Scoliosis electrical stimulation correction system and spinal electrical stimulation parameter information prediction method

Abstract

The embodiment of the invention discloses a scoliosis electrical stimulation correction system and a spinal electrical stimulation parameter information prediction method. A specific implementation mode of the system comprises a server, a target client and a spine electropuncture flexible support battery box, wherein the server is configured to execute the following steps: receiving spine characteristic data of a user; generating scoliosis detection data; generating scoliosis type information; inputting the scoliosis detection data, the scoliosis type information and the user basic information into a pre-trained spinal electrical stimulation parameter prediction model; the target client is configured to execute the following steps: generating spinal electrical stimulation adjustment parameter information and wearing alignment point configuration information; the electrospinal spine support battery box is configured to control starting of the electrical stimulation electrode sheet group and the alignment point assembly after position adjustment in the electrospinal spine flexible support. According to the embodiment, the consumption of computing resources is reduced, and the waiting time of the user in waiting for the prediction result is shortened.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technologies, and particularly to a scoliosis electrical stimulation correction system and a method for predicting spinal electrical stimulation parameter information. Background Art

[0002] With the development of the miniaturization of wearable devices, flexible electrodes and low-power chips have made long-term attachment electrical stimulation possible, and flexible spinal electrical stimulation brackets have been widely used in the correction of adolescent idiopathic scoliosis (AIS). A scoliosis electrical stimulation correction system is a system used to generate spinal electrical stimulation parameter information to control the electrical output of the electrical patches in the flexible spinal electrical stimulation bracket corresponding to the spinal electrical stimulation parameter information, so as to achieve the effect of correcting the scoliosis spine. Currently, when generating spinal electrical stimulation parameter information, the commonly used method is to predict spinal electrical stimulation parameter information by finite element simulation.

[0003] However, when generating spinal electrical stimulation parameter information in the above manner, the following technical problems often exist:

[0004] When predicting spinal electrical stimulation parameter information by finite element simulation, it is necessary to simulate the coupling effects of multiple tissues such as vertebral bodies, intervertebral discs, ligaments, and muscles. The amount of calculation increases exponentially, resulting in a large consumption of computing resources, and the waiting time for users to wait for the prediction results is relatively long.

[0005] The above information disclosed in this background art section is only used to enhance the understanding of the background of the inventive concept, and thus, it may include information that does not form the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] This content part of the present disclosure is used to briefly introduce the concepts, which will be described in detail in the following detailed implementation part. This content part of the present disclosure is not intended to identify the key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0007] Some embodiments of the present disclosure propose a scoliosis electrical stimulation correction system and a method for predicting spinal electrical stimulation parameter information to solve one or more of the technical problems mentioned in the above background art section.

[0008] In a first aspect, some embodiments of the present disclosure provide a scoliosis electrical stimulation correction system, which includes: a server, a target client, and a battery box of a flexible spinal electrical stimulation bracket. Among them: The above server is configured to perform the following steps: receive the user spinal feature data sent by the above target client, where the above user spinal feature data includes user basic information, user spinal image data, and user spinal dynamic data; construct a three-dimensional spinal model based on the above user spinal image data; generate scoliosis detection data based on the above user spinal image data; generate scoliosis type information based on the user spinal dynamic data; label the above scoliosis detection data on the above three-dimensional spinal model; input the above scoliosis detection data, the above scoliosis type information, and the above user basic information into a pre-trained spinal electrical stimulation parameter prediction model to obtain spinal electrical stimulation parameter information; transmit the three-dimensional spinal model with the scoliosis detection data labeled thereon, the above scoliosis type information, and the above spinal electrical stimulation parameter information to the above target client; The above target client is configured to perform the following steps: in response to receiving the three-dimensional spinal model, the above scoliosis type information, and the above spinal electrical stimulation parameter information sent by the server, display the three-dimensional spinal model, the above scoliosis type information, and the above spinal electrical stimulation parameter information on a preset parameter adjustment and wearing alignment point configuration page; generate spinal electrical stimulation adjustment parameter information and wearing alignment point configuration information based on the interaction operation information of the target user and the above preset parameter adjustment and wearing alignment point configuration page; send the above spinal electrical stimulation adjustment parameter information and wearing alignment point configuration information to the above battery box of the flexible spinal electrical stimulation bracket; The above battery box of the flexible spinal electrical stimulation bracket is configured to receive the spinal electrical stimulation adjustment parameter information and wearing alignment point configuration information sent by the above target client to control the activation of the electrically stimulated electrode patch group and the alignment point component with adjusted positions in the flexible spinal electrical stimulation bracket.

[0009] In a second aspect, some embodiments of the present disclosure provide a method for predicting spinal electrical stimulation parameter information, which includes: receiving the user spinal feature data sent by the above target client, where the above user spinal feature data includes user basic information, user spinal image data, and user spinal dynamic data; constructing a three-dimensional spinal model based on the above user spinal image data; generating scoliosis detection data based on the above user spinal image data; generating scoliosis type information based on the user spinal dynamic data; labeling the above scoliosis detection data on the above three-dimensional spinal model; inputting the above scoliosis detection data, the above scoliosis type information, and the above user basic information into a pre-trained spinal electrical stimulation parameter prediction model to obtain spinal electrical stimulation parameter information; transmitting the three-dimensional spinal model with the scoliosis detection data labeled thereon, the above scoliosis type information, and the above spinal electrical stimulation parameter information to the above target client.

