A scoliosis neuromuscular dynamic guidance method and system

Abstract

This application provides a method and system for neuromuscular dynamic guidance of scoliosis, relating to the fields of rehabilitation engineering and intelligent control technology. The method includes: receiving full-length DR images of the spine uploaded by the patient; obtaining the Cobb angle; establishing a spatial mapping relationship between spinal segments and surface landmarks; calculating the target position coordinates of each action point of the orthotic brace in three-dimensional space; constructing an individualized muscle tension assessment benchmark based on muscle contraction characteristic parameters; and using the assessment benchmark to generate initial control parameters for the orthotic control and adaptive adjustment phases. This application solves the problems of existing scoliosis orthotic braces lacking electromyographic feedback collaborative control and unable to achieve dynamic adjustment during the orthotic process. It realizes neuromuscular closed-loop guidance and adaptive orthotic control based on the fusion of DR images, surface mapping, and surface electromyographic signals, thereby improving orthotic accuracy, process controllability, and patient compliance, significantly enhancing the orthotic intervention effect and dynamic monitoring capability.

Description

Technical Field

[0001] This application relates to the fields of rehabilitation engineering and intelligent control technology, and in particular to a method and system for dynamic neuromuscular guidance in scoliosis. Background Technology

[0002] Scoliosis is a common three-dimensional spinal deformity, most prevalent in adolescents. Its main manifestations include coronal scoliosis, sagittal abnormalities, and axial rotation. For patients with mild to moderate scoliosis, non-surgical intervention with orthotic braces is typically used clinically. This involves applying external force to the trunk to inhibit the progression of the curvature and promote spinal morphological restoration.

[0003] Traditional orthopedic braces often use fixed structures or manual adjustment methods during wear, making it difficult to dynamically adjust according to changes in the patient's posture and the progress of orthopedic treatment. They usually lack real-time perception and feedback of posture information, force distribution and muscle activity status during wear, and cannot form an effective closed-loop control mechanism, thus making it difficult to correct orthopedic deviations in a timely manner.

[0004] In summary, existing technologies still have shortcomings in terms of dynamic adjustment capabilities during the orthopedic process, real-time perception of posture and force status, and coordination between muscle activity information and orthopedic control, making it difficult to achieve real-time feedback and closed-loop adjustment in scoliosis correction. Summary of the Invention

[0005] The purpose of this application is to provide a neuromuscular dynamic guidance method and system for scoliosis, in order to solve the problems in the prior art that are due to the lack of accurate modeling based on image parameters and spatial calculation of correction points, and the lack of real-time perception and coordinated adjustment of posture information, force state and muscle activity during the correction process, resulting in insufficient correction control accuracy, difficulty in timely correction of correction deviations and inability to achieve closed-loop adjustment.

[0006] In view of the above problems, this application provides a method and system for dynamic neuromuscular guidance of scoliosis.

[0007] In a first aspect, this application provides a method for neuromuscular dynamic guidance of scoliosis, which is implemented through a neuromuscular dynamic guidance system for scoliosis. The method includes: receiving a full-length DR spinal image uploaded by a patient via terminal software; performing scale calibration, denoising, and enhancement processing on the image; automatically identifying each vertebral structure based on an image recognition algorithm; calculating the supplementary angle between two straight lines as the Cobb angle; and simultaneously recording the scoliosis direction and the position of the apex vertebra; establishing a spatial mapping relationship between spinal segments and surface landmarks based on the Cobb angle, the apex vertebra position, and preset anatomical landmarks, wherein the surface landmarks include at least the acromion, the posterior midline of the spine, and a pelvic reference point; and calculating the target position coordinates of each action point of the orthotic brace in three-dimensional space according to preset segment division rules.(x, y, z) The points of application include the main force application point, the reaction support point, and the limiting point, and generate corresponding orthopedic force direction vectors and spatial distribution parameters. The orthopedic force direction vector is used for subsequent spatial control of the orthopedic brace and generation of mechanical output parameters. The system guides the patient to perform a standard test action sequence, including flexion, extension, left tilt, and right tilt, and sets the duration and action range identifier for each action. This is used to divide the time of different posture stages and establish a data synchronization benchmark to build a time synchronization relationship between posture state and muscle response.

