Skeletal muscle motion trajectory tracking system for early screening of myasthenia gravis patients

Abstract

The present application relates to the technical field of motion trajectory tracking, in particular to a skeletal muscle motion trajectory tracking system for early screening of myasthenia gravis patients. The system comprises: acquiring position coordinates and motion trajectories of key skeletal muscle nodes; determining the abnormal degree of muscle strength efficiency according to the instantaneous motion state fluctuation and curvature distribution of the motion trajectories; acquiring the bending angle and time sequence electrical signals of the target muscle pair of the muscle with synergistic effect, and determining the degree of synergy breakdown according to the fluctuation correlation of the time sequence electrical signals and the bending angles of different muscles; combining the abnormal degree of muscle strength efficiency and the degree of synergy breakdown to determine the motion trajectory abnormality coefficient, and tracking and screening based on the motion trajectory abnormality coefficient. The present application can effectively capture the irregular transition characteristics from "steady state to tremor state" of intermittent myasthenia, and effectively improve the sensitivity of early myasthenia screening.

Description

Technical Field

[0001] This invention relates to the field of motion trajectory tracking technology, specifically to a skeletal muscle motion trajectory tracking system for early screening of patients with myasthenia gravis. Background Technology

[0002] Myasthenia gravis (MG) is primarily characterized by skeletal muscle weakness and fatigue, especially during sustained physical activity. Early diagnosis is crucial for controlling and improving treatment outcomes. Therefore, skeletal muscle movement trajectory tracking systems for myasthenia gravis patients aim to optimize the diagnostic process through systematic analysis of movement trajectories, significantly improving the sensitivity and specificity of early screening, thereby saving patients time and effort.

[0003] Existing motion tracking technologies, relying on static data at discrete time points in the early screening of myasthenia gravis, cannot effectively analyze the spatiotemporal phase coupling relationship of multiple muscle groups in complex movements (such as the force delay of the deltoid and biceps brachii during upper limb raising), and fail to capture uncoordinated movements with micro-trajectory deviations. In particular, due to the lack of dynamic continuous analysis capabilities, the system cannot model the micro-scale spatiotemporal evolution law (such as random trajectory jitter corresponding to intermittent myasthenia gravis), resulting in poor sensitivity to screening for early myasthenia gravis phenomena. Summary of the Invention

[0004] To address the technical problem of insufficient dynamic and continuous analysis capabilities in related technologies, which prevents the modeling of micro-scale spatial evolution and results in poor sensitivity for screening early myasthenia gravis, this invention provides a skeletal muscle movement trajectory tracking system for early screening of myasthenia gravis patients. The specific technical solution adopted is as follows:

[0005] This invention proposes a skeletal muscle movement trajectory tracking system for early screening of patients with myasthenia gravis. The system includes:

[0006] The acquisition module is used to acquire the position coordinates of key skeletal muscle nodes in each frame during the complete motion cycle, and to determine the motion trajectory of each key skeletal muscle node based on the position coordinates.

[0007] The muscle efficacy module is used to determine the instantaneous motion dispersion factor at each key skeletal muscle node based on the instantaneous motion state fluctuation of the motion trajectory; determine the instantaneous curvature dispersion factor based on the curvature distribution of the motion trajectory; and determine the degree of muscle efficacy abnormality by combining the instantaneous motion dispersion factor and the instantaneous curvature dispersion factor.

[0008] The coordination module is used to acquire the bending angle and temporal electrical signals of the target muscle pairing muscles that have a synergistic effect. Based on the fluctuation correlation of the temporal electrical signals of different muscles in the target muscle pairing, time delay analysis is performed to determine the time delay anomaly index; based on the bending angle of different muscles, coordination analysis is performed to determine the non-coordination index; and combined with the time delay anomaly index and the non-coordination index, the degree of coordination failure is determined.

