Evaluation method and system for cerebral apoplexy recovery stage

Abstract

The invention relates to an assessment method and system for a stroke recovery stage, and belongs to the technical field of medical assessment, the method comprises the following steps: obtaining demographic information of a stroke patient, and obtaining motion video data of the stroke patient, the motion video data comprising upper limb motion data, lower limb motion data and / or hand motion data; key points are extracted from the motion video data of each type based on a key point recognition algorithm, corresponding motion posture data in the motion video data of each type are calculated based on the positions of the key points, and the motion posture data comprise angle data and displacement data; and determining preset motion attitude data based on a Brunnstrom six-stage theory and demographic information, comparing the motion attitude data with the preset motion attitude data, and obtaining a recovery stage of the stroke patient based on a comparison result. Real-time monitoring and intelligent evaluation of the rehabilitation process of the stroke patient are realized, and the evaluation accuracy and diagnosis efficiency are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical assessment, and in particular relates to an assessment method and system for a stroke recovery stage. Background Art

[0002] Stroke is a serious neurological disease, and its recovery process is complex and changeable. The six-stage recovery theory proposed by Swedish physiotherapist Signe Brunnstrom provides theoretical guidance for the rehabilitation of stroke patients. However, the existing technology mainly relies on manual evaluation of the recovery stage of stroke patients, which is easily affected by subjective factors and lacks real-time and accuracy. Therefore, how to better realize the evaluation of the recovery stage of stroke patients has become an urgent problem to be solved. Summary of the invention

[0003] In view of the above shortcomings of the prior art, the purpose of the invention is to provide a method and system for evaluating the recovery stage of stroke. The method realizes real-time monitoring and intelligent evaluation of the rehabilitation process of stroke patients, and improves the accuracy of the evaluation.

[0004] The first aspect of the present invention proposes a method for evaluating the recovery stage of a stroke, comprising: S1, obtaining demographic information of a stroke patient, and obtaining motion video data of the stroke patient, wherein the motion video data includes upper limb motion data, lower limb motion data and / or hand motion data; S2, extracting key points from each type of the motion video data based on a key point recognition algorithm, and calculating corresponding motion posture data in each type of the motion video data based on the positions of the key points, wherein the motion posture data includes angle data and displacement data; S3, determining preset motion posture data based on Brunnstrom's six-stage theory and the demographic information, comparing the motion posture data with the preset motion posture data, and obtaining the recovery stage of the stroke patient based on the comparison result.

[0005] Furthermore, obtaining the motion video data of the stroke patient includes: obtaining an action list of the stroke patient, wherein each type of the motion video data corresponds to the action list, and the actions in the action list are arranged in sequence based on the action level, and the higher the action level, the more complex the action execution; executing each action in the action list to obtain the motion video data of the stroke patient.

[0006] Furthermore, executing each action in the action list to obtain motion video data of the stroke patient includes: determining a preset evaluation parameter value of the first action in the action list; obtaining an action instruction of the first action; executing the first action based on the action instruction, and determining the action parameter value of the first action; judging that the first action is completed within a preset time and the action parameter value is within the preset evaluation parameter value range, obtaining the preset evaluation parameter value of the Nth action, and obtaining the action instruction of the Nth action; executing the Nth action based on the action instruction of the Nth action, and determining the action parameter value of the Nth action; judging that the Nth action is completed within the preset time and the action parameter value is within the preset evaluation parameter value, obtaining the upper limb motion data, the lower limb motion data and / or the hand motion data of the stroke patient.

[0007] Further, the angle data includes angle values, and the displacement data includes displacement values, wherein the corresponding motion posture data in each type of the motion video data is calculated based on the position of the key point, including: determining a calculation attribute based on a preset evaluation parameter; when the calculation attribute is a calculation angle, determining a joint position, and based on , calculate the angle value, where, , represents the inter-joint vector, , represents the modulus of the inter-joint vector, wherein the inter-joint vector is calculated based on the coordinate difference of the key point; in the case where the calculated attribute is the calculated displacement, the displacement time is determined based on , calculate the displacement value, where, , Represents the coordinates of key points.

[0008] Furthermore, the method further comprises: preprocessing the extracted key points, including: based on G = [ X 1 ， X 2 ，...X n ] , obtain the original key point sequence, where n represents the nth data set; through median filtering, with k as the time window, obtain the median result of the original key point sequence after median filtering G ' = [ X 1 ' ， X 2 ' ，...X n ' ] ; Based on Kalman filtering, the median result G ' = [ X 1 ' ， X 2 ' ，...X n ' ] Each key point in is smoothed.

[0009] Furthermore, the motion posture data is compared with the preset motion posture data, and the recovery stage of the stroke patient is obtained based on the comparison result, including: determining the numerical range corresponding to the preset motion posture data in each stage of the Brunnstrom six-stage theory; determining the target recovery stage corresponding to the numerical value of the motion posture data from the numerical range corresponding to the preset motion posture data in multiple stages, and using the target recovery stage as the recovery stage of the stroke patient.