[0010] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: Through the scoliosis electrical stimulation correction system of some embodiments of the present disclosure, the consumption of computing resources and the prediction time for users to wait for prediction results are reduced. Specifically, the reasons for the large consumption of computing resources and the long prediction time for users to wait for prediction results are as follows: When using finite element simulation to predict spinal electrical stimulation parameter information, it is necessary to simulate the coupled effects of multiple tissues such as vertebrae, intervertebral discs, ligaments, and muscles, and the amount of calculation increases exponentially, resulting in a large consumption of computing resources and a long waiting time for users to wait for prediction results. Based on this, the scoliosis electrical stimulation correction system of some embodiments of the present disclosure includes: a server, a target client, and a battery box for a spinal electrical stimulation flexible bracket. Among them: First, the above server is configured to execute the following steps: The first step is to receive the user's spinal feature data sent by the above target client, where the above user's spinal feature data includes user basic information, user spinal image data, and user spinal dynamic data. The second step is to construct a three-dimensional spinal model based on the above user's spinal image data. Thus, a three-dimensional spinal model of the user can be restored using the user's spinal image data. Generate scoliosis detection data based on the above user's spinal image data. Thus, scoliosis detection data for predicting spinal electrical stimulation parameter information can be obtained. The third step is to generate scoliosis type information based on the user's spinal dynamic data. Thus, scoliosis type information representing the scoliosis type can be generated. The third step is to label the above scoliosis detection data on the above three-dimensional spinal model. Input the above scoliosis detection data, the above scoliosis type information, and the above user basic information into a pre-trained spinal electrical stimulation parameter prediction model to obtain spinal electrical stimulation parameter information. Thus, based on the scoliosis detection data, the above scoliosis type information, and the above user basic information, the spinal electrical stimulation parameter information can be predicted through the spinal electrical stimulation parameter prediction model without simulating the coupled effects of multiple tissues such as vertebrae, intervertebral discs, ligaments, and muscles, avoiding the high-complexity calculation of multi-tissue coupling in finite element simulation, and achieving an exponential reduction in the consumption of computing resources. The fourth step is to transmit the three-dimensional spinal model with the scoliosis detection data labeled thereon, the above scoliosis type information, and the above spinal electrical stimulation parameter information to the above target client. Thus, the three-dimensional spinal model with the scoliosis detection data labeled thereon, the scoliosis type information, and the above spinal electrical stimulation parameter information can be transmitted to the target client, so that the user of the target client can intuitively understand the scoliosis situation and obtain the spinal electrical stimulation parameter information for generating spinal electrical stimulation adjustment parameter information. The above target client is configured to execute the following steps: The first step is to, in response to receiving the three-dimensional spinal model, the above scoliosis type information, and the above spinal electrical stimulation parameter information sent by the above server, display the above three-dimensional spinal model, the above scoliosis type information, and the above spinal electrical stimulation parameter information on a preset parameter adjustment and wearing alignment point configuration page.Accordingly, a preset parameter adjustment and wearing alignment point configuration page can be displayed for adjusting spine electrical stimulation parameter information and configuring wearing alignment points to generate spine electrical stimulation adjustment parameter information and wearing alignment point configuration information. In the second step, based on the interaction operation information of the target user with the above preset parameter adjustment and wearing alignment point configuration page, spine electrical stimulation adjustment parameter information and wearing alignment point configuration information are generated. Accordingly, through the above target client, a three-dimensional spine model, scoliosis type information, and spine electrical stimulation parameter information can be visualized, and spine electrical stimulation adjustment parameter information and wearing alignment point configuration information for controlling the activation of the electrical stimulation electrode patch group and the alignment point component are generated. In the third step, the above spine electrical stimulation adjustment parameter information and wearing alignment point configuration information are sent to the above spine electrical stimulation flexible bracket battery box. The above spine electrical stimulation bracket battery box is configured to receive the spine electrical stimulation adjustment parameter information and wearing alignment point configuration information sent by the above target client to control the activation of the electrical stimulation electrode patch group and the alignment point component with adjusted positions in the spine electrical stimulation flexible bracket. Accordingly, the activation of the electrical stimulation electrode patch group and the alignment point component in the spine electrical stimulation flexible bracket can be controlled according to the spine electrical stimulation adjustment parameter information and wearing alignment point configuration information to release electrical stimulation in the scoliosis area, achieving the effect of scoliosis correction. Also, because before controlling the activation of the electrical stimulation electrode patch group and the alignment point component in the spine electrical stimulation flexible bracket to release electrical stimulation in the scoliosis area, based on the scoliosis detection data, the above scoliosis type information, and the above user basic information included in the scoliosis electrical stimulation correction system, the server predicts the spine electrical stimulation parameter information through the spine electrical stimulation parameter prediction model, without the need to simulate the multi-tissue coupling effects of vertebrae, intervertebral discs, ligaments, muscles, etc., avoiding the high-complexity calculation of multi-tissue coupling in finite element simulation, realizing an exponential reduction in computing resource consumption, reducing computing resource consumption, and reducing the waiting time of the user for the prediction result. Brief Description of the Drawings

[0011] In combination with the accompanying drawings and with reference to the following detailed description, the above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic and the elements and elements are not necessarily drawn to scale.

[0012] Figure 1 is an architecture diagram of an exemplary system of a scoliosis electrical stimulation correction system according to the present disclosure;

[0013] Figure 2 Flowchart of some embodiments of a method for predicting spine electrical stimulation parameter information according to the present disclosure. Detailed Description of the Embodiments

[0014] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0015] In addition, it should be noted that for ease of description, only parts related to the relevant invention are shown in the drawings. Without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other.

[0016] It should be noted that concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependent relationships.

[0017] It should be noted that the modifications of "one" and "plural" mentioned in the present disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless otherwise clearly stated in the context, it should be understood as "one or more".

[0018] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only for illustrative purposes and are not used to limit the scope of these messages or information.

[0019] The present disclosure will be described in detail below with reference to the drawings and in combination with embodiments.

[0020] Figure 1 An exemplary system architecture 100 of a heterogeneous data exchange system to which some embodiments of the present disclosure can be applied is shown.

[0021] As Figure 1 shown, the system architecture 100 may include: a server 102, a target client 101, and a spinal electrostimulation flexible stent battery box 103. The above-mentioned server 102 and the above-mentioned target client 101 may be connected by means of a wired, wireless communication link or an optical fiber cable, etc. The above-mentioned target client 101 and the above-mentioned spinal electrostimulation flexible stent battery box 103 may be connected by means of a wired, wireless communication link or an optical fiber cable, etc.

[0022] In some embodiments, the above-mentioned server 102 may be configured to perform the following steps:

[0023] First, receive the user's spinal feature data sent by the above-mentioned target client. Among them, the above-mentioned user's spinal feature data includes user basic information, user spinal imaging data, and user spinal dynamic data. Among them, the above-mentioned user basic information may include at least one of the following: age, gender. The above-mentioned user spinal imaging data may include a full-length frontal image of the spine and at least one full-length lateral image of the spine. The above-mentioned full-length frontal image of the spine may be an AP view image of the spine. Each of the at least one full-length lateral image of the spine may be a spinal image parallel to the sagittal plane on the left or right side of the human body.

[0024] Second, based on the above-mentioned user spinal imaging data, construct a three-dimensional spinal model. Among them, the above-mentioned three-dimensional spinal model may be a digital three-dimensional model representing the human spine.

[0025] In some optional implementation manners of some embodiments, the above-mentioned server 102 may construct a three-dimensional spinal model based on the above-mentioned user spinal imaging data through the following steps:

[0026] Based on the full-length frontal image of the spine and at least one full-length lateral image of the spine included in the user spinal imaging data, construct a three-dimensional spinal model. In practice, the above-mentioned server may construct a three-dimensional spinal model based on the full-length frontal image of the spine and at least one full-length lateral image of the spine through medical image three-dimensional reconstruction technology.

[0027] Third, based on the above-mentioned user spinal imaging data, generate scoliosis detection data.

[0028] In the process of adopting technical solutions to solve the problems mentioned in the background technology, the following problems often accompany:

[0029] When detecting and positioning the apical vertebra and end vertebra in the full-length frontal image of the spine included in the user spinal imaging data and generating scoliosis degree information, the full-length frontal image of the spine included in the user spinal imaging data is detected by directly regressing the vertebral bounding box through the target detection network, without considering the influence of the background image on the detection, and the bounding box output by the target detection network is rectangular box information, only containing the coordinates of the minimum circumscribed rectangle of the vertebra. The four vertices of the bounding box are only the projection circumscribed points of the vertebra in the image, which is different from the true corner points of the vertebra, resulting in poor accuracy of the vertebral feature point position information including the vertebral vertex position information and the center point position information, and further resulting in poor accuracy of the scoliosis detection data generated based on the vertebral feature point position information.

[0030] Facing the above technical problems, the inventor decides to adopt the following solutions:

[0031] In some alternative implementations of some embodiments, the above server 102 may generate scoliosis detection data based on the above user spinal image data through the following steps:

[0032] First, determine the full-length frontal image of the spine included in the above user spinal image data as the spine image to be detected.

[0033] Second, perform spine region segmentation processing on the above spine image to be detected to obtain a spine region segmentation image to be detected. In practice, the above server may perform spine region segmentation processing on the spine image to be detected through a pre-trained U-Net network to obtain a spine region segmentation image to be detected. Among them, the above spine region segmentation image to be detected may be a spine image to be detected with the background removed (for example, the image where the ribs and soft tissues are located).