[0008] Secondly, this application also provides a scoliosis neuromuscular dynamic guidance system for executing a scoliosis neuromuscular dynamic guidance system as described in the first aspect, wherein the system includes: a DR image preprocessing module, used to receive DR full-length spinal images uploaded by the patient through terminal software, and perform scale calibration, noise reduction, and enhancement processing on the images; a vertebral body recognition and Cobb angle calculation module, used to automatically identify each vertebral structure based on an image recognition algorithm, calculate the supplementary angle between two straight lines as the Cobb angle, and simultaneously record the scoliosis direction and the position of the apex vertebra; a spinal space mapping module, used to establish a spatial mapping relationship between spinal segments and surface landmarks based on the Cobb angle, the position of the apex vertebra, and preset anatomical landmarks, wherein the surface landmarks include at least the acromion point, the posterior midline of the spine, and a pelvic reference point; and a brace mechanical parameter generation module, used to calculate the target position coordinates of each action point of the orthotic brace in three-dimensional space according to preset segment division rules. (x, y, z) The application points include the main force application point, the reaction support point, and the limiting point, and generate corresponding orthopedic force direction vectors and spatial distribution parameters. The orthopedic force direction vector is used for subsequent spatial control of the orthopedic brace and generation of mechanical output parameters. The action guidance and synchronization modeling module is used to guide the patient to perform standard test action sequences, including flexion, extension, left tilt, and right tilt, and to set the duration and action interval labels for each action. This is used to divide the time of different posture stages and establish data synchronization benchmarks to build a time synchronization relationship between posture state and muscle response.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: This application achieves precise three-dimensional spatial positioning of the orthotic brace's application point by introducing Cobb angle calculation based on DR images and constructing spatial mapping relationships of spinal segments. Compared to traditional methods relying on experience for point selection, this significantly improves the accuracy and consistency of orthotic point determination. Furthermore, by constructing a multi-point synergistic mechanism involving the main force application point, reaction support point, and limiting point, the distribution of orthotic force in space becomes more rational, contributing to improved stability and continuous correction during the orthotic process. Simultaneously, this application integrates a patch electrode assembly to collect and extract features from the surface electromyographic signals of the target muscle groups, constructing an individualized muscle tension assessment benchmark. This allows orthotic control to incorporate the patient's own muscle exertion state, achieving dynamic adjustment based on physiological feedback, thereby enhancing the individual fit and control precision of the orthotic process. Furthermore, by introducing multimodal sensor data such as posture, pressure, and torque, real-time monitoring of the brace wearing status and the orthotic process is achieved. A closed-loop adjustment mechanism is constructed based on spatial deviation, enabling dynamic optimization of the orthotic force output according to the actual orthotic effect, thereby reducing the risk of under- or over-correction. Furthermore, by setting a zero-tension initial fit mechanism, the initial wearing comfort and stability of the brace are improved. Combined with anomaly detection, high-frequency vibration alerts, and tension guidance, proactive intervention against muscle fatigue and postural deviation is achieved, promoting neuromuscular synergy in the orthopedic process. In summary, this application constructs a closed-loop orthopedic control method based on image modeling, multimodal perception, and neuromuscular feedback synergy, achieving precise, dynamic, and individualized control of the orthopedic process. In conclusion, the scoliosis neuromuscular dynamic guidance method and system provided in this application, through Cobb angle calculation based on DR images and construction of spatial mapping relationships of spinal segments, three-dimensional spatial positioning of multiple action points of the brace, and multimodal sensor data fusion control, achieves precise distribution and dynamic closed-loop adjustment of the spatial force of the orthopedic brace, solving the technical problems of existing orthopedic braces relying on experience-based point selection, lacking individualized muscle feedback, and being unable to perform real-time dynamic orthopedic control.

[0010] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0012] Figure 1 This is a flowchart illustrating a neuromuscular dynamic guidance method for scoliosis according to this application. Figure 2 This is a schematic diagram of the structure of a neuromuscular dynamic guidance system for scoliosis according to this application.

[0013] Explanation of reference numerals in the attached figures: DR image preprocessing module 11, vertebral body recognition and Cobb angle calculation module 12, spinal space mapping module 13, brace mechanical parameter generation module 14, motion guidance and synchronous modeling module 15. Detailed Implementation

[0014] This application provides a method and system for dynamic neuromuscular guidance of scoliosis, which solves the problems in the prior art where orthotic braces lack precise spatial modeling based on image data, cannot combine muscle physiological state for dynamic feedback control, and rely on manual experience for adjustment during the orthotic process. It realizes three-dimensional spatial modeling based on DR images, fusion of multimodal physiological signals, and closed-loop adaptive adjustment of orthotic force, thereby improving the individual adaptation and dynamic control level of the orthotic process, and significantly improving the accuracy, stability and controllability of scoliosis correction.

[0015] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0016] Example 1 Please see the appendix Figure 1 This application provides a method for dynamic neuromuscular guidance of scoliosis, wherein the method is applied to a dynamic neuromuscular guidance system for scoliosis, and the method specifically includes the following steps: S1: Receives full-length DR spinal images uploaded by the patient via terminal software, automatically identifies each vertebral structure based on image recognition algorithms, calculates the supplementary angle between two straight lines as the Cobb angle, and records the lateral curvature direction and the position of the apex vertebra.

