Intelligent knee joint prosthesis device and detection system

Abstract

The invention provides an intelligent knee joint prosthesis device and a detection system, and belongs to the technical field of medical instruments. A femoral condyle prosthesis and a tibial plateau; the fixing rod is fixedly connected into the femoral condyle prosthesis; the platform stand column is fixedly connected to the lower end of the tibia platform; according to the intelligent knee joint prosthesis device, the manufactured knee joint prosthesis can be accurately matched with the anatomical structure of each patient by using a personalized skeleton modeling technology, the integrating degree between the prosthesis and the skeleton of the patient is improved through the highly personalized solution, the discomfort and complications possibly occurring after an operation are reduced, and the operation efficiency is improved. Therefore, the life quality of a patient is remarkably improved, potential problems can be found and adjusted in time by continuously monitoring the pressure change and other motion parameters of the knee joint, and abrasion possibly generated in the long-term use process is avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of medical devices, and particularly relates to an intelligent knee joint prosthesis device and a detection system. Background Art

[0002] The knee joint is the largest, anatomically complex, and highly demanding joint for motor function in the human body. The present invention belongs to the field of implantable medical devices and relates to existing total knee joint prosthesis replacement and unicompartmental knee arthroplasty. Total knee arthroplasty is a surgical method for treating severe knee joint diseases, usually used for treating end-stage knee joint diseases such as degenerative osteoarthritis. This surgery relieves pain and improves joint function by removing the damaged joint surface and replacing it with an artificial joint. According to the analysis and summary of existing clinical data, total knee arthroplasty has significantly improved in terms of pain, joint function, and range of motion, and the excellent and good rate of the surgery reaches 93.75%. However, attention also needs to be paid to the selection of indications, the correction of knee joint varus and valgus and flexion deformities, and the correct placement of the tibial prosthesis to reduce postoperative complications;

[0003] Unicompartmental knee arthroplasty is a minimally invasive surgery that targets patients with unicompartmental knee osteoarthritis. Compared with total knee arthroplasty, unicompartmental knee arthroplasty only replaces the diseased compartment, that is, only performs surface replacement on the medial or lateral compartment of the knee joint to replace the damaged cartilage surface of the knee joint. This surgical method preserves all ligament tissues and the articular cartilage of the remaining compartments, thus achieving rapid recovery after surgery.

[0004] Existing knee joint prostheses and unicompartmental prostheses are suitable for conventional knee joint osteoarthritis replacement. However, for problems such as the implantation effect of the prosthesis after joint prosthesis implantation, daily stress monitoring, collection of knee joint movement data after surgery, and rehabilitation evaluation, doctors can only judge through postoperative CT or X-ray images, patient behavior, and patient oral statements, and it is difficult to qualitatively or quantitatively evaluate. Therefore, it is necessary to design an intelligent knee joint prosthesis detection system that can detect relevant parameter data such as knee joint prostheses and knee joint movement after surgery, and at the same time, doctors can provide evaluation diagnosis and rehabilitation based on the prosthesis detection data. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent knee joint prosthesis device and a detection system, aiming to solve the problem that existing knee joint prostheses and unicompartmental prostheses in the prior art are suitable for conventional knee joint osteoarthritis replacement, but for problems such as the implantation effect of the prosthesis after joint prosthesis implantation, daily stress monitoring, collection of knee joint movement data after surgery, and rehabilitation evaluation, doctors can only judge through postoperative CT or X-ray images, patient behavior, and patient oral statements, and it is difficult to qualitatively or quantitatively evaluate.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An intelligent knee joint prosthesis device, comprising:

[0008] A femoral condyle prosthesis and a tibial plateau;

[0009] A fixing rod, which is fixedly connected inside the femoral condyle prosthesis;

[0010] A platform column, which is fixedly connected to the lower end of the tibial plateau;

[0011] An anti-rotation wing, which is fixedly connected to the circumferential surface of the platform column;

[0012] Two outer brace straps, both of which are sleeved on the outer side of the leg;

[0013] A wireless charging coil, which is located at the closer ends of the two outer brace straps or is built into an annular outer brace strap;

[0014] An intelligent cushion, which is arranged between the femoral condyle prosthesis and the tibial plateau;

[0015] An in vitro detection sensor IMU, which is embedded in the surface of the in vitro brace strap.