[0010] Furthermore, it also includes: according to , obtain the matching score between the motion posture data and the preset motion posture data in the target recovery phase, where N represents the total number of parameters, represents the weight of the parameter, It represents the difference between the motion posture data value and the preset motion posture data value, or the difference between the preset motion posture data value and the motion posture data value.

[0011] The second aspect of the present invention proposes an evaluation system for the recovery stage of a stroke, comprising: an acquisition module, used to acquire demographic information of a stroke patient, and acquire motion video data of the stroke patient, wherein the motion video data includes upper limb motion data, lower limb motion data and / or hand motion data; a calculation module, used to extract key points from each type of the motion video data based on a key point recognition algorithm, and calculate the corresponding motion posture data in each type of the motion video data based on the position of the key points, wherein the motion posture data includes angle data and displacement data; an acquisition module, used to determine preset motion posture data based on Brunnstrom's six-stage theory and the demographic information, compare the motion posture data with the preset motion posture data, and obtain the recovery stage of the stroke patient based on the comparison result.

[0012] According to a third aspect of the present invention, an electronic device is proposed, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any of the methods described in the first aspect of the present invention.

[0013] According to a fourth aspect of the present invention, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute any one of the methods according to the first aspect of the present invention.

[0014] The beneficial effects of the present invention are as follows:

[0015] The stroke recovery stage assessment method and system of the present invention obtains demographic information of stroke patients, and obtains motion video data of stroke patients, the motion video data including upper limb motion data, lower limb motion data and / or hand motion data; extracts key points from each type of motion video data based on a key point recognition algorithm, and calculates corresponding motion posture data in each type of motion video data based on the position of the key points, the motion posture data including angle data and displacement data; determines preset motion posture data based on Brunnstrom's six-stage theory and demographic information, compares the motion posture data with the preset motion posture data, and obtains the recovery stage of the stroke patient based on the comparison result. The method realizes real-time monitoring and intelligent evaluation of the rehabilitation process of stroke patients, improves the accuracy of evaluation, and improves diagnostic efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are only used to illustrate specific embodiments and are not considered to limit the present invention. In the entire drawings, the same reference symbols represent the same components. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0017] Figure 1 is a flow chart of a method for evaluating a stroke recovery stage according to an embodiment of the present invention;

[0018] Figure 2 is a flow chart of a method for evaluating a stroke recovery stage according to a specific embodiment of the present invention;

[0019] Figure 3 is a flow chart of a method for acquiring motion video data of a stroke patient according to an embodiment of the present invention;

[0020] Figure 4 is a schematic diagram of an evaluation system for stroke recovery stages according to an embodiment of the present invention;

[0021] Figure 5 It is a structural block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making creative work should fall within the scope of protection of the present invention.

[0023] Furthermore, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concepts disclosed in the present invention.

[0024] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the orientation or position relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, the terms "first", "second", and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. The terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0025] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of methods and systems consistent with some aspects of the present invention as detailed in the appended claims.

[0026] In the existing technology, the problems with the methods for evaluating the recovery stage of stroke patients include: strong subjectivity: traditional methods rely on the experience of medical staff, and the evaluation results are easily affected by personal judgment and lack objectivity; insufficient real-time performance: most existing evaluation tools find it difficult to obtain and analyze the patient's recovery status in real time and cannot meet the needs of dynamic monitoring; lack of personalization: existing technologies cannot dynamically adjust the evaluation criteria according to individual characteristics such as the patient's age and muscle tone, and have poor adaptability; high equipment dependence: for wearable solutions, wearable sensors may cause data deviation or instability due to improper wearing methods, affecting the evaluation results.

[0027] To this end, the present invention proposes an evaluation method, system and related equipment for the stroke recovery stage. Specifically, the evaluation method, system and related equipment for the stroke recovery stage of an embodiment of the present invention are described below with reference to the accompanying drawings.

[0028] Figure 11 is a flow chart of a method for evaluating the stroke recovery stage according to an embodiment of the present invention. It should be noted that the method for evaluating the stroke recovery stage of the embodiment of the present invention can be applied to the evaluation system for the stroke recovery stage of the embodiment of the present invention. The evaluation system for the stroke recovery stage can be configured on an electronic device or in a server. This embodiment of the present application does not limit this.

[0029] like Figure 1 As shown, the assessment methods for the stroke recovery stage include;

[0030] S110, acquiring demographic information of the stroke patient, and acquiring motion video data of the stroke patient, wherein the motion video data includes upper limb motion data, lower limb motion data and / or hand motion data.

[0031] In the embodiment of the present invention, demographic information includes but is not limited to name, age, gender, medical history, contact information, etc.

