Method and device for determining maximum Cobb angle between vertebral bodies

Abstract

The embodiment of the invention provides a method and device for determining the maximum Cobb angle between vertebral bodies. The method comprises the following steps: acquiring DR video data of user vertebral bodies, separating a vertebral body image from each frame of image in the DR video data, determining Cobb angle reference information of each vertebral body in the vertebral body image, determining a maximum Cobb angle between any two vertebral bodies in the vertebral bodies based on the Cobb angle reference information, and determining the maximum Cobb angle between any two vertebral bodies in the vertebral bodies based on the maximum Cobb angle. And outputting the maximum Cobb angle and the information of the two cones corresponding to the maximum Cobb angle. According to the embodiment of the invention, the automation of the measurement of the maximum Cobb angle of the cone is realized, and the measurement error and manpower consumption of manual measurement are reduced.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data processing technology, and in particular to a method and device for determining a maximum Cobb angle between vertebrae. Background Art

[0002] The Cobb angle refers to the curvature of the spine, including the cervical, vertebral, and lumbar vertebrae, and is used to assess the severity of abnormal spinal curvature.

[0003] The existing Cobb angle measurement methods for the cervical spine, spine, and lumbar spine can only measure the Cobb angles of two specified vertebrae. However, in medicine, it is necessary to find the maximum Cobb angle between two vertebrae to observe whether the patient has scoliosis and whether it can be corrected and restored through surgery. However, in the past, Cobb angle measurements were mostly performed manually on DR films by doctors based on their own experience. The search process usually requires all the Cobb angles between two vertebrae in each vertebra to be calculated, and then the maximum Cobb angle is found after comparing the sizes of the two vertebrae. The process is cumbersome, time-consuming, and not intuitive. Summary of the invention

[0004] The embodiments of the present application provide a method and device for determining the maximum Cobb angle between vertebrae, which realizes the automation of the measurement of the maximum Cobb angle between vertebrae, reduces the misdiagnosis rate and evaluation errors caused by previous manual measurement, and reduces the labor cost caused by manual measurement.

[0005] An embodiment of the present application provides a method for determining a maximum Cobb angle between vertebrae, comprising:

[0006] Obtain DR video data of the user's vertebral body;

[0007] Separating a vertebral image from each frame of the DR video data;

[0008] Determining Cobb angle reference information of each vertebra in the vertebral image;

[0009] The maximum Cobb angle between any two vertebrae in each vertebra is determined based on the Cobb angle reference information, and the maximum Cobb angle and information of the two vertebrae corresponding to the maximum Cobb angle are output.

[0010] In one aspect, an embodiment of the present application further provides a device for determining the maximum Cobb angle between vertebrae, comprising:

[0011] An acquisition module, used to acquire DR video data of a user's vertebral body;

[0012] A separation module, used for separating a vertebral body image from each frame of the DR video data;

[0013] A determination module, used to determine Cobb angle reference information of each vertebra in the vertebral image;

[0014] A processing module is used to determine the maximum Cobb angle between any two vertebrae in each vertebra based on the Cobb angle reference information, and output the maximum Cobb angle and information of the two vertebrae corresponding to the maximum Cobb angle.

[0015] In each embodiment of the present application, DR video data of the user's vertebra is acquired, a vertebral image is separated from each frame image in the DR video data, Cobb angle reference information of each vertebra is determined in the vertebral image, and the maximum Cobb angle between any two vertebrae in each vertebra is determined based on the Cobb angle reference information. Thus, the maximum Cobb angle of the vertebra can be automatically and accurately measured, thereby reducing the error, time and cost of manual measurement, and outputting the maximum Cobb angle and information of the two vertebrae corresponding to the maximum Cobb angle, thereby intuitively displaying the degree of curvature of the vertebra. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative labor.