[0016] As a preferred solution of the present invention, there are a personalized bone modeling module, a data acquisition module, a data transmission module, a data processing module, a visualization display module, an AI big data evaluation module and a wireless power supply module. The personalized bone modeling module is used to construct a three-dimensional bone model based on the knee joint CT image data of the patient. The data acquisition module includes an in-body sensor and an in-vitro sensor. The in-body sensor is used to detect the knee joint gap pressure, and the in-vitro sensor is used to detect the motion parameters of the knee joint. The data transmission module is used to wirelessly transmit the collected data to the client through Bluetooth. The data processing module is used to classify and process the received data, determine the data source and perform further analysis. The visualization display module is used to display the three-dimensional bone model and the real-time motion state on the client. The AI big data evaluation module is used to evaluate the knee joint stress state and provide rehabilitation suggestions. The wireless power supply module is used to supply power to the in-body sensor through a wireless charging component in the in-vitro knee brace.

[0017] As a preferred solution of the present invention, the personalized bone modeling module uses a deep learning model to segment and reconstruct the CT image to generate a three-dimensional model that precisely matches the patient's bone structure.

[0018] As a preferred embodiment of the present invention, the in-vivo sensor in the data acquisition module adopts a data detection and data transmission device formed by combining a resistive pressure strain gauge and a low-power Bluetooth transmission chip, which can continuously monitor the knee joint pressure change without affecting the patient's daily life.

[0019] As a preferred embodiment of the present invention, the data processing module can automatically identify the data source, analyze the data through a big data model, and judge whether the knee joint stress state is within the normal range.

[0020] As a preferred embodiment of the present invention, the visualization display module can display a dynamic three-dimensional model of the knee joint on the client side, intuitively presenting the motion state and stress distribution of the knee joint.

[0021] As a preferred embodiment of the present invention, the AI big data evaluation module can automatically identify abnormal stress states based on historical health data, and push warning information and rehabilitation suggestions to the user.

[0022] As a preferred embodiment of the present invention, the wireless power supply module adopts a combination of an inverter circuit and a charging coil circuit to realize wireless power supply for the in-vivo sensor through an external knee joint brace, reducing the safety risk of the implanted battery.

[0023] As a preferred embodiment of the present invention, the in-vivo sensor adopts an anatomical design to maximize the restoration of the original shape and function of the patient's knee joint, reducing postoperative complications.

[0024] As a preferred embodiment of the present invention, the external knee joint brace adopts a lightweight design to reduce the patient's burden and promote postoperative rehabilitation.

[0025] Compared with the prior art, the beneficial effects of the present invention are:

[0026] 1. The intelligent knee joint prosthesis device ensures that the manufactured knee joint prosthesis can accurately match the anatomical structure of each patient by using personalized bone modeling technology. This highly personalized solution improves the fit between the prosthesis and the patient's bone, reduces the discomfort and complications that may occur after surgery, thus significantly improving the patient's quality of life. By continuously monitoring the pressure changes and other movement parameters of the knee joint, potential problems can be detected and adjusted in a timely manner, avoiding wear that may occur during long-term use.

[0027] 2. With the help of advanced data collection, transmission, and processing technologies, the intelligent knee prosthesis detection system can achieve real-time monitoring of the knee joint status. Through the data analysis and rehabilitation suggestions provided by the AI big data evaluation module, patients and doctors can obtain instant feedback on the knee joint health condition, which helps to formulate a more scientific and reasonable rehabilitation plan. Such preventive maintenance measures can not only help patients better manage their rehabilitation process but also effectively reduce the risk of reoperation.