[0034] Third, perform vertebral body detection and segmentation processing on the above spine region segmentation image to obtain each vertebral body positioning information and each vertebral body mask image. Among them, each vertebral body positioning information in the above each vertebral body positioning information corresponds to a corresponding vertebral body mask image in the above each vertebral body mask image, and the vertebral body positioning information includes vertebral body position information and vertebral body coding identifier. In practice, first, the above server may use a pre-trained object detection model (for example, yolov8 object detection model, Faster R-CNN object detection model, etc.) to detect each vertebral body position information of each vertebral body in the spine region segmentation image. Among them, the above vertebral body position information may be the vertex coordinates of each vertex of the vertebral body bounding box. The above vertebral body position information may be represented by the upper left vertex coordinates of the vertebral body bounding box, the upper right vertex coordinates of the vertebral body bounding box, the lower left vertex coordinates of the vertebral body bounding box, and the lower right vertex coordinates of the vertebral body bounding box. Then, the above server may encode each vertebral body from top to bottom according to the position corresponding to the vertebral body position information to obtain each vertebral body coding identifier (for example, T1, T2, etc.). Then, for each vertebral body position information in each vertebral body position information, the above server may determine the above vertebral body position information and its corresponding vertebral body coding identifier as the vertebral body positioning information to obtain each vertebral body positioning information. Then, the above server may input the above spine region segmentation map into a pre-trained Mask R-CNN model to obtain each vertebral body mask image of each vertebral body in the spine region segmentation image. Among them, each vertebral body mask image in the above each vertebral body mask image may be a pixel-level binary segmentation image for the spine vertebral body. It should be noted that the vertebral body mask image is exactly the same size as the above spine region segmentation image.

[0035] Fourth step, based on each of the above vertebral body mask images, generate the position information of each vertebral body feature point corresponding to each of the above vertebral body mask images. Among them, each vertebral body feature point position information in the above vertebral body feature point position information includes vertebral body vertex position information and center point position information. In practice, for each vertebral body mask image in the above vertebral body mask images, the server can perform a bitwise AND operation on the vertebral body mask image and the above spinal region segmentation image to obtain a vertebral body image. After that, the server can perform corner detection on the vertebral body image through Harris corner detection to obtain vertebral body vertex position information. Among them, the above vertebral body vertex position information can be represented by the coordinates where each corner point of the vertebral body is located. Then, the server can use the mean value of the coordinates included in the vertebral body vertex position information as the center point position information. As an example, if the detected vertebral body vertex position information is: {(35, 25), (65, 25), (65, 75), (35, 75)}, then the center point position information can be: (50, 50). Optionally, the server can perform contour detection processing on the vertebral body image to obtain vertebral body contour information. Among them, the above vertebral body contour information includes the coordinates of each contour point. After that, it is possible to traverse the coordinates of each contour point, and determine the coordinates of the four contour points corresponding to the points with the minimum and maximum x coordinates and the minimum and maximum y coordinates as the vertebral body vertex position information. Then, use the mean value of the coordinates included in the vertebral body vertex position information as the center point position information.

[0036] Fifth step, based on the above position information of each vertebral body feature point, generate the fitted spinal midline information. In practice, the server can determine the center point position information included in the above position information of each vertebral body feature point as the center point position information set. After that, through the Spline Curve fitting technique, fit the position information of each vertebral body feature point to obtain the fitted spinal midline information. Among them, the above fitted spinal midline information can be represented by a function.

[0037] Sixth step, based on the above fitted spinal midline information, generate apical vertebral point position information, upper end vertebral point position information, and lower end vertebral point position information. In practice, the server can determine the coordinates of the curvature extreme points of the midline corresponding to the above fitted spinal midline information as the apical vertebral point position information. Traverse the midline upward from the apical vertebra, find the point where the curvature first significantly increases (such as curvature > 0.01 mm-1) from being close to zero (such as curvature < 0.005 mm-1), and determine the coordinates of the found point as the upper end vertebral point position information. Traverse the midline downward from the apical vertebra, find the point where the curvature first significantly decreases (such as curvature > 0.01 mm-1) to being close to zero (such as curvature < 0.005 mm-1), and determine the coordinates of the found point as the lower end vertebral point position information.

[0038] Step 7: Based on the above apex vertebra position information, the above upper end vertebra position information, the above lower end vertebra position information, and the above respective vertebral body positioning information, generate apex vertebra positioning information, end vertebra positioning information, and scoliosis degree information. In practice, first, the server can determine the vertebral body position information included in each vertebral body positioning information as each target vertebral body position information. Then, for each target vertebral body position information among the target vertebral body position information, in response to determining that the corresponding point of the apex vertebra position information is within the region represented by the target vertebral body position information, determine the target vertebral body position information as the apex vertebral body position information. Determine the vertebral body coding identifier corresponding to the apex vertebral body position information and the apex vertebral body position information as the apex vertebra positioning information. In response to determining that the corresponding point of the lower end vertebra position information is within the region represented by the target vertebral body position information, determine the target vertebral body position information as the vertebral body coding identifier corresponding to the lower end vertebral body position information and the lower end vertebral body position information as the lower end vertebra positioning information. In response to determining that the corresponding point of the upper end vertebra position information is within the region represented by the target vertebral body position information, determine the target vertebral body position information as the vertebral body coding identifier corresponding to the upper end vertebral body position information and the upper end vertebral body position information as the upper end vertebra positioning information. Determine the lower end vertebra positioning information and the upper end vertebra positioning information as the end vertebra positioning information. In practice, the server can determine the difference between the upper left vertex coordinate and the upper right vertex coordinate of the vertebral body bounding box included in the upper end vertebra position information as the upper endplate vector. Determine the difference between the lower left vertex coordinate and the lower right vertex coordinate of the vertebral body bounding box included in the lower end vertebra position information as the lower endplate vector. Then, input the upper endplate vector and the lower endplate vector into the Cobb angle calculation formula based on vector dot product for solution, and obtain the Cobb angle as the scoliosis degree information.

[0039] Step 8: Determine the above apex vertebra positioning information, the above end vertebra positioning information, and the above scoliosis degree information as scoliosis detection data.

