CN107115102A - A kind of osteoarticular function appraisal procedure and device - Google Patents

Abstract

The invention discloses a bone joint space angle measurement and function evaluation method and device, including the following three stages: the first stage, using somatosensory interactive equipment to collect bone joint depth information, and calculate the bone joint space angle; the second stage, according to the first The first stage of the bone joint space angle measurement method is to use the K-means clustering algorithm to complete the classification of different bone and joint diseases; the third stage is the visual analysis and evaluation of bone and joint functions. The present invention gets rid of the shackles of traditional medical imaging technology, can obtain the coordinates of bone joint points in real time, measure the angle of bone joints, complete the update of the maximum flexion and extension angles of joints of characters in a natural activity state, and present bone joint functions to users in a visualized manner The digital analysis and health assessment can provide a more objective and effective basis for medical staff in diagnosis, establishment of treatment plan, comparison and evaluation of function before and after treatment, and rehabilitation guidance.

Description

A method and device for evaluating bone and joint function

technical field

The invention relates to the technical field of bone and joint function health assessment, in particular to a method and device for bone joint space angle measurement and function assessment.

Background technique

Osteoarthritis is a common and frequently-occurring disease in clinical practice, and its prevalence increases with age. In recent years, the diagnosis and functional evaluation of bone and joint diseases are mostly based on doctors' clinical examination and medical imaging technology. By analyzing the results of MRI, CT, and X-ray examinations, we can make a rough judgment and analysis of the disease based on experience, and formulate corresponding treatment. Generally speaking, it is based on the subjective judgment and evaluation of doctors, and lacks objective and accurate analysis of functional parameters of patients. In addition, existing medical imaging equipment has radiation and is relatively expensive, which is not suitable for long-term rehabilitation treatment effect evaluation and drug guidance.

In order to solve the above problems, people began to introduce gait analysis into the diagnosis and functional evaluation of bone and joint diseases, such as the evaluation of sports rehabilitation based on gait analysis, the application of gait analysis in falls of the elderly, etc. The diagnosis, treatment and prevention of arthrosis provide a good theoretical research basis. However, since human gait involves autonomous movement of multiple joints such as hip joints, knee joints, and ankle joints, changes in each joint will cause changes in the overall gait image, and the real-time acquisition and processing of gait images and the function of bone joints The real-time calculation of parameters has become a technical problem in the clinical diagnosis and evaluation of bone and joint diseases.

With the development of computer information technology, somatosensory interactive devices based on augmented reality have been rapidly developed and applied, such as the Kinect released by Microsoft in 2010, and the new 3D real-sensing cameras R200 and SR300 successively launched by Intel in 2016. These 3D real-sensing camera devices The biggest feature is that it can capture the depth position information of the object in the scene, and make accurate tracking and positioning of the spatial position change of the object. Among them, because Kinect has the tracking and positioning of the overall bone information of the human body, it has been gradually applied to medical application research, such as rehabilitation training systems based on Kinect, 3D reconstruction based on Kinect depth information, etc. However, due to the variety of bone and joint diseases, only relying on the depth position information obtained by somatosensory interactive equipment cannot make quantitative analysis of various bone and joint diseases, nor can it achieve clinical medical evaluation.

There are many parameters for human bone and joint health assessment, such as angle parameters, muscle pain, personal bone conditions, etc. Among them, angle parameters, as an important parameter for the assessment of human bone and joint health status, play a role in the process of realizing human bone and joint health assessment. key role. How to combine the calculation of human bone joint space angle with the actual clustering and analysis of angle feature data to obtain the manifestations and range of motion of different joint states has become a new difficulty in bone and joint health status assessment.

Contents of the invention

In view of this, the present invention provides a bone and joint function assessment method and device to solve the above problems.

