Integrated device and system for measuring and correcting kyphosis malformation angle of fracture centrum
Through integrated devices and machine learning technology, the kyphosis angle of fractured vertebrae is directly measured and corrected, solving the cumbersome problems of relying on medical contrast images in the existing technology, and achieving accurate measurement and convenient correction.
Patent Information
- Application Number
- CN202510374540.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-27
- Publication Date
- 2025-07-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the prior art, the measurement of the kyphosis angle of fractured vertebrae relies on medical contrast images, resulting in cumbersome and inconvenient measurement process.
It adopts an integrated device, including a fixing part and a curved substrate, equipped with a high-precision drive motor and position sensor, combined with machine learning technology, directly measure and correct the spinal structure, and realizes accurate calculation and correction of Cobb angles through data modules and control modules.
It significantly simplifies the measurement process, improves the accuracy and convenience of measurement, provides real-time correction support, and improves measurement efficiency and credibility.
Smart Images

Figure CN120267272A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of reset devices, and specifically relates to an integrated device and system for measuring and correcting the kyphotic deformity angle of fractured vertebrae. Background Art
[0002] Kyphotic deformity of fractured vertebrae is an abnormal change in the spinal column morphology caused by vertebral fractures. The normal spinal column has a certain physiological curvature when viewed from the side. After vertebral fractures, especially in the thoracolumbar region, due to reasons such as vertebral body compression and collapse, the local kyphotic angle of the spinal column increases, forming a kyphotic deformity. Patients may experience symptoms such as back pain, limited mobility, and height loss. Severe kyphotic deformities may also affect cardiopulmonary function, digestive system function, etc. When the kyphotic deformity is severe, resulting in intractable pain, nerve function impairment, spinal instability, etc., surgical treatment is usually required. There are various surgical methods, such as percutaneous vertebroplasty (PVP) and percutaneous kyphoplasty (PKP), which inject bone cement into the vertebral body to restore the vertebral body height, relieve pain, and correct kyphotic deformities; for more severe cases, open surgery may be required, such as spinal osteotomy and orthopedic surgery, etc., to restore the normal sequence and stability of the spinal column. After a fracture, the kyphotic deformity angle of the vertebra is usually measured using the Cobb angle. This angle is obtained by drawing lines at specific positions on a lateral X-ray film and measuring. Specifically, a line parallel to the vertebral endplate needs to be drawn on the upper edge of the upper vertebral body and the lower edge of the lower vertebral body of the diseased vertebral body, and then vertical lines are drawn from these two lines respectively. The included angle between the two vertical lines is the Cobb angle. Traditionally, this measurement process needs to be carried out after obtaining medical images, involving drawing lines and measuring angles in the corresponding area on the image, and the process is relatively cumbersome.
[0003] The current method for measuring the kyphotic deformity angle of fractured vertebrae is to use automated means such as image recognition technology to replace manual measurement. However, this technology still relies on medical contrast images for measurement. Patients still need to use professional contrast equipment to obtain necessary medical images before these images can be measured and analyzed. Although the technology has made progress, the Cobb angle measurement process is still relatively cumbersome and requires reliance on medical contrast images.
[0004] Therefore, those skilled in the art have proposed an integrated device and system for measuring and correcting the kyphotic deformity angle of fractured vertebrae to solve the problems raised in the background art. Summary of the Invention
[0005] In order to solve the above technical problems, the present invention provides an integrated device and system for measuring and correcting the kyphotic deformity angle of fractured vertebrae to solve the problem that Cobb angle measurement in the prior art requires reliance on medical contrast equipment.
[0006] To achieve the above technical objectives and effects, the invention is realized through the following technical solutions: an integrated device for measuring and correcting the kyphosis angle of a fractured vertebral body, including a fixing part, the fixing part is wound and fixed on the limbs and torso of the patient, and an arc-shaped substrate for providing a fixing reference is connected to the fixing part, a soft area is wrapped around the edge of the arc-shaped substrate, and the central area surrounded by the soft area is set as the spinal measurement and reduction area;
[0007] Preferably, the number of high-precision drive motors is adapted to the number of position sensors. The high-precision drive motors drive the position sensors relative to the vertical axis of the arc-shaped substrate. The position sensors are connected to the outer surface of the spinal measurement and reduction area, and under the trend of the high-precision drive motors driving the position sensors, the structural change of the spinal measurement and reduction area is guided.