[0040] The above technical solution and its related content, as an inventive point of the embodiments of the present disclosure, solve the technical problems of "the accuracy of the generated vertebral feature point position information is poor and the accuracy of the scoliosis detection data is poor". The factors that lead to poor accuracy of vertebral feature point position information and poor accuracy of scoliosis detection data are often as follows: When detecting and positioning the apical vertebra and end vertebra in the full-length frontal image of the spine included in the user's spine image data and generating scoliosis degree information, the target detection network is directly used to regress the vertebral bounding box to detect the full-length frontal image of the spine included in the user's spine image data, without considering the influence of the background image on the detection. Moreover, the bounding box output by the target detection network is rectangular box information, which only contains the coordinates of the minimum circumscribed rectangle of the vertebra. The four vertices of the bounding box are only the projected circumscribed points of the vertebra in the image, and there are differences from the true corner points of the vertebra, resulting in poor accuracy of the generated vertebral feature point position information including vertebral vertex position information and center point position information, and further resulting in poor accuracy of the scoliosis detection data based on the vertebral feature point position information. If the above factors are solved, the effect of improving the accuracy of vertebral feature point position information and scoliosis detection data can be achieved. To achieve this effect, first, the full-length frontal image of the spine included in the above user's spine image data is determined as the spine image to be detected. Then, the spine region segmentation process is performed on the above spine image to be detected to obtain the spine region segmentation image to be detected. Thus, the spine region can be separated from the background, reducing the interference of the background (irrelevant tissues), and only retaining the spine region segmentation image to be detected with key information such as vertebrae, intervertebral spaces, and pedicles. After that, the vertebra detection and segmentation process is performed on the above spine region segmentation image to obtain the positioning information of each vertebra and each vertebral mask image, where each vertebra positioning information in the above positioning information of each vertebra corresponds to a corresponding vertebral mask image in the above vertebral mask images of each vertebra, and the above vertebra positioning information includes vertebra position information and vertebra coding identification. Thus, each vertebral mask image for generating the position information of the apical vertebra point, the upper end vertebra point, and the lower end vertebra point can be obtained. Then, based on the above vertebral mask images of each vertebra, the position information of each vertebral feature point of each vertebra corresponding to the above vertebral mask images of each vertebra is generated, where each vertebral feature point position information in the above position information of each vertebral feature point includes vertebral vertex position information and center point position information. Thus, the vertebral mask image can capture the actual geometric shape of the vertebra (such as trapezoid, irregular quadrilateral). Based on the vertebral mask image, generating the vertebral feature point position information can directly reflect the actual boundary of the vertebra in the image, and further improve the accuracy of the generated position information of each vertebral feature point. Based on the above position information of each vertebral feature point, the fitting spine midline information is generated. Then, based on the above fitting spine midline information, the position information of the apical vertebra point, the upper end vertebra point, and the lower end vertebra point is generated.After that, based on the above apex vertebra position information, the above upper end vertebra position information, the above lower end vertebra position information, and the above respective vertebral body positioning information, apex vertebra positioning information, end vertebra positioning information, and scoliosis degree information are generated. Then, the above apex vertebra positioning information, the above end vertebra positioning information, and the above scoliosis degree information are determined as scoliosis detection data. Thus, through the above steps, based on the position information of each vertebral body feature point with higher accuracy, scoliosis detection data with higher accuracy can be generated.

[0041] Fourth, based on the user's spinal dynamic data, scoliosis type information is generated.

[0042] In some alternative implementation manners of some embodiments, the above server 102 can generate scoliosis type information based on the user's spinal dynamic data through the following steps:

[0043] First step, the above user's spinal dynamic data is determined as the spinal dynamic data of the user to be detected. Among them, the above spinal dynamic data of the user to be detected includes each dynamic spinal image and spinal movement state information in each posture. Among them, the above spinal movement state information can represent the maximum movement angle that the spine can reach in each direction (forward flexion, backward extension, lateral flexion, etc.). As an example, the above spinal movement state information can be "maximum forward flexion angle: 60°, maximum backward extension angle: 20°, maximum left lateral flexion angle: 30°, maximum right lateral flexion angle: 30°".

[0044] Second step, based on the above respective spinal images, each scoliosis degree information in each posture is generated. In practice, for each spinal image among the above respective spinal images, the above server can perform cobb angle detection on the spinal image through the cobb angle measurement method based on the AiteekEngine algorithm model, and obtain the cobb angle corresponding to the above spinal image as the scoliosis degree information.

[0045] Third step, the above respective scoliosis degree information in each posture is determined as each dynamic scoliosis degree information. Among them, each dynamic scoliosis degree information in the above respective dynamic scoliosis degree information corresponds to one of the above respective spinal images. The above respective postures can be standing, forward flexion, right lateral flexion, and left lateral flexion.

[0046] Fourth, input the above-mentioned various dynamic scoliosis degree information and the above-mentioned spinal movement state information into a pre-trained scoliosis type prediction model to obtain scoliosis type information. Among them, the above-mentioned scoliosis type prediction model can be a pre-trained ResNet-LSTM network that takes the above-mentioned various dynamic scoliosis degree information and the above-mentioned spinal movement state information as input information and the scoliosis type information as output information. Among them, the scoliosis type information can characterize the type of scoliosis (for example, congenital scoliosis, postural scoliosis).

[0047] Fifth, label the above-mentioned scoliosis detection data on the above-mentioned three-dimensional spinal model. In practice, the above-mentioned server can label the above-mentioned scoliosis detection data on the above-mentioned three-dimensional spinal model through a preset three-dimensional visualization rendering engine (for example, the Unity3D engine).

[0048] Sixth, input the above-mentioned scoliosis detection data, the above-mentioned scoliosis type information, and the above-mentioned user basic information into a pre-trained spinal electrical stimulation parameter prediction model to obtain spinal electrical stimulation parameter information. Among them, the above-mentioned spinal electrical stimulation parameter prediction model includes an input layer, a feature extraction layer, an embedding layer, a feature fusion layer, a spinal electrical stimulation parameter prediction, and an output layer.

[0049] In some optional implementation manners of some embodiments, the above-mentioned server 102 can input the above-mentioned scoliosis detection data, the above-mentioned scoliosis type information, and the above-mentioned user basic information into a pre-trained spinal electrical stimulation parameter prediction model through the following steps to obtain spinal electrical stimulation parameter information:

[0050] First step, input the above-mentioned scoliosis detection data, the above-mentioned scoliosis type information, and the above-mentioned user basic information into the input layer of the above-mentioned intention recognition model to obtain scoliosis detection data feature information corresponding to the above-mentioned scoliosis detection data, scoliosis type feature information corresponding to the above-mentioned scoliosis type information, and user basic feature information corresponding to the above-mentioned user basic information. Among them, the above-mentioned input layer can convert the input data into a vector. The above-mentioned scoliosis detection data feature information can be a vector characterizing the scoliosis detection data. The above-mentioned scoliosis detection data feature information can be a vector characterizing the scoliosis detection data. The above-mentioned user basic feature information can be a vector characterizing the user basic information.

[0051] Second step, determine the above-mentioned scoliosis detection data feature information and the above-mentioned user basic feature information as the feature information to be extracted.

[0052] In the third step, input the above-mentioned feature information to be extracted into the above-mentioned feature extraction layer to obtain the extracted feature information. Among them, the above-mentioned feature extraction layer can be a convolutional layer that performs feature extraction and transformation on the feature information to be extracted. The above-mentioned extracted feature information can be a feature vector representing the feature information of scoliosis detection data and the above-mentioned user basic feature information.

[0053] In the fourth step, input the scoliosis type feature information into the above-mentioned embedding layer to obtain the scoliosis type encoded feature information. Among them, the above-mentioned embedding layer can be a neural network layer that takes scoliosis type information (such as "congenital scoliosis" or "postural scoliosis") as input and discrete classification variables (for example, 0 represents congenital scoliosis and 1 represents postural scoliosis) as output. The above-mentioned scoliosis type encoded feature information can represent the classification variables of the scoliosis type feature information.

[0054] In the fifth step, input the above-mentioned extracted feature information and the above-mentioned scoliosis type encoded feature information into the above-mentioned feature fusion layer to obtain the scoliosis feature fusion information. Among them, the above-mentioned feature fusion layer can be a splicing layer or an attention mechanism layer that fuses the above-mentioned extracted feature information and the above-mentioned scoliosis type encoded feature information (such as splicing, weighted summation, attention mechanism, etc.). The above-mentioned scoliosis feature fusion information can be a fused vector.