[0028] 3. The lightweight design of the external knee brace stabilizes the joint movement of patients while reducing their daily burden, enabling them to carry out various activities more easily. At the same time, the in-body sensors using wireless power supply technology do not require battery replacement, reducing the inconvenience and potential risks of battery implantation. These design optimizations make this intelligent knee prosthesis device and detection system more convenient for daily use, contributing to promoting patients' daily safe health fitness activities and extending the service life of the prosthesis. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The drawings are used to provide a further understanding of the present invention and form a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0030] Figure 1 is a three-dimensional view of the in-body implant device in the present invention;

[0031] Figure 2 is a schematic diagram of the system working process in the present invention;

[0032] Figure 3 is a schematic diagram of the big data AI evaluation process in the present invention;

[0033] Figure 4 is a schematic diagram of the Bluetooth transmission process in the present invention;

[0034] Figure 5 is a diagram of the external wearable device and IMU in the present invention;

[0035] Figure 6 is an anatomical design diagram of the intelligent cushion in the present invention;

[0036] Figure 7 is a design diagram of the external charging and in-body receiving circuits in the present invention;

[0037] Figure 8 is a flow chart of the inverter circuit generating stable alternating current in the present invention.

[0038] In the figure: 1. Femoral condyle prosthesis; 2. Tibial plateau; 3. Platform column; 4. Anti-rotation wing; 5. Fixing rod; 6. External brace strap; 7. Wireless charging coil; 8. Intelligent cushion; 9. External detection sensor IMU. Specific embodiments

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0040] Embodiment 1

[0041] Please refer to Figures 1-8 , the present invention provides the following technical solutions:

[0042] An intelligent knee joint prosthesis device, comprising:

[0043] Femoral condyle prosthesis 1 and tibial plateau 2;

[0044] Fixing rod 5, and the fixing rod 5 is fixedly connected inside the femoral condyle prosthesis 1;

[0045] Platform column 3, and the platform column 3 is fixedly connected to the lower end of the tibial plateau 2;

[0046] Anti-rotation wing 4, and the anti-rotation wing 4 is fixedly connected to the circumferential surface of the platform column 3;

[0047] Two external brace straps 6, and both of the two external brace straps 6 are sleeved on the outer side of the leg;

[0048] Wireless charging coil 7, and the wireless charging coil 7 is located at the adjacent ends of the two external brace straps 6 or is built into the annular strap;

[0049] Intelligent cushion 8, and the intelligent cushion 8 is arranged between the femoral condyle prosthesis 1 and the tibial plateau 2.

[0050] External detection sensor IMU 9, and the external detection sensor IMU 9 is embedded in the surface of the external brace strap 6.

[0051] In a specific embodiment of the present invention, the femoral condyle prosthesis 1 and the tibial plateau 2: These two components are respectively used to be fixed on the femur and the tibia to ensure that the entire prosthesis device is tightly combined with the user's skeletal system. The fixing rod 5 and the platform column 3 play a role in fixing the femoral prosthesis and the tibial prosthesis, preventing the prosthesis from rotating or even falling off due to joint movement, enhancing the stability and strength of the device, and transmitting force to the calf bone. The anti-rotation wing 4 increases the friction with the bone and at the same time avoids relative rotation between the prosthesis and the bone during movement. The two outer brace straps 6 are used to assist in fixing the entire device and provide additional safety guarantees. The wireless charging coil 7 is used to achieve wireless charging of the built-in electronic components, simplifying the maintenance and use steps. It is installed at the proximal ends of the two straps close to each other or built into the annular strap. The intelligent cushion 8 can monitor the movement state of the knee joint and adjust the support force. The in vitro detection sensor IMU 9 can collect the kinematic data of the patient and at the same time provide feedback to the user or medical professionals. The intelligent knee joint prosthesis device can provide a more natural, safe and efficient walking experience for the user and has an intelligent monitoring function, which helps to improve the quality of life of the patient.