[0009] The tracking and screening module is used to determine the abnormal coefficient of the movement trajectory by combining the degree of abnormality in muscle strength and efficiency and the degree of synergy failure, and to perform tracking and screening based on the abnormal coefficient of the movement trajectory.

[0010] Furthermore, the instantaneous motion state includes instantaneous velocity and instantaneous acceleration. Based on the fluctuations in the instantaneous motion state of the motion trajectory, the instantaneous motion discrete factor is determined, including:

[0011] The average instantaneous velocity of all frames is calculated as the velocity mean; the absolute value of the difference between the instantaneous velocity of each frame and the velocity mean is determined, and the fluctuation is amplified by calculating the cube of the absolute value of the difference to obtain the velocity mean difference. The average velocity mean difference of all frames is normalized to obtain the velocity fluctuation index.

[0012] Calculate the numerical information entropy of the instantaneous acceleration for all frames, and normalize it as the acceleration disorder index;

[0013] The average of the velocity fluctuation index and the acceleration disorder index is used as the instantaneous motion dispersion factor.

[0014] Further, determining the instantaneous curvature discrete factor based on the curvature distribution of the motion trajectory includes:

[0015] Curve fitting is performed based on the motion trajectory of key skeletal muscle nodes to determine the fitting curve; the instantaneous curvature of each static frame in the fitting curve is obtained.

[0016] The information entropy of all instantaneous curvatures is normalized and used as the instantaneous curvature discrete factor.

[0017] Furthermore, the determination of the degree of abnormality in muscle function by combining the instantaneous motion discrete factor and the instantaneous curvature discrete factor includes:

[0018] Calculate the product of the instantaneous motion discrete factor and the instantaneous curvature discrete factor of the same key skeletal muscle node, and normalize it as the node anomaly factor of the key skeletal muscle node.

[0019] The maximum value of the node abnormality factor of all key skeletal muscle nodes is taken as the degree of muscle function abnormality.

[0020] Furthermore, the target muscle pair includes agonist and passive muscles. Based on the fluctuation correlation of the temporal electrical signals of different muscles in the target muscle pair, time delay analysis is performed to determine the time delay anomaly index, including:

[0021] Determine the different preset movement delays of passive muscles for agonist muscles;

[0022] Under different preset motion delays, the temporal electrical signals of passive muscles are shifted forward to obtain the time delay analysis signals of passive muscles;

[0023] Pearson correlation coefficients were calculated for the temporal electrical signals of agonist muscles and the time delay analysis signals of passive muscles. The preset motion delay corresponding to the maximum Pearson correlation coefficient was taken as the target time delay.

[0024] The target delay is normalized to obtain the delay anomaly index.

[0025] Furthermore, the coordination analysis based on the bending angles of different muscles to determine the non-coordination index includes:

[0026] Determine the temporal sequence of bending angles of agonist and passive muscles in different frames;

[0027] The Pearson correlation coefficient between the flexion angle time series of the agonist and passive muscles was calculated, and the negative number of the Pearson correlation coefficient was normalized as the non-coordination index.

[0028] Furthermore, the determination of the degree of coordination breaking by combining the delay anomaly index and the non-coordination index includes:

[0029] The mean values ​​of the time delay abnormality index and the non-coordination index in the same target muscle pair are calculated as the coordination abnormality coefficient of the target muscle pair.

[0030] The maximum value of the coordination abnormality coefficient of all target muscle pairs is taken as the degree of coordination failure.

[0031] Furthermore, the determination of the motion trajectory abnormality coefficient by combining the degree of abnormality in muscle strength efficacy and the degree of synergy impairment includes:

[0032] The product of the degree of abnormal muscle efficacy and the degree of synergy failure was calculated and normalized to serve as the abnormality coefficient of the movement trajectory.

[0033] Furthermore, the tracking and filtering based on motion trajectory anomaly coefficients includes:

[0034] Obtain the motion trajectory abnormality coefficient within the action cycle of the current moment. When the motion trajectory abnormality coefficient is greater than a preset abnormal threshold, mark the current moment as an abnormal motion moment and filter out all abnormal motion moments.