[0055] In the sixth step, input the above-mentioned scoliosis feature fusion information into the spinal cord electrical stimulation parameter prediction layer to obtain the initial spinal cord electrical stimulation parameter prediction information. Among them, the above-mentioned spinal cord electrical stimulation parameter prediction layer can be a fully connected layer used to predict the initial spinal cord electrical stimulation parameter prediction information based on the scoliosis feature fusion information. The above-mentioned initial spinal cord electrical stimulation parameter prediction information can be a vector representing the first concave side electrical stimulation prediction information, the second concave side electrical stimulation prediction information, the first convex side electrical stimulation prediction information, and the second convex side electrical stimulation prediction information. The above-mentioned first concave side electrical stimulation prediction information can represent the parameter information for electrical stimulation above the upper end vertebra and below the apex concave side. The above-mentioned second concave side electrical stimulation prediction information can represent the parameter information for electrical stimulation below the lower end vertebra and above the apex concave side. The above-mentioned first convex side electrical stimulation prediction information can be the parameter information for electrical stimulation above the upper end vertebra and below the apex convex side. The above-mentioned second convex side electrical stimulation prediction information can be the parameter information for electrical stimulation below the lower end vertebra and above the apex convex side. The above-mentioned parameter information can include current intensity, frequency, and pulse width.

[0056] In the seventh step, input the above-mentioned initial spinal cord electrical stimulation parameter prediction information into the above-mentioned output layer to obtain the spinal cord electrical stimulation parameter information. Among them, the above-mentioned output layer can decode the initial spinal cord electrical stimulation parameter prediction information (such as a floating-point number array with a length of 256) that converts the initial spinal cord electrical stimulation parameter prediction information into an abstract feature vector into specific electrical stimulation parameters (such as current intensity, frequency, pulse width).

[0057] Seventh, transmit the three-dimensional spinal model with scoliosis detection data marked thereon, the above-mentioned scoliosis type information, and the above-mentioned spinal electrical stimulation parameter information to the above-mentioned target client.

[0058] In some optional implementation manners of some embodiments, the above-mentioned server 102 can transmit the three-dimensional spinal model with scoliosis detection data marked thereon, the above-mentioned scoliosis type information, and the above-mentioned spinal electrical stimulation parameter information to the above-mentioned target client through the following steps:

[0059] First step, determine the three-dimensional spinal model with scoliosis detection data marked thereon, the above-mentioned scoliosis type information, and the above-mentioned spinal electrical stimulation parameter information as the data to be transmitted.

[0060] Second step, perform compression processing on the above-mentioned data to be transmitted to obtain compressed data to be transmitted. In practice, the above-mentioned execution entity can use a lossless compression algorithm (for example, octree coding compression algorithm) to perform compression processing on the data to be transmitted to obtain compressed data to be transmitted.

[0061] Third step, send the above-mentioned compressed data to be transmitted to the above-mentioned target client. Among them, the above-mentioned target client can be a target terminal (for example, a doctor terminal, that is, an electronic device or software platform used by a doctor during diagnosis and treatment).

[0062] In some embodiments, the above-mentioned target client 101 can be configured to execute the following steps:

[0063] First, in response to receiving the three-dimensional spinal model, the above-mentioned scoliosis type information, and the above-mentioned spinal electrical stimulation parameter information sent by the above-mentioned server, display the three-dimensional spinal model, the above-mentioned scoliosis type information, and the above-mentioned spinal electrical stimulation parameter information on a preset parameter adjustment and wearing alignment point configuration page. In practice, the above-mentioned target client can display the above-mentioned three-dimensional spinal model in a first preset display box on the above-mentioned preset parameter adjustment and wearing alignment point configuration page, and can display the above-mentioned scoliosis type information and spinal electrical stimulation parameter information in a second preset display box on the preset parameter adjustment and wearing alignment point configuration page. The above-mentioned preset parameter adjustment and wearing alignment point configuration page can be a preset page for a target user (for example, a doctor) to adjust the displayed spinal electrical stimulation parameter information and configure the wearing alignment point.

[0064] Second, generate spinal electrical stimulation adjustment parameter information and wearing alignment point configuration information based on the interaction operation information of the target user with the above-mentioned preset parameter adjustment and wearing alignment point configuration page.

[0065] In some alternative implementation manners of some embodiments, the above-mentioned target client 101 may adjust the interaction operation information with the wearable alignment point configuration page based on the target user and the above-mentioned preset parameters through the following steps to generate spinal cord electrical stimulation adjustment parameter information and wearable alignment point configuration information:

[0066] In response to detecting a modification operation on the spinal cord electrical stimulation parameter information displayed in the above-mentioned preset parameter adjustment and wearable alignment point configuration page, the modified spinal cord electrical stimulation parameter information is determined as the spinal cord electrical stimulation adjustment parameter information. Among them, the above-mentioned spinal cord electrical stimulation adjustment parameter information includes apex electrical stimulation information, first concave side electrical stimulation information, second concave side electrical stimulation information, first convex side electrical stimulation information, second convex side electrical stimulation information, and the above-mentioned preset parameter adjustment and wearable alignment point configuration page includes an alignment point configuration interaction control. Among them, the apex electrical stimulation information may be the electrical stimulation parameters for electrical stimulation of the apex after the modification operation. The first concave side electrical stimulation information may be the electrical stimulation parameters for electrical stimulation below the upper end vertebra above the concave side of the apex after the modification operation. The second concave side electrical stimulation information may be the electrical stimulation parameters for electrical stimulation above the lower end vertebra below the concave side of the apex after the modification operation. The first convex side electrical stimulation information may be the electrical stimulation parameters for electrical stimulation below the upper end vertebra above the convex side of the apex after the modification operation. The second convex side electrical stimulation information may be the electrical stimulation parameters for electrical stimulation above the lower end vertebra below the convex side of the apex after the modification operation.

[0067] In response to detecting an interaction operation on the above-mentioned alignment point configuration interaction control, the information corresponding to the above-mentioned alignment point configuration interaction control is determined as the wearable alignment point configuration information. Among them, the above-mentioned alignment point configuration interaction control may be a lighting selection control or an alignment point current parameter information input box. The above-mentioned wearable alignment point configuration information may be information for controlling the activation of the alignment point component. The above-mentioned alignment point component may be a preset alignment point (for example, a preset point at the navel part of the spinal cord electrical stimulation flexible bracket, etc.). The above-mentioned alignment point component may be an electric sheet or a warning light that releases an alignment prompt.

[0068] In some embodiments, the battery box 103 of the spinal electrostimulation flexible bracket may be configured to receive the spinal electrostimulation adjustment parameter information and the wearing alignment point configuration information sent by the target client, so as to control the activation of the electrically stimulated electrode patch group and the alignment point assembly after position adjustment in the spinal electrostimulation flexible bracket. Among them, the electrically stimulated electrode patch group includes a top vertebra point stimulation electrode, an upper end vertebra lower patch above the concave side of the top vertebra, a lower end vertebra upper patch below the concave side of the top vertebra, an upper end vertebra lower patch above the convex side of the top vertebra, and a lower end vertebra upper patch below the convex side of the top vertebra. Among them, the top vertebra point stimulation electrode may be a patch installed at the corresponding top vertebra point in the spinal electrostimulation flexible bracket. The upper end vertebra lower patch above the concave side of the top vertebra may be a patch installed at the position corresponding to the lower part of the upper end vertebra above the concave side of the top vertebra in the spinal electrostimulation flexible bracket. The lower end vertebra upper patch below the concave side of the top vertebra may be a patch installed at the position corresponding to the upper part of the lower end vertebra below the concave side of the top vertebra in the spinal electrostimulation flexible bracket. The upper end vertebra lower patch above the convex side of the top vertebra may be a patch installed at the position corresponding to the lower part of the upper end vertebra above the convex side of the top vertebra in the installed spinal electrostimulation flexible bracket. The lower end vertebra upper patch below the convex side of the top vertebra may be a patch installed at the position corresponding to the upper part of the lower end vertebra below the convex side of the top vertebra in the spinal electrostimulation flexible bracket.