[0017] Specifically, in some embodiments, the scoliosis neuromuscular dynamic guidance system comprises three parts: a hardware layer, a software layer, and a user layer. The hardware layer includes a spinal orthotic brace and a terminal communication device. The spinal orthotic brace integrates a snap-fit ​​interface, a high-frequency vibration module, and a patch electrode assembly for wearing, mechanical output, and physiological signal acquisition. The terminal communication device is used for data interaction with the brace and for issuing control commands. The software layer includes a DR image analysis module, a muscle signal processing module, and a mechanical calculation engine, and enables user interaction and process visualization management via a mobile app. The user layer includes the patient or caregiver, who uses the mobile app to upload images, guide movement execution, and monitor the wearing process. Based on this system structure, the overall methodology is divided into three stages: basic signal acquisition and preprocessing, brace adjustment, and wearing monitoring. In the basic signal acquisition and preprocessing stage, the system acquires a full-length DR image of the spine and calculates the Cobb angle. Combined with a spinal biomechanical model, it determines the spatial coordinates of spinal segments and acquires surface electromyography signals during the patient's execution of standard test movements. This achieves the fusion analysis of image information and physiological signals, thereby generating the target orthotic spatial position and muscle tension benchmark. During the brace adjustment phase, the system determines the attachment direction and angle of the patch electrode assembly based on spatial point calculations and completes standardized attachment using a guided application device. Subsequently, the orthopedic brace is snapped together with the patch electrode assembly, and the device is initialized without applied orthopedic force, bringing the brace to a zero-tension baseline state. Based on this, the system drives the brace to perform progressive orthopedic control according to the calculated orthopedic force direction and intensity. During the wearing monitoring phase, the system continuously monitors the patient's spinal spatial position and muscle status during wear using a built-in IMU sensor and electromyography (EMG) signal acquisition module. Visual recording and trend analysis of DAY1 to DAYX are achieved via a mobile app. When muscle fatigue or spinal misalignment exceeds a preset threshold, the system triggers high-frequency vibration alerts and tension guidance, and, combined with app prompts, guides the patient to correct their posture, thereby achieving dynamic intervention and closed-loop control.

[0018] The patient uploads a full-length DR (Digital Radiographic) image of the spine via terminal software (preferably a mobile app). The DR image is an anteroposterior X-ray image covering the thoracic to lumbar vertebrae, reflecting the overall scoliosis morphology of the spine. The terminal software is deployed in the system's software layer and interacts with the orthotic brace in the hardware layer via a communication module. After receiving the image, the terminal software first performs scale calibration on the DR image. In some embodiments, when the image contains standard scale markings, the pixel spacing information is directly read to complete the calibration; when no markings are present, scale conversion is performed using a preset calibration template or reference object to establish a mapping relationship between pixel coordinates and actual spatial dimensions. Subsequently, the image undergoes preprocessing operations, including denoising and image enhancement. Denoising can employ median filtering or Gaussian filtering to reduce acquisition noise, while image enhancement can use contrast stretching or edge enhancement algorithms to improve the clarity and recognition stability of vertebral body boundaries. Through these processes, the input DR image possesses characteristics of uniform scale, low noise, and high contrast, thus providing a reliable data foundation for subsequent automatic vertebral body recognition, Cobb angle calculation, and spatial mapping of spinal segments. Furthermore, the preprocessed image data is transmitted to the DR image analysis module in the software layer for subsequent vertebral structure identification and angle measurement operations. After image scale calibration and preprocessing, the DR image analysis module in the terminal software automatically identifies and processes the images, locating and segmenting the vertebral structures based on image recognition algorithms to extract the spatial contour information of the vertebrae. Based on this, the system further identifies the upper and lower vertebrae constituting the lateral curvature line and extracts and reconstructs the upper and lower endplate boundaries of the corresponding vertebrae. The image recognition algorithm can be implemented based on edge detection, morphological processing, or deep learning segmentation models to improve the accuracy and robustness of vertebral boundary identification. According to the vertebral alignment direction and lateral curvature morphology, the upper and lower vertebrae with the greatest inclination are selected as the calculation reference vertebrae, and their upper and lower endplate boundary contours are extracted respectively. In some embodiments, the geometric boundary point set of the endplate is obtained by clustering or contour fitting the vertebral edge points, thereby constructing the basic data for line fitting. Through the above processing, the automatic positioning of key vertebrae in the lateral curvature line is achieved, providing a reliable structural basis for subsequent angle calculation. Geometric fitting is performed on the endplate boundaries of the upper and lower vertebrae to calculate the Cobb angle and determine the lateral curvature direction and the position of the apex vertebra. Linear fitting is performed on the boundary point sets of the upper and lower vertebrae respectively to obtain the corresponding upper and lower vertebrae endplate lines. Based on this, the angle between the two lines is calculated, and the supplementary angle is used as the numerical representation of the Cobb angle. Simultaneously, the system determines the lateral curvature direction based on the vertebral body's spatial offset direction and determines the apex vertebra position by combining the maximum deviation of the vertebral body from the spinal midline.In some implementations, the apical vertebral segment can be determined by calculating the offset distance of the vertebral body center point relative to the midline of the spine. This process achieves a standardized and quantitative expression of the degree and morphological parameters of scoliosis, providing key input parameters for subsequent spinal spatial mapping and orthopedic control.