[0008] Preferably, the high-precision drive motors fix a plurality of the sensors through telescopic rods, and the telescopic rods are directly driven by the high-precision drive motors to adjust the positions of the sensors.
[0009] Preferably, the fixing part further includes a displacement limiting member. The displacement limiting member includes a fixing block integrally extending from the arc-shaped substrate, and an adhesive part is provided between the fixing block and the patient's skin.
[0010] Preferably, at the end of the fixing part, that is, the end far from the arc-shaped substrate, a magic tape is provided for further fixing the arc-shaped substrate.
[0011] Another object of the present invention is to disclose a control system for controlling the device for measuring the kyphosis angle of a fractured vertebral body and assisting in reduction, including a data module for processing data and a control module for adjusting the driving conditions of the high-precision drive motors;
[0012] The data of the sensors is directly fed back to the data module. The data module is also connected to a data interface, and the data interface is connected to an external computer to obtain data;
[0013] The data module issues an instruction to the control module according to the data transmitted by the external computer to adjust the spinal measurement and reduction area to form a structure conforming to the normal thoracic kyphosis and lumbar lordosis. After being pressed, the sensors change their positions and transmit displacement data to the data module to calculate the Cobb angle.
[0014] Further, after calculating the Cobb angle, the data module issues a reset command to the high-precision drive motors, and the high-precision drive motors drive the sensors to continuously apply pressure to the displacement area until they return to the starting position.
[0015] Further, a processing model is built into the data module. The processing model is preset with the values corresponding to the thoracic kyphosis and lumbar lordosis under normal conditions. After receiving the displacement data, the following steps are carried out:
[0016] S1. Data preprocessing: According to the displacement data of the displacement sensor, a comparison value is obtained by comparing with the normal value input in advance, and the collected comparison value is scaled and the missing values are filled;
[0017] S2. Estimate the Cobb angle: Use the processed data to estimate the Cobb angle, find the maximum displacement value and take it as the center of the bulge; by analyzing the adjacent displacement data, find the area with the smallest displacement change, and take the area with the smallest displacement change as the upper edge of the vertebra above the affected vertebra and the lower edge of the vertebra below; finally, combine the displacement data of the center of the bulge, the upper edge and the lower edge to calculate the Cobb angle;
[0018] S3. Train the calculation results to build a model: Divide the extracted features into a training set and a test set, and perform model training on the training set to optimize the model.
[0019] Further, the step S2 specifically includes the following steps:
[0020] Step 21. Smooth the comparison value to eliminate noise;
[0021] Step 22. Calculate the first derivative of the displacement data to identify the areas with the largest and smallest position changes;
[0022] Step 23. Based on the first derivative, find the data point corresponding to the maximum displacement value and take it as the center of the bulge;
[0023] Step 24. Detect the local minimum value of the first derivative to find the area with the smallest displacement change;
[0024] Step 25. Take the area with the smallest displacement change as the upper edge of the vertebra above the affected vertebra and the lower edge of the vertebra below;
[0025] Step 26. Use the displacement data of the center of the bulge, the upper edge and the lower edge to calculate the slopes of two straight lines;
[0026] Step 27. Calculate the Cobb angle using the relationship between the slopes and convert the result to an angle.
[0027] Further, the step S3 specifically includes the following steps:
[0028] Step 31. Pre-load a large amount of displacement data and the corresponding true Cobb angles as training and validation data to build a model;
[0029] Step 32. Perform the pre-step S1 based on the training data;
[0030] Step 33: Extract features from the preprocessed displacement data. The features include the maximum value, minimum value, average value, and standard deviation.
