding to each gap distance in the gap distance sequence of each patient; obtaining the degree to which each gap distance in the gap distance sequence of each patient is affected by osteoporosis according to the change in the curvature angle value, the edge deformation degree and the degree of abnormality.

[0055] It should be noted that abnormal gaps may be caused by osteoporosis or spinal deformity. Osteoporosis can lead to a decrease in bone mass, which in turn causes the edges of the vertebral nodes to concave, thereby increasing the gap. Spinal deformity is often manifested as a certain degree of compression of the spine, that is, the spinal gap will decrease. The result of directly reflecting the source of the abnormal gap by the increase or decrease in the gap value will be inaccurate. Therefore, the confidence level of gap osteoporosis is obtained based on the deformation degree of the gap edge and the degree of spinal deformity. Then, the degree of gap osteoporosis reflection of the patient's vertebral node gap is obtained by combining the abnormal degree of the gap distance.

[0056] Specifically, according to the area change of the adjacent vertebral node regions corresponding to the gap distance, the edge deformation degree of the two adjacent vertebral node regions corresponding to each gap distance in the gap distance sequence of each patient is obtained, which is specifically as follows: ; In the formula, Indicates The gap distance sequence of the patient The gap distance corresponds to the average of the convex hull areas of two adjacent vertebral node regions, and the convex hull is obtained by a convex hull detection algorithm; Indicates The gap distance sequence of the patient The gap distance corresponds to the average area of ​​the two adjacent vertebral node regions; Indicates The gap distance sequence of the patient The gap distance corresponds to the edge deformation of the node area of ​​two adjacent vertebrae.

[0057] It should be noted that if the area of ​​the corresponding vertebral node is smaller than the area of ​​the convex hull, it means that the The greater the concavity of the vertebral node edge corresponding to the upper boundary of the gap between two adjacent vertebral node areas and the lower boundary of the gap, the greater the probability of osteoporosis and the more obvious the edge deformation.

[0058] Specifically, the curvature angle value corresponding to each gap distance in the gap distance sequence of each patient is obtained, as follows: For The gap distance sequence of the patient The gap distance and The gap distance corresponds to the node area of ​​two adjacent vertebrae; The gap distance corresponds to the closed area between two adjacent vertebral node areas, as the The gap area corresponding to the gap distance; get the The centroid of the gap area corresponding to the gap distance and the The gap distance corresponds to the two first centroids of the two adjacent vertebral node regions; a straight line is used to connect the centroids to the two first centroids, and the minimum angle formed by the connection is used as the first The gap distance sequence of the patient The curvature angle value corresponding to the gap distance.

[0059] It should be noted that the closed area is a closed area formed by connecting the four endpoints of the maximum width line segment of two adjacent vertebral node areas.

[0060] Furthermore, according to the change of the curvature angle value, the edge deformation degree and the abnormality degree, the degree to which each gap distance in the gap distance sequence of each patient is affected by osteoporosis is obtained, as follows: ; In the formula, Indicates The gap distance sequence of the patient The gap distance corresponds to the edge deformation degree of the node region of two adjacent vertebrae; Indicates The gap distance sequence of the patient The degree of abnormality of the gap distance; Indicates The gap distance sequence of the patient The curvature angle value corresponding to the gap distance; Indicates The standard curvature angle value corresponding to the gap distance is a preset value, which is used to represent the curvature angle value of a normal person; Indicates taking the absolute value; Represents a linear normalization function, used for normalization processing; Indicates The gap distance sequence of the patient The degree to which the gap distance is affected by osteoporosis; Represents a hyperparameter that prevents the denominator from being 0. In this embodiment, Give a narrative.

[0061] It should be noted that The smaller the curvature angle corresponding to the gap between the vertebral nodes is, the smaller the difference between the curvature angle of the normal spine is. The gap distance sequence of the patient The larger the edge deformation of the two adjacent vertebral node regions corresponding to the gap distance, the The gap distance sequence of the patient The greater the abnormality of the gap distance, the more the gap deformation is affected by osteoporosis. The gap distance sequence of the patient The greater the gap distance is, the more it is affected by osteoporosis.

[0062] Thus, the degree to which each gap distance in the gap distance sequence of each patient is affected by osteoporosis is obtained.

[0063] Step S005: Obtain the osteoporosis risk level of each vertebral node in the spine of each patient based on the impact level, the first impact level and the degree of destruction of the bone density rule; and evaluate the osteoporosis condition of each patient based on the osteoporosis risk level.

