Temporomandibular joint information processing method and device

Abstract

The embodiment of the invention provides an information processing method for a temporomandibular joint, which comprises the following steps: acquiring sensor information, determining six-degree-of-freedom motion information of the temporomandibular joint according to the sensor information, generating a three-dimensional motion track curve of the temporomandibular joint according to the six-degree-of-freedom motion information, and acquiring pain level information. According to the pain level information and the three-dimensional motion track curve, determining a lesion joint and obtaining a joint bouncing audio, according to the joint bouncing audio and the three-dimensional motion track curve, determining a bouncing type and obtaining muscle activity information, and according to the muscle activity information and the three-dimensional motion track curve, determining a muscle abnormal mode, and determining a diagnosis result of the temporomandibular joint based on the three-dimensional motion track information, the diseased joint, the bouncing type and the muscle abnormal mode. On the basis, the method and the device are used for fusing various information of the temporomandibular joint of the patient, and the accuracy of determining the cause of the temporomandibular joint disorder is improved through the motion-sound-myoelectricity combined characteristics.

Description

Technical Field

[0001] The present invention relates to the field of joint lesion detection, and particularly to a method and device for processing information of the temporomandibular joint. Background Art

[0002] Temporomandibular joint disorder is a common disease that affects the orofacial muscles, the temporomandibular joint, or both. Its symptoms usually include limited mouth opening, facial muscle pain, and joint clicking. And research surveys show that about 23% of patients with temporomandibular joint disorder may also experience tension, anxiety, insomnia, etc.

[0003] In related technologies, it mainly relies on asking the patient's subjective symptoms (such as pain location, clicking frequency) rather than objective data, making it difficult to distinguish whether temporomandibular joint disorder is joint - sourced (such as disc displacement) or muscle - sourced (such as masseter spasm), with insufficient diagnostic accuracy and unable to synchronously record different types of information, resulting in a lack of precision in subsequent coping strategies. Summary of the Invention

[0004] In view of the above problems, a method for processing information of the temporomandibular joint is proposed to provide a solution to overcome or at least partially solve the problem that it is difficult to accurately determine the cause relying on subjective symptoms in the traditional method, including: Obtain sensor information, and determine the six - degree - of - freedom motion information of the temporomandibular joint according to the sensor information; Generate a three - dimensional motion trajectory curve of the temporomandibular joint according to the six - degree - of - freedom motion information; Obtain pain level information, and determine the diseased joint according to the pain level information and the three - dimensional motion trajectory curve; Obtain joint clicking audio information, and determine the clicking type according to the joint clicking audio information and the three - dimensional motion trajectory curve; Obtain muscle activity information, and determine the muscle abnormal pattern according to the muscle activity information and the three - dimensional motion trajectory curve; Determine the diagnosis result of the temporomandibular joint based on the three - dimensional motion trajectory information, the diseased joint, the clicking type, and the muscle abnormal pattern.

[0005] In an alternative embodiment of the present application, the obtaining of the sensor information includes: Obtain the information measured by multiple micro - inertial measurement units at multiple joint parts of the patient, and the multiple joint parts include the posterior - lateral positions of bilateral mandibular condyles, the mental tubercle position, and the bilateral mandibular angle positions.

[0006] In an alternative embodiment of the present application, the information measured by the multiple micro inertial measurement units includes acceleration information, gyroscope information, and magnetometer information. Determining the six-degree-of-freedom motion information of the temporomandibular joint based on the sensor information includes: Calculating the six-degree-of-freedom motion information of the temporomandibular joint based on the acceleration information, gyroscope information, and magnetometer information. The six-degree-of-freedom motion information includes translational motion information and rotational motion information; Generating a three-dimensional motion trajectory curve based on the six-degree-of-freedom motion information includes: Generating three-dimensional motion trajectory curves of the sagittal plane, coronal plane, and horizontal projection plane based on the translational motion information and rotational motion information, and marking the opening degree, condylar sliding distance, and rotation angle on the three-dimensional motion trajectory curve.