[0035] Furthermore, the preset abnormal threshold is 0.8.

[0036] The present invention has the following beneficial effects:

[0037] This invention acquires the position coordinates of key skeletal muscle nodes in each frame of a complete movement cycle, determines the motion trajectory of each key skeletal muscle node based on the position coordinates, and then combines the motion trajectory analysis with instantaneous motion state fluctuations and the curvature distribution of the motion trajectory. Addressing the shortcomings of existing technologies in capturing micro-scale spatiotemporal evolution, the system introduces a high-precision frame-based feature extraction mechanism. Combined with instantaneous sudden jerking capture, velocity fluctuations, and dual verification of curvature distribution, it effectively distinguishes between pathological tremors and inertial jerking, improving the reliability of muscle function anomaly analysis. Furthermore, it performs time delay analysis by analyzing the fluctuation correlation of temporal electrical signals of different muscles in a target muscle pair. The non-coordination index reveals energy transfer interruptions, and the combination of time delay anomaly index and non-coordination index solves the problem of spatiotemporal phase coupling analysis of multiple muscle groups. Finally, it determines the motion trajectory anomaly coefficient by combining the degree of muscle function anomaly and the degree of synergy failure, and performs tracking and screening based on the motion trajectory anomaly coefficient. In summary, this invention can effectively capture the irregular transition characteristics from the "steady state to tremor state" in intermittent myasthenia gravis, effectively improving the sensitivity of early myasthenia gravis screening. Attached Figure Description

[0038] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention 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 only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 A structural diagram of a skeletal muscle movement trajectory tracking system for early screening of patients with myasthenia gravis, provided in an embodiment of the present invention;

[0040] Figure 2 This is a schematic diagram of a timing electrical signal provided in an embodiment of the present invention. Detailed Implementation

[0041] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a skeletal muscle movement trajectory tracking system for early screening of patients with myasthenia gravis according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0042] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0043] The following description, in conjunction with the accompanying drawings, details the specific solution of a skeletal muscle movement trajectory tracking system for early screening of patients with myasthenia gravis provided by this invention.

[0044] Please see Figure 1 The diagram shows a skeletal muscle movement trajectory tracking system for early screening of patients with myasthenia gravis, according to an embodiment of the present invention. The system includes: an acquisition module 101, a muscle efficacy module 102, a coordination module 103, and a tracking and screening module 104.

[0045] The acquisition module 101 is used to acquire the position coordinates of key skeletal muscle nodes in each frame during the complete motion cycle, and to determine the motion trajectory of each key skeletal muscle node based on the position coordinates.

[0046] Myasthenia gravis (MG) is primarily characterized by skeletal muscle weakness and fatigue, especially during sustained physical activity. Early diagnosis is crucial for controlling and improving treatment outcomes. Therefore, skeletal muscle movement trajectory tracking systems for myasthenia gravis patients aim to optimize the diagnostic process through systematic analysis of movement trajectories, significantly improving the sensitivity and specificity of early screening, thereby saving patients time and effort.

[0047] Existing motion tracking technologies, relying on static data at discrete time points in the early screening of myasthenia gravis, cannot effectively analyze the spatiotemporal phase coupling relationship of multiple muscle groups in complex movements (such as the force delay of the deltoid and biceps brachii during upper limb raising), and fail to capture uncoordinated movements with micro-trajectory deviations. In particular, due to the lack of dynamic continuous analysis capabilities, the system cannot model the micro-scale spatiotemporal evolution law (such as random trajectory jitter corresponding to intermittent myasthenia gravis), resulting in poor sensitivity to screening for early myasthenia gravis phenomena.

