Measurement system and method for personalized articular skeleton and cartilage morphology

Abstract

To provide doctors with dynamic and more accurate medical examination information for determining personalized treatment methods and inspecting treatment effects.SOLUTION: A measurement system for personalized articular skeleton and cartilage morphology includes: an image capture module to capture the plurality of skeletal images of a subject; an image analysis module to generate 3D models of the skeleton and cartilage from skeletal images using a statistical shape model and principal component analysis; a neural network model to generate skeletal motion parameters on the basis of the input skeletal and cartilage shape parameters; a model building module to generate a personalized articular skeleton and cartilage model on the basis of 3D models of the skeleton and cartilage and the skeletal motion parameters; and a calculation module to simulate relative positions between the 3D models of the skeleton and cartilage during exercise on the basis of the personalized articular skeleton and cartilage models and to calculate the actual cartilage shape and the cartilage wear value of the subject by eliminating overlapping cartilage regions in the 3D models of the skeleton and cartilage during the exercise.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an articular skeleton and cartilage measurement system and method, and particularly to a personalized articular skeleton and cartilage morphology measurement system and method using conventional artificial intelligence techniques.

Background Art

[0002] Cartilage is a type of connective tissue that plays a very important role in the joints of the human body. It contributes to reducing the impact and friction during joint movement, ensuring the smooth operation of the joints. However, with aging, excessive use of joints, or trauma, cartilage is easily damaged, which may lead to the occurrence of osteoarthritis (OA). Osteoarthritis, also known as degenerative arthritis, is an arthritis caused by damage to articular cartilage or subchondral bone. The sites where it is likely to occur are the distal interphalangeal joints, the base of the thumb, the neck, the waist, the knees, and the hips. Among them, knee osteoarthritis (Knee OA) is the most common. In such diseases, joint inflammation and damage cause skeletal deformities, tendon and ligament degeneration, and cartilage wear, resulting in joint pain, swelling, deformity, damage to joint function, and a decline in quality of life. Therefore, for accurate treatment, early diagnosis and examination of treatment effects are extremely important, and the detection of cartilage changes is an extremely important factor.

[0003] The detection of cartilage changes has hitherto usually relied on conventional clinical evaluations and imaging diagnostic methods such as X-rays and MRI. Currently, the most commonly used grading system for osteoarthritis is the Kellgren-Lawrence Grading System. In this system, based on X-ray images of the standing knee joint, the degree of reduction of the joint space (representing the degree of cartilage wear) and the degree of osteophyte formation are used to divide osteoarthritis of the knee joint into five stages. However, there are several limitations to the methods using X-rays and MRI examinations. For example, with the X-ray method, actual cartilage information cannot be obtained, and only the severity of osteoarthritis of the knee joint can be estimated from the joint space, so there may be differences in evaluation by doctors. Also, with the MRI method, due to limitations in image quality, the positions of damaged cartilage and normal cartilage cannot be accurately identified. Moreover, all of these methods can only obtain information at rest. In addition, both require high costs and dedicated equipment and are affected by the skills of the operator.

[0004] Therefore, it is necessary to research and develop a new joint skeleton and cartilage measurement system and method to solve the above-mentioned conventional problems.

Summary of the Invention

Problems to be Solved by the Invention

[0005] In view of the above, the present invention provides a personalized joint skeleton and cartilage morphology measurement system to solve the above-mentioned conventional problems.