[0031] Step 34: Use the support vector machine (SVM) and support vector regression (SVR) as the basic models of the machine learning algorithm.
[0032] Step 35: Perform model training on the training set.
[0033] Step 36: Use methods such as cross-validation to evaluate the performance of the model on the training set and test set, and adjust the hyperparameters according to the evaluation results.
[0034] Step 37: Select the optimal model according to the evaluation results and retrain the model.
[0035] Step 38: Input the processed displacement data into the trained support vector regression model to obtain a predicted value as the estimated value of the Cobb angle.
[0036] Compared with the prior art, the present invention has the following beneficial effects:
[0037] 1. The present invention can directly correspond to the position of the patient's fractured vertebral body, and ensure the stable position of the arc-shaped substrate relative to the patient's waist through a specially designed fixing member, so as to achieve accurate measurement and effective correction of the Cobb angle; this design significantly simplifies the traditional Cobb angle measurement process, which no longer relies on medical imaging, but utilizes the characteristic of almost no barrier between the spine and the skin, and directly performs the test through the sensor on the arc-shaped substrate.
[0038] 2. The present invention introduces machine learning technology to construct a test model, which can intelligently evaluate and correct the single measurement result, thereby improving the reliability and accuracy of the data; this method combining machine learning not only optimizes the measurement process, but also improves the measurement accuracy and credibility.
[0039] 3. The present invention can achieve the correction effect by setting an auxiliary correction function, which can apply appropriate pressure to the diseased area by pushing the sensor; this integrated design not only provides a convenient test method for patients, but also can assist in correction to a certain extent, bringing substantial treatment help to patients.
[0040] 4. Through technological innovation and intelligent application, the present invention significantly improves the efficiency and convenience of measuring the kyphosis angle of the fractured vertebral body, and at the same time provides real-time correction support for patients. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] Figure 1 It is a device diagram for measuring the kyphosis angle of the fractured vertebral body and assisting in reduction of the present invention.
[0042] Figure 2 Internal structure diagram of the device for measuring the kyphotic deformity angle of a fractured vertebra and assisting in reduction according to the present invention;
[0043] Figure 3 Flow chart for training and constructing a model according to the present invention.
[0044] In the figure: 1. Arc-shaped substrate; 101. High-precision drive motor; 102. Position sensor; 2. Fixing part; 3. Vertebral measurement and reduction area; 4. Magic tape. Specific implementation manners
[0045] The following further describes in detail the implementation manners of the present invention in conjunction with the accompanying drawings and embodiments. The following embodiments are used to illustrate the present invention, but cannot be used to limit the scope of the present invention.
[0046] As Figure 1 and Figure 2 shown:
[0047] Embodiment: The present invention provides an integrated device for measuring and correcting the kyphotic deformity angle of a fractured vertebra. The device includes key components such as a fixing part 2, an arc-shaped substrate 1, a vertebral measurement and reduction area 3, a position sensor 102, and a high-precision drive motor 101;
[0048] The fixing part 2 has a unique design, including components that are wound and fixed to the limbs and torso of the patient, and a displacement limiting member connected to the arc-shaped substrate 1; the displacement limiting member ensures a stable relative position between the arc-shaped substrate 1 and the patient's spine through a fixing block and an adhesion part, which is the basis for accurate measurement;
[0049] The arc-shaped substrate 1 is the core structure of the device. Its edge is wrapped with a soft area to provide comfortable support for the patient and prevent skin damage; a number of uniformly distributed position sensors 102 are arranged in the vertebral measurement and reduction area 3 at the center of the substrate. These sensors are actively adjusted in position by a high-precision drive motor 101; the sensors can accurately capture the displacement data of the patient's spine, providing key information for subsequent Cobb angle calculation and spinal correction.
[0050] Specifically, each sensor is matched with a high-precision drive motor 101. The high-precision drive motor 101 can adjust the position of the sensor vertically along the axis; this design enables the sensor to closely fit the patient's spine and accurately measure its structural changes. The sensor is fixed by a telescopic rod and its position is directly driven to adjust, thereby ensuring high-precision and reliability of the measurement.