[0032] In an embodiment of the present invention, demographic information of a stroke patient can be obtained based on a terminal device, and motion video data of a stroke patient can be obtained, wherein an action list of a stroke patient can be obtained, wherein each type of motion video data corresponds to an action list, and the actions in the action list are arranged in sequence based on the action level, and the higher the action level, the more complex the action execution; each action in the action list is executed to obtain motion video data of a stroke patient. The specific implementation method can refer to the subsequent embodiments.

[0033] S120, extracting key points from each type of motion video data based on a key point recognition algorithm, and calculating corresponding motion posture data in each type of motion video data based on the positions of the key points, wherein the motion posture data includes angle data and displacement data.

[0034] In an embodiment of the present invention, when motion video data of a stroke patient is obtained, key points can be extracted from each type of motion video data based on a key point recognition algorithm, the positions of the key points can be determined based on the extracted key points, and then the corresponding motion posture data in each type of motion video data can be calculated based on the positions of the key points, and the motion posture data includes angle data and displacement data. The specific implementation method can refer to the subsequent embodiments.

[0035] S130, determining preset motion posture data based on Brunnstrom's six-stage theory and demographic information, comparing the motion posture data with the preset motion posture data, and obtaining the recovery stage of the stroke patient based on the comparison result.

[0036] In an embodiment of the present invention, when the corresponding motion posture data in each type of motion video data is obtained, the motion posture data can be compared with the preset motion posture data, and then the recovery stage of the stroke patient can be obtained based on the comparison result. The specific implementation method can refer to the subsequent embodiments.

[0037] According to the stroke recovery stage assessment method of the embodiment of the present invention, demographic information of the stroke patient is obtained, and motion video data of the stroke patient is obtained, the motion video data includes upper limb motion data, lower limb motion data and / or hand motion data; key points are extracted from each type of motion video data based on the key point recognition algorithm, and the corresponding motion posture data in each type of motion video data is calculated based on the position of the key points, and the motion posture data includes angle data and displacement data; based on Brunnstrom's six-stage theory and demographic information, the preset motion posture data is determined, the motion posture data is compared with the preset motion posture data, and the recovery stage of the stroke patient is obtained based on the comparison result. This method realizes real-time monitoring and intelligent evaluation of the rehabilitation process of stroke patients, improves the accuracy of evaluation, and improves diagnostic efficiency.

[0038] In order to make it easier for those skilled in the art to understand the present invention, Figure 2 is a method for evaluating the stroke recovery stage according to a specific embodiment of the present invention, such as Figure 2 As shown, the assessment methods for this stage of stroke recovery include:

[0039] S210, obtaining demographic information of stroke patients.

[0040] In an embodiment of the present invention, the demographic information may be set in a demographic information form. Correspondingly, the demographic information form of the stroke patient may be obtained based on the terminal, and then the demographic information may be obtained based on the demographic information form.

[0041] S220, obtaining motion video data of the stroke patient, where the motion video data includes upper limb motion data, lower limb motion data and / or hand motion data.

[0042] In an embodiment of the present invention, when demographic information of a stroke patient is obtained, motion video data of the stroke patient can be obtained based on the demographic information. The motion video data of the stroke patient can be obtained in real time, and the motion video data includes image data; the motion video data of the stroke patient can also be directly obtained when the motion video data of the stroke patient is recorded.

[0043] In an embodiment of the present invention, Figure 3 As shown, the implementation method of obtaining motion video data of stroke patients includes:

[0044] S310, obtaining an action list of the stroke patient, wherein each type of motion video data corresponds to an action list, and the actions in the action list are arranged in sequence based on the action level, and the higher the action level, the more complex the action execution.

[0045] In an embodiment of the present invention, an action list corresponding to each type of motion video data of a stroke patient is obtained, wherein the action list includes one or more actions, wherein, in the case of including multiple actions, the multiple actions are arranged in sequence based on the action level, and the higher the action level, the more complex the action execution is, and in other words, the lower the action level, the simpler the action execution is.

[0046] In an embodiment of the present invention, the action level may be determined based on a preset action level database, where the action level database includes actions and action levels corresponding to the actions.

[0047] S320, executing each action in the action list to obtain motion video data of the stroke patient.

[0048] In an embodiment of the present invention, a preset evaluation parameter value of the first action in an action list is determined; an action instruction of the first action is obtained; the first action is executed based on the action instruction, and the action parameter value of the first action is determined; if it is judged that the first action is completed within a preset time and the action parameter value is within a preset evaluation parameter value range, the preset evaluation parameter value of the Nth action is obtained, and the action instruction of the Nth action is obtained; based on the action instruction of the Nth action, the Nth action is executed, and the action parameter value of the Nth action is determined; if it is judged that the Nth action is completed within the preset time and the action parameter value is within the preset evaluation parameter value, the upper limb movement data, lower limb movement data and / or hand movement data of the stroke patient are obtained.