[0019] S2: Based on the Cobb angle, the position of the apex vertebra and the preset anatomical landmarks, establish a spatial mapping relationship between the spinal segments and the surface landmarks, wherein the surface landmarks include at least the acromion point, the posterior midline of the spine and the pelvic reference point.

[0020] Specifically, based on the obtained Cobb angle, apical vertebra position, and preset anatomical landmarks, a spatial mapping relationship between spinal segments and the human body surface is established. This enables the conversion from imaging parameters to orthopedic control points on the body surface, providing a spatial basis model for subsequent calculation of orthopedic brace application points. Specifically, after calculating the Cobb angle and determining the apical vertebra position, the terminal software, based on the assumption of a three-dimensional biomechanical structure of the spine, divides the spine into multiple functional segments and associates each segment with corresponding structures on the human body surface. In some embodiments, the anatomical landmarks include the acromion, the posterior midline of the spine, and a pelvic reference point. A basic spatial reference coordinate system for the human trunk is constructed using these landmarks. Based on this, the system establishes a three-dimensional spatial coordinate system for the human trunk, using the posterior midline of the spine as the longitudinal reference axis and the spatial connection between the pelvic reference point and the acromion as a posture reference constraint. The spinal segments are then projected and mapped within this coordinate system. Furthermore, the spatial offset center of the scoliosis is determined based on the position of the apex vertebra, and the spatial offset weights of each segment are allocated in conjunction with the Cobb angle, thus establishing a correspondence between spinal segments and surface landmarks, enabling the mapping of radiographic structures to specific surface regions. This spatial mapping relationship is used to determine the effective area and mechanical direction of subsequent orthotic braces, thereby transforming abstract spinal deformity parameters into executable surface orthopedic control parameters. Through the above processing, a unified spatial expression based on radiographic parameters and surface anatomical structures is achieved, providing a basic spatial model support for subsequent orthopedic point calculations and brace mechanical control.

[0021] S3: Calculate the target position coordinates of each action point of the orthotic brace in three-dimensional space according to the preset segment division rules. (x, y, z) The points of application include the main force application point, the reaction support point, and the limiting point, and generate corresponding orthopedic force direction vectors and spatial distribution parameters. The orthopedic force direction vector is used for subsequent spatial control and mechanical output parameter generation of the orthopedic brace.

[0022] Specifically, after establishing the spatial mapping relationship between spinal segments and surface landmarks, the spine is functionally segmented according to a preset segmentation rule, and the spatial positions of each action point of the orthotic brace are calculated based on the human three-dimensional coordinate system. These action points include the main force application point, the reaction support point, and the limiting point, used to respectively apply orthotic thrust, provide mechanical balance support, and constrain non-target displacement, ensuring the stability and directional control of the orthotic process. Furthermore, each action point is represented in three-dimensional space as the target position coordinates. (x, y, z) This forms a unified spatial positioning expression, and generates orthopedic force direction vectors and spatial distribution parameters based on the spatial relationship between each point of action. The orthopedic force direction vector is used to characterize the spatial direction of the orthopedic force, and the spatial distribution parameters are used to describe the mechanical synergy between each point of action, thus providing a parameter input basis for the subsequent spatial control and mechanical output of the orthopedic brace.

[0023] S4: Guide the patient to perform a standard test sequence of movements, including flexion, extension, left tilt, and right tilt, and set the duration and movement range for each movement. This is used to divide the time into different posture stages and establish a data synchronization benchmark to build a time synchronization relationship between posture state and muscle response.

[0024] Specifically, the terminal software sends action guidance instructions to the patient or monitoring device via a mobile app, guiding the patient to perform a standard test action sequence in sequence. This sequence includes forward flexion, extension, left tilt, and right tilt. In some implementations, each standard test action is performed sequentially in a preset order, with corresponding duration parameters set to ensure stable holding times for each posture, meeting the stability requirements for subsequent physiological signal acquisition and analysis. Furthermore, the system assigns action interval identifiers to each standard test action and segments the action execution process based on time information, assigning unique time interval labels to different action stages, thereby constructing a time synchronization benchmark between posture state and muscle response. Through this processing, structured segmentation and time synchronization calibration of different posture stages are achieved, providing a unified time alignment basis for subsequent segmented analysis of electromyographic signals and extraction of muscle features under different postures.

[0025] S5: Based on the built-in sensors of the brace, the current posture state is obtained, and the spatial deviation between the current posture state and the target position is determined in combination with the spatial target position. Based on the spatial deviation, the output direction and output force of the orthopedic force are determined, wherein the orthopedic force is used to drive the orthopedic brace to apply directional pushing or pulling force to the human body, and the output of the orthopedic force is dynamically adjusted according to the degree of deviation in order to gradually reduce the spatial deviation.