[0064] It should be noted that the above analysis was performed on the coronal CT images of the patient's spine to obtain the degree to which each gap distance in each patient's gap distance sequence is affected by osteoporosis. In order to more accurately analyze the patient's osteoporosis condition, this embodiment also combines the sagittal CT images for analysis.

[0065] Specifically, several first vertebral node areas in each sagittal CT image are obtained; the first gap distances of adjacent vertebral node areas in the sagittal CT image of the spine of each patient are obtained; the first gap distances of all adjacent first vertebral node areas in the sagittal CT image of the spine of each patient are arranged to obtain a first gap distance sequence for each patient; and the first degree of influence of osteoporosis on each first gap distance in the first gap distance sequence of each patient is obtained.

[0066] It should be noted that the above steps analyze the coronal CT image of the patient's spine to obtain the degree to which each gap distance in the gap distance sequence of each patient is affected by osteoporosis. Here, the same analysis needs to be performed on the sagittal CT image of each patient to obtain the first degree to which each first gap distance in the first gap distance sequence of each patient is affected by osteoporosis. The specific implementation method is the same and will not be repeated in this embodiment. It is only necessary to replace the coronal CT image with the sagittal CT image for analysis.

[0067] Furthermore, according to the impact degree, the first impact degree and the degree of destruction of the bone density law, the osteoporosis risk degree of each vertebral node in the spine of each patient is obtained, as follows: ; Indicates The patient's spine The degree of disruption of the bone density pattern of the vertebral nodes; Indicates The patient's spine The average value of the distance between two adjacent gaps corresponding to the vertebral nodes affected by osteoporosis; Indicates The patient's spine The average value of the first influence degree of osteoporosis on the distance between two adjacent first gaps corresponding to the vertebral nodes; Represents a linear normalization function, used for normalization processing; Indicates The patient's spine The risk of osteoporosis in each vertebral node.

[0068] It should be noted that Indicates that from The coronal CT images and sagittal CT images of each patient were comprehensively analyzed to obtain the osteoporosis status of the vertebral nodes. The larger the size, the higher the risk of osteoporosis. The patient's spine The greater the degree of destruction of the bone density pattern of the vertebral nodes, the The patient's spine The higher the likelihood that a vertebral node has osteoporosis, the greater the risk of osteoporosis in that vertebral node in the patient's spine.

[0069] Specifically, the osteoporosis status of each patient is assessed according to the risk level of osteoporosis, including the following steps: First, according to the degree of osteoporosis risk, the comprehensive osteoporosis risk index of each patient was obtained.

[0070] Secondly, the osteoporosis status of each patient was assessed based on the size of the comprehensive osteoporosis risk index.

[0071] Furthermore, according to the osteoporosis risk level, the comprehensive osteoporosis risk index of each patient is obtained, as follows: The first The average osteoporosis risk level of all vertebral nodes in the spine of each patient is taken as the The overall osteoporosis risk of a patient.

[0072] ; In the formula, Indicates The overall osteoporosis risk level of each patient; It represents the average value of the comprehensive osteoporosis risk level of all patients; Represents a linear normalization function, used for normalization processing; Indicates Comprehensive osteoporosis risk index for each patient.

[0073] It should be noted that if The comprehensive osteoporosis risk level of the patient is higher than the average comprehensive osteoporosis risk level of all patients, indicating that The more likely a patient is to have osteoporosis, the The greater the patient's comprehensive osteoporosis risk index.

[0074] Furthermore, the osteoporosis status of each patient was evaluated according to the size of the comprehensive osteoporosis risk index, as follows: Jordi The comprehensive osteoporosis risk index of patients is less than , think that The probability of osteoporosis in each patient is low, and a few follow-up examinations can be performed; The comprehensive osteoporosis risk index of patients is greater than or equal to , but less than , dual-energy X-ray should be used for auxiliary analysis to ensure accurate assessment of osteoporosis in patients and to achieve accurate screening of osteoporosis in patients with spinal deformation; if The comprehensive osteoporosis risk index of patients is greater than or equal to , think that The probability of osteoporosis in each patient is high, and medical staff need to pay special attention to the patient's osteoporosis symptoms in the later stage and specify a treatment and care plan according to the symptoms; and are respectively the preset first threshold and the second threshold. , Give a narrative.

[0075] Through the above steps, the method of using spiral CT images to screen for osteoporosis in patients with spinal deformation is completed.