[0048] This application aims to solve this problem. First, it is necessary to obtain relevant data foundation. In this embodiment of the invention, fixed training movements are set, such as elbow flexion and squatting. The start / end points of all movements are automatically marked by the optical system, synchronously triggering all sensors to start data recording. 4mm reflective markers are attached to key bony landmarks of the patient's upper limb (acromion, lateral epicondyle of the humerus, etc.). Eight 120fps high-speed infrared cameras (1920×1080 resolution) are arranged diagonally at the top of the area to achieve multi-angle three-dimensional motion trajectory image capture of the limb (accuracy ±0.1mm), followed by static frame image segmentation. The motion trajectory information of key skeletal muscle nodes in continuous frames is then determined.

[0049] The muscle efficacy module 102 is used to determine the instantaneous motion dispersion factor at each key skeletal muscle node based on the instantaneous motion state fluctuation of the motion trajectory; determine the instantaneous curvature dispersion factor based on the curvature distribution of the motion trajectory; and determine the degree of muscle efficacy abnormality by combining the instantaneous motion dispersion factor and the instantaneous curvature dispersion factor.

[0050] The essence of myasthenia gravis is impaired nerve signal transmission, resulting in incomplete or excessively rapid muscle contraction upon receiving nerve signals, manifesting as asynchronous contraction of muscle fibers (microscopic tremors of non-inertial movement). Therefore, in this embodiment of the invention, the microscopic tremors can be analyzed based on the movement and trajectory of key skeletal muscle nodes.

[0051] Furthermore, in some embodiments of the present invention, the instantaneous motion state includes instantaneous velocity and instantaneous acceleration. Based on the fluctuations in the instantaneous motion state of the motion trajectory, the instantaneous motion discrete factor is determined, including: calculating the mean of instantaneous velocities across all frames as the velocity mean; determining the absolute value of the difference between the instantaneous velocity and the velocity mean for each frame, amplifying the fluctuation by calculating the cube of the absolute value of the difference to obtain the velocity mean difference, normalizing the mean of the velocity mean differences across all frames to obtain the velocity fluctuation index; calculating the numerical information entropy of the instantaneous acceleration across all frames, normalizing it to obtain the acceleration disorder index; and using the mean of the velocity fluctuation index and the acceleration disorder index as the instantaneous motion discrete factor.

[0052] The velocity fluctuation index represents the fluctuation of velocity. It is obtained by amplifying the mean difference to get the velocity mean difference, which represents the overall dispersion. The velocity fluctuation index is obtained by averaging all velocity mean differences. The larger the velocity fluctuation index, the more dispersed the velocity changes in different frames, which means that the state of possible small jitter phenomena is greater.

[0053] Similarly, the acceleration disorder index represents the discrete characteristics of instantaneous acceleration itself. By analyzing instantaneous acceleration in the form of information entropy, the acceleration disorder index is determined. The acceleration disorder index is used to reflect the degree of disorder in muscle control during the movement phase.

[0054] Therefore, in this embodiment of the invention, the mean values ​​of the velocity fluctuation index and the acceleration disorder index are directly calculated as instantaneous motion dispersion factors. The larger the value of the instantaneous motion dispersion factor, the more disordered and discrete the corresponding overall instantaneous state fluctuation is, that is, the more likely there is a small overall jitter of non-inertial motion.

[0055] Furthermore, in some embodiments of the present invention, determining the instantaneous curvature discrete factor based on the curvature distribution of the motion trajectory includes: performing curve fitting based on the motion trajectory of key skeletal muscle nodes to determine the fitting curve; obtaining the instantaneous curvature of each static frame in the fitting curve; and normalizing the information entropy of all instantaneous curvatures as the instantaneous curvature discrete factor.

[0056] Further analysis of the complexity of jitter patterns in the motion trajectory is introduced to distinguish between real muscle weakness and instantaneous motion instability caused by motion decay due to inertia. Therefore, by analyzing the instantaneous curvature and determining the instantaneous curvature discrete factor based on information entropy, a high instantaneous curvature discrete factor indicates a complex jitter pattern in the stage trajectory (suspected muscle weakness tremor).