[0049] That is to say, when the action list includes multiple actions, the preset evaluation parameter value of the first action in the action list can be determined. When the action instruction of the first action is obtained, the first action is executed based on the action instruction, and the action parameter value of the first action is determined. When it is judged that the first action is completed within the preset time and the action parameter value of the first action is within the preset evaluation parameter value range, the preset evaluation parameter value of the second action in the action list is obtained. When the action instruction of the second action is obtained, the second action is executed based on the action instruction, and the action parameter value of the second action is determined. When it is judged that the second action is completed within the preset time and the action parameter value of the second action is within the preset evaluation parameter value range, the preset evaluation parameter value of the third action in the action list is obtained, so as to execute the third action and determine that the third action is completed within the preset time and the action parameter value of the third action is within the preset evaluation parameter value range, until the action parameter value of the last action in the action list is obtained, thereby obtaining the upper limb movement data, lower limb movement data and / or hand movement data of the stroke patient.

[0050] Among them, different stroke patients have different preset evaluation parameter values ​​for the corresponding actions. For example, when the stroke patient is less than 60 years old, the action list for upper limb motion data includes 5 actions, namely action 1: (muscle contraction as the degree); action 2 (shoulder joint lateral displacement continues to be >0); action 3 (shoulder flexion >70°, elbow flexion <10°, abduction <±10°); action 4 (shoulder flexion >150°, elbow flexion <10°, abduction <30°); action 5 (the speed is more than 2 / 3 of the healthy hand). When the stroke patient is more than 60 years old, the action list for upper limb motion data includes 5 actions, namely action 1: (muscle contraction as the degree); action 2 (shoulder joint lateral displacement continues to be >0); action 3 (shoulder flexion >60°, elbow flexion <20°, abduction ±10°); action 4 (shoulder flexion >130°, elbow flexion <20°, abduction <30°); action 5 (the speed is more than 2 / 3 of the healthy hand). That is to say, younger patients have relatively good physical functions and greater recovery potential, so relatively high standards will be set for the preset action evaluation parameter values; while older patients have reduced physical functions and relatively greater difficulty in recovery, so the corresponding evaluation parameter standards will be appropriately lowered. That is, by setting different preset action evaluation parameter values ​​for different age groups, the recovery level of upper limb movement, lower limb movement and / or hand movement function of stroke patients can be more accurately measured. This personalized setting helps to improve the effect and quality of rehabilitation treatment for stroke patients and make the evaluation of recovery results more scientific, reasonable and humane.

[0051] S230 , extracting key points from each type of motion data of the motion video data based on a key point recognition algorithm.

[0052] In an embodiment of the present invention, when each type of motion video data is obtained, data preprocessing can be performed on each type of motion video data, that is, the motion video data is decoded and converted from a compressed video format into an image sequence that can be processed by a computer, so that each frame of the image can be analyzed subsequently; then the decoded image is normalized, including adjusting the size, brightness, contrast, etc. of the image to make it have a consistent format and features, which is convenient for the algorithm to better process and reduce recognition errors caused by image differences; filtering and other methods are used to remove noise in the image, such as Gaussian filtering can effectively remove Gaussian noise, improve the quality of the image, and avoid noise interference with key point recognition.

[0053] After data preprocessing, the preprocessed image is input into the selected key point recognition algorithm, and the algorithm will extract features from the image according to its principle and model structure. For traditional algorithms, features are calculated based on information such as the grayscale value of the image; for deep learning algorithms, CNN automatically extracts high-level features of the image through operations such as convolutional layers and pooling layers; based on the extracted features, the algorithm detects key points according to certain rules and thresholds. For example, the SIFT algorithm detects extreme points as key points in the scale space, while the OpenPose algorithm predicts the key point positions of various parts of the human body by analyzing the feature map; for the detected key points, their positions are further refined to improve the accuracy of the key points. Sub-pixel precision positioning methods can be used, such as fitting curves or surfaces to determine more accurate coordinates of key points.

[0054] In the embodiment of the present invention, when the key points are extracted, the extracted key points can be preprocessed, wherein based on G = [ X 1 ， X 2 ，...X n ] , get the original key point sequence, where n represents the nth data set; through median filtering, with k as the time window, get the median result of the original key point sequence after median filtering G ' = [ X 1 ' ， X 2 ' ，...X n ' ] ; Based on the median result of Kalman filter G ' = [ X 1 ' ， X 2 ' ，...X n ' ] Each key point in is smoothed.

[0055] Among them, based on X i ' = median （[X i − k ，...，X i ，...，X i + k ]） , calculate the median filter of each key point in the original key point sequence, where, represents the median filter of the i-th key point, represents a key point sequence, and k represents the time window size; k can be preset, and k is usually an odd number, such as k=3 or k=5.

[0056] S240, calculating corresponding motion posture data in each type of motion data based on the positions of the key points.

[0057] In an embodiment of the present invention, the motion posture data includes angle data and displacement data, wherein the angle data includes angle values, and the displacement data includes displacement values.