[0007] In an alternative embodiment of the present application, the pain level information includes pain trigger time and pain intensity grading information. The three-dimensional motion trajectory information further includes trajectory abnormality information. Determining the diseased joint based on the pain level information and the three-dimensional motion trajectory curve includes: Determining the diseased joint based on the pain trigger time, pain intensity grading information, the pain trigger time, and the pain intensity grading information.

[0008] In an alternative embodiment of the present application, obtaining the joint clicking audio information includes: Obtaining the clicking audio information through a dual-channel contact microphone. The dual-channel contact microphone is provided with a high-pass filter to filter out the ambient noise around the patient; Determining the clicking type based on the joint clicking audio information and the three-dimensional motion trajectory curve includes: Generating the clicking time relationship information between the joint audio clicking information and time based on the joint audio clicking information; Determining the clicking type based on the clicking time relationship information and the three-dimensional motion trajectory curve. The clicking type includes clicking at the initial stage of opening, clicking at the end stage of opening, and clicking during closing.

[0009] In an alternative embodiment of the present application, obtaining the muscle activity information includes: Obtaining the muscle activity information of multiple parts of the patient through surface electromyography sensors. The multiple parts include bilateral masseter muscles and bilateral temporalis muscles; Determining the muscle abnormality pattern based on the muscle activity information and the three-dimensional motion trajectory curve includes: Calculating the muscle activation timing, muscle contraction intensity, and muscle fatigue index based on the muscle activity information; Determine the muscle abnormal pattern according to the muscle activation time sequence, muscle contraction intensity, muscle fatigue index and the three-dimensional motion trajectory curve.

[0010] In an alternative embodiment of the present application, the method further includes: Based on preset lesion information, establish a motion trajectory feature template, where the preset lesion information includes the motion trajectory, popping information and muscle activity information respectively corresponding to each lesion joint.

[0011] In an alternative embodiment of the present application, the determining the diagnosis result of the temporomandibular joint based on the three-dimensional motion trajectory information, the lesion joint, the popping type and the muscle abnormal pattern includes: Use a classification network to perform classification prediction based on the three-dimensional motion trajectory information, the lesion joint, the popping type and the muscle abnormal pattern to obtain the diagnosis result of the temporomandibular joint, where the diagnosis result of the temporomandibular joint includes diagnosis information and the probability corresponding to the diagnosis information.

[0012] In an alternative embodiment of the present application, the using a classification network to perform classification prediction based on the three-dimensional motion trajectory information, the lesion joint, the popping type and the muscle abnormal pattern to obtain the diagnosis result of the temporomandibular joint includes: Match the three-dimensional motion trajectory information, the lesion joint, the popping type and the muscle abnormal pattern with the motion trajectory feature template to obtain a matching result; Determine the diagnosis result of the temporomandibular joint according to the matching result.

[0013] An embodiment of the present invention also discloses an information processing device for a temporomandibular joint, and the device includes: A data acquisition module, configured to acquire sensor information and determine the six-degree-of-freedom motion information of the temporomandibular joint according to the sensor information; A trajectory generation module, configured to generate a three-dimensional motion trajectory curve of the temporomandibular joint according to the six-degree-of-freedom motion information; A position determination module, configured to acquire pain level information and determine a lesion joint according to the pain level information and the three-dimensional motion trajectory curve; A popping determination module, configured to acquire joint popping audio and determine the popping type according to the joint popping audio and the three-dimensional motion trajectory curve; A muscle abnormality determination module, configured to acquire muscle activity information and determine a muscle abnormal pattern according to the muscle activity information and the three-dimensional motion trajectory curve; A prediction module, configured to determine the diagnosis result of the temporomandibular joint based on the three-dimensional motion trajectory information, the lesion joint, the popping type and the muscle abnormal pattern.