[0057] Therefore, in this embodiment of the invention, the determination of the degree of abnormality in muscle strength performance by combining the instantaneous motion discrete factor and the instantaneous curvature discrete factor includes: calculating the product of the instantaneous motion discrete factor and the instantaneous curvature discrete factor of the same key skeletal muscle node, normalizing it as the node abnormality factor of the key skeletal muscle node; and taking the maximum value of the node abnormality factors of all key skeletal muscle nodes as the degree of abnormality in muscle strength performance.

[0058] The higher the value of abnormal muscle function, the more significant the shaking in the phase of the movement trajectory. Moreover, this shaking pattern is not the normal skeletal muscle shaking caused by inertial movement, which means that the muscle action is more abnormal during the movement.

[0059] The coordination module 103 is used to acquire the bending angle and temporal electrical signal of the target muscle pairing muscles that have a synergistic effect. Based on the fluctuation correlation of the temporal electrical signals of different muscles in the target muscle pairing, time delay analysis is performed to determine the time delay anomaly index. Based on the bending angle of different muscles, coordination analysis is performed to determine the non-coordination index. Combining the time delay anomaly index and the non-coordination index, the degree of coordination failure is determined.

[0060] See Figure 2 , Figure 2 This is a schematic diagram of a timing electrical signal provided in an embodiment of the present invention; optical markers are used to automatically identify the action boundary (such as the start / end frame of a horizontal lift), and data segments are divided according to the action cycle to avoid data interference across cycles; then, the electromyographic timing signals of each musculoskeletal group under the timing image of the patient's movement trajectory are acquired synchronously as timing electrical signals.

[0061] The target muscle pairs can be, for example, the anterior / middle deltoid, biceps brachii, and upper trapezius. 16-lead fabric electrodes are deployed with a sampling rate ≥2000Hz to synchronously capture the temporal electrical signals of muscle activation.

[0062] Specifically, the target muscle pair includes an agonist and a passive muscle. In this embodiment of the invention, the bending angle of the muscle is specifically the angle data between the agonist and passive muscle groups in the target muscle pair. The agonist muscle group can be, for example, the anterior deltoid, and the corresponding passive muscle group is the biceps brachii. The bending angle is obtained by aligning the anterior deltoid with the joint it connects to and the biceps brachii with the joint it connects to.

[0063] Based on the correlation of fluctuations in the temporal electrical signals of different muscles in the target muscle pair, time delay analysis is performed to determine the time delay anomaly index. This includes: determining different preset movement delays of the passive muscle against the agonist muscle; shifting the temporal electrical signals of the passive muscle forward under different preset movement delays to obtain the time delay analysis signal of the passive muscle; calculating the Pearson correlation coefficient between the temporal electrical signals of the agonist muscle and the time delay analysis signal of the passive muscle, and taking the preset movement delay corresponding to the maximum Pearson correlation coefficient as the target time delay; and normalizing the target time delay to obtain the time delay anomaly index.

[0064] The preset motion delay is the time delay information set for time delay analysis, specifically 20ms, 60ms, 100ms, 140ms, and 180ms. Since the agonist muscles move first, influencing the passive muscles, the electromyographic signal shows that the agonist muscles are activated first, followed by the passive muscles. The longer this delay, the more likely there is a neurotransmitter disorder. Due to neurotransmitter disorders, patients with myasthenia gravis experience significant activation delays and reduced synergy among different muscles during motor coordination. Therefore, anomaly analysis is performed by analyzing the time delay.

[0065] The temporal electrical signal of the passive muscle is shifted forward by a distance corresponding to a preset motion delay to obtain a new electrical signal. The higher the correlation between this electrical signal and the temporal electrical signal of the agonist muscle, the more accurate the corresponding delay effect. Therefore, in this embodiment of the invention, correlation analysis is performed using the Pearson correlation coefficient to determine the preset motion delay corresponding to the maximum Pearson correlation coefficient as the target delay. The target delay is then normalized to obtain the delay anomaly index.