[0058] In an embodiment of the present invention, a calculated attribute is determined based on a preset evaluation parameter; in the case where the calculated attribute is a calculated angle, a joint position is determined, and based on , calculate the angle value, where , represents the inter-joint vector, , Represents the modulus of the inter-joint vector, where the inter-joint vector is calculated based on the coordinate difference of the key points; when the calculated attribute is the calculated displacement, the displacement time is determined based on , calculate the displacement value, where, , Represents the coordinates of key points.

[0059] The preset evaluation parameters can be understood as the measurement criteria set for the joint movement, which are used for subsequent judgment and calculation, and the calculation attributes can be judged according to the content and purpose involved in the preset evaluation parameters. For example, if the parameters focus on the change of joint angle, the calculation attribute is determined to be the calculation angle; if the focus is on the position movement of the joint, the calculation attribute is determined to be the calculation displacement.

[0060] S250, determining preset motion posture data based on Brunnstrom's six-stage theory and demographic information, comparing the motion posture data with the preset motion posture data, and obtaining the recovery stage of the stroke patient based on the comparison result.

[0061] In an embodiment of the present invention, preset motion posture data is determined based on Brunnstrom's six-stage theory and demographic information. That is, the preset motion posture data is determined in combination with the patient's demographic information (such as age, medical history, and other factors that affect the recovery process), and multiple factors can be comprehensively considered to more accurately set a reference standard that meets the individual situation of each stroke patient. By individually setting the preset motion posture data and comparing it with the actual motion posture data, it is possible to more accurately determine which stage of recovery the stroke patient is currently in.

[0062] In an embodiment of the present invention, according to , obtain the matching score between the motion posture data and the preset motion posture data in the target recovery phase, where N represents the total number of parameters, represents the weight of the parameter, It represents the difference between the motion posture data value and the preset motion posture data value, or the difference between the preset motion posture data value and the motion posture data value.

[0063] In other words, through the matching score S, we can know that the higher the matching score S, the closer the stroke patient's movement posture data is to the preset movement posture data, and the better the rehabilitation status; conversely, it means that there is a large gap between the stroke patient and the standard of the target recovery stage, and rehabilitation work needs to be strengthened. That is, by calculating the matching score S, we can assist in judging the level of rehabilitation of stroke patients and provide an objective basis for adjusting the rehabilitation plan and evaluating the efficacy.

[0064] N represents the total number of parameters. In stroke rehabilitation assessment, parameters may include joint angles, displacement distances, movement speeds and other data. For example, when evaluating upper limb movement posture, multiple parameters such as shoulder flexion angle, elbow flexion and extension angle, and wrist displacement may be involved, that is, the sum of the number of these parameters.

[0065] In an embodiment of the present invention, in the upper limb movement data, Brunnstrom's six-stage theory includes: Stage I: relaxation, no movement; Stage II: only coordinated movement patterns appear; Stage III: coordinated movement patterns can be initiated at will; Stage IV: abnormal movements begin to weaken, and the following activities can be performed: shoulder 0°, elbow flexion 90°, forearm pronation, supination; elbow straight, shoulder flexion 90°; the back of the hand can touch the back of the waist; Stage V: separation movement occurs, such as elbow straight, shoulder abduction 90°; elbow straight, shoulder flexion 30°-90°, forearm pronation, supination; elbow straight, forearm neutral position, upper limbs can be raised forward over the head; Stage VI: movement coordination is normal or close to normal.

[0066] In an embodiment of the present invention, in the lower limb movement data, Brunnstrom's six-stage theory includes: Stage I: relaxation, without any movement; Stage II: very little voluntary movement occurs; Stage III: the abnormal extensor movement pattern reaches a peak; Stage IV: the abnormal movement begins to weaken, and the following activities can be performed: when sitting, the knee is flexed more than 90°, and the foot can slide backward; when sitting, the heel touches the ground and the ankle can dorsiflex; when sitting, the knee joint can be extended; Stage V: separation movement occurs, such as when sitting, the knee joint is extended, the ankle joint can dorsiflex, and the hip can be internally rotated; when standing, the knee joint is extended and the ankle joint can dorsiflex; when standing, the hip of the affected limb can be extended and the knee flexed; Stage VI: the movement speed and coordination are close to normal.

[0067] In an embodiment of the present invention, in the hand movement data, Brunnstrom's six-stage theory includes: Stage I: relaxation, without any movement; Stage II: only slight flexion of the fingers; Stage III: able to make hook-like grasping, but unable to extend the fingers; Stage IV: able to grasp laterally and release the thumb, and the fingers can be extended in a small range at will; Stage V: able to grasp cylindrical or spherical objects, the fingers can be extended together, but not individually; Stage VI: able to perform various grasping movements, but the speed and accuracy are slightly poor.