[0051] In order to achieve the fixation of the aforementioned structure, the displacement limiting member plays a key role; it stably fixes the curved substrate 1 on the patient's skin through the fixing block and the adhesive portion, ensuring that the device will not move or deviate during the measurement and correction process.
[0052] More specifically, the present invention further discloses a control system for controlling the aforementioned device and realizing complex calculation processes; the control system can receive data from sensors, perform accurate Cobb angle calculations, and formulate corresponding correction strategies based on the calculation results; by working in conjunction with the high-precision drive motor 101, the control system can achieve accurate measurement and effective correction of the patient's spine.
[0053] As can be seen from the above, the present invention provides an efficient and accurate fracture vertebral kyphosis angle measurement and auxiliary reduction device and its control system; the device not only has comfortable support and fixation functions, but also can achieve accurate measurement and effective correction of the spine through high-precision sensors and high-precision drive motors 101, providing strong support for the diagnosis and treatment of patients;
[0054] Specifically, the present invention further includes a data module and a control module, which work together to achieve the measurement of the kyphosis angle of the fractured vertebra and assist in the reduction;
[0055] The data module is responsible for processing the data from the sensor and interacting with the external computer. The data from the sensor is directly fed back to the data module, and the data module is also equipped with a data interface to connect to an external computer to obtain additional data or transmit data. In order to carry the functions of the data module and the control module, the present invention can use a microcomputer with sufficient computing power and memory, such as a Raspberry Pi or similar embedded systems, which can easily communicate and interact with each module and an external computer.
[0056] During the measurement process, the data module will issue instructions to the control module based on the data transmitted by the external computer, and adjust the spinal measurement reset area 3 to simulate the normal thoracic kyphosis and lumbar lordosis structure; when the sensor is compressed and changes position, it will transmit the displacement data to the data module, which is then used to calculate the Cobb angle; the calculation of the Cobb angle is achieved by measuring the angle between the upper and lower end plates of the two most inclined adjacent vertebrae in the spine; the displacement data of the sensor reflects the relative position relationship between the upper and lower end plates of the vertebrae, so that the Cobb angle can be accurately calculated;
[0057] Once the measurement is completed, the data module will issue a reset command to the high-precision drive motor 101; during the correction process, the control module will adjust the driving force and direction of the high-precision drive motor 101 according to the calculation results of the data module to assist in correcting the spine, making the Cobb angle gradually approach the normal range; the reset operation can be achieved by the high-precision drive motor 101 driving the sensor to continuously apply pressure to the displacement area until the sensor returns to the starting position, thereby realizing the simple correction of the spine.
[0058] As can be seen from the above, the data module and the control module of the present invention cooperate with each other, and by processing the sensor data and adjusting the high-precision drive motor 101, the accurate measurement and effective assisted reduction of the kyphosis angle of the fractured vertebral body are realized.
[0059] More specifically, combining the foregoing content, it can be known that the measurement of the Cobb angle needs to be realized through complex calculations, and since its test is calculated by the difference between the diseased shape and the normal structure, there may be a large error; to solve the above problems, in this embodiment, the data module is built-in with a processing model, and the processing model is preset with the values corresponding to the thoracic kyphosis and lumbar lordosis under normal conditions, and the following steps are performed after receiving the displacement data:
[0060] S1. Data preprocessing;
[0061] According to the displacement data of the displacement sensor, a comparison value is obtained by comparing with the pre-input normal value, and the collected comparison value is scaled and the missing values are filled.
[0062] S2. Estimate the Cobb angle:
[0063] Apply the processed data to estimate the Cobb angle, find the maximum displacement value and use it as the convex center; by analyzing the adjacent displacement data, find the area with the smallest displacement change and use the area with the smallest displacement change as the upper edge of the upper vertebral body of the diseased vertebra and the lower edge of the lower vertebral body;
[0064] Combine the displacement data of the convex center, the upper edge and the lower edge to calculate the Cobb angle;
[0065] S3. Train the calculation results to construct a model:
[0066] Divide the extracted features into a training set and a test set, and perform model training on the training set to optimize the model, as Figure 3 shown.