[0066] The higher the value of the time delay anomaly index, the longer the time delay of the corresponding agonist and passive muscles, which in turn reflects the poorer motor coordination control effect between the target muscle pair.

[0067] Coordination analysis was performed based on the bending angles of different muscles to determine the non-coordination index. This included: determining the temporal sequence of bending angles of the agonist and passive muscles in different frames; calculating the Pearson correlation coefficient between the temporal sequences of bending angles of the agonist and passive muscles; and normalizing the negative value of the Pearson correlation coefficient as the non-coordination index.

[0068] After completing the phase coupling analysis of the target muscles, we further verified whether the failure of neural control caused joint-level kinematic dysfunction (interruption of energy transfer) in order to address the disruption of inter-joint energy transfer caused by neuromuscular delay in patients with myasthenia gravis.

[0069] The noncoordination index is represented by calculating the temporal correlation between the bending angles of the agonist and passive muscles. The larger the value of the noncoordination index, the more significant the mismatch between the agonist and passive muscles is reflected at the data analysis level, that is, the more obvious the motor coordination problem is during exercise.

[0070] Furthermore, in some embodiments of the present invention, the degree of coordination failure is determined by combining the time delay anomaly index and the non-coordination index, including: calculating the mean of the time delay anomaly index and the non-coordination index in the same target muscle pair as the coordination anomaly coefficient of the target muscle pair; and taking the maximum value of the coordination anomaly coefficient of all target muscle pairs as the degree of coordination failure.

[0071] Among them, the larger the value of the time delay abnormality index, the longer the time delay of the corresponding agonist and passive muscles, which indirectly reflects the poorer motor coordination control effect between the target muscle pair. In addition, the larger the value of the noncoordination index, the more significant the imbalance between agonist and passive muscles is reflected at the data analysis level, that is, the more obvious the motor coordination problem during the movement.

[0072] Therefore, in this embodiment of the invention, the delay anomaly index and the non-coordination index are fused to obtain the coordination anomaly coefficient, which is used to evaluate the motion state at the current stage. The larger the value of the coordination anomaly coefficient, the worse the corresponding coordination. Therefore, the maximum value of the coordination anomaly coefficient of all target muscle pairs is taken as the degree of coordination failure.

[0073] The tracking and screening module 104 is used to determine the abnormal coefficient of the movement trajectory by combining the degree of abnormality of muscle strength efficacy and the degree of synergy failure, and to perform tracking and screening based on the abnormal coefficient of the movement trajectory.

[0074] Both the degree of abnormal muscle function and the degree of synergy deficit are analyzed by maximizing the detection accuracy and sensitivity.

[0075] Furthermore, in some embodiments of the present invention, the abnormal coefficient of the movement trajectory is determined by combining the degree of abnormal muscle efficacy and the degree of synergy failure, including: calculating the product of the degree of abnormal muscle efficacy and the degree of synergy failure, and normalizing it as the abnormal coefficient of the movement trajectory.

[0076] The degree of abnormal muscle efficacy characterizes the abnormal changes in the image dimension during the movement process. A larger value indicates significant jitter in the stage of the movement trajectory, and this jitter pattern is not the normal skeletal muscle jitter caused by inertial movement, that is, the more abnormal the muscle action is during the movement. The degree of coordination failure characterizes the abnormality in electromyographic signals and muscle angle changes during the movement process. A larger value indicates a worse effect of motor coordination control between muscles and a worse coordination. Therefore, the product of the degree of abnormal muscle efficacy and the degree of coordination failure is calculated and normalized to obtain the abnormality coefficient of the movement trajectory.

[0077] The motion trajectory anomaly coefficient is an anomaly index obtained by combining data analysis from two dimensions, which is used to analyze muscle weakness in the motion process in a more refined and sensitive way.