[0068] In a specific embodiment of the present invention, when the motion video data of the stroke patient is obtained as upper limb motion data, an action list of the upper limb motion data can be determined, wherein the action list includes moving the affected shoulder, raising the affected hand, raising both hands to shoulder height, raising both hands above the head, and pointing to the nose. When the instruction "please move your affected shoulder" is received, the affected shoulder is moved. If the movement of the affected shoulder is completed within a preset time and the movement parameters of the affected shoulder are within a preset evaluation parameter range, it is evaluated as upper limb level II. If the movement of the affected shoulder is not completed within the preset time and the movement parameters are within the preset evaluation parameter range, it is evaluated as upper limb level II. If the motion parameters of the affected shoulder are not within the preset evaluation parameter range, it is evaluated as upper limb level I; if the instruction "Please raise your affected hand" is received, the affected hand is raised, and the action of raising the affected hand is completed within the preset time and the motion parameters of raising the affected hand are within the preset evaluation parameter range, it is evaluated as upper limb level III; if the action of raising the affected hand is not completed within the preset time and the motion parameters of raising the affected hand are not within the preset evaluation parameter range, it is evaluated as upper limb level II; if the instruction "Please raise your hands to the height of your shoulders" is received, the hands are raised to Shoulder height: if the action of raising both hands to shoulder height is completed within the preset time and the action parameters of raising both hands to shoulder height are within the preset evaluation parameter range, it is evaluated as upper limb level IV; if the action of raising both hands to shoulder height is not completed within the preset time and the action parameters of raising both hands to shoulder height are not within the preset evaluation parameter range, it is evaluated as upper limb level III; when receiving the instruction of "please raise your hands above your head", the action of raising both hands above your head is completed within the preset time and the action parameters of raising both hands above your head are within the preset evaluation parameter range. If the action is within the range of evaluation parameters, it is evaluated as upper limb level V; if the action of raising both hands over the head is not completed within the preset time and the action parameters of raising both hands over the head are not within the preset evaluation parameter range, it is evaluated as upper limb level IV; when the "finger-to-nose test" instruction is received, the finger-to-nose test is performed, and if the finger-to-nose action is completed within the preset time and the action parameters of the finger-to-nose are within the preset evaluation parameter range, it is evaluated as upper limb level VI; if the finger-to-nose action is not completed within the preset time and the action parameters of the finger-to-nose are not within the preset evaluation parameter range, it is evaluated as upper limb level V.

[0069] According to the stroke recovery stage assessment method of the embodiment of the present invention, the method sets different preset action assessment parameter values ​​for stroke patients of different age groups, takes into account the influence of age on physical function and recovery potential, and can more accurately measure the recovery level of the patient's upper limb, lower limb and / or hand motor function, making the assessment result more scientific, reasonable and humane, which is helpful to improve the effect and quality of rehabilitation treatment; not only the demographic information of stroke patients is obtained, but also the upper limb, lower limb and / or hand motor function recovery level is obtained. The motion video data of the patient's hand or hand motion data can be used to record the patient's motion conditions from multiple dimensions, providing a rich data basis for comprehensive evaluation; a corresponding action list is set for each type of motion video data, and the actions are arranged in sequence based on the action level, so that the evaluation process has clear steps and standards, which can clearly judge the patient's execution under different action difficulties, and help to accurately evaluate the patient's motor function recovery stage; after obtaining the motion video data, through data preprocessing operations such as decoding, normalization, filtering, etc., the image quality is improved and the recognition error caused by image differences and noise is reduced; the key point recognition algorithm is used to extract key points, and further preprocessing and precise position operations are performed, which can more accurately obtain the key information of the patient's movement, providing a reliable basis for the subsequent calculation of motion posture data; the motion posture data is calculated based on the position of the key points, including angle data and position data. The data can be transferred to quantify the patient's movement status, making the evaluation results more objective and comparable, which is convenient for doctors and rehabilitation personnel to intuitively understand the patient's motor function recovery degree; based on Brunnstrom's six-stage theory and demographic information, the preset movement posture data is determined, the movement posture data is compared with the preset movement posture data, and the matching score is calculated, which can scientifically determine the recovery stage of stroke patients, provide an objective basis for the adjustment of rehabilitation programs and efficacy evaluation, and help to formulate more targeted rehabilitation plans and improve rehabilitation effects; through specific action instructions, patients are asked to perform corresponding actions, and are rated according to the completion of the actions and whether the action parameters are within the preset range. This method intuitively reflects the patient's ability to perform actions of different difficulty levels, making the evaluation process more operational and visual, which is convenient for doctors and patients to understand the progress of rehabilitation and improves diagnostic efficiency.