Means for Solving the Problems

[0006] The present invention provides a personalized joint skeleton and cartilage morphology measurement system for constructing a personalized joint skeleton and cartilage model of a subject and calculating a cartilage wear value of the subject based on the personalized joint skeleton and cartilage model. The personalized joint skeleton and cartilage morphology measurement system includes a database, an image acquisition module, an image analysis module, a neural network model, a model construction module, and a calculation module. The database is used to store a dataset. The dataset includes a plurality of joint skeleton and cartilage images of a plurality of healthy subjects, a skeleton and cartilage 3D model corresponding to the joint skeleton and cartilage images, and a plurality of shape parameters. The image acquisition module is used to acquire a plurality of skeleton images of the subject. Each of the skeleton images includes a first skeleton image and a second skeleton image. The image analysis module is connected to the image acquisition module and the database, and obtains the skeleton and cartilage 3D model for the skeleton image of the subject from a statistical shape model learned using the dataset. Also, based on the skeleton and cartilage 3D model and the shape parameters, a plurality of first skeleton and cartilage shape parameters corresponding to the first skeleton image and a plurality of second skeleton and cartilage shape parameters corresponding to the second skeleton image are obtained by principal components analysis (PCA). And, based on the first skeleton and cartilage shape parameters and the second skeleton and cartilage shape parameters, a first skeleton and cartilage 3D model and a second skeleton and cartilage 3D model are generated. The neural network model is connected to the image analysis module, and when the first skeleton and cartilage shape parameters and the second skeleton and cartilage shape parameters are input, generates and outputs a plurality of first skeleton motion parameters and a plurality of second skeleton motion parameters corresponding to the first skeleton and cartilage shape parameters and the second skeleton and cartilage shape parameters. The neural network model is obtained by training using a machine learning method based on the dataset.The model construction module is connected to the image analysis module and the neural network model, and generates the personalized joint skeleton and cartilage model based on the first skeleton and cartilage 3D model, the second skeleton and cartilage 3D model, the first skeleton motion parameters, and the second skeleton motion parameters. The calculation module is connected to the model construction module, and based on the personalized joint skeleton and cartilage model, simulates the relative positions of the first skeleton and cartilage 3D model and the second skeleton and cartilage 3D model during the movement of the subject. Then, by deleting the regions where the cartilage of the first skeleton and cartilage 3D model and the second skeleton and cartilage 3D model interfere with each other during movement, the actual cartilage shape and the cartilage wear value of the subject are calculated.

[0007] The personalized joint skeleton and cartilage morphology measurement system further includes an image registration module connected to the image analysis module and the database, which adjusts the angles and positions of the first skeleton and cartilage 3D model and the second skeleton and cartilage 3D model for projection, and collates with the joint skeleton and cartilage images of the healthy subjects in the dataset by the single-plane dynamic image registration method to calculate the first skeleton motion parameters and the second skeleton motion parameters of the subject.

[0008] Each of the skeleton images of the subject further includes an X-ray image.

[0009] The first skeleton motion parameters and the second skeleton motion parameters further include translation parameters and rotation parameters in three directions of the XYZ axes.

[0010] The personalized joint skeleton and cartilage model is further visualized and displayed by color-matched images and perspective methods.

[0011] Another aspect of the present invention provides a method for measuring personalized joint skeleton and cartilage morphology. The method includes the following steps.

[0012] Store the dataset in a database. The dataset includes a plurality of joint skeleton-cartilage images of a plurality of healthy individuals, a skeleton-cartilage 3D model corresponding to the joint skeleton-cartilage images, and a plurality of shape parameters.

[0013] Use an image acquisition module to acquire a plurality of skeleton images of the subject. Each of the skeleton images includes a first skeleton image and a second skeleton image.

[0014] Using the image analysis module, obtain the skeleton-cartilage 3D model for the skeleton image of the subject from a statistical shape model (Statistical Shape Model) learned using the dataset. Also, based on the skeleton-cartilage 3D model and the shape parameters, obtain a plurality of first skeleton-cartilage shape parameters corresponding to the first skeleton image and a plurality of second skeleton-cartilage shape parameters corresponding to the second skeleton image by principal component analysis (Principal components analysis, PCA). And generate a first skeleton-cartilage 3D model and a second skeleton-cartilage 3D model based on the first skeleton-cartilage shape parameters and the second skeleton-cartilage shape parameters.