[0052] Specifically, please refer to Figures 1-8 , a personalized bone modeling module, a data acquisition module, a data transmission module, a data processing module, a visualization display module, an AI big data evaluation module and a wireless power supply module. The personalized bone modeling module is used to construct a three-dimensional bone model based on the knee joint CT image data of the patient. The data acquisition module includes an in vivo sensor and an in vitro sensor. The in vivo sensor is used to detect the knee joint gap pressure, and the in vitro sensor is used to detect the movement parameters of the knee joint. The data transmission module is used to wirelessly transmit the collected data to the client through Bluetooth. The data processing module is used to classify and process the received data, determine the data source and perform further analysis. The visualization display module is used to display the three-dimensional bone model and the real-time movement state on the client. The AI big data evaluation module is used to evaluate the knee joint stress state and provide rehabilitation suggestions. The wireless power supply module is used to power the in vivo sensor through the wireless charging component in the in vitro knee joint brace.

[0053] In this embodiment: The personalized bone modeling module constructs an accurate three-dimensional bone model based on the knee joint CT image data provided by the patient, using medical image processing software. By adopting advanced image segmentation technology, it automatically identifies the bone structure and generates an interactive 3D model. The data acquisition module includes an in-vivo sensor and an ex-vivo sensor. The in-vivo sensor detects the pressure change in the knee joint space. The sensor is integrated inside the prosthesis and can measure the pressure distribution in the joint space under different activity states. The ex-vivo sensor monitors parameters such as the movement angle, speed, and acceleration of the knee joint. A micro MEMS sensor is used and installed on the brace outside the knee joint. The data transmission module wirelessly transmits the data collected by the sensor to the user's smartphone or computer via Bluetooth. It has a built-in low-power Bluetooth module to ensure stable data transmission. The data processing module preprocesses, classifies, and performs necessary data analysis on the original data. The visualization display module displays the three-dimensional model of the knee joint and its movement state on the user's client device. A dedicated application or web interface is developed, and a 3D graphics engine is used to render the model and movement trajectory in real time. The AI big data evaluation module combines the patient's personal information and historical data to evaluate the stress state of the knee joint and provides rehabilitation suggestions. Machine learning algorithms are used to train the model and analyze a large amount of relevant data to provide personalized rehabilitation guidance for each user. The wireless power supply module provides power for the sensor implanted in the body. Through the wireless charging component in the ex-vivo knee brace, it uses the principle of electromagnetic induction to power the in-vivo sensor, which can effectively monitor the movement state and biomechanical characteristics of the knee joint, helping doctors better understand the specific situation of the patient, thereby improving the rehabilitation effect.

[0054] For details, please refer to Figures 1-8 , and the personalized bone modeling module uses a deep learning model to segment and reconstruct the CT image to generate a three-dimensional model that accurately matches the patient's bone structure.

[0055] In this embodiment: The personalized bone modeling module is divided into five processes: data preparation, image segmentation, three-dimensional reconstruction, model optimization and verification, and model interaction. For data preparation, the knee joint CT image data of the patient is collected and the images are preprocessed, such as removing noise, enhancing contrast, etc. For image segmentation, a deep learning model is used to segment the CT images to distinguish the bone region from other tissues. The model needs to be trained with a large amount of labeled data to accurately identify bone edges and other important features. For three-dimensional reconstruction, the segmented two-dimensional CT image sequence is converted into three-dimensional volume data, and three-dimensional reconstruction algorithms are applied to create an accurate three-dimensional bone model. For model optimization and verification, post-processing is performed on the generated three-dimensional model, such as smoothing, filling holes, etc., to improve the model quality. The accuracy of the model is verified by comparing it with the actual CT images. For model interaction, the three-dimensional model is made interactive, allowing users to observe it from different angles and even simulate the movement of the knee joint. The model is integrated into the client application for easy viewing by doctors and patients. Doctors can obtain a very accurate three-dimensional model of the knee joint, which helps them better understand the patient's condition and provides a basis for subsequent data collection, data analysis, and other processes.