[0017] Figure 1 is a flow chart of a method for determining the maximum Cobb angle between vertebrae provided in this embodiment;

[0018] Figure 2 is an image of a vertebra included in a DR video in the method for determining the maximum Cobb angle between vertebrae provided in this embodiment;

[0019] Figure 3 yes Figure 2 The image of the vertebral body separated in the image shown;

[0020] Figure 4 is a schematic diagram of determining a vertebral center point in a method for determining a maximum Cobb angle between vertebrae provided in an embodiment of the present invention;

[0021] Figure 5 is a schematic diagram of marking a vertebral normal vector in a method for determining a maximum Cobb angle between vertebrae provided in an embodiment of the present invention;

[0022] Figure 6 is a schematic diagram of the upper edge line and the lower edge line in the method for determining the maximum Cobb angle between vertebrae provided by an embodiment of the present invention;

[0023] Figure 7 is a schematic diagram of the angle formed by the unit vector and the normal vector in the method for determining the maximum Cobb angle between vertebrae provided by an embodiment of the present invention;

[0024] Figure 8 is a schematic diagram of two vertebrae corresponding to the maximum Cobb angle in the method for determining the maximum Cobb angle between vertebrae provided by an embodiment of the present invention;

[0025] Fig. 9 It is a schematic diagram of the structure of a device for determining the maximum Cobb angle between vertebrae provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0027] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present application, are intended only to indicate specific features, numbers, steps, operations, elements, components, or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing items or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations of the foregoing items.

[0028] Furthermore, the terms “first”, “second”, “third”, etc. are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0029] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present application belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present application.

[0030] The maximum Cobb angle of the cervical spine is a key parameter for evaluating the degree of abnormal cervical curvature, and is widely used in the diagnosis, classification and treatment of cervical deformity in clinical practice. Abnormal cervical curvature may lead to poor head posture, neck stiffness, limited movement, and even symptoms such as neck muscle fatigue, nerve compression and pain. In severe cases, it may affect daily life and work quality. With age, especially in the elderly and patients with certain spinal diseases, abnormal cervical curvature is more common. Therefore, timely and accurate assessment of the cervical curvature is crucial for monitoring and treating the disease.

[0031] The maximum Cobb angle of the spine is an important indicator for assessing the severity of scoliosis and is widely used in diagnosis, treatment planning, and surgical decisions. Scoliosis may cause back pain, abnormal posture, and limited movement, seriously affecting the quality of life. Through imaging examinations, the Cobb angle quantifies the angle of spinal curvature, provides standardized assessments, and eliminates subjective errors in traditional diagnosis. This method helps doctors determine the severity of scoliosis, monitor disease progression, and determine treatment plans. For mild scoliosis, conservative treatment can be adopted; severe scoliosis may require surgical intervention. Cobb angle measurement provides a scientific basis for personalized treatment and prognosis management.

[0032] Lumbar scoliosis (abnormal lumbar curvature) often leads to poor posture, lumbar discomfort, limited movement, and even symptoms such as lumbar muscle fatigue, nerve compression or intermittent claudication, which seriously affects daily life and quality of life. Lumbar scoliosis is more common in adolescents, the elderly and patients with spinal diseases. Therefore, timely and accurate assessment of the degree of lumbar scoliosis is crucial for its classification diagnosis and subsequent treatment. The maximum Cobb angle is an important clinical evaluation indicator for lumbar scoliosis. By measuring the angle of scoliosis, it can accurately quantify the severity of scoliosis and play a key role in formulating personalized treatment plans. In the past, based on traditional imaging evaluation and naked eye observation, it was difficult to accurately grasp the specific angle of lumbar scoliosis, which was prone to subjective errors and inconsistent measurements. The introduction of the maximum Cobb angle provides a standardized and quantitative evaluation method, which can not only help doctors judge the progression of scoliosis more objectively, but also provide a scientific basis for surgical or non-surgical treatment, greatly improving the treatment effect and patient prognosis management.

[0033] See also Figure 1 , Figure 1 A method for determining the maximum Cobb angle between vertebrae is shown. The method can be applied to an electronic device, which can be a computer or other electronic device with data processing capability. The electronic device is connected to a DR (Digital Radiography) device and can obtain data from the DR device. The method includes:

[0034] S101, obtaining DR video data of a user's vertebral body;

[0035] The vertebral body image of the user is captured by a DR device, and the vertebral body may include one, two or three of the cervical vertebrae, the spine and the lumbar vertebrae.