[0014] The embodiments of the present invention have the following advantages: By obtaining sensor information, determining the six-degree-of-freedom motion information of the temporomandibular joint based on the sensor information, generating a three-dimensional motion trajectory curve of the temporomandibular joint based on the six-degree-of-freedom motion information, obtaining pain level information, determining the diseased joint based on the pain level information and the three-dimensional motion trajectory curve, obtaining joint clicking audio information, determining the clicking type based on the joint clicking audio information and the three-dimensional motion trajectory curve, obtaining muscle activity information, determining the muscle abnormal pattern based on the muscle activity information and the three-dimensional motion trajectory curve, and determining the diagnosis result of the temporomandibular joint based on the three-dimensional motion trajectory information, the diseased joint, the clicking type, and the muscle abnormal pattern. Based on this, the present application fuses multiple types of information of the patient's temporomandibular joint and improves the accuracy of determining the cause of temporomandibular joint disorders through combined motion-sound-electromyogram features. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the present invention, the drawings required for the description of the present invention will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0016] Figure 1 It is a flowchart of the steps of an information processing method for a temporomandibular joint provided by an embodiment of the present invention; Figure 2 It is a specific structural diagram of temporomandibular joint information processing provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the drawings and specific embodiments. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0018] The muscles involved in the movement of the temporomandibular joint can be divided into the masseteric muscles, the depressor muscles, the protruder / retractor muscles, and the lateral movement muscles. These muscles achieve the complex movement of the mandible through synergistic or antagonistic actions.

[0019] Therefore, the etiology of temporomandibular joint disorders is multifactorial. There are rarely definitive treatment methods for temporomandibular joint disorders. Most clinicians rely on maintenance therapies to relieve the signs and symptoms of patients, such as controlling pain and restoring the function of the masticatory system through medical treatment (usually using non-steroidal anti-inflammatory drugs) and physical therapy (using heat therapy, acupuncture, transcutaneous electrical nerve stimulation, ultrasonic therapy, orthotic therapy, etc.).

[0020] However, different treatment methods target different etiologies. For example, orthotics are only applicable to patients with occlusal abnormalities and are ineffective for bony structural abnormalities or severe cases. Moreover, physical therapy lacks quantitative feedback. Therefore, it is necessary to develop an information processing method for the temporomandibular joint to improve the accuracy of etiology determination and provide a more accurate etiology location for subsequent treatment plans.

[0021] Referring to Figure 1 , a step flowchart of an information processing method for the temporomandibular joint provided by an embodiment of the present invention is shown, which may specifically include the following steps: Step 101, obtain sensor information, and determine the six-degree-of-freedom motion information of the temporomandibular joint according to the sensor information.

[0022] Among them, the sensor refers to an IMU (Micro Inertial Measurement Unit, micro inertial measurement unit). An IMU is an integrated micro-sensor device used to measure the acceleration, angular velocity, and magnetic field direction of an object; the sensor information refers to the acceleration information, angular velocity information, and magnetic field direction information measured by the IMU; the six-degree-of-freedom motion of the temporomandibular joint refers to six independent motion modes that it can perform in three-dimensional space, including three translational degrees of freedom and three rotational degrees of freedom. These motions together achieve complex mandibular functions such as chewing, speaking, and swallowing.

[0023] According to the information measured by the IMU, the six-degree-of-freedom motion information of the temporomandibular joint can be determined.

[0024] In some embodiments of the present application, "obtain sensor information" in step 101 may include the following sub-steps: Sub-step 11: Obtain the information measured by multiple micro inertial measurement units at multiple joint sites of the patient. The multiple joint sites include the posterolateral positions of the bilateral mandibular condyles, the mental tubercle position, and the bilateral mandibular angle positions.

[0025] In a specific implementation, 5 micro inertial measurement unit IMU patches can be used to be respectively fixed at multiple joint sites of the patient: (1) the posterolateral sides of the bilateral mandibular condyles (bony landmarks, avoiding the joint capsule), (2) the mental tubercle (midline positioning), (3) the bilateral mandibular angles, so as to obtain the sensor information of multiple sites.

[0026] In some embodiments of the present application, the information measured by multiple micro inertial measurement units includes acceleration information, gyroscope information, and magnetometer information. "Determining the six-degree-of-freedom motion information of the temporomandibular joint based on the sensor information" in step 101 may include the following sub-steps: Sub-step 21: Calculate the six-degree-of-freedom motion information of the temporomandibular joint based on the acceleration information, gyroscope information, and magnetometer information. The six-degree-of-freedom motion information includes translational motion information and rotational motion information.