[0015] By inputting the first skeleton-cartilage shape parameters and the second skeleton-cartilage shape parameters into a neural network model, generate and output a plurality of first skeleton motion parameters and a plurality of second skeleton motion parameters corresponding to the first skeleton-cartilage shape parameters and the second skeleton-cartilage shape parameters. The neural network model is obtained by training using a machine learning method based on the dataset.

[0016] Use a model construction module to generate the personalized joint skeleton-cartilage model based on the first skeleton-cartilage 3D model and the second skeleton-cartilage 3D model, and the first skeleton motion parameters and the second skeleton motion parameters.

[0017] The calculation module simulates the relative positions of the first skeletal cartilage 3D model and the second skeletal cartilage 3D model during the movement of the subject based on the personalized joint skeletal cartilage model, and deletes the regions where the cartilages of the first skeletal cartilage 3D model and the second skeletal cartilage 3D model interfere with each other during movement, thereby calculating the actual cartilage shape and the cartilage wear value of the subject.

[0018] The personalized joint skeletal cartilage morphology measurement method further includes the following steps.

[0019] The image registration module adjusts the angles and positions of the first skeletal cartilage 3D model and the second skeletal cartilage 3D model and projects them, and collates them with the joint skeletal cartilage images of the healthy subjects in the dataset by the single-plane dynamic image registration method, thereby calculating the first skeletal movement parameters and the second skeletal movement parameters of the subject.

[0020] Each of the skeletal images of the subject further includes an X-ray image.

[0021] The first skeletal movement parameters and the second skeletal movement parameters further include translation parameters and rotation parameters in the three directions of the XYZ axes.

[0022] The personalized joint skeletal cartilage model is further visualized and displayed by a color-corresponding image and a perspective method.

Advantages of the Invention

[0023] In summary, the present invention provides a personalized joint skeleton and cartilage morphology measurement system that reconstructs the skeleton and cartilage models of a patient's knee joint by combining dynamic X-ray technology and artificial intelligence to reconstruct the morphology of joint bones and cartilage, and accurately calculates the degree and location of cartilage changes. In addition, the personalized joint skeleton and cartilage model in the present invention can be visualized and displayed by color-matched images and fluoroscopy, enabling a visual understanding of the cartilage state and allowing for a more rapid and comprehensive evaluation of cartilage health. Further, the artificial intelligence-based joint skeleton and cartilage three-dimensional morphology planar X-ray measurement system in the present invention can provide dynamic and more accurate diagnostic information to doctors for determining personalized treatment methods for each patient and examining treatment effects.

Brief Description of the Drawings

[0024]

Figure 1

Figure 2

Figure 3

Figure 4

Modes for Carrying Out the Invention

[0025] Subsequently, in order to make the advantages, spirit, and features of the present invention more easily and clearly understandable, a detailed description and examination will be made with reference to the drawings using specific embodiments. It should be noted that these specific embodiments are merely representative specific embodiments of the present invention, and the specific methods, apparatuses, conditions, materials, etc. exemplified do not limit the present invention or the corresponding specific embodiments. Moreover, each component in the drawings is used only to represent their relative positions and is not described based on actual ratios. Also, the step numbers of the present invention are only for distinguishing different steps and do not represent the order of the steps. The above is explained in advance.

