Automatic assessment method and device for stiffness of cervical vertebra
By extracting the key geometric points of the cervical vertebrae from the DR video data and automatically assessing the cervical vertebrae hardness, the problem of inaccurate quantification of the degree of cervical vertebrae in the existing technology is solved, and efficient and accurate cervical vertebrae stiffness evaluation is achieved.
Patent Information
- Application Number
- CN202411574558.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-06
- Publication Date
- 2025-02-25
AI Technical Summary
The prior art cannot accurately quantify the degree of cervical stiffness, resulting in qualitative evaluation and measurement errors, and manual evaluation is time-consuming and labor-intensive, and there are misdiagnosis and evaluation errors.
By obtaining DR video data of the cervical spine movement process, separating the cervical spine images, extracting key geometric points of the cervical spine block, and evaluating the cervical spine stiffness based on these points, achieving automated evaluation.
It realizes automatic and accurate assessment of cervical stiffness, reduces misdiagnosis and evaluation errors, reduces manpower consumption, and improves evaluation efficiency and accuracy.
Smart Images
Figure CN119515818A_ABST
Abstract
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 automatically evaluating cervical spine stiffness. Background Art
[0002] Mild cervical stiffness can lead to poor head posture and limited movement, affecting daily life and appearance, and may even cause nerve compression and neck deformity, causing intractable neck pain and neurological dysfunction. Cervical stiffness is more common in middle-aged and elderly people, so early diagnosis and preoperative and postoperative evaluation of cervical stiffness are crucial. Accurate assessment of cervical stiffness is crucial for the classification diagnosis and treatment of cervical stiffness. In the past, based on doctors' visual inspection, palpation and manual range of motion examinations, it was impossible to accurately quantify the degree of cervical stiffness and only qualitative assessments could be performed. In addition, manual inspections are prone to measurement errors and are not intuitive. Summary of the invention
[0003] The embodiments of the present application provide an automatic evaluation method and device for cervical stiffness, which realizes the automation of cervical stiffness evaluation, solves the misdiagnosis and evaluation errors caused by previous manual evaluation methods, and solves the manpower consumption caused by manual evaluation.
[0004] The embodiment of the present application provides, on one hand, a method for automatically evaluating cervical spine stiffness, comprising: acquiring DR video data of a user's cervical spine movement process;
[0005] Separating a cervical spine image from each frame of the DR video data;
[0006] Extracting key geometric points of each cervical vertebra block in the cervical vertebra image;
[0007] Cervical spine stiffness was evaluated based on the key geometric points of each cervical spine block at different times.
[0008] The present application also provides an automatic evaluation device for cervical stiffness, including:
[0009] An acquisition module, used to acquire DR video data of the user's cervical spine movement process;
[0010] A separation module, used for separating a cervical vertebra image from each frame of the DR video data;
[0011] An extraction module, used for extracting key geometric points of each cervical vertebra block in the cervical vertebra image;
[0012] The evaluation module is used to evaluate the cervical spine stiffness according to the key geometric points of each cervical spine block at different times.
[0013] In each embodiment of the present application, by acquiring DR video data of the user's cervical spine movement process, the cervical spine image is separated from each frame image in the DR video data, and the dynamic cervical spine state that can provide the entire cervical spine activity cycle can be obtained from the dynamic DR video, and the key geometric points of each cervical spine block in the cervical spine image are extracted. The cervical spine stiffness is evaluated according to the key geometric points of each cervical spine block at different times, and the cervical spine stiffness can be accurately calculated through the position of the key geometric points, so that the cervical spine stiffness can be automatically and accurately evaluated, and an accurate analysis of the current health status of the cervical spine can be achieved. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] 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.
[0015] Figure 1 is a flow chart of an automatic evaluation method for cervical vertebra stiffness provided in this embodiment;
[0016] Figure 2 is an image including the cervical vertebra in the DR video in the automatic evaluation method for cervical vertebra stiffness provided in this embodiment;
[0017] Figure 3 yes Figure 2 The image of the cervical spine isolated in the image shown;
[0018] Figure 4 is a schematic diagram of the morphological line of the cervical spine in the automatic evaluation method of cervical spine stiffness provided by an embodiment of the present invention;
[0019] Figure 5 is a schematic diagram of an evaluation area formed by cervical vertebrae movement in the automatic evaluation method for cervical vertebrae stiffness provided by an embodiment of the present invention;
[0020] Figure 6 It is a schematic diagram of the structure of an automatic evaluation device for cervical vertebra stiffness provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0021] 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 ordinary technicians in this field without creative work are within the scope of protection of this application.