[0027] As can be seen from the foregoing, the IMU in the present application is an integrated micro-sensor device. By acquiring the acceleration information, gyroscope information, and magnetometer information measured by the IMU, the six-degree-of-freedom (6-DoF) motion information (including translational motion information and rotational motion information) of the temporomandibular joint (TMJ) can be calculated in real time according to the measured information.

[0028] Step 102: Generate a three-dimensional motion trajectory curve of the temporomandibular joint based on the six-degree-of-freedom motion information.

[0029] In some embodiments of the present application, step 102 may include the following sub-steps: Sub-step 31: Generate three-dimensional motion trajectory curves of the sagittal plane, coronal plane, and horizontal projection plane based on the translational motion information and rotational motion information, and mark the mouth opening degree, condylar sliding distance, and rotation angle on the three-dimensional motion trajectory curves.

[0030] In a specific implementation, the skull can be used as a reference to define the sagittal plane (XZ plane), coronal plane (YZ plane), and horizontal plane (XY plane). Generate a three-dimensional motion trajectory curve, and mark the mouth opening degree (the vertical displacement of the condyle from the closed position to the maximum opening position), condylar sliding distance, and rotation angle (including the anterior inclination angle of the condyle in the sagittal plane and the internal rotation / external rotation angle in the horizontal plane) on the curve.

[0031] Step 103: Obtain pain level information, and determine the diseased joint based on the pain level information and the three-dimensional motion trajectory curve.

[0032] In some embodiments of the present application, the pain level information includes pain trigger time and pain intensity grading information, and the three-dimensional motion trajectory information further includes trajectory abnormality information. Step 103 may include the following sub-steps: Sub-step 41: Determine the diseased joint based on the pain trigger time point, pain duration, and pain intensity.

[0033] In a specific implementation, wireless pressure sensors can be set on both sides of the patient's seat. For example, the wireless pressure sensor can be a lightweight button the size of a thumb. The patient can independently press the button to mark the pain point when the pain is most severe during the opening and closing of the mouth. The button is built-in with a vibration prompt and sends a timestamp signal to the host after being pressed, which is synchronized to the motion trajectory curve. The pain level information includes the pain trigger time point, the duration of pain, and the pain intensity. In a specific implementation, the moment when the patient presses the sensor is the pain trigger time point. The duration of pain can be quantified by the pressing duration, and the pain intensity can be quantified by the pressing force. Mark the pain trigger time, the duration of pain, and the pain intensity on the three-dimensional motion trajectory, and combine the trajectory abnormalities (such as excessive anterior movement of the condyle, offset of the rotation center) on the three-dimensional motion trajectory to locate the diseased joint side (left / right) and the possible damaged structures involved (articular disc, ligament).

[0034] Step 104: Obtain the joint clicking audio, and determine the clicking type based on the joint clicking audio and the three-dimensional motion trajectory curve.

[0035] In some embodiments of the present application, "obtaining the joint clicking audio" in step 104 may include the following sub-steps: Sub-step 51: Obtain the joint clicking audio through a dual-channel contact microphone, wherein the dual-channel contact microphone is provided with a high-pass filter to filter out the ambient noise around the patient.

[0036] In a specific implementation, a dual-channel contact microphone can be attached and worn 1 cm in front of the tragus on both sides of the patient (TMJ surface auscultation area). The dual-channel contact microphone can be built-in with a high-pass filter (>500 Hz) to eliminate ambient noise, so as to focus on the characteristic frequency of joint clicking (1-2 kHz).

[0037] In some embodiments of the present application, "determining the clicking type based on the joint clicking audio and the three-dimensional motion trajectory curve" in step 104 may include the following sub-steps: Sub-step 61: Generate the clicking time relationship information of the joint clicking audio based on the joint clicking audio; Sub-step 62: Determine the clicking type based on the clicking time relationship information and the three-dimensional motion trajectory curve. The clicking type includes clicking at the initial stage of opening, clicking at the end stage of opening, and clicking during closing.