A bone joint function evaluation method and device, the device includes a Kinect device and a supporting software system for bone joint space angle measurement and function evaluation, the method includes the following three stages:

The first stage: Use somatosensory interactive equipment to collect bone joint depth information, calculate the distance between joint points, use the three-point method, that is, calculate the distance between three bone joint points to calculate the bone joint space angle, specifically including:

1) Use somatosensory interactive equipment to collect bone joint depth information, determine the position of each joint, and calculate its depth image coordinates;

2) Calculate the space point coordinates of each joint point according to the conversion formula from depth image coordinates to space point coordinates;

3) Use the Euclidean distance to find the distance between two joint nodes;

4) Use the three-point method to calculate the bone joint space angle.

The second stage: According to the bone joint space angle measurement method of the first stage, the maximum joint flexion and extension angles of patients with different types of bone joint diseases are measured in the natural state, and with a sufficient number of samples, the K-means clustering algorithm is used Complete the classification of different bone and joint diseases, and use this as the standard of health assessment, including:

1) Measure and collect the growth of normal bones and joints to obtain the data range of healthy functions;

2) Collect and organize the data of joints with bone and joint diseases, and use the K-means clustering algorithm to classify the data of the disease.

The third stage: digitize and accurately display the space angle of the bone joint, dynamically update the maximum flexion and extension angle of the bone joint, and realize the visual analysis and functional evaluation of the bone joint function, including:

1) Visually display the angle information and maximum flexion angle of each bone joint in real time;

2) Through the comparison of the angle information captured by the system and the data results of cluster analysis, the health status assessment of human bone and joint functions is completed.

There are many parameters for human bone and joint health assessment, such as angle characteristics under different exercise states, muscle pain, personal congenital bone conditions, etc. Angle parameters are an important parameter for the assessment of human bone and joint health. Played a key role in the health assessment process. Compared with the existing devices and technologies, this patent takes the maximum flexion and extension angle of bone joints as the main parameter of clustering, and can complete the classification of bone joint angle characteristics in different states through the observation and analysis of the range of motion of human body joint flexion and extension .

Furthermore, in the technical solution of the present invention, by performing cluster analysis on a large amount of measured data, different categories can be obtained, and healthy joint angle standards can be analyzed. Using cluster analysis, the clustering of joint data with different angle characteristics can be completed. The system results are real, effective and highly accurate. Through the analysis of the clustering results, angle detection of different angle characteristics can be realized, and the buckling deficiency, Insufficient stretching, or data that the system measures incorrectly, should be included in a separate category. The difference in results caused by posture problems is more obvious and is not included in the scope of clustering.

Furthermore, the entire device of this patent has a good human-computer interaction interface, and the measurement results can be directly displayed on the operation interface. The user can complete the angle measurement and function evaluation of different joints of the human body through simple operations; this device can not only digitally display the patient's natural The joint angle parameters in the environment can also be used for dynamic monitoring of bone and joint activities of patients, monitoring the detailed growth of bone and joints and recording and displaying related parameters, and at the same time classifying and evaluating bone and joint diseases, which can be used as a reference for doctors to analyze and treat. It can provide patients with the best treatment plan, and can also conduct preliminary evaluation and follow-up monitoring of the postoperative correction effect of bone and joint patients, in order to provide clinical reference and improve the level of diagnosis and treatment of orthopedic diseases.

In order to make the above-mentioned objects, features and advantages of the present invention more comprehensible, preferred embodiments will be described in detail below together with the accompanying drawings.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and thus It should be regarded as a limitation on the scope, and those skilled in the art can also obtain other related drawings based on these drawings without creative work.

Fig. 1 is a schematic flowchart of a method for assessing bone and joint function according to an embodiment of the present invention.

Fig. 2 is a schematic flow diagram of a classification evaluation algorithm according to an embodiment of the present invention.

Fig. 3 is a schematic diagram of the software interface of bone and joint function assessment according to an embodiment of the present invention.

detailed description

In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. Accordingly, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

As shown in FIG. 1 , a bone joint function evaluation method and device according to an embodiment of the present invention includes the following steps.

Step S110, bone joint depth data collection.