[0069] In some optional implementation manners of some embodiments, the battery box 103 of the spinal electrostimulation flexible bracket may receive the spinal electrostimulation adjustment parameter information and the wearing alignment point configuration information sent by the target client through the following steps, so as to control the activation of the electrically stimulated electrode patch group and the alignment point assembly after position adjustment in the spinal electrostimulation flexible bracket:

[0070] The first step is to execute the following steps in response to receiving the opening information sent by the preset control device:

[0071] The first sub-step is to control the activation of the alignment point assembly based on the wearing alignment point configuration information to guide the wearer of the spinal electrostimulation flexible bracket to complete the wearing alignment of the spinal electrostimulation flexible bracket. Among them, the preset control device may be a remote controller for controlling the opening and closing of the battery box of the spinal electrostimulation flexible bracket. The battery box of the spinal electrostimulation flexible bracket integrates a microcontroller or a dedicated chip.

[0072] The second sub-step is to control the top vertebra point stimulation electrode to release a current corresponding to the top vertebra electrostimulation information based on the top vertebra electrostimulation information included in the spinal electrostimulation adjustment parameter information, so as to prompt the area where the scoliosis part of the wearer of the spinal electrostimulation flexible bracket is located.

[0073] The third sub-step is to control the upper end vertebra lower patch above the concave side of the top vertebra to release a current corresponding to the first concave side electrostimulation information based on the first concave side electrostimulation information included in the spinal electrostimulation adjustment parameter information, so as to exercise the paravertebral muscles on the concave side under the upper end vertebra lower patch above the concave side of the top vertebra.

[0074] The fourth sub-step: Based on the second concave-side electrical stimulation information included in the above-mentioned spinal cord electrical stimulation adjustment parameter information, control the electrical patch above the lower end vertebra below the concave side of the apex vertebra to release a current corresponding to the second concave-side electrical stimulation information, so as to exercise the paravertebral muscles on the concave side under the electrical patch above the lower end vertebra below the concave side of the apex vertebra. Among them, the above-mentioned first concave-side electrical stimulation information and second concave-side electrical stimulation information can represent currents (electrical stimulations) with a high frequency (such as 40-60 Hz) that cause complete tetanic contractions of the muscles.

[0075] The fifth sub-step: Based on the first convex-side electrical stimulation information included in the above-mentioned spinal cord electrical stimulation adjustment parameter information, control the electrical patch below the upper end vertebra above the convex side of the apex vertebra to release a current corresponding to the first convex-side electrical stimulation information, so as to relax the paravertebral muscles on the convex side under the electrical patch below the upper end vertebra above the convex side of the apex vertebra.

[0076] The sixth sub-step: Based on the second convex-side electrical stimulation information included in the above-mentioned spinal cord electrical stimulation adjustment parameter information, control the electrical patch above the lower end vertebra below the convex side of the apex vertebra to release a current corresponding to the first convex-side electrical stimulation information, so as to relax the paravertebral muscles on the convex side under the electrical patch above the lower end vertebra below the convex side of the apex vertebra. Among them, the above-mentioned first convex-side electrical stimulation information and second convex-side electrical stimulation information can represent low-frequency pulsed currents (such as 1-5 Hz) that can cause single contractions of the muscles.

[0077] The above technical solution and its related contents, as an inventive point of the embodiment of the present disclosure, solve the technical problem of "poor user experience of the spinal electrostimulation flexible support". The factors that lead to the poor user experience of the spinal electrostimulation flexible support are often as follows: when the user wears the spinal electrostimulation flexible support for scoliosis correction, the top vertebra point stimulation electrode is not controlled to release the current in the area where the scoliosis part of the wearer of the spinal electrostimulation flexible support is located, and the user of the spinal electrostimulation flexible support is relatively vague about the scoliosis part. At the same time, the start of the alignment point component is not controlled, and the correction force point is easily offset when wearing the spinal electrostimulation flexible support, resulting in poor correction effect, which leads to poor user experience of the spinal electrostimulation flexible support. If the above factors are solved, the effect of improving the user experience of the spinal electrostimulation flexible support can be achieved. In order to achieve this effect, first, in response to detecting the start-up information sent by the preset control device, the following steps are performed: the first sub-step, based on the above-mentioned wear alignment point configuration information, the start of the above-mentioned alignment point component is controlled to guide the wearer of the spinal electrostimulation flexible support to complete the wear alignment of the spinal electrostimulation flexible support. Thus, the start-up of the alignment point assembly can be controlled to guide the wearer of the spinal electrostimulation flexible support to complete the wearing alignment of the spinal electrostimulation flexible support. The second sub-step is to control the top cone point stimulation electrode to release a current corresponding to the top cone electrical stimulation information based on the top cone electrical stimulation information included in the spinal electrostimulation adjustment parameter information, so as to prompt the area where the scoliosis of the wearer of the spinal electrostimulation flexible support is located. The third sub-step is to control the electric sheet below the upper vertebra above the concave side of the top cone to release a current corresponding to the first concave side electrical stimulation information based on the first concave side electrical stimulation information included in the spinal electrostimulation adjustment parameter information, so as to exercise the concave side paraspinal muscles under the electric sheet below the upper vertebra above the concave side of the top cone. The fourth sub-step is to control the electric sheet above the lower vertebra below the concave side of the top cone to release a current corresponding to the second concave side electrical stimulation information based on the second concave side electrical stimulation information included in the spinal electrostimulation adjustment parameter information, so as to exercise the concave side paraspinal muscles under the electric sheet above the lower vertebra below the concave side of the top cone. The fifth sub-step is to control the electric sheet below the upper vertebra above the convex side of the above-mentioned top cone to release a current corresponding to the first convex side electric stimulation information based on the first convex side electric stimulation information included in the above-mentioned spinal electric stimulation adjustment parameter information, so as to relax the convex side paraspinal muscles under the electric sheet below the upper vertebra above the convex side of the above-mentioned top cone. The sixth sub-step is to control the electric sheet above the lower vertebra below the convex side of the above-mentioned top cone to release a current corresponding to the first convex side electric stimulation information based on the second convex side electric stimulation information included in the above-mentioned spinal electric stimulation adjustment parameter information, so as to relax the convex side paraspinal muscles under the electric sheet above the lower vertebra below the convex side of the above-mentioned top cone. Also, because when the user wears the spinal electric stimulation flexible support for scoliosis correction, the activation of the control alignment point component is adopted to guide the wearer of the spinal electric stimulation flexible support to complete the wearing alignment of the spinal electric stimulation flexible support, the possibility of deviation of the correction force application point is reduced, thereby improving the correction effect.And control the top vertebra point stimulating electrode to release a current corresponding to the above-mentioned top vertebra electrical stimulation information, so as to prompt the area where the scoliosis part of the wearer of the spinal electrical stimulation flexible bracket is located, and improve the experience of the user of the spinal electrical stimulation flexible bracket.