[0036] The posture presented by the user when photographing the vertebral body impact corresponds to the item that needs to be checked.

[0037] The electronic device obtains the DR video data captured by the DR device from the DR device.

[0038] S102, separating a vertebral body image from each frame of the DR video data;

[0039] Through deep learning segmentation algorithm or threshold segmentation algorithm, the vertebral image is separated from each frame of DR data. The separation result consists of 0 and 1, where 0 represents the non-vertebral area and 1 represents the vertebral area. Take lumbar separation as an example, see Figure 2 and Figure 3 , the image of the lumbar spine in the DR video before separation is as follows Figure 2 As shown, from Figure 2 The separated lumbar vertebrae images are shown in Figure 3 shown.

[0040] Among them, deep learning segmentation algorithms such as CNN (Convolutional Neural Networks) algorithm, FCN (Fully Convolutional Networks) algorithm, U-Net algorithm, etc. can complete the segmentation of DR images and obtain vertebral images through these deep learning segmentation algorithms;

[0041] The threshold segmentation algorithm is a region-based image segmentation technology. The principle is to divide image pixels into several categories. It is simple to implement, has low computational complexity and relatively stable performance.

[0042] S103, determining Cobb angle reference information of each vertebra in the vertebral image;

[0043] The Cobb angle reference information is used to calculate the Cobb angle between vertebrae.

[0044] Specifically, the preset geometric features of each vertebra are determined, and the Cobb angle reference vector of each vertebra is determined according to the geometric features;

[0045] The preset geometric features may include the center point, the center of gravity, the upper edge and the lower edge of each vertebral body;

[0046] In one embodiment, when the geometric feature is the center point or the center of gravity, the Cobb angle reference vector is the limiting vector in the normal direction of the center point or the center of gravity, that is, the normal vector.

[0047] The centroid is the point where the center of gravity of each vertebra is located;

[0048] The center point is the intersection of the two diagonals of the circumscribed rectangle of each vertebra. The circumscribed rectangle refers to the smallest rectangle that can contain the vertebra, such as Figure 4 As shown, Figure 4 The intersection point 43 of the two diagonal lines of the circumscribed rectangle 42 of the vertebral body 41 in FIG. 4 is the center point.

[0049] Determining the center point or center of gravity of each vertebra includes:

[0050] The coordinates of all the pixels in each vertebra are obtained from the vertebral image, and the center point or the center of gravity of each vertebra is calculated based on the coordinates of all the pixels in each vertebra.

[0051] The coordinates of all the pixel points in each vertebra are obtained from the vertebral image, and the center of gravity or the center point of each vertebra is calculated based on the coordinates of all the pixel points in each vertebra.

[0052] Take the calculation of the center of gravity of a vertebra as an example:

[0053] The i-th pixel point of the vertebra is [x i ,y i ], the total number of pixel points is n, the coordinates of all pixel points of the vertebra are averaged to obtain the centroid of the vertebra The calculation formula is as follows:

[0054]

[0055] The center of gravity of each vertebra can be calculated according to the above formula.

[0056] Furthermore, the normal vector of each vertebra is determined according to the center point or the center of gravity point. Specifically, a curve may be fitted through the geometric points of the vertebra, and the normal vector may be obtained based on the fitted curve.

[0057] Taking the centroid as an example, the centroid of the vertebra in each frame of vertebral image is fitted with a curve by a calculation method selected from linear fitting, polynomial fitting, nonlinear fitting, interpolation method, regularization and robust fitting, machine learning and neural network fitting, Bayesian linear regression or Gaussian process regression, and the normal vector at the centroid is obtained according to the fitted curve, and the vertebra is marked with the normal vector. Figure 5 , Figure 5 FIG. 5 is a schematic diagram of a cone with a normal vector 51 marked.

[0058] In another embodiment, see Figure 6 When the geometric feature is the upper edge or the lower edge, the Cobb angle reference vector is the corresponding upper edge line 61 or lower edge line 62.