[0022] 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.
[0023] 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.
[0024] 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.
[0025] See also Figure 1 , Figure 1 An automatic evaluation method for cervical stiffness is shown, which is applied to an automatic evaluation device, which can be an electronic device such as a computer with data processing capabilities. The automatic evaluation device is connected to a DR (Digital Radiography) device and can obtain data from the DR device. The method includes:
[0026] S101, obtaining DR video data of the user's cervical spine movement process;
[0027] The DR device can be used to capture images of the user's cervical spine moving along a preset trajectory, specifically the process of moving from a head-down state to a head-up state.
[0028] The electronic device obtains the DR video data shot by the DR device from the DR device.
[0029] S102, separating a cervical vertebra image from each frame of the DR video data;
[0030] Through deep learning segmentation algorithm or threshold segmentation algorithm, the cervical spine image is separated from each frame of DR data. The separation result consists of 0 and 1, where 0 represents the non-cervical spine area and 1 represents the cervical spine area. Figure 2 As shown, the image of the cervical spine after separation is as follows Figure 3 shown.
[0031] Among them, deep learning segmentation algorithms such as CNN (Convolutional Neural Networks) algorithm, FCN (Fully Convolutional Networks) algorithm, U-Net algorithm, etc. can complete image segmentation and obtain cervical spine images through these deep learning segmentation algorithms;
[0032] 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.
[0033] S103, extracting key geometric points of each cervical vertebra block in the cervical vertebra image;
[0034] The key geometric points may include the centroid or center point of each cervical vertebra block, where the centroid is the point where the center of gravity of each cervical vertebra block is located, and the center point is the intersection of two diagonals of the circumscribed rectangle of each cervical vertebra block, where the circumscribed rectangle refers to the smallest rectangle that can contain the cervical vertebra block.
[0035] The coordinates of all the pixels in each cervical vertebra block are obtained from the cervical vertebra image, and the center of gravity or the center point of each cervical vertebra block is calculated based on the coordinates of all the pixels in each cervical vertebra block.
[0036] Take the calculation of the center of gravity of a cervical vertebra block as an example:
[0037] The i-th pixel point of the cervical vertebra block is [x i ,y i ], the total number of pixel points is n, the coordinates of all pixel points of the cervical vertebra block are averaged to obtain the center of gravity of the cervical vertebra block The calculation formula is as follows:
[0038]
[0039] The center of gravity of each cervical vertebra block can be calculated according to the above formula.
[0040] S104. Evaluate cervical stiffness according to key geometric points of each cervical vertebrae block at different times.
[0041] According to the center of gravity or the center point of each cervical vertebra block at different times, the cervical vertebra elastic area and the cervical vertebra active area are obtained, and according to the ratio of the cervical vertebra elastic area to the cervical vertebra active area, the cervical vertebra stiffness is obtained.
[0042] Specifically, the cervical stiffness is calculated based on the center of gravity or the center point of each cervical vertebra block in the first frame of cervical vertebra image obtained at the first moment, and based on the center of gravity or the center point of each cervical vertebra block in the last frame of cervical vertebra image obtained at the last moment.
[0043] Specifically, the centroid points or the center points of each cervical vertebra block in the first frame of the cervical vertebra image are sequentially connected to obtain a first morphological line, and the centroid points or the center points of each cervical vertebra block in the last frame of the cervical vertebra image are sequentially connected to obtain a second morphological line;
[0044] The center of gravity or the center point of the first and last two cervical vertebrae blocks in the first frame of the cervical vertebrae image is connected by a straight line to obtain a third morphological line, and the center of gravity or the center point of the first and last two cervical vertebrae blocks in the last frame of the cervical vertebrae image is connected by a straight line to obtain a fourth morphological line;
[0045] Among them, the head cervical vertebra block is the uppermost cervical vertebra block in each frame of the cervical vertebra image, and the tail cervical vertebra block is the lowermost cervical vertebra block in each frame of the cervical vertebra image; in the cervical vertebra image, the cervical vertebra blocks are C2 to C7 cervical vertebra blocks from the uppermost to the lowermost.
[0046] The caudal cervical vertebra block in the first frame is aligned and overlapped with the caudal cervical vertebra block in the last frame, so as to form a first area sandwiched between the first morphological line and the third morphological line, a second area sandwiched between the second morphological line and the fourth morphological line, and a third area sandwiched between the first morphological line and the second morphological line;
[0047] Calculating the sum of the area of the first region sandwiched between the first morphological line and the third morphological line and the area of the second region sandwiched between the second morphological line and the fourth morphological line to obtain the cervical vertebra elastic area;
[0048] The area of the third region sandwiched between the first morphological line and the second morphological line is used as the cervical vertebra activity area;
[0049] The ratio of the elastic area of the cervical vertebra to the active area of the cervical vertebra is calculated to obtain the stiffness of the cervical vertebra.