[0026] Refer to FIG. 1. FIG. 1 shows a functional block diagram of a personalized joint skeleton and cartilage morphology measurement system 1 based on a specific embodiment of the present invention. As shown in FIG. 1, the personalized joint skeleton and cartilage morphology measurement system 1 in this specific embodiment includes a database 11, an image acquisition module 12, an image analysis module 13, a neural network model 14, a model construction module 15, and a calculation module 16. The database 11 is used to store a dataset. The dataset includes a plurality of joint skeleton and cartilage images of a plurality of healthy individuals, a skeleton and cartilage 3D model corresponding to the joint skeleton and cartilage images, and a plurality of shape parameters. The image acquisition module 12 is used to acquire a plurality of skeleton images of a subject. Each skeleton image includes a first skeleton image and a second skeleton image. The image analysis module 13 is connected to the image acquisition module 12 and the database 11, and obtains a skeleton and cartilage 3D model for the subject's skeleton image from a statistical shape model learned using the dataset. Also, based on the skeleton and cartilage 3D model and the shape parameters, a plurality of first skeleton and cartilage shape parameters corresponding to the first skeleton image and a plurality of second skeleton and cartilage shape parameters corresponding to the second skeleton image are obtained by principal components analysis (PCA). And based on the first skeleton and cartilage shape parameters and the second skeleton and cartilage shape parameters, a first skeleton and cartilage 3D model and a second skeleton and cartilage 3D model are generated. The neural network model 14 is connected to the image analysis module 13, and when the first skeleton and cartilage shape parameters and the second skeleton and cartilage shape parameters are input, a plurality of first skeleton movement parameters and a plurality of second skeleton movement parameters corresponding to the first skeleton and cartilage shape parameters and the second skeleton and cartilage shape parameters are generated and output. Note that the neural network model 14 is obtained by training using a machine learning method based on the dataset.The model construction module 15 is connected to the image analysis module 13 and the neural network model 14, and is used to generate a personalized joint skeletal cartilage model based on the first skeletal cartilage 3D model, the second skeletal cartilage 3D model, the first skeletal motion parameters, and the second skeletal motion parameters. The calculation module 16 is connected to the model construction module 15, and simulates the relative positions of the first skeletal cartilage 3D model and the second skeletal cartilage 3D model during the movement of the subject based on the personalized joint skeletal cartilage model. Then, by deleting the areas where the cartilage of the first skeletal cartilage 3D model and the second skeletal cartilage 3D model interfere with each other during movement, the actual cartilage shape and cartilage wear value of the subject are calculated. In this specific embodiment, each skeletal image of the subject further includes an X-ray image. In addition, the first skeletal motion parameters and the second skeletal motion parameters further include translation parameters and rotation parameters in the three directions of the XYZ axes.

[0027] Please refer to FIGS. 1 and 2 together. FIG. 2 shows a flowchart of the steps of a personalized joint skeletal cartilage morphology measurement method based on a specific embodiment of the present invention. The steps of the personalized joint skeletal cartilage morphology measurement method in FIG. 2 can be achieved by the personalized joint skeletal cartilage morphology measurement system 1 in FIG. 1. As shown in FIG. 2, in this specific embodiment, the personalized joint skeletal cartilage morphology measurement method includes the following steps.

[0028] Step S1: Store the dataset in the database 11. The dataset includes a plurality of joint skeletal cartilage images of a plurality of healthy subjects, the skeletal cartilage 3D models corresponding to the joint skeletal cartilage images, and a plurality of shape parameters.

[0029] Step S2: Use the image acquisition module 12 to acquire a plurality of skeletal images of the subject. Each skeletal image includes a first skeletal image and a second skeletal image.

[0030] Step S3: Using the dataset, the image analysis module 13 obtains a skeletal-cartilage 3D model for the subject's skeletal image from a Statistical Shape Model trained by the dataset. Further, by Principal components analysis (PCA), based on the skeletal-cartilage 3D model and shape parameters, a plurality of first skeletal-cartilage shape parameters corresponding to the first skeletal image and a plurality of second skeletal-cartilage shape parameters corresponding to the second skeletal image are obtained. And based on the first skeletal-cartilage shape parameters and the second skeletal-cartilage shape parameters, a first skeletal-cartilage 3D model and a second skeletal-cartilage 3D model are generated.

[0031] Step S4: By inputting the first skeletal-cartilage shape parameters and the second skeletal-cartilage shape parameters into the neural network model 14, a plurality of first skeletal motion parameters and a plurality of second skeletal motion parameters corresponding to the first skeletal-cartilage shape parameters and the second skeletal-cartilage shape parameters are generated and output. Note that the neural network model 14 is obtained by training with a machine learning method based on the dataset.