[0067] In some specific embodiments:
[0068] First, smooth the displacement data to eliminate noise and better identify local changes; methods such as moving average, median filtering, or Gaussian filtering can be used; the purpose of this step is to reduce random noise and mutations in the displacement data, thereby improving the accuracy of subsequent calculations and analyses;
[0069] Calculate the first derivative of the displacement data to identify the regions with the largest and smallest position changes; the derivative can be calculated by backward difference, central difference, or other finite difference methods; based on the first derivative, find the data point corresponding to the maximum displacement value and use it as the center of the bulge; detect the local minima of the first derivative to find the region with the smallest displacement change; methods such as non-maximum suppression (NMS) can be used; non-maximum suppression (NMS) is an algorithm commonly used in edge detection and feature point detection. It suppresses non-local maximum points in the first derivative waveform, thereby retaining only local maximum points, which can better find the regions with the largest and smallest displacement change amplitudes;
[0070] Take the region with the smallest displacement change as the upper edge of the upper vertebra and the lower edge of the lower vertebra of the diseased vertebra;
[0071] Using the displacement data of the center of the bulge, the upper edge, and the lower edge, calculate the slopes k1 and k2 of two straight lines; the slope formula between two points can be used: k = (y2 - y1) / (x2 - x1);
[0072] Calculate the Cobb angle using the relationship between the slopes: Cobb angle = arctan(abs((k2 - k1) / (1 + k1 * k2))) * 180 / π; convert the result to an angle; the purpose of this step of calculating the Cobb angle is to determine the spinal correction effect, and then the driving situation of the high-precision drive motor 101 can be adjusted accordingly, so that the structure of the patient's spine gradually approaches the normal range.
[0073] Furthermore, to verify the accuracy of the measurement results of the device of the present invention, the following steps are taken:
[0074] First, a large amount of displacement data and corresponding real Cobb angles are collected from clinical cases to ensure the representativeness and comprehensiveness of the data. These data will be used as the basis for training and validating the model. Further, the displacement data is carefully preprocessed, specifically including removing noise, such as using methods like moving average, median filtering, or Gaussian filtering to improve the smoothness of the data. At the same time, data normalization is also carried out to scale the data to a unified range, eliminate the influence of dimensions, and make the model easier to process; for missing values in the dataset, interpolation methods, mean filling, or establishing a regression model to predict and fill are used to ensure the integrity of the data;
[0075] In the feature extraction stage, meaningful features such as the maximum value, minimum value, average value, and standard deviation of displacement data are selected. These features will be used as the input for model training. Then, the extracted features are divided into a training set and a test set. The training set is used to train the model, while the test set is used to evaluate the performance of the model.
[0076] When selecting a machine learning algorithm, the support vector machine SVM is adopted, especially its regression variant - support vector regression SVR. SVR is suitable for predicting continuous values, such as the Cobb angle in this embodiment.
[0077] During the model training process, a suitable kernel function is selected according to the characteristics of the problem, such as a linear kernel, polynomial kernel, or Gaussian radial basis kernel, and hyperparameters such as C and epsilon are adjusted to obtain the best model performance.
[0078] To evaluate the performance of the model, those skilled in the art adopted a cross - validation method and conducted multiple validations on the training set and the test set. The hyperparameters are continuously adjusted according to the evaluation results until the model with the best performance is found.
[0079] Finally, the processed displacement data is input into the trained SVR model to obtain the predicted value of the Cobb angle. To evaluate the accuracy of the prediction, evaluation metrics such as the mean squared error MSE between the predicted value and the true value are calculated using statistical methods, and the reliability of the prediction result is analyzed according to the confidence interval.
[0080] As can be seen from the above, the present invention not only improves the accuracy of the model in predicting the Cobb angle, but also provides more reliable data support for the diagnosis and treatment process.