[0050] Specifically, the above-mentioned morphological line is the morphological line of the cervical vertebra. The first morphological line is obtained by connecting the center of gravity points of each cervical vertebra block in the first frame of the cervical vertebra image in sequence or connecting the center points in sequence; the second morphological line is obtained by connecting the center of gravity points of each cervical vertebra block in the last frame of the cervical vertebra image in sequence or connecting the center points in sequence.
[0051] For example, Figure 4 As shown in FIG. 1 , the center points of each cervical vertebra block in the cervical vertebra image are connected in sequence with straight lines to obtain a morphological line of the cervical vertebra at this time. The center points of each cervical vertebra block in the cervical vertebra image are connected in sequence with straight lines to obtain a morphological line of the cervical vertebra at this time. Figure 4 The centroid points shown are connected to form the pattern line.
[0052] Figure 4 The 6 cervical vertebrae in the body are C2 to C7 from top to bottom. Figure 4Based on the cervical vertebrae morphology line, the center of gravity of the C7 cervical vertebra is used as the reference point for registration. Figure 5 . Figure 5 In the cervical image, the center of gravity of the C2 cervical vertebra and the center of gravity of the C7 cervical vertebra in the first frame are connected by a straight line to obtain the third morphological line L3, and the center of gravity of the C2 cervical vertebra and the center of gravity of the C7 cervical vertebra in the last frame are connected by a straight line to obtain the fourth morphological line L4, wherein the first area S11 represents the area of the area sandwiched by the third morphological line L3 of the first frame and the first morphological line L1 of the six center of gravity points of each cervical vertebra block in the first frame, and the second area S12 represents the area of the area sandwiched by the fourth morphological line L4 of the last frame and the second morphological line L2 of the six center of gravity points of each cervical vertebra block, then the calculation method of the cervical stiffness Sc is as follows:
[0053] Sc=S2 / (S1+S2)
[0054] Among them, S1 represents the elastic area of the cervical vertebra, which is the sum of the first area S11 and the second area S12; S2 represents the active area of the cervical vertebra, which is the area of the third area sandwiched by the first morphological line L1 and the second morphological line L2, that is, the movement range of the cervical vertebra from the first frame to the last frame of the cervical vertebra image.
[0055] The larger the calculated cervical stiffness Sc, the stiffer the cervical spine, and the smaller the calculated cervical stiffness Sc, the more flexible the cervical spine.
[0056] Furthermore, after step S104, the method further includes: outputting a visualization result of the cervical stiffness, the visualization result including a first area sandwiched between the first morphology line and the third morphology line, a second area sandwiched between the second morphology line and the fourth morphology line, and a third area sandwiched between the first morphology line and the second morphology line.
[0057] That is, the display screen of the automatic evaluation device for cervical spine stiffness shows Figure 5 The first area S11 and the second area S12 formed by the first shape line L1, the second shape line L2, the third shape line L3 and the fourth shape line L4 form the cervical vertebra elastic area S1 and the third area cervical vertebra activity area S2. Thus, the size of the cervical vertebra stiffness Sc can be intuitively obtained by comparing the S2 area with the S1 area on the display screen, and can also be further Figure 5 The specific value of Sc is marked on the graph shown.
[0058] In an embodiment of the present application, by acquiring DR video data of the user's cervical spine movement process, the cervical spine image is separated from each frame image in the DR video data, and the dynamic cervical spine state that can provide the entire cervical spine activity cycle can be obtained from the dynamic DR video. The key geometric points of each cervical spine block in the cervical spine image are extracted, and the cervical spine stiffness is evaluated according to the key geometric points of each cervical spine block at different times. The cervical spine stiffness can be accurately calculated through the position of the key geometric points, thereby automatically and accurately evaluating the cervical spine stiffness and achieving accurate analysis of the current health status of the cervical spine.
[0059] See also Figure 6 , Figure 6 An automatic evaluation device for cervical stiffness is shown, which is an electronic device such as a computer with data processing capabilities. The automatic evaluation device is connected to a DR device and may include:
[0060] An acquisition module 201 is used to acquire DR video data of the user's cervical spine movement process;
[0061] A separation module 202, configured to separate a cervical vertebra image from each frame of the DR video data;
[0062] An extraction module 203 is used to extract key geometric points of each cervical vertebra block in the cervical vertebra image;
[0063] The evaluation module 204 is used to evaluate the cervical stiffness according to the key geometric points of each cervical block at different times.