[0078] Tracking and filtering based on motion trajectory abnormality coefficients includes: obtaining the motion trajectory abnormality coefficient within the action cycle of the current moment; marking the current moment as an abnormal motion moment when the motion trajectory abnormality coefficient is greater than a preset abnormal threshold; and filtering out all abnormal motion moments.

[0079] Among them, since the larger the value of the abnormality coefficient of the movement trajectory, the worse the motor coordination control effect between the corresponding muscles is, and there is obvious non-inertial movement causing conventional skeletal muscle tremors, the more abnormal the movement process is. In this embodiment of the invention, threshold analysis is used to filter normal and abnormal movement moments.

[0080] First, determine the motion trajectory abnormality coefficient within the action cycle of the current moment. Then, if the motion trajectory abnormality coefficient is greater than the preset abnormal threshold, it is regarded as an abnormal motion moment; otherwise, it is regarded as a normal motion moment.

[0081] In this embodiment of the invention, the preset abnormal threshold can be, for example, 0.8. That is, when the abnormal coefficient of the motion trajectory is greater than 0.8, it is regarded as an abnormal motion moment.

[0082] In this embodiment of the invention, after determining the abnormal movement moment, recording and alarm feedback can help to achieve early screening and treatment of myasthenia gravis in a timely manner, and effectively locate and track the abnormal movement cycle.

[0083] This invention acquires the position coordinates of key skeletal muscle nodes in each frame of a complete movement cycle, determines the motion trajectory of each key skeletal muscle node based on the position coordinates, and then combines the motion trajectory analysis with instantaneous motion state fluctuations and the curvature distribution of the motion trajectory. Addressing the shortcomings of existing technologies in capturing micro-scale spatiotemporal evolution, the system introduces a high-precision frame-based feature extraction mechanism. Combined with instantaneous sudden jerking capture, velocity fluctuations, and dual verification of curvature distribution, it effectively distinguishes between pathological tremors and inertial jerking, improving the reliability of muscle function anomaly analysis. Furthermore, it performs time delay analysis by analyzing the fluctuation correlation of temporal electrical signals of different muscles in a target muscle pair. The non-coordination index reveals energy transfer interruptions, and the combination of time delay anomaly index and non-coordination index solves the problem of spatiotemporal phase coupling analysis of multiple muscle groups. Finally, it determines the motion trajectory anomaly coefficient by combining the degree of muscle function anomaly and the degree of synergy failure, and performs tracking and screening based on the motion trajectory anomaly coefficient. In summary, this invention can effectively capture the irregular transition characteristics from the "steady state to tremor state" in intermittent myasthenia gravis, effectively improving the sensitivity of early myasthenia gravis screening.