As an implementation, the measurement and calculation of the space angle of human bone joints must complete the data collection of bone joints in advance. Use the somatosensory interactive device Kinect to complete the detection and tracking of the human body. Through the configuration of the interactive environment and the writing of the driver program, the collection of bone and joint data can be effectively completed. The specific process includes the binding of character control and bone points, the generation of the skeleton system and real-time monitor. Through the control and real-time monitoring of the movement of the characters, the coordinates of each joint point of the lower limbs of the human body are obtained to complete the data collection.

Step S120, calculation of bone joint space angle.

As an implementation manner, the calculation of the bone joint space angle is to calculate the Euclidean distance between joint points according to the space point coordinates, and then calculate the bone joint space angle according to the three-point method. The specific calculation method is as follows.

Assuming that the space coordinates of the two joint points are (x ₁ , y ₁ , z ₁ ), (x ₂ , y ₂ , z ₂ ), the formula for calculating the Euclidean distance between the two joint points is as follows.

Solving the angle between the joint points of the human body mainly uses the three-point method, that is, calculates the Euclidean distance between two nodes through the obtained spatial coordinates of the three joint points, and then calculates the distance between the joint points according to the law of cosines. For example, assuming that three space points A, B, and C represent the coordinates of the left hip joint (x ₁ , y ₁ , z ₁ ), knee joint coordinates (x ₂ , y ₂ , z ₂ ), ankle joint coordinates (x ₃ , y ₃ , z ₃ ), then the space vector from the hip joint to the knee joint , the space vector from the knee joint to the ankle joint , the spatial angle between the thigh and the calf, that is, the calculation formula of the knee joint angle is as follows.

Step S130, a large number of sample collection and cluster analysis.

After implementing Kinect’s bone joint space angle measurement method, a large number of samples can be collected, including normal bone joint data collection and diseased bone joint data collection, and then through cluster analysis, the classification of different bone joint diseases can be completed, and this can be used as taxonomy.

As an implementation, the system uses the K-means clustering algorithm to complete the data classification. First, it analyzes the normal bone and joint data to obtain the standard data range, and then uses the normal data range as the standard for analysis and comparison. The joint angle data of the joint condition is collected and sorted, and the K-means clustering algorithm is used to perform specific clustering analysis on the joint data of different conditions, and the data range and cluster center point of each joint condition are obtained, and their error sum of squares is calculated , for the system to perform effective health assessment and early disease diagnosis on the detected human bone and joint data. For the specific clustering analysis algorithm, please refer to the subsequent description in Figure 2.

Step S140, bone and joint function test evaluation.

As an implementation manner, the analysis and evaluation of bone and joint function of subsequent samples can be based on the classification criteria obtained in step S130 to determine which category the current sample belongs to, and perform sample evaluation and testing.

Step S150, visual display and evaluation analysis.

As an implementation mode, the visual display of this embodiment is based on the Unity3D development platform, and the visual operation and test evaluation of the interface are realized by using the C# programming language. Through Kinect bone tracking and real-time display of measured angles, the maximum flexion and extension angles of the bone joints are dynamically updated, and the bone joint function analysis is completed according to the test and evaluation results obtained in step S140.

As shown in FIG. 2 , a flow diagram of an evaluation algorithm for bone and joint function classification according to an embodiment of the present invention includes the following steps.

Step S210, initialize the sample data, and determine the number n of clusters.

As an implementation mode, in this embodiment, a large number of samples need to be collected first, and the samples are classified and analyzed. Assuming that a large sample of k case data is obtained, 12 data of hip joints, knee joints, ankle joints, and left and right feet are divided into 6 cases, and 6 clusters are performed, and the number of clusters is n (n>1).

Step S220, initializing the center coordinates of n clusters.

In a certain clustering, the coordinate meaning of the current point is given, assuming that the current point object x represents the flexion angle of the left hip joint, y represents the extension angle of the left hip joint, and initializes the center coordinate point1[n] of n clusters.

Step S230, calculating the sum of the squares of the distances between the k sets of data and the central point.

Clustering is performed according to the current clustering center coordinate point1[n], that is, the clusters that are close to the cluster center are grouped into one class, and the sum of squared distances between k groups of data and the center point point1[n] at this time is calculated, sum1, and a new one is found The center coordinate point2[n] of the class.