[0076] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for screening osteoporosis in patients with spinal deformation using spiral CT images, characterized in that: The method comprises the following steps: Scanning several patients with spinal deformity with a spiral CT machine to obtain coronal CT images, sagittal CT images of the spine, and cross-sectional CT images of each vertebral node in the spine of each patient; The cross-sectional CT images are segmented to obtain the cancellous bone area in each cross-sectional CT image; the bone density of each vertebral node in the spine of each patient is obtained according to the gray value change of pixels in the cancellous bone area; the bone disorder degree of each vertebral node in the spine of each patient is obtained according to the gray value distribution of the local area in the cancellous bone area; the bone density excellence of each vertebral node in the spine of each patient is obtained according to the bone density and bone disorder; According to the difference in the bone density excellence of adjacent vertebral nodes, the degree of destruction of the bone density rule of each vertebral node in the spine of each patient is obtained; a number of vertebral node areas are obtained in each coronal CT image; the gap distances of adjacent vertebral node areas in the coronal CT image of the spine of each patient are obtained; the trend term curve of the gap distances of adjacent vertebral node areas in the coronal CT image of the spine of each patient is obtained; the gap distances of all adjacent vertebral node areas in the coronal CT image of the spine of each patient are arranged to obtain the gap distance sequence of each patient; the abnormal degree of each gap distance in the gap distance sequence of each patient is obtained according to the offset distance of the gap distance at the corresponding position in the trend term curve; According to the change of the area of ​​the adjacent vertebral node area corresponding to the gap distance, the edge deformation degree of the two adjacent vertebral node areas corresponding to each gap distance in the gap distance sequence of each patient is obtained; the curvature angle value corresponding to each gap distance in the gap distance sequence of each patient is obtained; according to the change of the curvature angle value, the edge deformation degree and the abnormality degree, the degree of influence of osteoporosis on each gap distance in the gap distance sequence of each patient is obtained; Acquire a number of first vertebral node areas in each sagittal CT image; acquire first gap distances between adjacent vertebral node areas in the sagittal CT image of the spine of each patient; arrange the first gap distances between all adjacent first vertebral node areas in the sagittal CT image of the spine of each patient to acquire a first gap distance sequence for each patient; acquire a first degree of influence of osteoporosis on each first gap distance in the first gap distance sequence for each patient; According to the degree of influence, the first degree of influence and the degree of destruction of bone density rules, the osteoporosis risk degree of each vertebral node in the spine of each patient is obtained; according to the osteoporosis risk degree, the osteoporosis status of each patient is evaluated.

2. The method for screening osteoporosis in patients with spinal deformity using spiral CT images according to claim 1, characterized in that: The method of obtaining the bone density of each vertebral node in the spine of each patient according to the change of the gray value of the pixels in the cancellous bone area includes the following specific steps: ； In the formula, Indicates The patient's spine The number of pixels in the cancellous bone area of ​​the cross-sectional CT image of the vertebral node; Indicates The patient's spine The first vertebral node in the cross-sectional CT image of the cancellous bone area The gray value of pixels; Indicates The patient's spine The grayscale mean of all pixels in the cancellous bone area in the cross-sectional CT image of the vertebral node; Indicates taking the absolute value; Indicates The patient's spine The density of bone at each vertebral node; The first hyperparameter to prevent the denominator from being zero.

3. The method for screening osteoporosis in patients with spinal deformation using spiral CT images according to claim 1, characterized in that: The step of obtaining the bone disorder degree of each vertebral node in the spine of each patient according to the gray value distribution of the local area in the cancellous bone area includes the following specific steps: For The patient's spine K-means clustering was performed on all pixels in the cancellous bone region of the cross-sectional CT images of the vertebral nodes. The distance metric was the absolute difference in grayscale values ​​between pixels. The patient's spine Several clusters within the cancellous bone region in the cross-sectional CT image of the vertebral node; ； In the formula, Indicates The patient's spine The number of clusters in the cancellous bone area of ​​the cross-sectional CT images of the vertebral nodes; Indicates The patient's spine The first vertebral node in the cross-sectional CT image of the cancellous bone area The area of ​​each cluster; Indicates The patient's spine The mean area of ​​all clusters in the cancellous bone region of the cross-sectional CT images of the vertebral nodes; Indicates The patient's spine The degree of bone disorder at the nodes of the vertebrae.

4. The method for screening osteoporosis in patients with spinal deformation using spiral CT images according to claim 1, characterized in that: The method of obtaining the bone density excellence of each vertebral node in the spine of each patient according to the bone density and bone disorder degree includes the following specific steps: For The patient's spine The bone density of the first vertebrae The patient's spine The ratio of the bone disorder degree of the two vertebrae nodes is normalized, and the result of the normalization is used as the first The patient's spine The bone density of each vertebra is excellent.