[0032] Step S5: Using the model construction module 15, a personalized joint skeletal-cartilage model is generated based on the first skeletal-cartilage 3D model and the second skeletal-cartilage 3D model, and the first skeletal motion parameters and the second skeletal motion parameters.

[0033] Step S6: The calculation module 16 simulates the relative positions of the first skeletal-cartilage 3D model and the second skeletal-cartilage 3D model during the subject's movement based on the personalized joint skeletal-cartilage model. And by deleting the regions where the cartilages of the first skeletal-cartilage 3D model and the second skeletal-cartilage 3D model interfere with each other during movement, the actual cartilage shape and cartilage wear value of the subject are calculated.

[0034] In addition, the personalized joint skeleton and cartilage model can be generated by combining a statistical shape model with principal component analysis and adjusting the shape parameters of the model based on the characteristics of the joint. In practical applications, the personalized joint skeleton and cartilage morphology measurement system of this specific embodiment can be used for reconstructing a personalized knee joint model. In practice, after constructing a database of knee joint sample models, the average model and the variation of the constructed shape can be further calculated using the model samples in this database as training models. Then, by applying the shape variation to principal component analysis (PCA), eigenvalues (eigenvalue λi) and eigenvectors (eigenvector φi) can be obtained. The new knee joint model is represented by adding the model variation to the average model.

[0035]

Number

[0036] b i is the shape model parameter belonging to the said model.

[0037] In practical applications, furthermore, an artificial intelligence-based method can be used to construct a 3D skeletal model of the joint, and by combining dynamic X-rays and calculating kinematics, the skeletal distance distribution between the femur and the tibia at each time point during the passive flexion and extension movements of the joint can be obtained. Then, by comparing these skeletal distance distributions with the thickness of the cartilage 3D model constructed in advance by artificial intelligence and calculating the penetration area, penetration degree, and penetration volume, the wear condition of the cartilage and the distribution of its severity can be evaluated. In practice, the personalized joint skeleton and cartilage model can be further visualized and displayed by means of color-coded images and perspective methods. According to this method, it is helpful to more comprehensively evaluate the health of joint cartilage, and it is also possible to use the detection of cartilage changes as a new method for examining treatment effects.

[0038] In addition, in practice, the database plays an important role in machine learning. The database provides basic data for the training, evaluation, and improvement of machine learning models. As a result, the machine learning model can learn using the data in the database and adjust its parameters, thereby improving the performance and accuracy of the machine learning model. The data stored in the database in this specific embodiment may include multiple skeletal images for multiple joints, multiple skeletal 3D models corresponding to the skeletal images, multiple position parameters of the joints, and multiple cartilage 3D models.

[0039] In actual applications, the method for constructing a personalized joint skeleton-cartilage model mainly uses dynamic X-ray images on different planes and utilizes artificial intelligence techniques and machine learning to adjust the shape parameters of the model. Then, by comparing the similarity between the skeletal part of the reconstructed joint 3D model and the dynamic X-ray image using image registration technology, the optimal shape parameters of the model are found to reconstruct the personalized joint 3D model. The image registration method is mainly a process of geometrically transforming two or more images to align or match them in space. It is also possible to find the proper accurate position of the object in the actual space by comparing and collating the object in the three-dimensional space with the two-dimensional image. In addition, it is possible to correspond or overlap specific features or regions between images through operations such as translation, rotation, and scaling of the images. In this specific embodiment, the personalized joint skeleton-cartilage model may further include the distal end of the femur, the proximal end of the tibia, and cartilage. Moreover, by using the image registration method, the relative positions of the distal end of the femur, the proximal end of the tibia, and cartilage are further found to obtain an accurate knee joint model.

[0040] Refer to FIG. 3. FIG. 3 shows a functional block diagram of a personalized joint skeleton and cartilage morphology measurement system 2 based on another specific embodiment of the present invention. As shown in FIG. 3, this specific embodiment is different from the above-described specific embodiment in the following points. That is, in this specific embodiment, further, an image registration module 21 is included. In this specific embodiment, the image registration module 21 is connected to the image analysis module 13 and the model construction module 15, and adjusts and projects the angles and positions of the first skeleton-cartilage 3D model and the second skeleton-cartilage 3D model. Then, by using the single-plane dynamic image registration method and comparing with the joint skeleton-cartilage images of healthy subjects in the dataset, the first skeleton motion parameters and the second skeleton motion parameters of the subject are calculated.