[0056] Specifically, please refer to Figures 1-8 For the in-vivo sensor in the data acquisition module, a data detection and data transmission device formed by combining a resistive pressure strain gauge and a low-power Bluetooth transmission chip is used, which can continuously monitor the knee joint pressure change without affecting the patient's daily life; for the ex-vivo sensor in the data acquisition module, a data detection and data transmission device formed by combining a six-axis gyroscope (IMU) and a low-power Bluetooth transmission chip is used and implanted in the strap of the ex-vivo knee brace, which can continuously monitor the knee joint movement state change while protecting the patient's knee joint during daily life and exercise.

[0057] In this embodiment: In the data acquisition module, the in-vivo sensor is a data detection and data transmission device formed by combining a resistive pressure strain gauge and a low-power Bluetooth transmission chip. It can achieve daily monitoring, data transmission and analysis, and feedback and adjustment functions through implantation surgery. The ex-vivo sensor in the data acquisition module is a data detection and data transmission device formed by combining a 6-axis gyroscope (IMU) and a low-power Bluetooth transmission chip. It can achieve daily monitoring, data transmission and analysis, and feedback and adjustment functions by cooperating with a knee brace. For implantation surgery, the doctor implants the sensor into the patient's knee joint through an arthroplasty. The position of the sensor should be able to accurately reflect the pressure distribution of the knee joint. For daily monitoring, the sensor starts to continuously record the pressure changes of the knee joint. The patient can carry out daily activities normally, and the sensor will not cause any discomfort to the patient. For data transmission and analysis, the sensor sends the data to a smartphone application or the doctor's monitoring system through low-power Bluetooth. The doctor can evaluate the functional recovery of the knee joint based on this data and adjust the rehabilitation plan accordingly. For feedback and adjustment, the patient can receive feedback on the status of the knee joint, such as when to rest or how to improve the activity pattern. The doctor can adjust the treatment plan in a timely manner according to the collected data to achieve the best treatment effect. The sensor provides a valuable tool for the research and treatment of knee joint diseases. It can help doctors understand the patient's condition more deeply and formulate a more personalized treatment plan. At the same time, for patients, such a monitoring method reduces frequent hospital visits and improves the quality of life.

[0058] For details, please refer to Figures 1-8 The data processing module can automatically identify the data source and analyze the data through a big data model to determine whether the stress state of the knee joint is within the normal range.

[0059] In this embodiment: The data processing module is divided into data classification, data analysis, anomaly detection, and feedback mechanism. For data classification, a dedicated algorithm is developed to automatically identify the data source through data features, and the device identification code is used to distinguish different types of sensor data. For data analysis, a big data analysis model is constructed, which combines the patient's historical data and personal information to evaluate the stress state of the knee joint, extracts key features from the sensor data, such as pressure values, motion parameters, etc., and uses statistical methods or machine learning algorithms to establish an analysis model, and trains the model using the historical data set to identify normal and abnormal stress states. For anomaly detection, thresholds are set or anomaly detection algorithms are used to identify data points outside the normal range, and reasonable stress thresholds are set based on clinical experience and big data analysis results, continuously monitoring the data stream, and immediately issuing a warning when an anomaly is detected. For the feedback mechanism, the analysis results are fed back to the AI big data evaluation module to provide further rehabilitation suggestions, communicate with the AI big data evaluation module through the API interface, and transmit the analysis results. With the data processing module, the intelligent knee joint prosthesis detection system can more accurately evaluate the health status of the knee joint.

[0060] For details, please refer to Figures 1-8 , and the visualization display module can display a dynamic three-dimensional model of the knee joint on the client side, intuitively presenting the motion state and stress distribution of the knee joint.