[0064] Furthermore, the extraction module 203 is also used to obtain the coordinates of all pixel points in each cervical vertebra block from the cervical vertebra image;
[0065] The center of gravity or center point of each cervical vertebra block is calculated based on the coordinates of all pixel points of each cervical vertebra block.
[0066] Furthermore, the evaluation module 204 is also used to obtain the cervical elastic area and the cervical active area according to the center of gravity or the center point of each cervical vertebra block at different times, and obtain the cervical stiffness according to the ratio of the cervical elastic area to the cervical active area.
[0067] Furthermore, the evaluation module 204 is further configured to sequentially connect the centroids or the center points of each cervical vertebra block in the first frame of the cervical vertebra image to obtain a first morphological line, and sequentially connect the centroids or the center points of each cervical vertebra block in the last frame of the cervical vertebra image to obtain a second morphological line;
[0068] Connecting the center of gravity or the center point of the first and last two cervical vertebrae blocks in the first frame of the cervical vertebrae image to obtain a third morphology line, and connecting the center of gravity or the center point of the first and last two cervical vertebrae blocks in the last frame of the cervical vertebrae image to obtain a fourth morphology line;
[0069] The head cervical vertebra block is the top cervical vertebra block in each frame of the cervical vertebra image, and the tail cervical vertebra block is the bottom cervical vertebra block in each frame of the cervical vertebra image;
[0070] The caudal cervical vertebra block in the first frame is aligned and overlapped with the caudal cervical vertebra block in the last frame, so as to form the first area sandwiched between the first morphological line and the third morphological line, the second area sandwiched between the second morphological line and the fourth morphological line, and the third area sandwiched between the first morphological line and the second morphological line;
[0071] Calculating the sum of the area of the first region sandwiched between the first morphological line and the third morphological line and the area of the second region sandwiched between the second morphological line and the fourth morphological line to obtain the cervical vertebra elastic area;
[0072] The area of the third region sandwiched between the first morphological line and the second morphological line is used as the cervical vertebra activity area.
[0073] Furthermore, the automatic assessment device also includes an output module for outputting a visualization result of the cervical spine stiffness, wherein the visualization result includes a first area sandwiched between the first morphology line and the third morphology line, a second area sandwiched between the second morphology line and the fourth morphology line, and a third area sandwiched between the first morphology line and the second morphology line.
[0074] The separation module 202 is further configured to separate the cervical vertebra image from each frame of image by using a deep learning segmentation algorithm or a threshold segmentation algorithm.
[0075] For other technical details, please refer to the description of the aforementioned embodiment.
[0076] In an embodiment of the present application, an acquisition module acquires DR video data of a user's cervical spine movement process, a separation module separates a cervical spine image from each frame of the DR video data, and can obtain a dynamic cervical spine state that can provide the entire cervical spine activity cycle from the dynamic DR video; an extraction module extracts key geometric points of each cervical spine block in the cervical spine image; an evaluation module evaluates cervical spine stiffness based on the key geometric points of each cervical spine block at different times, and can accurately calculate cervical spine stiffness through the positions of key geometric points, thereby being able to automatically and accurately evaluate cervical spine stiffness and achieve accurate analysis of the current health status of the cervical spine.
[0077] 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.
[0078] The above is a description of the automatic assessment method and device for cervical stiffness 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 automatically evaluating cervical spine stiffness, characterized in that: include: Obtain DR video data of the user's cervical spine movement process; Separating a cervical spine image from each frame of the DR video data; Extracting key geometric points of each cervical vertebra block in the cervical vertebra image; Cervical spine stiffness was evaluated based on the key geometric points of each cervical spine block at different times.
2. The method according to claim 1, characterized in that The step of extracting key geometric points of each cervical vertebra block in the cervical vertebra image comprises: Obtaining coordinates of all pixel points in each cervical vertebra block from the cervical vertebra image; The center of gravity or center point of each cervical vertebra block is calculated based on the coordinates of all pixel points of each cervical vertebra block.
3. The method according to claim 2, characterized in that The step of evaluating the stiffness of the cervical spine according to the key geometric points of the cervical spine of each cervical spine block at different times includes: The cervical vertebra elastic area and the cervical vertebra active area are obtained according to the center of gravity or the center point of each cervical vertebra block at different times, and the cervical vertebra stiffness is obtained according to the ratio of the cervical vertebra elastic area to the cervical vertebra active area.