[0038] In a specific implementation, after obtaining the joint clicking audio, a sound-time waveform diagram (i.e., the information on the relationship between the joint clicking audio and the clicking time at the clicking moment) can be generated, and the peak value of the clicking can be automatically identified. For example, the peak value of the clicking can be identified through a threshold algorithm. The clicking moment is synchronously marked with the movement trajectory to analyze the clicking type, and the clicking types include: clicking at the initial stage of opening, clicking at the end stage of opening, and clicking during closing. For example, the etiologies corresponding to the clicking at the initial stage of opening include but are not limited to anterior disc displacement of the joint, the etiologies corresponding to the clicking at the end stage of opening include but are not limited to joint capsule relaxation, and the etiologies corresponding to the clicking during closing include but are not limited to posterior disc displacement of the joint.

[0039] Step 105: Obtain muscle activity information, and determine the muscle abnormality pattern based on the muscle activity information and the three-dimensional movement trajectory curve.

[0040] In some embodiments of the present application, "obtaining muscle activity information" in step 105 may include the following sub-steps: Sub-step 71: Obtain the muscle activity information of multiple muscle parts of the patient through surface electromyography sensors, and the multiple muscle parts include bilateral masseters and bilateral temporalis muscles.

[0041] In a specific implementation, sEMG (Surface Electromyography Sensor) can be set on the patient's face to monitor muscle activity. For example, 4 sEMG patches are attached to the bilateral masseters (2 cm above the mandibular angle) and the temporalis muscles (above the zygomatic arch) to monitor muscle activity. Further, impedance matching can also be used to optimize the information. For example, dry electrodes + flexible circuits are adopted to reduce motion artifacts.

[0042] In some embodiments of the present application, "determining the muscle abnormality pattern based on the muscle activity information and the three-dimensional movement trajectory curve" in step 105 may include the following sub-steps: Sub-step 81: Calculate the muscle activation timing, muscle contraction intensity, and muscle fatigue index based on the muscle activity information; Sub-step 82: Determine the muscle abnormality pattern based on the muscle activation timing, muscle contraction intensity, muscle fatigue index, and the three-dimensional movement trajectory curve.

[0043] In a specific implementation, the muscle activation timing, contraction intensity (RMS value), and fatigue index (median frequency slope) can be calculated based on the measured muscle information. The electromyographic activity can also be synchronized with the joint movement trajectory to identify the muscle abnormality pattern. For example, high electromyogram at the initial stage of mouth opening, indicating that the corresponding etiology of joint compensation is over-activation of the masseter muscle, and phase delay, indicating that the corresponding etiology of neuromuscular control abnormality is the coordination disorder between the temporalis muscle and the masseter muscle.

[0044] In some embodiments of the present application, the following steps may further be included: Based on preset lesion information, a motion trajectory feature template is established. The preset lesion information includes the motion trajectory, clicking information, and muscle activity information respectively corresponding to each diseased joint.

[0045] The preset lesion information may specifically be various different classification information corresponding to temporomandibular joint disorders. For example, disc displacement, osteoarthritis, and myofascial pain. In a specific implementation, these preset lesion information can be used to establish a motion trajectory feature template (which can also be referred to as establishing an abnormal pattern library). The motion trajectory feature template includes but is not limited to motion trajectory features, clicking features, and muscle abnormality features. For example, the motion trajectory feature template corresponding to anterior disc displacement is that the condylar motion trajectory is "S"-shaped distorted + clicking at the initial stage of opening + delayed activation of the masseter muscle.

[0046] Step 106: Based on the three-dimensional motion trajectory information, diseased joint, clicking type, and muscle abnormal pattern, determine the diagnosis result of the temporomandibular joint.

[0047] In some embodiments of the present application, step 106 may include the following sub-steps: Sub-step 91: Use a classification network to perform classification prediction based on the three-dimensional motion trajectory information, diseased joint, clicking type, and muscle abnormal pattern to obtain the diagnosis result of the temporomandibular joint. The diagnosis result of the temporomandibular joint includes diagnosis information and the probability corresponding to the diagnosis information.