Step S240, calculating the sum of the squares of the distances between the k sets of data and the new central point.

Calculate the sum sum2 of the squares of the distances between k groups of data and the new center point point2[n] at this time.

Step S250, judging whether the value of sum1 is equal to the value of sum2.

If they are equal, go to step S260; if they are not equal, return to step S230.

In step S260, the current cluster is optimal, and the center coordinates of the current n clusters are saved.

The current clustering is already optimal. In the obtained clusters, the same class will have similar characteristic cases, and the center coordinate point[n] of the current n clusters will be saved.

As shown in FIG. 3 , a schematic diagram of an interface of bone and joint function assessment software according to an embodiment of the present invention includes the following parts.

On the left is the control button for the software, in the middle is the test data of bone joints and gait, and the two images on the right are the depth information of the image captured by the upper camera and the color of the image captured by the lower camera information. When the software is running, when the tester stands in front of the camera and can see [0002] the complete body image on the right, he can click to start the evaluation system, and then the software will start to measure the angle of the bone joint. When measuring the bone joint space angle, it is in the order of a hip joint, knee joint, and ankle joint, and in the order of the left foot first and then the right foot. The tester needs to measure in the correct order, and the data of untested joints will be It will indicate that it has not been tested, and the data being tested will show that the test is in progress. When the current test is completed, you need to manually click the next test. If the tester makes a mistake in the measurement and the data is wrong, you can click the retest button. When all joint tests are completed, you can click the health assessment and analysis button to perform a simple joint health assessment and analysis. If you want to measure gait, you need to click to measure gait first within the visible range of the camera, and then follow the predetermined walking posture, such as normal walking, climbing stairs, passing obstacles, etc. When the tester walks, double When the feet are close together, it means that the data entry of gait is stopped, and the software stops data entry. At this time, you can click on the gait data to display the gait conditions in the current test, such as gait cycle, single-foot support period, double-foot support period, etc., which is convenient Perform a gait analysis.

Compared with the prior art, the bone joint function evaluation method and device provided by the embodiment of the present invention are based on the application of the latest augmented reality somatosensory interaction equipment, and the function evaluation system with digitalization of bone joint space angle is a new The clinical application of technology; through the cluster analysis of a large number of samples, a scientific and objective standard is formed, which is an innovative standard. People can use this technology for early diagnosis, early treatment and prevention of bone and joint diseases, reducing the possibility of bone and joint surgery caused by the deterioration of the disease; at the same time, it can also track and collect the recovery information of patients after bone and joint deformity correction surgery, and investigate the patient's health. condition and improve diagnosis and treatment.

In the several embodiments provided in this application, it should be understood that the disclosed method may also be implemented in other ways. The device embodiments described above are only illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functions and possible implementations of devices, methods and computer program products according to multiple embodiments of the present invention. operate. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or part of code that includes one or more Executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified function or action , or may be implemented by a combination of dedicated hardware and computer instructions.

The above is only a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Anyone skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present invention. Should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be determined by the protection scope of the claims.

Claims (2)

1. a kind of osteoarticular function appraisal procedure, it is characterised in that this method includes the following three stage：

First stage, Bones and joints depth information is gathered using body feeling interaction equipment, calculate the space length between artis, utilized Line-of-sight course, that is, the distance between wherein three Bones and joints points obtained calculate Bones and joints space angle；

Second stage, according to the Bones and joints spatial angle measuring method of first stage, in its natural state respectively to variety classes Bone and joint diseases patient carry out joint maximum bend and stretch angular surveying, under enough sample sizes, calculated by using K mean cluster Method is completed to the classification with different bone and joint diseases, and in this, as the standard of health evaluating；

Phase III, the accurate display Bones and joints space angle of digitlization, the maximum that dynamic updates Bones and joints bends and stretches angle, realizes bone Function of joint visual analyzing and functional assessment.

2. a kind of osteoarticular function apparatus for evaluating, it is characterized in that, including Kinect device and supporting software systems, wherein soft Part system performs the osteoarticular function appraisal procedure described in the claims 1.