[0081] The embodiments of the present invention are given for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above - mentioned embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above - mentioned embodiments within the scope of the present invention.
Claims
1. An integrated device for measuring and correcting the kyphotic deformity angle of a fractured vertebra, characterized in that: It includes a fixing part (2) which is wound around and fixed to the limbs and torso of a patient, and an arc-shaped substrate (1) for providing a fixing reference is connected to the fixing part (2). A soft area is wrapped around the edge of the arc-shaped substrate (1), and a spinal measurement and reduction area (3) is arranged in the central area surrounded by the soft area; A plurality of uniformly distributed position sensors (102) are arranged in the spinal measurement and reduction area (3), and a high-precision driving motor (101) for actively adjusting the position of the position sensor (102) is connected to each position sensor (102).
2. The integrated device for measuring and correcting the kyphosis angle of a fractured vertebral body according to claim 1, wherein: The number of the high-precision driving motors (101) is adapted to the number of the position sensors (102). The high-precision driving motors (101) drive the position sensors (102) axially perpendicular to the arc-shaped substrate (1). The position sensors (102) are connected to the outer surface of the spinal measurement and reduction area (3), and the structural change of the spinal measurement and reduction area (3) is guided under the trend of the high-precision driving motors (101) driving the position sensors (102).
3. The integrated device for measuring and correcting the kyphosis angle of a fractured vertebral body according to claim 1, wherein: The output end of the high-precision driving motor (101) is connected with a telescopic rod, and several position sensors (102) are fixed on the telescopic rod.
4. The integrated device for measuring and correcting the kyphosis angle of a fractured vertebral body according to claim 1, wherein: The fixing part (2) further includes a displacement limiting member. The displacement limiting member includes a fixing block integrally extending from the arc-shaped substrate (1), and an adhesion part is arranged between the fixing block and the patient's skin.
5. The system of the integrated device for measuring and correcting the kyphosis angle of a fractured vertebral body according to any one of claims 1-4, characterized in that: It includes a data module and a control module. The data module is used for processing data, and the control module is used for adjusting the driving state of the high-precision driving motor (101); the data of the position sensors (102) is directly fed back to the data module, and the data module is also connected with a data interface to access an external computer to obtain data; the data module adjusts the spinal measurement and reduction area (3) through the control module according to the data transmitted by the external computer, so that it forms a structure conforming to the normal thoracic kyphosis and lumbar lordosis; when the sensor is pressed and changes its position, the displacement data is transmitted to the data module to calculate the Cobb angle.
6. The system of the integrated device for measuring and correcting the kyphosis angle of a fractured vertebral body according to claim 5, characterized in that: After calculating the Cobb angle, the data module issues a reset command to the high-precision driving motor (101), and the high-precision driving motor (101) then drives the position sensor (102) to continuously press on the displacement area until it returns to the starting position.
7. The system of the integrated device for measuring and correcting the kyphosis angle of a fractured vertebral body according to claim 5, wherein: The data module is built-in with a processing model, and the processing model presets the values corresponding to the normal thoracic kyphosis and lumbar lordosis; after receiving the displacement data, the processing model will perform the following steps: data preprocessing, estimating the Cobb angle, and training and constructing a model according to the calculation results.
8. The system of the integrated device for measuring and correcting the kyphosis angle of a fractured vertebral body according to claim 7, characterized in that: In the step of estimating the Cobb angle, it includes the specific steps of smoothing the data, calculating the first derivative, identifying the center of the convexity and the area with the smallest displacement change, and calculating the Cobb angle using relevant data.
9. The system of the integrated device for measuring and correcting the kyphosis angle of a fractured vertebral body according to claim 7, characterized in that: In the steps of model training, including preloading data, preprocessing, feature extraction, selecting machine learning algorithms, model training, and evaluating and selecting the optimal model, the processed displacement data is input into the trained model to obtain a predicted value as the estimated value of the Cobb angle.