5. The method for screening osteoporosis in patients with spinal deformation using spiral CT images according to claim 1, characterized in that: The method of obtaining the degree of destruction of the bone density rule of each vertebral node in the spine of each patient according to the difference in the bone density excellence of adjacent vertebral nodes includes the following specific steps: For The patient's spine The bone density of the first vertebrae is excellent The spine of the patient The difference in the mean values ​​of the bone density excellence of adjacent vertebral nodes of the first vertebral node was normalized, and the result obtained by the normalization was used as the The patient's spine The degree of destruction of the bone density pattern of the vertebral nodes.

6. The method for screening osteoporosis in patients with spinal deformity using spiral CT images according to claim 1, characterized in that: The step of obtaining the trend curve of the gap distance between adjacent vertebral node regions in the coronal CT image of the spine of each patient includes the following specific steps: For The gap distances of all adjacent vertebral node areas in the coronal CT image of the spine of each patient are obtained, and a two-dimensional rectangular coordinate system is constructed with the order value of the gap distance from top to bottom in the spine as the horizontal axis and the gap distance as the vertical axis; the point corresponding to the gap distance in the two-dimensional rectangular coordinate system is obtained according to the first order value and the gap distance corresponding to the first order value; the points corresponding to all gap distances in the two-dimensional rectangular coordinate system are obtained, and the first The distribution scatter plot of the gap distance between adjacent vertebral nodes in the coronal CT image of the spine of the patient was obtained by performing STL trend decomposition on the distribution scatter plot. A trend term curve of gap distances between adjacent vertebral node regions in a coronal CT image of a patient's spine is provided, wherein the trend term curve includes several standard gap distances.

7. The method for screening osteoporosis in patients with spinal deformation using spiral CT images according to claim 6, characterized in that: The specific steps of obtaining the abnormality degree of each gap distance in the gap distance sequence of each patient according to the offset distance of the gap distance at the corresponding position in the trend item curve are as follows: The first The gap distance sequence of the patient The absolute difference between the gap distance and the standard gap distance at the corresponding position in the trend item curve is taken as the The offset distance of the gap distance; For The gap distance sequence of the patient The offset distance of the first gap distance is The absolute difference of the mean of the offset distances of all gap distances in the gap distance sequence of each patient is normalized, and the result of the normalization is used as the The gap distance sequence of the patient The abnormality of the gap distance.

8. The method for screening osteoporosis in patients with spinal deformation using spiral CT images according to claim 1, characterized in that: The step of obtaining the edge deformation degree of two adjacent vertebral node regions corresponding to each gap distance in the gap distance sequence of each patient according to the area change of the adjacent vertebral node regions corresponding to the gap distance includes the following specific steps: The first The gap distance sequence of the patient The average convex hull area of ​​the two adjacent vertebral nodes corresponding to the gap distance is The gap distance sequence of the patient The gap distance corresponds to the ratio of the mean area of ​​the two adjacent vertebral node regions, which is taken as the The gap distance sequence of the patient The gap distance corresponds to the edge deformation of the node area of ​​two adjacent vertebrae.

9. The method for screening osteoporosis in patients with spinal deformation using spiral CT images according to claim 1, characterized in that: The method of obtaining the degree to which each gap distance in the gap distance sequence of each patient is affected by osteoporosis according to the change of the curvature angle value, the edge deformation degree and the abnormality degree includes the following specific steps: ； In the formula, Indicates The gap distance sequence of the patient The gap distance corresponds to the edge deformation of the node area of ​​two adjacent vertebrae; Indicates The gap distance sequence of the patient The degree of abnormality of the gap distance; Indicates The gap distance sequence of the patient The curvature angle value corresponding to the gap distance; Indicates The standard curvature angle value corresponding to the gap distance; Indicates taking the absolute value; represents the linear normalization function; Indicates The gap distance sequence of the patient The degree to which the gap distance is affected by osteoporosis; represents a hyperparameter that prevents the denominator from being zero.

10. The method for screening osteoporosis in patients with spinal deformity using spiral CT images according to claim 1, characterized in that: The step of obtaining the osteoporosis risk level of each vertebral node in the spine of each patient according to the impact level, the first impact level and the degree of damage to the bone density law includes the following specific steps: ; Indicates The patient's spine The degree of disruption of the bone density pattern of the vertebral nodes; Indicates The patient's spine The average value of the distance between two adjacent gaps corresponding to the vertebral nodes affected by osteoporosis; Indicates The patient's spine The average value of the first influence degree of osteoporosis on the distance between two adjacent first gaps corresponding to the vertebral nodes; represents the linear normalization function; Indicates The patient's spine The risk of osteoporosis in each vertebral node.

Images