[0026] Specifically, during the process of a patient wearing an orthotic brace, a posture sensor installed inside the brace acquires real-time information about the patient's current posture. In some embodiments, the posture sensor may include an inertial measurement unit (IMU), an angle sensor, or a displacement detection unit, used to acquire the spatial orientation, angular changes, and displacement of the human torso in different postures. Based on the real-time acquired posture information, the system compares it with the spatial target position obtained in step S3 to determine the spatial deviation between the current posture and the target position, thus characterizing the degree of deviation of the current spinal state from the target orthotic state. Further, based on the spatial deviation, corresponding orthotic force output parameters are generated, including the output direction and output force of the orthotic force, wherein the orthotic force is used to drive the orthotic brace to apply directional pushing or pulling force to the human body, guiding the current spinal posture to gradually adjust towards the target position. In some embodiments, the output direction may be determined based on the lateral bending direction and the spatial offset direction, and the output force may be adaptively adjusted based on the magnitude of the spatial deviation, the patient's tolerance, and a preset safety threshold. Further, the orthotic force output is dynamically adjusted according to the degree of spatial deviation. When the spatial deviation is detected to decrease, the system gradually reduces the orthopedic force output in the corresponding area; when the spatial deviation is detected to persist or increase, the system increases the orthopedic force output in the corresponding direction to form a progressive dynamic orthopedic process, thereby realizing closed-loop orthopedic control based on real-time posture feedback.

[0027] Furthermore, this application also includes a brace fitting and initialization stage: Based on the spatial mapping relationship and the calculation results of the target spatial position, the attachment direction and attachment angle parameters of the patch electrode assembly are determined. The attachment angle is the angle between the center line of the patch electrode assembly and the posterior midline of the spine. The patch electrode assembly is positioned and attached using a matching applicator, which includes a guide groove structure for constraining and guiding the spatial position and direction of the patch electrode assembly. The patch electrode assembly uses kinesiology tape, which stimulates proprioception through pulling force and kinesiology tape stimulation. The orthotic brace body is connected to the attached patch electrode assembly to form a stable fit between the orthotic brace and the human body. During the connection process, the orthotic brace is in an inactive state and no orthopedic force is applied. A communication connection is established with the orthotic brace through terminal software and an initialization program is executed. The motor drive mechanism inside the brace is controlled to adjust to a preset zero-tension state, so that the contact point between the brace and the human body is in a pressure-free or preset low-pressure contact state, which serves as the initial reference for subsequent orthopedic control.

[0028] Specifically, firstly, based on the established spatial mapping relationship between spinal segments and surface landmarks, and combined with the spatial target position calculation results obtained in step S4, the attachment direction and attachment angle parameters of the patch electrode assembly are determined. The attachment angle is the angle between the centerline of the patch electrode assembly and the posterior midline of the spine, used to characterize the spatial relationship between the attachment direction and the human anatomical reference. Based on this, the terminal software generates attachment guidance information. The user, following this guidance information, uses a matching application device to position and attach the patch electrode assembly. This application device includes a guide groove structure to constrain and guide the spatial position and attachment direction of the patch electrode assembly, ensuring standardized attachment along a preset direction, thereby improving the consistency and repeatability of the attachment process. Furthermore, in some embodiments, the patch electrode assembly employs a kinesiology tape structure with elastic tensile properties. After being attached to the human body surface, the kinesiology tape can exert a continuous elastic traction on the skin and superficial soft tissues along the preset attachment direction, thereby providing continuous stimulation to the human proprioceptive system. Specifically, the human skin, fascia, and superficial muscle groups contain a large number of mechanoreceptors and proprioceptors. When kinesiology tape exerts a continuous pulling force, it can provide directional stimulation to these receptors and influence the muscle tone and postural control of the corresponding muscle groups through nerve conduction, thereby guiding the patient to actively adjust their posture. Unlike traditional orthopedic methods that rely solely on external mechanical support, this application uses kinesiology tape to provide continuous neuromuscular sensory input, enabling the body to perceive the current postural deviation direction. Based on the directional force applied by the orthopedic brace, it guides the target muscle groups to actively exert force, thus forming a synergistic regulatory mechanism between "external orthopedic force—proprioceptive stimulation—active muscle response." Furthermore, because kinesiology tape can maintain a flexible fit during human movement, it can maintain a stable proprioceptive stimulation effect when the patient performs dynamic movements such as flexion, extension, and lateral tilting. This transforms the orthopedic process from a static support mode to a dynamic neuromuscular guidance mode, improving active participation, postural control, and long-term adaptability during the orthopedic process. In some embodiments, the kinesiology patch also serves as an electrode attachment carrier, integrating surface electromyography (EMG) electrodes to form an integrated structure that combines EMG signal acquisition with proprioceptive stimulation, thereby achieving coordinated operation of muscle state perception and neuromuscular guidance. After the electrode assembly is attached, the orthotic body is connected to the electrode assembly via a snap-fit ​​structure, forming a stable fit between the orthotic and the human body. During this connection process, the orthotic is in an inactive state and does not apply orthopedic force to the human body.Subsequently, a communication connection is established with the orthotic brace through the terminal software, and an initialization procedure is executed to complete the equipment status calibration and control preparation. During the initialization process, the motor drive mechanism inside the control brace is adjusted to a preset zero tension state, so that the contact point between the brace and the human body is in a pressure-free or preset low-pressure contact state, thereby eliminating the initial assembly stress and establishing the initial reference state for subsequent orthotic control.