[0078] Figure 2 FIG. 200 shows a flowchart of some embodiments of a method for predicting spinal electrical stimulation parameter information of a server included in the above-mentioned spinal scoliosis electrical stimulation correction system according to the present disclosure. The method for predicting spinal electrical stimulation parameter information includes the following steps:

[0079] Step 201, receiving user spinal feature data sent by a target client.

[0080] In some embodiments, an execution body of the method for predicting spinal electrical stimulation parameter information (for example, a server included in the spinal scoliosis electrical stimulation correction system) may receive the user spinal feature data sent by the above-mentioned target client. Among them, the above-mentioned user spinal feature data includes user basic information, user spinal image data, and user spinal dynamic data.

[0081] Step 202, constructing a three-dimensional spinal model based on the user spinal image data.

[0082] In some embodiments, the above-mentioned execution body may generate spinal scoliosis detection data based on the above-mentioned user spinal image data.

[0083] Step 203, generating spinal scoliosis detection data based on the user spinal image data.

[0084] In some embodiments, the above-mentioned execution body may generate spinal scoliosis detection data based on the above-mentioned user spinal image data.

[0085] Step 204, generating spinal scoliosis type information based on the user spinal dynamic data.

[0086] In some embodiments, the above-mentioned execution body may generate spinal scoliosis type information based on the user spinal dynamic data.

[0087] Step 205, labeling the spinal scoliosis detection data on the three-dimensional spinal model.

[0088] In some embodiments, the above-mentioned execution body may label the above-mentioned spinal scoliosis detection data on the above-mentioned three-dimensional spinal model.

[0089] Step 206, inputting the spinal scoliosis detection data, the spinal scoliosis type information, and the user basic information into a pre-trained spinal electrical stimulation parameter prediction model to obtain spinal electrical stimulation parameter information.

[0090] In some embodiments, the above-mentioned execution entity may input the above-mentioned scoliosis detection data, the above-mentioned scoliosis type information, and the above-mentioned user basic information into a pre-trained spinal cord electrical stimulation parameter prediction model to obtain spinal cord electrical stimulation parameter information.

[0091] Step 207: Transmit the spinal three-dimensional model annotating the scoliosis detection data, the scoliosis type information, and the spinal cord electrical stimulation parameter information to the target client.

[0092] In some embodiments, the above-mentioned execution entity may transmit the spinal three-dimensional model annotating the scoliosis detection data, the above-mentioned scoliosis type information, and the above-mentioned spinal cord electrical stimulation parameter information to the above-mentioned target client.

[0093] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: Through the scoliosis electrostimulation correction system of some embodiments of the present disclosure, the consumption of computing resources and the prediction time for users to wait for prediction results are reduced. Specifically, the reasons for the large consumption of computing resources and the long prediction time for users to wait for prediction results are as follows: When using finite element simulation to predict spinal electrostimulation parameter information, it is necessary to simulate the coupled effects of multiple tissues such as vertebrae, intervertebral discs, ligaments, and muscles, and the amount of calculation increases exponentially, resulting in a large consumption of computing resources and a long waiting time for users to wait for prediction results. Based on this, the scoliosis electrostimulation correction system of some embodiments of the present disclosure includes: a server, a target client, and a battery box of a spinal electrostimulation flexible bracket. Among them: First, the above-mentioned server is configured to perform the following steps: The first step is to receive the user spinal feature data sent by the above-mentioned target client, where the above-mentioned user spinal feature data includes user basic information, user spinal image data, and user spinal dynamic data. The second step is to construct a three-dimensional spinal model based on the above-mentioned user spinal image data. Thus, a three-dimensional spinal model of the user can be restored using the user spinal image data. Generate scoliosis detection data based on the above-mentioned user spinal image data. Thus, scoliosis detection data for predicting spinal electrostimulation parameter information can be obtained. The third step is to generate scoliosis type information based on the user spinal dynamic data. Thus, scoliosis type information characterizing the scoliosis type can be generated. The third step is to label the above-mentioned scoliosis detection data on the above-mentioned three-dimensional spinal model. Input the above-mentioned scoliosis detection data, the above-mentioned scoliosis type information, and the above-mentioned user basic information into a pre-trained spinal electrostimulation parameter prediction model to obtain spinal electrostimulation parameter information. Thus, based on the scoliosis detection data, the above-mentioned scoliosis type information, and the above-mentioned user basic information, the spinal electrostimulation parameter information can be predicted through the spinal electrostimulation parameter prediction model, without simulating the coupled effects of multiple tissues such as vertebrae, intervertebral discs, ligaments, and muscles through simulation, avoiding the high-complexity calculation of multi-tissue coupling in finite element simulation, and achieving an exponential reduction in the consumption of computing resources. The fourth step is to transmit the three-dimensional spinal model labeled with scoliosis detection data, the above-mentioned scoliosis type information, and the above-mentioned spinal electrostimulation parameter information to the above-mentioned target client. Thus, the three-dimensional spinal model labeled with scoliosis detection data, the scoliosis type information, and the above-mentioned spinal electrostimulation parameter information can be transmitted to the target client, so that the user of the target client can intuitively understand the scoliosis situation and obtain the spinal electrostimulation parameter information for generating spinal electrostimulation adjustment parameter information. The above-mentioned target client is configured to perform the following steps: The first step is to, in response to receiving the three-dimensional spinal model, the above-mentioned scoliosis type information, and the above-mentioned spinal electrostimulation parameter information sent by the server, display the three-dimensional spinal model, the above-mentioned scoliosis type information, and the above-mentioned spinal electrostimulation parameter information on a preset parameter adjustment and wearing alignment point configuration page.Thus, a preset parameter adjustment and wearing alignment point configuration page can be displayed for adjusting and configuring the spinal cord electrical stimulation parameter information and wearing alignment points to generate spinal cord electrical stimulation adjustment parameter information and wearing alignment point configuration information. In the second step, based on the interaction operation information between the target user and the above preset parameter adjustment and wearing alignment point configuration page, spinal cord electrical stimulation adjustment parameter information and wearing alignment point configuration information are generated. Thus, the three-dimensional spinal cord model, scoliosis type information, and spinal cord electrical stimulation parameter information can be visualized through the above target client, and spinal cord electrical stimulation adjustment parameter information and wearing alignment point configuration information for controlling the activation of the electrical stimulation electrode patch group and alignment point component are generated. In the third step, the above spinal cord electrical stimulation adjustment parameter information and wearing alignment point configuration information are sent to the above spinal cord electrical stimulation flexible stent battery box. The above spinal cord electrical stimulation stent battery box is configured to receive the spinal cord electrical stimulation adjustment parameter information and wearing alignment point configuration information sent by the above target client to control the activation of the electrical stimulation electrode patch group and alignment point component with adjusted positions in the spinal cord electrical stimulation flexible stent. Thus, the activation of the electrical stimulation electrode patch group and alignment point component in the spinal cord electrical stimulation flexible stent can be controlled according to the spinal cord electrical stimulation adjustment parameter information and wearing alignment point configuration information to release electrical stimulation in the scoliosis area, achieving the effect of scoliosis correction. Also, because before controlling the activation of the electrical stimulation electrode patch group and alignment point component in the spinal cord electrical stimulation flexible stent to release electrical stimulation in the scoliosis area, based on the scoliosis detection data, the above scoliosis type information, and the above user basic information included in the scoliosis electrical stimulation correction system, the spinal cord electrical stimulation parameter information is predicted through the spinal cord electrical stimulation parameter prediction model, without the need to simulate the multi-tissue coupling effects of the vertebral body, intervertebral disc, ligament, muscle, etc. through simulation, avoiding the high-complexity calculation of multi-tissue coupling in finite element simulation, realizing an exponential reduction in computational resource consumption, reducing computational resource consumption, and reducing the waiting time of the user for the prediction result.