[0048] In a specific implementation, the motion-sound-EMG joint features collected in the foregoing steps can be analyzed through a CNN network, and classification prediction is performed based on the joint features to obtain the diagnosis result of the temporomandibular joint. The diagnosis result includes diagnosis information, that is, the cause of the disease; the diagnosis result also includes the probability corresponding to the diagnosis information, that is, the probability corresponding to this cause of the disease. For example, the diagnosis result is "Cause: reducible anterior disc displacement, Probability: 82%".

[0049] In some embodiments of the present application, sub-step 91 may further include the following sub-steps: Sub-step 111: Match the three-dimensional motion trajectory information, diseased joint, clicking type, and muscle abnormal pattern with the motion trajectory feature template to obtain a matching result; Sub-step 112: Determine the diagnosis result of the temporomandibular joint according to the matching result.

[0050] In a specific implementation, the established motion trajectory feature template can be used to assist the classification and prediction of the CNN network. The three-dimensional motion trajectory information, diseased joints, clicking types, and muscle abnormal patterns are matched with the motion trajectory feature template to obtain a matching result. Based on the matching result, the diagnosis result of the temporomandibular joint is determined. For example, the matching result is "reducible anterior disc displacement: 68%, joint capsule or ligament laxity: 32%", so based on the "reducible anterior disc displacement: 68%" with a higher probability in the matching result, the cause is determined to be reducible anterior disc displacement.

[0051] In some embodiments of the present application, a real-time face dynamic synchronization can be collected by a three-direction face image acquisition system to assist the accuracy of the three-dimensional motion trajectory curve. At the same time, a voice broadcast system is configured to guide the patient to complete the examination. In a specific implementation, the three-direction face image acquisition system can use 3 small cameras or cameras that can freely adjust the direction angle. The cameras or cameras can have telescopic brackets and bottom counterweight plates. After the patient is seated, the three-direction face image acquisition system automatically scans and establishes a facial three-dimensional coordinate system, and configures a system voice prompt: "Please keep the natural occlusion state for 3 seconds", "Please slowly open your mouth to the maximum extent", "Please slowly close your mouth".

[0052] As Figure 2 shown, it is a specific structure diagram of the temporomandibular joint information processing method provided by the embodiment of the present application. A multi-channel data fusion system is used to fuse various data collected by the micro inertial measurement unit (IMU), surface electromyography sensor (sEMG), dual-channel contact microphone, and three-direction face image acquisition system in the foregoing steps, and align the time axes of the various data. Specifically, the error can be set to be less than 1 ms based on the IMU clock. The three-dimensional motion trajectory, pain information, clicking audio information, muscle information, and face image information can also be superimposed and displayed through a visualization interface, that is, all the collected data is synchronized with the motion trajectory, pain, and clicking monitoring, and curves or images are formed on the visualization device at the doctor's end. In a specific implementation, the visualization interface can include a main view and a sub-view. Among them, the main view shows the three-dimensional motion trajectory curve, superimposed with pain markers (red), clicking markers (yellow), and myoelectric heat maps, and the sub-view shows the clicking audio waveform and the time-frequency analysis of the electromyogram signal. The information processing method of the temporomandibular joint in the present application determines the cause of the patient based on various data, so as to distinguish between arthrogenic (abnormal trajectory + clicking) and myogenic (abnormal electromyogram + no clicking). For example, arthrogenic corresponds to abnormal trajectory and clicking, and myogenic corresponds to abnormal electromyogram and no clicking; it should be noted that the method of the present application can also be used for treatment evaluation and occlusal reconstruction assistance. The treatment evaluation is used to compare the pain point distribution and clicking frequency before and after treatment to quantify the curative effect, and the occlusal reconstruction assistance is used to optimize the occlusal splint or orthodontic design through the motion trajectory.

[0053] Through multimodal synchronous analysis, a full-dimensional assessment of temporomandibular joint disorders with motion trajectory + pain + clicking + electromyogram is achieved, and the dynamic pain marking technique is used to obtain the patient's autonomous feedback, so as to directly correlate the autonomous feedback information with the objective data. In the trial stage, 50 patients with temporomandibular joint disorders were recruited. Comparing the diagnostic consistency with MRI instruments (Kappa>0.85), it shows that the consistency of using the method of this application for diagnosis and using MRI is far beyond random probability, close to perfect, and has extremely high clinical credibility. Among them, the spatial coincidence rate between the pain point and the disc displacement of the joint is >90%; comparing auscultation, the detection sensitivity of clicking is >95%.