[0029] Furthermore, this application also includes an orthopedic control and adaptive adjustment stage: Based on posture, pressure, or torque data collected by the brace's built-in sensors, the current orthopedic state is evaluated. According to the degree of spatial deviation between the current posture and the target position, the orthopedic state is classified as either completed or deviated. When a deviation is identified, the direction or intensity of the orthopedic force output is dynamically adjusted based on the degree of deviation to gradually reduce the spatial deviation. Manual adjustment of the orthopedic force output parameters is also allowed via terminal software.

[0030] Specifically, during the operation of the orthotic brace, sensors installed inside the brace collect real-time interaction data between the human body and the brace. In some embodiments, the sensors include posture sensors, pressure sensors, or torque sensors, used to acquire the current posture state of the human body, the force state of the brace, and changes in local forces. Based on the data collected by the sensors, the system performs real-time evaluation of the current orthotic state and classifies the current orthotic state by combining the degree of spatial deviation between the current posture state and the target position. Further, when the spatial deviation between the current posture state and the target position is within a preset allowable range, the system determines the current state as a completed orthotic state; when the spatial deviation exceeds a preset threshold, the system determines the current state as a deviation state, indicating that there is still a posture deviation or insufficient orthosis in the current orthotic process. When the system determines that the orthotic state is a deviation state, it dynamically adjusts the orthotic force output parameters based on the degree of spatial deviation. In some implementations, the dynamic adjustment includes correcting the direction of the orthopedic force output or adjusting the intensity of the orthopedic force output to generate a new directional force in the corresponding area of ​​action, thereby gradually reducing the spatial deviation between the current posture and the target position, achieving a progressive dynamic orthopedic process. Furthermore, in some implementations, the system allows for manual adjustment of the orthopedic force output parameters via terminal software. Users or caregivers can intervene and set local orthopedic intensity, area of ​​action, or adjustment intensity through the terminal software to meet the individualized orthopedic needs of different patients at different stages, thereby improving the flexibility, safety, and adaptability of the orthopedic control process.

[0031] Furthermore, the orthopedic control and adaptive adjustment stage described in this application also includes an anomaly detection step: Based on spatial deviation data and electromyographic signal data collected by the built-in sensors of the brace, the current orthopedic status is monitored; a prompting mechanism is triggered when any of the following conditions are met: when the spatial deviation does not decrease within a preset time or shows a continuous increasing trend; when the electromyographic signal is lower than the preset baseline range, it indicates muscle fatigue.

[0032] Specifically, the system monitors the current orthopedic status based on spatial deviation data and electromyographic (EMG) signal data collected by sensors built into the brace. The system triggers a prompting mechanism when either of the following conditions is met: first, when the spatial deviation does not decrease or shows a continuous increasing trend within a preset time, where the spatial deviation is determined based on the difference between the current position and the target position; second, when the EMG signal is below a preset baseline range, indicating that the target muscle group is in a state of fatigue. Through the above anomaly detection, the system identifies and prompts the spatial deviation and muscle fatigue states during the orthopedic process.

[0033] Furthermore, after triggering the aforementioned prompting mechanism, this application executes a guided intervention step: The system controls the orthotic brace to output high-frequency vibration; adjusts the local tension or thrust output of the orthotic brace to form a mechanical guide in a preset direction; and outputs posture adjustment prompts through the terminal software.

[0034] Specifically, after the prompting mechanism is triggered, the system executes guided intervention steps. These include: controlling the orthotic brace to output high-frequency vibrations to provide tactile cues to the target muscle groups; adjusting the local tension or thrust output of the orthotic brace to create mechanical guidance in a preset direction; and outputting posture adjustment prompts via terminal software. Through these methods, the system provides prompts and guided intervention for abnormal user posture.

[0035] Furthermore, the application device described in this application includes a guide groove structure for constraining the attachment direction and position of the application electrode assembly: Specifically, the applicator includes a guide groove structure for constraining and guiding the spatial position and application direction of the electrode assembly. In some embodiments, the guide groove structure matches the shape and size of the electrode assembly, allowing the electrode assembly to enter the guide groove along a preset trajectory during placement and maintain a predetermined orientation under the structural constraint, thereby achieving standardized control of the application direction and position. Through the above structural design, the electrode assembly can complete rapid and stable application under assisted positioning conditions, thereby improving application consistency and repeatability.

[0036] Furthermore, the orthopedic force described in this application is a progressive output force that increases over time: Specifically, the orthopedic force is a progressive output force that increases over time. That is, a lower orthopedic force is output in the initial stage of orthodontic treatment, and the output level is gradually increased as time goes on and the orthodontic condition improves, so as to reduce initial discomfort and improve long-term wearing compliance.