[0041] Refer to FIGS. 3 and 4 together. FIG. 4 shows a flowchart of the procedure of a personalized joint skeleton and cartilage morphology measurement method based on another specific embodiment of the present invention. The steps of the personalized joint skeleton and cartilage morphology measurement method in FIG. 4 can be achieved by the personalized joint skeleton and cartilage morphology measurement system 2 in FIG. 3. This specific embodiment is different from the above-described specific embodiment in the following points. That is, this specific embodiment further includes the following steps.

[0042] Execute the following after step S3.

[0043] Step S41: The image registration module 21 adjusts and projects the angles and positions of the first skeleton-cartilage 3D model and the second skeleton-cartilage 3D model. Then, by using the single-plane dynamic image registration method and comparing with the joint skeleton-cartilage images of healthy subjects in the dataset, the first skeleton motion parameters and the second skeleton motion parameters of the subject are calculated.

[0044] In actual applications, the database may further include a database of knee joint sample models. It is also possible to store personalized knee joint models of healthy individuals and patients constructed by CT scans and use them as a source of digital data for machine learning. The personalized knee joint model may further include the distal femur, proximal tibia, and cartilage. First, perform a CT scan within an appropriate joint scan range (i.e., ensure that the knee joint is at the center of the image). Then, import the CT images of the skeleton obtained by the image acquisition module into visualization software for image selection and stack them as a three-dimensional skeletal 3D model by the three-dimensional modeling module. The three-dimensional skeletal 3D model is subjected to image registration by the image registration module to calculate the three-dimensional kinematic information of the knee joint including translation and rotation in three directions (X, Y, Z axes). In practice, the image registration module may include a single-plane image matching technique of the graphical user interface (GUI) developed by Matlab. Through this interface, the user can move the position of the bone in space and visually perform initial registration of the bone and the dynamic X-ray image. Then, using this position as the initial position, determine the initial guess of the six degrees of freedom in the three-dimensional skeletal 3D model. By combining the dynamic X-ray projection parameters and distortion correction parameters corrected and obtained by the system, it is possible to generate a digitally reconstructed radiograph (DRR) of the volume model. Next, continuously adjust the six degrees of freedom position of the model in space to generate a new DRR image (I DRR ) and calculate the similarity with the dynamic X-ray image (I fl ) to find the optimal position of the bone in space by an optimization method. The optimization method may be a genetic algorithm based on vectorization. For similarity measurement, based on the Gradient Difference (GD), I DRR and I flApply horizontal and vertical Sobel Operators to obtain four gradient images dI DRR / di, dI DRR / dj, dI fl / di, dI fl / dj, and subtract the DRR gradient images and dynamic X-ray gradient images in two directions to obtain vertical and horizontal gradient difference images I diffV and I diffH can be obtained. And the measurement performed by the gradient difference method is represented by the following equation.

[0045]

Equation

[0046] In actual applications, the data and acquisition methods in the database are not limited to the above, and may be selected according to the user's requirements. It should be noted that other modules and functions in the personalized joint skeleton and cartilage morphology measurement system 2 in this specific embodiment are almost the same as the corresponding modules in the above-described specific embodiments, so they will not be described in detail here again. In this specific embodiment, a training model is constructed based on joint images obtained by CT scan and digital data. Then, by combining dynamic X-ray technology and artificial intelligence, the knee joint skeleton and cartilage model of the patient are reconstructed by machine learning method to obtain a more accurate degree and position of cartilage change. In addition, according to this specific embodiment, the problem that the actual cartilage information cannot be directly obtained by the conventional X-ray method and MRI method, and the exact position of the cartilage cannot be accurately obtained can be solved. In addition, according to this specific embodiment, dynamic joint information can be obtained, and dedicated equipment is not required, and it is not affected by the skills of the operator, so the time and human costs are reduced.