[0070] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, disk, CD), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0071] According to one aspect of the embodiments of the present invention, a stroke recovery stage assessment system is also provided. Figure 4 is a schematic diagram of an evaluation system for stroke recovery stages according to an embodiment of the present invention; Figure 4 As shown, including:

[0072] An acquisition module 410 is used to acquire demographic information of a stroke patient and acquire motion video data of the stroke patient, wherein the motion video data includes upper limb motion data, lower limb motion data and / or hand motion data;

[0073] A calculation module 420, configured to extract key points from each type of the motion video data based on a key point recognition algorithm, and calculate corresponding motion posture data in each type of the motion video data based on the positions of the key points, wherein the motion posture data includes angle data and displacement data;

[0074] The module 430 is obtained, which is used to determine the preset movement posture data based on Brunnstrom's six-stage theory and the demographic information, compare the movement posture data with the preset movement posture data, and obtain the recovery stage of the stroke patient based on the comparison result.

[0075] According to the stroke recovery stage evaluation system of the embodiment of the present invention, demographic information of the stroke patient is obtained, and motion video data of the stroke patient is obtained, and the motion video data includes upper limb motion data, lower limb motion data and / or hand motion data; key points are extracted from each type of motion video data based on the key point recognition algorithm, and the corresponding motion posture data in each type of motion video data is calculated based on the position of the key points, and the motion posture data includes angle data and displacement data; based on Brunnstrom's six-stage theory and demographic information, the preset motion posture data is determined, the motion posture data is compared with the preset motion posture data, and the recovery stage of the stroke patient is obtained based on the comparison result. In this way, real-time monitoring and intelligent evaluation of the rehabilitation process of stroke patients are realized, the accuracy of the evaluation is improved, and the diagnostic efficiency is improved.

[0076] Optionally, the acquisition module 410 is specifically used to obtain an action list of the stroke patient, wherein each type of the motion video data corresponds to the action list, and the actions in the action list are arranged in sequence based on the action level, and the higher the action level, the more complex the action execution; execute each action in the action list to obtain the motion video data of the stroke patient.

[0077] Optionally, the acquisition module 410 is specifically used to determine the preset evaluation parameter value of the first action in the action list; obtain the action instruction of the first action; execute the first action based on the action instruction, and determine the action parameter value of the first action; when it is judged that the first action is completed within the preset time and the action parameter value is within the preset evaluation parameter value range, obtain the preset evaluation parameter value of the Nth action, and obtain the action instruction of the Nth action; execute the Nth action based on the action instruction of the Nth action, and determine the action parameter value of the Nth action; when it is judged that the Nth action is completed within the preset time and the action parameter value is within the preset evaluation parameter value, obtain the upper limb movement data, the lower limb movement data and / or the hand movement data of the stroke patient.

[0078] Optionally, the angle data includes an angle value, and the displacement data includes a displacement value, wherein the calculation module 420 is used to determine a calculation attribute based on a preset evaluation parameter; when the calculation attribute is a calculation angle, determine the joint position, and based on , calculate the angle value, where, , represents the inter-joint vector, , represents the modulus of the inter-joint vector, wherein the inter-joint vector is calculated based on the coordinate difference of the key point; in the case where the calculated attribute is the calculated displacement, the displacement time is determined based on , calculate the displacement value, where, , Represents the coordinates of key points.

[0079] Optionally, the system further comprises a preprocessing module for, based on G = [ X 1 ， X 2 ，...X n ] , obtain the original key point sequence, where n represents the nth data set; through median filtering, with k as the time window, obtain the median result of the original key point sequence after median filtering G ' = [ X 1 ' ， X 2 ' ，...X n ' ] ; Based on Kalman filtering, the median result G ' = [ X 1 ' ， X 2 ' ，...X n ' ] Each key point in is smoothed.

[0080] Optionally, a module 430 is obtained, which is specifically used to determine the numerical range corresponding to the preset motion posture data of each stage in the Brunnstrom six-stage theory; determine the target recovery stage corresponding to the numerical value of the motion posture data from the numerical range corresponding to the preset motion posture data of multiple stages, and use the target recovery stage as the recovery stage of the stroke patient.

[0081] Optionally, the system further comprises: a matching score module for , obtain the matching score between the motion posture data and the preset motion posture data in the target recovery phase, where N represents the total number of parameters, represents the weight of the parameter, It represents the difference between the motion posture data value and the preset motion posture data value, or the difference between the preset motion posture data value and the motion posture data value.

[0082] According to one aspect of an embodiment of the present invention, an electronic device is provided.

[0083] Figure 5 Schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Figure 5 As shown, the electronic device may include one or more ( Figure 5Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a microprocessor (Microprocessor Unit, referred to as MPU) or a programmable logic device (Programmable logic device, referred to as PLD)) and a memory 104 for storing data. In an exemplary embodiment, the electronic device may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 5 The structure shown is for illustration only and does not limit the structure of the above terminal device. Figure 5 More or fewer components as shown, or with Figure 5 Equivalent functions or comparisons shown Figure 5 A different configuration with more features is shown.

[0084] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for evaluating the stroke recovery stage in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0085] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the switching device. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0086] The present invention provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute a method for evaluating a stroke recovery stage.