[0037] Furthermore, this application also includes steps for electromyography signal acquisition and initial parameter generation: Specifically, this application also includes steps for electromyography (EMG) signal acquisition and initial parameter generation. During the execution of a standard test movement, surface EMG signals of the target muscle group are acquired in real time using a patch electrode assembly integrated on the orthotic brace, and the EMG signals are time-synchronized and marked. Further, the EMG signals are segmented based on preset movement interval markers to extract muscle contraction characteristic parameters under different posture conditions, and an individualized muscle tension assessment benchmark is constructed based on these muscle contraction characteristic parameters. Initial control parameters for the orthotic control and adaptive adjustment phases are generated using these assessment benchmarks, thereby realizing the conversion of muscle physiological signals into orthotic control input parameters.

[0038] Example 2 Based on the same inventive concept as the neuromuscular dynamic guidance method for scoliosis described in the foregoing embodiments, this application also provides a neuromuscular dynamic guidance system for scoliosis. Please refer to the appendix. Figure 2 The system includes: The image acquisition and preprocessing module 11 is used to receive the full-length DR spine image uploaded by the patient through terminal software, and to perform scale calibration, noise reduction and enhancement processing on the image. The vertebral body recognition and Cobb angle calculation module 12 is used to automatically identify each vertebral structure based on image recognition algorithm, calculate the supplementary angle between two straight lines as the Cobb angle, and record the lateral bending direction and the position of the apex vertebra. The spinal spatial mapping modeling module 13 is used to establish a spatial mapping relationship between spinal segments and surface landmarks based on the Cobb angle, the position of the apex vertebra and preset anatomical landmarks. The surface landmarks include at least the acromion point, the posterior midline of the spine and the pelvic reference point. The orthopedic point spatial calculation module 14 is used to calculate the target position coordinates of each action point of the orthopedic brace in three-dimensional space according to the preset segment division rules. (x, y, z) The points of application include the main force application point, the reaction support point, and the limiting point, and generate corresponding orthopedic force direction vectors and spatial distribution parameters. The orthopedic force direction vector is used for subsequent spatial control and mechanical output parameter generation of the orthopedic brace. The standard movement guidance module 15 is used to guide patients to perform standard test movement sequences, including flexion, extension, left tilt and right tilt, and to set the duration and movement range labels for each movement. It is used to divide the time of different posture stages and establish data synchronization benchmarks to build a time synchronization relationship between posture state and muscle response.

[0039] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Figure 1 The method and specific examples for dynamic neuromuscular guidance of scoliosis in Embodiment 1 are also applicable to the dynamic neuromuscular guidance system for scoliosis in this embodiment. Through the foregoing detailed description of the method for dynamic neuromuscular guidance of scoliosis, those skilled in the art can clearly understand the dynamic neuromuscular guidance system for scoliosis in this embodiment; therefore, for the sake of brevity, it will not be described in detail here. As the system disclosed in the embodiments corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant details can be found in the method section.

[0040] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0041] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for dynamic neuromuscular guidance in scoliosis, characterized in that, The method includes: S1. Receive the full-length DR spinal image uploaded by the patient through the terminal software, automatically identify the structure of each vertebra based on the image recognition algorithm, calculate the supplementary angle between the two straight lines as the Cobb angle, and record the lateral curvature direction and the position of the apex vertebra at the same time. S2. Based on the Cobb angle, the position of the apex vertebra and the preset anatomical landmarks on the body surface, establish a spatial mapping relationship between the spinal segments and the surface landmarks, wherein the surface landmarks include at least the acromion point, the posterior midline of the spine and the pelvic reference point. S3. Calculate the target position coordinates of each action point of the orthotic brace in three-dimensional space according to the preset segment division rules. (x, y, z) The points of application include the main force application point, the reaction support point, and the limiting point, and generate corresponding orthopedic force direction vectors and spatial distribution parameters. The orthopedic force direction vector is used for subsequent spatial control and mechanical output parameter generation of the orthopedic brace. S4. Guide the patient to perform a standard test sequence of movements, including flexion, extension, left tilt, and right tilt, and set the duration and movement range for each movement. This is used to divide the time into different posture stages and establish a data synchronization benchmark to build a time synchronization relationship between posture state and muscle response. S5. Based on the built-in sensors of the brace, the current posture state is obtained, and the spatial deviation between the current posture state and the target position is determined in combination with the spatial target position. Based on the spatial deviation, the output direction and output force of the orthopedic force are determined, wherein the orthopedic force is used to drive the orthopedic brace to apply directional pushing or pulling force to the human body, and the output of the orthopedic force is dynamically adjusted according to the degree of deviation in order to gradually reduce the spatial deviation.