[0084] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0085] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A skeletal muscle movement trajectory tracking system for early screening of patients with myasthenia gravis, characterized in that, The system includes: The acquisition module is used to acquire the position coordinates of key skeletal muscle nodes in each frame during the complete motion cycle, and to determine the motion trajectory of each key skeletal muscle node based on the position coordinates. The muscle efficacy module is used to determine the instantaneous motion dispersion factor at each key skeletal muscle node based on the instantaneous motion state fluctuation of the motion trajectory; determine the instantaneous curvature dispersion factor based on the curvature distribution of the motion trajectory; and determine the degree of muscle efficacy abnormality by combining the instantaneous motion dispersion factor and the instantaneous curvature dispersion factor. The coordination module is used to acquire the bending angle and temporal electrical signals of the target muscle pairing muscles that have a synergistic effect. Based on the fluctuation correlation of the temporal electrical signals of different muscles in the target muscle pairing, time delay analysis is performed to determine the time delay anomaly index; based on the bending angle of different muscles, coordination analysis is performed to determine the non-coordination index; and combined with the time delay anomaly index and the non-coordination index, the degree of coordination failure is determined. The tracking and screening module is used to determine the abnormality coefficient of the movement trajectory by combining the degree of abnormality of muscle strength efficacy and the degree of synergy failure, and to perform tracking and screening based on the abnormality coefficient of the movement trajectory. The method for determining the instantaneous motion discrete factor includes: calculating the mean of instantaneous velocities across all frames as the velocity mean; determining the absolute value of the difference between the instantaneous velocity and the velocity mean for each frame, amplifying the fluctuation by calculating the cube of the absolute value of the difference to obtain the velocity mean difference, normalizing the mean of the velocity mean differences across all frames to obtain the velocity fluctuation index; calculating the numerical information entropy of the instantaneous acceleration across all frames, normalizing it to obtain the acceleration disorder index; and using the mean of the velocity fluctuation index and the acceleration disorder index as the instantaneous motion discrete factor. The method for determining the instantaneous curvature discrete factor includes: performing curve fitting based on the motion trajectory of key skeletal muscle nodes to determine the fitting curve; obtaining the instantaneous curvature of each static frame in the fitting curve; and normalizing the information entropy of all instantaneous curvatures as the instantaneous curvature discrete factor. The method for determining the time delay anomaly index includes: determining different preset motion delays for the passive muscle against the agonist muscle; shifting the time-series electrical signal of the passive muscle forward under different preset motion delays to obtain the time delay analysis signal of the passive muscle; calculating the Pearson correlation coefficient between the time-series electrical signal of the agonist muscle and the time delay analysis signal of the passive muscle, and taking the preset motion delay corresponding to the maximum Pearson correlation coefficient as the target time delay; and normalizing the target time delay to obtain the time delay anomaly index. The method for determining the incoordination index includes: determining the temporal sequence of bending angles of the agonist and passive muscles in different frames; calculating the Pearson correlation coefficient between the temporal sequences of bending angles of the agonist and passive muscles; and normalizing the negative value of the Pearson correlation coefficient as the incoordination index.

2. The skeletal muscle movement trajectory tracking system for early screening of patients with myasthenia gravis as described in claim 1, characterized in that, The determination of the degree of muscle strength dysfunction by combining instantaneous motion discrete factor and instantaneous curvature discrete factor includes: Calculate the product of the instantaneous motion discrete factor and the instantaneous curvature discrete factor of the same key skeletal muscle node, and normalize it as the node anomaly factor of the key skeletal muscle node. The maximum value of the node abnormality factor of all key skeletal muscle nodes is taken as the degree of muscle function abnormality.

3. The skeletal muscle movement trajectory tracking system for early screening of myasthenia gravis patients as described in claim 1, characterized in that, The determination of the degree of coordination failure by combining the delay anomaly index and the non-coordination index includes: The mean values ​​of the time delay abnormality index and the non-coordination index in the same target muscle pair are calculated as the coordination abnormality coefficient of the target muscle pair. The maximum value of the coordination abnormality coefficient of all target muscle pairs is taken as the degree of coordination failure.

4. The skeletal muscle movement trajectory tracking system for early screening of myasthenia gravis patients as described in claim 1, characterized in that, The determination of the motion trajectory abnormality coefficient by combining the degree of abnormality in muscle strength efficacy and the degree of synergy impairment includes: The product of the degree of abnormal muscle efficacy and the degree of synergy failure was calculated and normalized to serve as the abnormality coefficient of the movement trajectory.

5. A skeletal muscle movement trajectory tracking system for early screening of patients with myasthenia gravis as described in claim 1, characterized in that, The tracking and filtering based on motion trajectory anomaly coefficient includes: Obtain the motion trajectory abnormality coefficient within the action cycle of the current moment. When the motion trajectory abnormality coefficient is greater than a preset abnormal threshold, mark the current moment as an abnormal motion moment and filter out all abnormal motion moments.

6. A skeletal muscle movement trajectory tracking system for early screening of patients with myasthenia gravis as described in claim 5, characterized in that, The preset abnormal threshold is 0.8.

Images