4. The method according to claim 3, characterized in that The cervical vertebra elastic area and cervical vertebra activity area are obtained according to the center of gravity or the center point of each cervical vertebra block at different times, including: The centroids or the center points of each cervical vertebra block in the first frame of the cervical vertebra image are sequentially connected to obtain a first morphological line, and the centroids or the center points of each cervical vertebra block in the last frame of the cervical vertebra image are sequentially connected to obtain a second morphological line; A third morphology line is obtained by connecting the center of gravity or the center point of the first and last two cervical vertebrae blocks in the first frame of the cervical vertebrae image in a straight line, and a fourth morphology line is obtained by connecting the center of gravity or the center point of the first and last two cervical vertebrae blocks in the last frame of the cervical vertebrae image in a straight line, wherein the first cervical vertebrae block is the uppermost cervical vertebrae block in each frame of the cervical vertebrae image, and the last cervical vertebrae block is the lowermost cervical vertebrae block in each frame of the cervical vertebrae image; The caudal cervical vertebra block in the first frame is aligned and overlapped with the caudal cervical vertebra block in the last frame to obtain a first area sandwiched between the first morphological line and the third morphological line, a second area sandwiched between the second morphological line and the fourth morphological line, and a third area sandwiched between the first morphological line and the second morphological line; Calculating the sum of the area of the first region and the area of the second region to obtain the cervical vertebra elastic area; The area of the third region is used as the cervical vertebra activity area.
5. The method according to claim 4, characterized in that After evaluating the cervical vertebra stiffness according to the cervical vertebra key geometric points of each cervical vertebra block at different times, the method further includes: Outputting a visualization result of the cervical stiffness, the visualization result includes a first area sandwiched between the first morphology line and the third morphology line, a second area sandwiched between the second morphology line and the fourth morphology line, and a third area sandwiched between the first morphology line and the second morphology line.
6. The method according to claim 1, characterized in that The step of separating the cervical vertebra image from each frame of the DR video comprises: The cervical vertebra image is separated from each frame of the image by a deep learning segmentation algorithm or a threshold segmentation algorithm.
7. An automatic evaluation device for cervical vertebra stiffness, characterized in that: include: An acquisition module, used to acquire DR video data of the user's cervical spine movement process; A separation module, used for separating a cervical vertebra image from each frame of the DR video data; An extraction module, used for extracting key geometric points of each cervical vertebra block in the cervical vertebra image; The evaluation module is used to evaluate the cervical spine stiffness according to the key geometric points of each cervical spine block at different times.
8. The automatic evaluation device according to claim 7, characterized in that: The extraction module is further used to obtain the coordinates of all pixel points in each cervical vertebra block from the cervical vertebra image; The center of gravity or center point of each cervical vertebra block is calculated based on the coordinates of all pixel points of each cervical vertebra block.
9. The automatic evaluation device according to claim 8, characterized in that: The evaluation module is also used to obtain the cervical elastic area and the cervical active area according to the center of gravity or the center point of each cervical vertebra block at different times, and to obtain the cervical stiffness according to the ratio of the cervical elastic area to the cervical active area.
10. The automatic evaluation device according to claim 9, characterized in that: The evaluation module is further configured to sequentially connect the centroids or the center points of each cervical vertebra block in the first frame of the cervical vertebra image to obtain a first morphological line, and sequentially connect the centroids or the center points of each cervical vertebra block in the last frame of the cervical vertebra image to obtain a second morphological line; Connecting the center of gravity or the center point of the first and last two cervical vertebrae blocks in the first frame of the cervical vertebrae image to obtain a third morphology line, and connecting the center of gravity or the center point of the first and last two cervical vertebrae blocks in the last frame of the cervical vertebrae image to obtain a fourth morphology line; The head cervical vertebra block is the uppermost cervical vertebra block in each frame of the cervical vertebra image, and the tail cervical vertebra block is the lowermost cervical vertebra block in each frame of the cervical vertebra image; The caudal cervical vertebra block in the first frame is aligned and overlapped with the caudal cervical vertebra block in the last frame to obtain a first area sandwiched between the first morphological line and the third morphological line, a second area sandwiched between the second morphological line and the fourth morphological line, and a third area sandwiched between the first morphological line and the second morphological line; Calculating the sum of the area of the first region and the area of the second region to obtain the cervical vertebra elastic area; The area of the third region is used as the cervical vertebra activity area.