2. The method for dynamic neuromuscular guidance of scoliosis according to claim 1, characterized in that, It also includes the brace fitting and initialization stage, the steps of which include: Based on the spatial mapping relationship and the calculation results of the spatial target position, the attachment direction and attachment angle parameters of the patch electrode assembly are determined. The attachment angle is the angle between the center line of the patch electrode assembly and the posterior midline of the spine. The patch electrode assembly is positioned and attached using a matching applicator. The applicator includes a guide groove structure for constraining and guiding the spatial position and orientation of the patch electrode assembly. The patch electrode assembly is a kinesiology patch, which is applied through pulling force and stimulation of proprioception by the kinesiology patch. The orthotic brace body is connected to the attached patch electrode assembly to form a stable fit between the orthotic brace and the human body. During the connection process, the orthotic brace is in an inactive state and no orthotic force is applied. Establish a communication connection with the orthotic brace through terminal software and execute the initialization program; The motor drive mechanism inside the control brace is adjusted to a preset zero-tension state, so that the contact point between the brace and the human body is in a pressure-free or preset low-pressure contact state, which serves as the initial reference for subsequent orthopedic control.

3. The method for dynamic neuromuscular guidance of scoliosis according to claim 1, characterized in that, It also includes a corrective control and adaptive adjustment phase, the steps of which include: Based on the posture data, pressure data, or torque data collected by the built-in sensors of the brace, the current orthopedic state is evaluated, and the orthopedic state is divided into orthopedic completion state or orthopedic deviation state according to the degree of spatial deviation between the current posture state and the target position in the point space. When a state of orthopedic deviation is determined, the direction or intensity of the orthopedic force output is dynamically adjusted according to the degree of deviation in order to gradually reduce the spatial deviation. It also allows manual adjustment of the orthopedic force output parameters via terminal software.

4. The method for dynamic neuromuscular guidance of scoliosis according to claim 3, characterized in that, The orthopedic control and adaptive adjustment stage also includes an anomaly detection step, specifically: The current orthopedic status is monitored based on spatial deviation data and electromyographic signal data collected by the built-in sensors of the brace; The prompt mechanism is triggered when any of the following conditions are met: When the spatial deviation does not decrease within a preset time or shows a continuous increasing trend; When the electromyographic signal is below the preset baseline range, it indicates muscle fatigue.

5. The method for dynamic neuromuscular guidance of scoliosis according to claim 4, characterized in that, After the prompting mechanism is triggered, a guided intervention step is performed, which specifically includes: Control the orthotic brace to execute high-frequency vibration output; Adjust the local tension or thrust output of the orthotic brace to create mechanical guidance in a preset direction; It also outputs posture adjustment prompts via terminal software.

6. The method for dynamic neuromuscular guidance of scoliosis according to claim 1, characterized in that, The applicator includes a guide groove structure for constraining the application direction and position of the patch electrode assembly.

7. The method for dynamic neuromuscular guidance of scoliosis according to claim 1, characterized in that, The orthopedic force is a progressive output force that increases over time.

8. The method for dynamic neuromuscular guidance of scoliosis according to claim 1, characterized in that, The method also includes steps for electromyography signal acquisition and initial parameter generation: During the execution of the standard test action, electromyographic signals of the target muscle group were collected, and the electromyographic signals were time-synchronized and segmented based on the action interval label to extract muscle contraction characteristic parameters under different posture conditions. An individualized muscle tension assessment benchmark is constructed based on the muscle contraction characteristic parameters and used to generate initial control parameters in the orthopedic control and adaptive adjustment phases.

9. A neuromuscular dynamic guidance system for scoliosis, characterized in that, The system is used for implementing the neuromuscular dynamic guidance method for scoliosis according to any one of claims 1 to 8, wherein the system comprises: The DR image preprocessing module is used to receive the full-length DR spine image uploaded by the patient through the terminal software, automatically identify the structure of each vertebra based on the image recognition algorithm, calculate the supplementary angle between two straight lines as the Cobb angle, and record the lateral curvature direction and the position of the apex vertebra. The vertebral body recognition and Cobb angle calculation module is used to automatically identify each vertebral structure based on image recognition algorithms, calculate the supplementary angle between two straight lines as the Cobb angle, and record the lateral bending direction and the position of the apex vertebra. The spinal space mapping module is used to establish a spatial mapping relationship between spinal segments and surface landmarks based on the Cobb angle, the position of the apex vertebra and preset anatomical landmarks. The surface landmarks include at least the acromion point, the posterior midline of the spine and the pelvic reference point. The orthotic mechanical parameter generation module is used to calculate the target position coordinates of each action point of the orthotic brace in three-dimensional space according to the preset segment division rules. (x, y, z) The points of application include the main force application point, the reaction support point, and the limiting point, and generate corresponding orthopedic force direction vectors and spatial distribution parameters. The orthopedic force direction vector is used for subsequent spatial control and mechanical output parameter generation of the orthopedic brace. The motion guidance and synchronization modeling module guides patients to perform standard test motion sequences, including flexion, extension, left tilt, and right tilt, and sets the duration and motion range labels for each motion. This is used to divide the time into different posture stages and establish data synchronization benchmarks to build a time synchronization relationship between posture state and muscle response.

Images