[0047] In summary, the present invention provides a personalized joint skeleton and cartilage morphology measurement system that reconstructs the skeleton and cartilage models of a patient's knee joint by combining dynamic X-ray technology and artificial intelligence to reconstruct the morphology of joint bones and cartilage, and accurately calculates the degree and location of cartilage changes. In addition, the personalized joint skeleton and cartilage model in the present invention can be visualized and displayed by color-matched images and fluoroscopy, enabling a visual understanding of the cartilage state and allowing for a more rapid and comprehensive evaluation of cartilage health. Further, the artificial intelligence-based joint skeleton and cartilage three-dimensional morphology planar X-ray measurement system in the present invention can provide dynamic and more accurate diagnostic information to doctors for determining personalized treatment methods for each patient and examining treatment effects.

[0048] The detailed description of the above preferred specific embodiments is intended to more clearly describe the features and spirit of the present invention, and is not intended to limit the scope of the present invention by the preferred specific embodiments disclosed above. Rather, it is intended that various modifications and equivalent configurations be encompassed within the scope of the claims sought to be patented in the present invention. Therefore, the scope of the claims sought to be patented in the present invention should be construed as broadly as possible based on the above description to encompass all possible modifications and equivalent configurations.

Explanation of Reference Numerals

[0049] 1, 2 Personalized joint skeleton and cartilage morphology measurement system 11 Database 12 Image acquisition module 13 Image analysis module 14 Neural network model 15 Model construction module 16 Calculation module 21 Image registration module S1~S6, S41 Steps

Claims

1. A personalized joint skeleton / cartilage morphology measurement system for constructing a personalized joint skeleton / cartilage model of a subject and calculating a cartilage wear value of the subject based on the personalized joint skeleton / cartilage model, comprising: a database used for storing a dataset, the dataset including a plurality of joint skeleton / cartilage images for a plurality of healthy subjects, a skeleton / cartilage 3D model corresponding to the joint skeleton / cartilage images, and a plurality of shape parameters; an image acquisition module adapted to acquire a plurality of skeletal images of the subject, each of the skeletal images including a first skeletal image and a second skeletal image; an image analysis module connected to the image acquisition module and the database, for acquiring the skeleton / cartilage 3D model for the skeleton image of the subject from a statistical shape model trained using the dataset, acquiring a plurality of first skeleton / cartilage shape parameters corresponding to the first skeleton image and a plurality of second skeleton / cartilage shape parameters corresponding to the second skeleton image by principal components analysis (PCA) based on the skeleton / cartilage 3D model and the shape parameters, and generating a first skeleton / cartilage 3D model and a second skeleton / cartilage 3D model based on the first skeleton / cartilage shape parameters and the second skeleton / cartilage shape parameters; a neural network model connected to the image analysis module, which receives the first skeletal / cartilage shape parameters and the second skeletal / cartilage shape parameters, and generates and outputs a plurality of first skeletal motion parameters and a plurality of second skeletal motion parameters corresponding to the first skeletal / cartilage shape parameters and the second skeletal / cartilage shape parameters, the neural network model being obtained by training the neural network model using a machine learning method based on the data set; a model construction module connected to the image analysis module and the neural network model, the model construction module being configured to generate the personalized joint skeletal and cartilage model based on the first skeletal and cartilage 3D model and the second skeletal and cartilage 3D model, the first skeletal motion parameters and the second skeletal motion parameters; A system including a calculation module connected to the model construction module, which calculates the actual cartilage shape and the cartilage wear value of the subject by simulating the relative positions of the first skeleton / cartilage 3D model and the second skeleton / cartilage 3D model during movement based on the personalized joint skeleton / cartilage model, and removing areas where the cartilage of the first skeleton / cartilage 3D model and the second skeleton / cartilage 3D model interfere with each other during movement.