[0094] The above description is only some preferred embodiments of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combination of technical features, and should also cover other technical solutions formed by any combination of technical features or their equivalent features without departing from the inventive concept. For example, a technical solution formed by mutually replacing a feature with a technical feature (but not limited to) having a similar function disclosed in the embodiments of the present disclosure.

Claims

1. A scoliosis electrical stimulation correction system, comprising: Server, target client, and spinal electrostimulation flexible stent battery box, where: The server is configured to perform the following steps: Receive user spinal feature data sent by the target client, where the user spinal feature data includes user basic information, user spinal image data, and user spinal dynamic data; Based on the user spinal image data, construct a three-dimensional spinal model; Based on the user spinal image data, generate spinal scoliosis detection data; Based on the user spinal dynamic data, generate spinal scoliosis type information; Label the spinal scoliosis detection data on the three-dimensional spinal model; Input the spinal scoliosis detection data, the spinal scoliosis type information, and the user basic information into a pre-trained spinal electrostimulation parameter prediction model to obtain spinal electrostimulation parameter information; Transmit the three-dimensional spinal model with labeled spinal scoliosis detection data, the spinal scoliosis type information, and the spinal electrostimulation parameter information to the target client; The target client is configured to perform the following steps: In response to receiving the three-dimensional spinal model, the spinal scoliosis type information, and the spinal electrostimulation parameter information sent by the server, display the three-dimensional spinal model, the spinal scoliosis type information, and the spinal electrostimulation parameter information on a preset parameter adjustment and wearing alignment point configuration page; Based on the interaction operation information of the target user with the preset parameter adjustment and wearing alignment point configuration page, generate spinal electrostimulation adjustment parameter information and wearing alignment point configuration information; Send the spinal electrostimulation adjustment parameter information and the wearing alignment point configuration information to the spinal electrostimulation flexible stent battery box; The spinal electrostimulation stent battery box is configured to receive the spinal electrostimulation adjustment parameter information and the wearing alignment point configuration information sent by the target client to control the activation of the electrically stimulated electrode patch group and the alignment point component after position adjustment in the spinal electrostimulation flexible stent.

2. The scoliosis electrical stimulation correction system according to claim 1, wherein, The user spinal image data includes a full-length frontal image of the spine and at least one full-length lateral image of the spine, and the server is further configured to construct a three-dimensional spinal model based on the user spinal image data through the following steps: Based on the full-length frontal image of the spine and at least one full-length lateral image of the spine included in the user spinal image data, construct a three-dimensional spinal model.

3. The scoliosis electrical stimulation correction system according to claim 1, wherein, The server is further configured to transmit the three-dimensional spinal model with labeled spinal scoliosis detection data, the spinal scoliosis type information, and the spinal electrostimulation parameter information to the target client through the following steps, including: Determine the three-dimensional spinal model with labeled spinal scoliosis detection data, the spinal scoliosis type information, and the spinal electrostimulation parameter information as data to be transmitted; Perform compression processing on the data to be transmitted to obtain compressed data to be transmitted; Send the compressed data to be transmitted to the target client.

4. The scoliosis electrical stimulation correction system according to claim 1, wherein, The server is further configured to generate spinal scoliosis type information based on the user spinal dynamic data through the following steps, including: Determine the user's spinal dynamic data as the spinal dynamic data to be detected, where the spinal dynamic data to be detected includes various dynamic spinal images and spinal movement state information in each posture; Generate information on the degree of scoliosis in each posture based on the various spinal images; Determine the information on the degree of scoliosis in each posture as the information on the degree of dynamic scoliosis, where each piece of information on the degree of dynamic scoliosis in the information on the degree of dynamic scoliosis corresponds to a corresponding spinal image among the various spinal images; Input the information on the degree of dynamic scoliosis and the spinal movement state information into a pre-trained scoliosis type prediction model to obtain scoliosis type information.

5. The scoliosis electrical stimulation correction system according to claim 1, wherein, The spinal electrical stimulation parameter prediction model includes an input layer, a feature extraction layer, an embedding layer, a feature fusion layer, a spinal electrical stimulation parameter prediction layer, and an output layer, and the server is further configured to input the scoliosis detection data, the scoliosis type information, and the user basic information into a pre-trained spinal electrical stimulation parameter prediction model through the following steps to obtain spinal electrical stimulation parameter information, including: Input the scoliosis detection data, the scoliosis type information, and the user basic information into the input layer of the intention recognition model to obtain scoliosis detection data feature information corresponding to the scoliosis detection data, scoliosis type feature information corresponding to the scoliosis type information, and user basic feature information corresponding to the user basic information; Determine the scoliosis detection data feature information and the user basic feature information as the feature information to be extracted; Input the feature information to be extracted into the feature extraction layer to obtain the extracted feature information; Input the scoliosis type feature information into the embedding layer to obtain scoliosis type encoded feature information; Input the extracted feature information and the scoliosis type encoded feature information into the feature fusion layer to obtain scoliosis feature fusion information; Input the scoliosis feature fusion information into the spinal electrical stimulation parameter prediction layer to obtain initial spinal electrical stimulation parameter prediction information; Input the initial spinal electrical stimulation parameter prediction information into the output layer to obtain spinal electrical stimulation parameter information.

6. The scoliosis electrical stimulation correction system according to claim 1, wherein, The target client is further configured to generate spinal electrical stimulation adjustment parameter information and wearing alignment point configuration information based on the interaction operation information between the target user and the preset parameter adjustment and wearing alignment point configuration page through the following steps, including: In response to detecting an operation to modify the spinal electrical stimulation parameter information displayed on the preset parameter adjustment and wearing alignment point configuration page, determine the modified spinal electrical stimulation parameter information as the spinal electrical stimulation adjustment parameter information, where the spinal electrical stimulation adjustment parameter information includes apical cone electrical stimulation information, first concave side electrical stimulation information, second concave side electrical stimulation information, first convex side electrical stimulation information, second convex side electrical stimulation information, and the preset parameter adjustment and wearing alignment point configuration page includes an alignment point configuration interaction control; In response to detecting an interaction operation acting on the alignment point configuration interaction control, determine the information corresponding to the alignment point configuration interaction control as the wearable alignment point configuration information.

7. A method for predicting spinal electrical stimulation parameter information, which is applied to the server included in the spinal scoliosis electrical stimulation correction system according to any one of claims 1-6, and the method includes: Receive the user spinal feature data sent by the target client, where the user spinal feature data includes user basic information, user spinal image data, and user spinal dynamic data; Construct a three-dimensional spinal model based on the user spinal image data; Generate spinal scoliosis detection data based on the user spinal image data; Generate spinal scoliosis type information based on the user spinal dynamic data; Mark the spinal scoliosis detection data on the three-dimensional spinal model; Input the spinal scoliosis detection data, the spinal scoliosis type information, and the user basic information into a pre-trained spinal electrical stimulation parameter prediction model to obtain spinal electrical stimulation parameter information; Transmit the three-dimensional spinal model with marked spinal scoliosis detection data, the spinal scoliosis type information, and the spinal electrical stimulation parameter information to the target client.

Images