[0054] In the embodiment of the present invention, by obtaining sensor information, based on the sensor information, six-degree-of-freedom motion information of the temporomandibular joint is determined. Based on the six-degree-of-freedom motion information, a three-dimensional motion trajectory curve of the temporomandibular joint is generated. Pain level information is obtained. Based on the pain level information and the three-dimensional motion trajectory curve, the diseased joint is determined. The joint clicking audio is obtained. Based on the joint clicking audio and the three-dimensional motion trajectory curve, the clicking type is determined. Muscle activity information is obtained. Based on the muscle activity information and the three-dimensional motion trajectory curve, the muscle abnormal pattern is determined. Based on the three-dimensional motion trajectory information, the diseased joint, the clicking type, and the muscle abnormal pattern, the diagnosis result of the temporomandibular joint is determined. Based on this, this application fuses various information of the patient's temporomandibular joint, and improves the accuracy of determining the cause of temporomandibular joint disorders through motion-sound-electromyogram joint features.

[0055] It should be noted that for the method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of the present invention are not limited by the described action sequence, because according to the embodiments of the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0056] The embodiment of the present invention also provides an information processing device for the temporomandibular joint, which may specifically include the following modules: A data acquisition module, configured to acquire sensor information, and based on the sensor information, determine six-degree-of-freedom motion information of the temporomandibular joint; A trajectory generation module, configured to generate a three-dimensional motion trajectory curve of the temporomandibular joint based on the six-degree-of-freedom motion information; A position determination module, configured to acquire pain level information, and based on the pain level information and the three-dimensional motion trajectory curve, determine the diseased joint; A popping sound determination module, configured to obtain the audio of the joint popping sound, and determine the popping sound type according to the joint popping sound audio and the three-dimensional motion trajectory curve; A muscle abnormality determination module, configured to obtain muscle activity information, and determine the muscle abnormality pattern according to the muscle activity information and the three-dimensional motion trajectory curve; A prediction module, configured to determine the diagnosis result of the temporomandibular joint based on the three-dimensional motion trajectory information, the diseased joint, the popping sound type, and the muscle abnormality pattern.

[0057] For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For the relevant parts, please refer to the partial description of the method embodiment.

[0058] The above provides a detailed introduction to an information processing method for the temporomandibular joint. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for processing information of a temporomandibular joint, characterized in that: The method comprises: Acquiring sensor information, and determining six-degree-of-freedom motion information of the temporomandibular joint based on the sensor information; Generating a three-dimensional motion trajectory curve of the temporomandibular joint according to the six-degree-of-freedom motion information; Acquiring pain level information, and determining a diseased joint according to the pain level information and the three-dimensional motion trajectory curve; Acquire joint clicking audio, and determine the type of clicking according to the joint clicking audio and the three-dimensional motion trajectory curve; Acquire muscle activity information, and determine a muscle abnormality pattern based on the muscle activity information and the three-dimensional motion trajectory curve; The diagnosis result of the temporomandibular joint is determined based on the three-dimensional motion trajectory information, the diseased joint, the clicking type and the muscle abnormality pattern.

2. The method according to claim 1, characterized in that The obtaining of sensor information includes: The information measured by multiple micro-inertial measurement units of multiple joints of the patient is obtained, wherein the multiple joints include the posterolateral positions of the bilateral mandibular condyles, the positions of the mental tuberosities, and the positions of the bilateral mandibular angles.

3. The method according to claim 2, characterized in that The information measured by the multiple micro inertial measurement units includes acceleration information, gyroscope information and magnetometer information. The six-degree-of-freedom motion information of the temporomandibular joint is determined based on the sensor information, including: Calculating six-degree-of-freedom motion information of the temporomandibular joint according to the acceleration information, the gyroscope information and the magnetometer information, wherein the six-degree-of-freedom motion information includes translational motion information and rotational motion information; The step of generating a three-dimensional motion trajectory curve based on the six-degree-of-freedom motion information includes: According to the translational motion information and the rotational motion information, three-dimensional motion trajectory curves of the sagittal plane, the coronal plane and the horizontal projection plane are generated, and the opening degree, the condylar sliding distance and the rotation angle are marked on the three-dimensional motion trajectory curve.