[0059] The upper edge line is obtained by linear regression of the upper edge of the segmented vertebral body, and the lower edge line is obtained by linear regression of the lower edge of the segmented vertebral body.

[0060] S104: Determine the maximum Cobb angle between any two vertebrae in each vertebra based on the Cobb angle reference information, and output the maximum Cobb angle and information of the two vertebrae corresponding to the maximum Cobb angle.

[0061] A unit vector with a certain direction is preset, and the certain direction can be any direction. Preferably, the certain direction is a vertical direction, such as Figure 7 The unit vector 71 is shown.

[0062] Calculate the angle between the unit vector 71 of the preset direction and the Cobb angle reference vector 72 of each vertebra. Figure 7 The Cobb angle reference vector in is the normal vector;

[0063] See also Figure 8 , determine the first vertebra 73 with the largest angle between the unit vector 71 and the Cobb angle reference vector 72 among each vertebra, and determine the second vertebra 74 with the smallest angle between the unit vector 71 and the Cobb angle reference vector 72, and determine the Cobb angle between the first vertebra 73 and the second vertebra 74 as the maximum Cobb angle between each vertebra.

[0064] The angle value of the maximum Cobb angle is output, and the information of the first vertebra and the second vertebra may be the number information, position information, etc. of the vertebra.

[0065] In an embodiment of the present application, by acquiring DR video data of the user's vertebrae, the vertebral image is separated from each frame image in the DR video data, the Cobb angle reference information of each vertebra is determined in the vertebral image, and the maximum Cobb angle between any two vertebrae in each vertebra is determined based on the Cobb angle reference information. In this way, the maximum Cobb angle of the vertebra can be automatically and accurately measured, reducing the error, time and cost of manual measurement, and outputting the maximum Cobb angle and the information of the two vertebrae corresponding to the maximum Cobb angle, thereby intuitively displaying the degree of curvature of the vertebra.

[0066] See also Fig. 9 , Fig. 9 A device for determining the maximum Cobb angle between vertebrae is shown. The device is an electronic device such as a computer with data processing capability in the above embodiment. The device is connected to a DR device and may include:

[0067] An acquisition module 901 is used to acquire DR video data of a user's vertebral body;

[0068] A separation module 902, configured to separate a vertebral body image from each frame of the DR video data;

[0069] A determination module 903, configured to determine Cobb angle reference information of each vertebra in the vertebral image;

[0070] The processing module 904 is used to determine the maximum Cobb angle between any two vertebrae in each vertebra based on the Cobb angle reference information, and output the maximum Cobb angle and information of the two vertebrae corresponding to the maximum Cobb angle.

[0071] Furthermore, the determination module 903 is further configured to determine a preset geometric feature of each vertebra, and determine a Cobb angle reference vector of each vertebra according to the geometric feature.

[0072] The determination module 903 is further used to determine the center point or the center of gravity of each vertebral body;

[0073] For the center point or center of gravity of each vertebra, a fitting curve is obtained according to a preset fitting algorithm, and based on the fitting curve, a vector of the normal direction of the center point or center of gravity of each vertebra is obtained, which corresponds to the Cobb angle reference vector of each vertebra.

[0074] Furthermore, the determination module 903 is further configured to determine the upper edge line or the lower edge line of each vertebral body, and determine the direction of the upper edge line or the lower edge line of each vertebral body as the Cobb angle reference vector of each vertebral body.

[0075] The processing module 904 is further used to calculate the angle between the unit vector of the preset direction and the Cobb angle reference vector of each vertebra;

[0076] Determine the first vertebra with the largest angle and the second vertebra with the smallest angle;

[0077] The Cobb angle between the first vertebral body and the second vertebral body is determined as the maximum Cobb angle.

[0078] Further, the preset direction includes a vertical direction.

[0079] The determination module 903 is further used to obtain the coordinates of all pixel points in each vertebra from the vertebra image;

[0080] According to the coordinates of all the pixel points of each vertebra, the center point or the center of gravity of each vertebra is calculated.

[0081] For other technical details, please refer to the description of the aforementioned embodiment.