[0061] In this embodiment: The visualization display module is divided into three-dimensional model rendering, real-time data update, interactive function, stress distribution visualization, motion state animation, and user interface design. Among them, for three-dimensional model rendering, modern 3D graphics libraries are used to achieve real-time rendering, and the three-dimensional model generated by the personalized bone modeling module is rendered on the client side. For real-time data update, real-time data from the sensor is received through the data transmission module, and WebSocket or other real-time communication technologies are used to maintain the connection between the client and the server to ensure that the data can be updated to the model in real time. For the interactive function, touch screen or mouse operations are implemented, allowing users to view the model from different angles, developing a user-friendly interface that allows users to rotate and zoom the model and view specific areas. For stress distribution visualization, color coding or heat maps are used to represent the pressure distribution, and according to the data of the in-vivo sensors, areas with different pressure levels are marked with different colors, making the pressure distribution clear at a glance. For motion state animation, bone animation technology is used to simulate the movement of the knee joint, and according to the data of the ex-vivo sensors, the posture of the model is updated in real time to simulate the movement of the knee joint during activities such as walking and running. For user interface design, modern front-end frameworks are used to build the user interface, designing a simple and easy-to-use user interface that allows users to easily view and understand the state of the knee joint.

[0062] For details, please refer to Figures 1-8, the AI big data evaluation module can automatically identify abnormal stress states based on historical health data and push warning messages and rehabilitation suggestions to users.

[0063] In this embodiment: The AI big data evaluation module includes data collection and processing, data analysis, anomaly detection, a warning system, rehabilitation suggestion generation, and a user feedback loop. The data collection and processing uses Internet of Things (IoT) devices to collect biomechanical data during knee joint activities, including but not limited to pressure distribution, movement trajectories, etc., continuously collects data through in-vivo and in-vitro sensors, and uploads it to the cloud database. The data analysis uses machine learning algorithms to perform pattern recognition and predictive analysis on the data, trains the model to identify the differences between normal and abnormal stress states, so as to be able to automatically identify abnormal situations. The anomaly detection uses anomaly detection algorithms, such as statistical-based methods or deep learning models. When the monitored data deviates from the normal range, the system triggers an anomaly detection alarm. The warning system integrates a push notification service and immediately sends a warning message to the user's mobile device once an abnormal stress state is detected. The rehabilitation suggestion generation combines domain expert knowledge and machine learning algorithms to provide personalized rehabilitation suggestions, recommends corresponding exercise methods, physical therapy plans, or lifestyle adjustments according to the specific conditions of the knee joint. The user feedback loop establishes a feedback mechanism to collect the user's feedback information on the suggestions, continuously optimizes the algorithm, improves the accuracy and effectiveness of the rehabilitation suggestions, and gives targeted suggestions, which helps prevent knee joint injuries and promote the rehabilitation process.

[0064] Specifically, please refer to Figures 1-8 , the wireless power supply module adopts a combination of an inverter circuit and a charging coil circuit to realize wireless power supply for in-vivo sensors through an external knee brace, reducing the safety risk of the implanted device's built-in battery.

[0065] In this embodiment: The wireless power supply module is divided into an inverter circuit, a charging coil circuit, and energy transmission. The inverter circuit converts direct current into alternating current for easy transmission through a magnetic field, usually using efficient switching power supply technology and a control circuit to generate high-frequency alternating current signals. The charging coil circuit converts the alternating current signal into magnetic energy through the principle of electromagnetic induction, and then the in-vivo receiving coil converts it back into electrical energy. Appropriate coil designs and materials are used to ensure efficient energy conversion and transmission. The wireless power supply module can provide stable power supply for implanted sensors without interfering with the patient's daily life, which not only improves the working reliability and service life of the sensors but also significantly enhances the patient's quality of life.

[0066] Specifically, please refer to Figures 1-8 , the in-vivo sensor adopts an anatomical design to maximize the restoration of the patient's original knee joint morphology and functionality and reduce postoperative complications.