4. The method according to claim 3, characterized in that The pain level information includes the pain triggering time point, the pain duration and the pain intensity, the three-dimensional motion trajectory information also includes trajectory abnormality information, and determining the diseased joint based on the pain level information and the three-dimensional motion trajectory curve includes: The affected joint is determined based on the time of pain triggering, duration of pain and intensity of pain.

5. The method according to claim 1, characterized in that The step of obtaining the joint clicking audio comprises: Acquiring the clicking audio through a dual-channel contact microphone, wherein the dual-channel contact microphone is provided with a high-pass filter to filter out ambient noise around the patient; The determining of the snapping type according to the joint snapping audio and the three-dimensional motion trajectory curve includes: Generating the joint clicking time relationship information of the joint clicking audio according to the joint clicking audio; The type of the snap is determined according to the snap time relationship information and the three-dimensional motion trajectory curve, and the snap type includes an opening initial stage snap, an opening final stage snap and a closed stage snap.

6. The method according to claim 1, characterized in that The obtaining of muscle activity information comprises: Acquiring muscle activity information of multiple muscle parts of the patient through a surface electromyography sensor, wherein the multiple muscle parts include bilateral masseter muscles and bilateral temporalis muscles; Determining the muscle abnormality pattern based on the muscle activity information and the three-dimensional motion trajectory curve includes: Calculating muscle activation timing, muscle contraction intensity, and muscle fatigue index based on the muscle activity information; The muscle abnormality pattern is determined based on the muscle activation timing, muscle contraction intensity, muscle fatigue index and the three-dimensional motion trajectory curve.

7. The method according to claim 1, characterized in that The method further comprises: Based on the preset lesion information, a motion trajectory feature template is established, wherein the preset lesion information includes the motion trajectory, snapping information and muscle activity information corresponding to each lesion joint.

8. The method according to claim 7, characterized in that Determining the diagnosis result of the temporomandibular joint based on the three-dimensional motion trajectory information, the diseased joint, the clicking type and the muscle abnormality pattern includes: A classification network is used to perform classification prediction based on the three-dimensional motion trajectory information, the diseased joint, the clicking type and the muscle abnormality pattern to obtain a diagnosis result of the temporomandibular joint. The diagnosis result of the temporomandibular joint includes diagnostic information and the probability corresponding to the diagnostic information.

9. The method according to claim 8, characterized in that The classification network is used to perform classification prediction based on the three-dimensional motion trajectory information, the diseased joint, the snapping type and the muscle abnormality pattern to obtain the diagnosis result of the temporomandibular joint, including: Matching the three-dimensional motion trajectory information, the diseased joint, the snapping type and the muscle abnormality pattern with the motion trajectory feature template to obtain a matching result; The diagnosis result of the temporomandibular joint is determined based on the matching result.

10. An information processing device for a temporomandibular joint, characterized in that: The device comprises: A data acquisition module, used to acquire sensor information, and determine six-degree-of-freedom motion information of the temporomandibular joint based on the sensor information; A trajectory generation module, used for generating a three-dimensional motion trajectory curve of the temporomandibular joint according to the six-degree-of-freedom motion information; A position determination module, used to obtain pain level information, and determine the diseased joint according to the pain level information and the three-dimensional motion trajectory curve; A snapping determination module, used to obtain audio information of joint snapping, and determine the snapping type according to the audio information of joint snapping and the three-dimensional motion trajectory curve; A muscle abnormality determination module, used to obtain muscle activity information, and determine a muscle abnormality pattern based on the muscle activity information and the three-dimensional motion trajectory curve; A prediction module is used to determine the diagnosis result of the temporomandibular joint based on the three-dimensional motion trajectory information, the diseased joint, the clicking type and the muscle abnormality pattern.

Images