[0082] In an embodiment of the present application, an acquisition module acquires DR video data of a user's vertebra, a separation module separates a vertebral image from each frame of the DR video data, a determination module determines Cobb angle reference information of each vertebra in the vertebral image, and a processing module determines the maximum Cobb angle between any two vertebrae in each vertebra based on the Cobb angle reference information, thereby automatically and accurately measuring the maximum Cobb angle of the vertebra, reducing the error, time and cost of manual measurement. The processing module is also used to output the maximum Cobb angle and information of the two vertebrae corresponding to the maximum Cobb angle, thereby intuitively displaying the degree of curvature of the vertebra.

[0083] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0084] The above is a description of the method and device for determining the maximum Cobb angle between vertebrae provided in the present application. For technicians in this field, according to the ideas of the embodiments of the present application, there may be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for determining the maximum Cobb angle between vertebrae, characterized in that: include: Obtain DR video data of the user's vertebral body; Separating a vertebral image from each frame of the DR video data; Determining Cobb angle reference information of each vertebra in the vertebral image; The maximum Cobb angle between any two vertebrae in each vertebra is determined based on the Cobb angle reference information, and the maximum Cobb angle and information of the two vertebrae corresponding to the maximum Cobb angle are output.

2. The method according to claim 1, characterized in that Determining the Cobb angle reference information of each vertebra in the vertebral image includes: The preset geometric features of each vertebra are determined, and the Cobb angle reference vectors of each vertebra are determined according to the geometric features.

3. The method according to claim 2, characterized in that The determining of the preset geometric features of each vertebra, and determining the Cobb angle reference vector of each vertebra according to the geometric features comprises: Determine the center point or center of gravity of each vertebral body; For the center point or center of gravity of each vertebra, a fitting curve is obtained according to a preset fitting algorithm, and based on the fitting curve, a vector of the normal direction of the center point or center of gravity of each vertebra is obtained, which corresponds to the Cobb angle reference vector of each vertebra.

4. The method according to claim 2, characterized in that: The determining of the preset geometric features of each vertebra, and determining the Cobb angle reference vector of each vertebra according to the geometric features comprises: The upper edge line or the lower edge line of each vertebra is determined, and the direction of the upper edge line or the lower edge line of each vertebra is determined as the Cobb angle reference vector of each vertebra.

5. The method according to claim 2, characterized in that: Determining the maximum Cobb angle between any two vertebrae in each vertebra based on the Cobb angle reference information comprises: Calculating the angle between the unit vector of the preset direction and the Cobb angle reference vector of each vertebra; Determine the first vertebra with the largest angle and the second vertebra with the smallest angle; A Cobb angle between the first vertebral body and the second vertebral body is determined as the maximum Cobb angle.

6. The method according to claim 5, characterized in that The preset direction includes a vertical direction.

7. The method according to claim 3, characterized in that Determining the center point or center of gravity of each vertebral body comprises: Obtaining coordinates of all pixel points in each vertebra from the vertebra image; The center point or the center of gravity of each vertebra is calculated based on the coordinates of all the pixel points of each vertebra.

8. A device for determining the maximum Cobb angle between vertebrae, characterized in that: include: An acquisition module, used to acquire DR video data of a user's vertebral body; A separation module, used for separating a vertebral body image from each frame of the DR video data; A determination module, used to determine Cobb angle reference information of each vertebra in the vertebral image; A processing module is used to determine the maximum Cobb angle between any two vertebrae in each vertebra based on the Cobb angle reference information, and output the maximum Cobb angle and information of the two vertebrae corresponding to the maximum Cobb angle.

9. The determination device according to claim 8, characterized in that: The determination module is further used to determine preset geometric features of each vertebra, and determine the Cobb angle reference vector of each vertebra according to the geometric features.

10. The determination device according to claim 9, characterized in that: The determination module is further used to determine the center point or center of gravity of each vertebral body; For the center point or center of gravity of each vertebra, a fitting curve is obtained according to a preset fitting algorithm, and based on the fitting curve, a vector of the normal direction of the center point or center of gravity of each vertebra is obtained, which corresponds to the Cobb angle reference vector of each vertebra.

Images