2. The personalized joint skeletal and cartilage morphology measurement system of claim 1, further comprising an image registration module connected to the image analysis module and the model construction module, for adjusting the angle and position of the first skeletal / cartilage 3D model and the second skeletal / cartilage 3D model, projecting them, and comparing them with the joint skeletal / cartilage images of the healthy subject in the dataset using a single-plane dynamic image registration method, thereby calculating the first skeletal motion parameters and the second skeletal motion parameters of the subject.

3. The personalized joint skeletal and cartilage morphology measurement system of claim 1 , wherein each of the skeletal images of the subject further includes an X-ray image.

4. The personalized joint skeletal and cartilage morphology measurement system of claim 1 , wherein the first skeletal motion parameters and the second skeletal motion parameters further include translation parameters and rotation parameters in three directions of X, Y and Z axes.

5. The personalized joint skeletal and cartilage morphometry system according to claim 1 , wherein the personalized joint skeletal and cartilage model is further visualized and displayed using color-matched images and perspective methods.

6. A personalized joint skeletal and cartilage morphology measurement method, comprising: storing a data set in a database, the data set including a plurality of joint skeletal / cartilage images for a plurality of healthy subjects, a skeletal / cartilage 3D model corresponding to the joint skeletal / cartilage images, and a plurality of shape parameters; acquiring a plurality of skeletal images of the subject using an image acquisition module, each of the skeletal images including a first skeletal image and a second skeletal image; obtaining, by an image analysis module, the skeleton / cartilage 3D model for the skeleton image of the subject from a statistical shape model (Statistical Shape Model) trained using the dataset, obtaining a plurality of first skeleton / cartilage shape parameters corresponding to the first skeleton image and a plurality of second skeleton / cartilage shape parameters corresponding to the second skeleton image based on the skeleton / cartilage 3D model and the shape parameters by principal components analysis (PCA), and generating a first skeleton / cartilage 3D model and a second skeleton / cartilage 3D model based on the first skeleton / cartilage shape parameters and the second skeleton / cartilage shape parameters; inputting the first skeletal / cartilage shape parameters and the second skeletal / cartilage shape parameters into a neural network model to generate and output a plurality of first skeletal motion parameters and a plurality of second skeletal motion parameters corresponding to the first skeletal / cartilage shape parameters and the second skeletal / cartilage shape parameters, the neural network model being obtained by training the neural network model using a machine learning method based on the data set; generating the personalized articular skeletal and cartilage model based on the first and second skeletal and cartilage 3D models and the first and second skeletal motion parameters using a model construction module; A method comprising: a step of simulating, by a calculation module, the relative positions of the first skeleton / cartilage 3D model and the second skeleton / cartilage 3D model during movement of the subject based on the personalized articular skeleton / cartilage model, and calculating the actual cartilage shape and the cartilage wear value of the subject by removing areas where the cartilage of the first skeleton / cartilage 3D model and the second skeleton / cartilage 3D model interfere with each other during movement.

7. Furthermore, The personalized joint skeleton / cartilage morphology measurement method of claim 6, further comprising a step of: adjusting the angle and position of the first skeleton / cartilage 3D model and the second skeleton / cartilage 3D model and projecting them using an image registration module, and calculating the first skeleton motion parameters and the second skeleton motion parameters of the subject by matching them with the joint skeleton / cartilage images of the healthy subject in the dataset using a single-plane dynamic image registration method.

8. The method of claim 6, wherein each of the skeletal images of the subject further includes an X-ray image.

9. The personalized joint skeleton / cartilage morphology measurement method according to claim 6 , wherein the first skeletal motion parameters and the second skeletal motion parameters further include translation parameters and rotation parameters in three directions of X, Y and Z axes.

10. The method for measuring personalized joint bone and cartilage morphology according to claim 6 , wherein the personalized joint bone and cartilage model is further visualized and displayed using color-matched images and a perspective method.

Images