[0087] The applicant of the present invention has made a detailed explanation and description of the implementation examples of the present invention in conjunction with the drawings in the specification. However, those skilled in the art should understand that the above implementation examples are only preferred implementation schemes of the present invention, and the detailed description is only to help readers better understand the spirit of the present invention, but not to limit the scope of protection of the present invention. On the contrary, any improvements or modifications based on the inventive spirit of the present invention should fall within the scope of protection of the present invention.

[0088] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0089] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the above embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. Any changes or replacements that can be easily thought of by those skilled in the art within the technical scope disclosed in the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for evaluating the recovery stage of stroke, characterized in that: include: S1, obtaining demographic information of a stroke patient, and obtaining motion video data of the stroke patient, wherein the motion video data includes upper limb motion data, lower limb motion data and / or hand motion data; S2, extracting key points from each type of the motion video data based on a key point recognition algorithm, and calculating corresponding motion posture data in each type of the motion video data based on the positions of the key points, wherein the motion posture data includes angle data and displacement data; S3, determining preset movement posture data based on Brunnstrom's six-stage theory and the demographic information, comparing the movement posture data with the preset movement posture data, and obtaining the recovery stage of the stroke patient based on the comparison result.

2. The method for evaluating the stroke recovery stage according to claim 1, characterized in that: Acquiring motion video data of the stroke patient, including: Acquire an action list of the stroke patient, wherein each type of the motion video data corresponds to the action list, and the actions in the action list are arranged in sequence based on action levels, and the higher the action level, the more complex the action execution; Execute each action in the action list to obtain motion video data of the stroke patient.

3. The method for evaluating the stroke recovery stage according to claim 2, characterized in that: Executing each action in the action list to obtain motion video data of the stroke patient includes: Determining a preset evaluation parameter value for a first action in the action list; Obtaining an action instruction for the first action; Execute the first action based on the action instruction, and determine an action parameter value of the first action; If it is determined that the first action is completed within a preset time and the action parameter value is within the preset evaluation parameter value range, obtaining the preset evaluation parameter value of the Nth action and obtaining the action instruction of the Nth action; Execute the Nth action based on the action instruction of the Nth action, and determine the action parameter value of the Nth action; When it is determined that the Nth action is completed within a preset time and the action parameter value is within the preset evaluation parameter value, the upper limb movement data, the lower limb movement data and / or the hand movement data of the stroke patient are obtained.

4. The method for evaluating the stroke recovery stage according to claim 3, characterized in that: The angle data includes an angle value, and the displacement data includes a displacement value, wherein the corresponding motion posture data in each type of the motion video data is calculated based on the position of the key point, including: Determining a calculation attribute based on preset evaluation parameters; In the case where the calculated attribute is a calculated angle, the joint position is determined, and based on , calculate the angle value, where, , represents the inter-joint vector, , represents a modulus of an inter-joint vector, wherein the inter-joint vector is calculated based on the coordinate difference of the key point; In the case where the calculated attribute is calculated displacement, the displacement time is determined based on , calculate the displacement value, where, , Represents the coordinates of key points.

5. The method for evaluating the stroke recovery stage according to claim 1, characterized in that: Also includes: Preprocessing the extracted key points includes: based on , obtain the original key point sequence, where n represents the nth data set; Through median filtering, with k as the time window, the median result of the original key point sequence after median filtering is obtained ; Based on Kalman filtering, the median result Each key point in is smoothed.

6. The method for evaluating the stroke recovery stage according to claim 1, characterized in that: Comparing the motion posture data with the preset motion posture data, and obtaining the recovery stage of the stroke patient based on the comparison result, includes: Determine the corresponding numerical range of the preset motion posture data in each stage of the Brunnstrom six-stage theory; The target recovery stage corresponding to the numerical value of the motion posture data is determined from the numerical value ranges corresponding to the preset motion posture data of multiple stages, and the target recovery stage is used as the recovery stage of the stroke patient.

7. The method for evaluating the stroke recovery stage according to claim 6, characterized in that: Also includes: according to , obtain the matching score between the motion posture data and the preset motion posture data in the target recovery phase, where N represents the total number of parameters, represents the weight of the parameter, It represents the difference between the motion posture data value and the preset motion posture data value, or the difference between the preset motion posture data value and the motion posture data value.

8. A stroke recovery stage assessment system, characterized in that: include: An acquisition module, used for acquiring demographic information of a stroke patient, and acquiring motion video data of the stroke patient, wherein the motion video data includes upper limb motion data, lower limb motion data and / or hand motion data; A calculation module, used for extracting key points from each type of the motion video data based on a key point recognition algorithm, and calculating corresponding motion posture data in each type of the motion video data based on the positions of the key points, wherein the motion posture data includes angle data and displacement data; The module is used to determine preset motion posture data based on Brunnstrom's six-stage theory and the demographic information, compare the motion posture data with the preset motion posture data, and obtain the recovery stage of the stroke patient based on the comparison result.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 7.

Images