[0067] In this embodiment: The shape and size of the in-vivo sensor are customized according to the anatomical structure of the knee joint to ensure the best fit with the surrounding tissues. An advanced manufacturing technology is used to produce a precisely matching sensor based on the patient's CT image data. A medical-grade biocompatible material is used to ensure that the selected material is harmless to human tissues and will not cause an immune response or inflammation. The surface of the sensor is specially treated. The force-bearing surface of the pad is physically divided into multiple smaller force-bearing surfaces using a finite element module. The sensor structure design needs to consider long-term stability to avoid displacement or damage. The design is optimized through finite element analysis methods to ensure structural strength and durability. The sensor adopts a low-power design to reduce heat generation and energy consumption. Advanced integrated circuit technology and low-power Bluetooth chips are used to ensure that the sensor can work stably for a long time after implantation. The sensor should have good anti-interference ability to ensure that the accuracy of the data is not affected by other factors in the body. Shielding technology or digital signal processing technology is used to reduce the impact of external electromagnetic interference. The in-vivo sensor can not only accurately monitor the pressure changes of the knee joint, but also minimize the impact on the patient, improve the success rate of the operation, and reduce the risk of postoperative complications. The design of this sensor fully reflects the progress of modern medical technology.

[0068] Specifically, please refer to Figures 1-8 , and the external knee brace adopts a lightweight design to reduce the patient's burden and promote postoperative rehabilitation.

[0069] In this embodiment: The external knee brace ensures that the brace is light enough to reduce the discomfort of the patient when wearing it, supports the natural movement of the knee joint during the rehabilitation process, accelerates the rehabilitation process, has breathability, ventilation holes are provided on the brace to improve breathability and reduce the discomfort caused by sweat accumulation, and a moisture-absorbing and sweat-wicking material is used to make the inner lining to keep the skin dry. The external knee brace can not only effectively support the rehabilitation process of the knee joint, but also minimize the discomfort of the patient and improve their quality of life. This lightweight design reflects the humanized concept and technological progress of modern rehabilitation technology.

[0070] Working principle and usage process of the present invention: For personalized bone modeling, CT image data of the patient's knee joint is obtained. A deep learning model is used to segment and reconstruct the CT image to generate a three-dimensional model that precisely matches the patient's bone structure. The three-dimensional model is optimized to ensure its accuracy and usability. For sensor implantation and installation, based on the three-dimensional model generated by the personalized bone modeling module, the optimal implantation position of the in-vivo sensor is determined. The in-vivo sensor is implanted during the operation, and its good fit with the knee joint is ensured. The in-vitro sensor is installed in the in-vitro knee brace to ensure that the sensor matches the lightweight design of the brace. For data collection, the in-vivo sensor continuously monitors the pressure change in the knee joint space, and the in-vitro sensor monitors the motion parameters of the knee joint. The sensor data is collected and stored in real time. For data transmission, the in-vivo sensor sends the data to the receiver in the in-vitro knee brace through a low-power Bluetooth chip. The receiver in the in-vitro knee brace wirelessly transmits all the sensor data to the client through Bluetooth. For data processing, the data processing module automatically identifies the data source and classifies and processes the data. A big data model is used to analyze the data to determine whether the stress state of the knee joint is within the normal range. When an abnormality is found, the data is marked for further analysis. For visual display, a dynamic three-dimensional model of the knee joint is presented on the client, and the model is updated in real time to intuitively show the motion state and stress distribution of the knee joint. The user can view the state of the knee joint through the client. For AI big data evaluation, based on historical health data, abnormal stress states are automatically identified, warning messages and rehabilitation suggestions are pushed to the user, and the evaluation model is adjusted according to the user's feedback. For wireless power supply, the in-vivo sensor is powered by the wireless charging component in the in-vitro knee brace. The inverter circuit is combined with the charging coil circuit to ensure that the in-vivo sensor can continuously work. The intelligent knee prosthesis detection system can comprehensively monitor the state of the knee joint, help doctors better evaluate the patient's rehabilitation progress, and provide personalized rehabilitation suggestions for the patient.

[0071] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent knee joint prosthesis device, characterized in that: include: Femoral condyle prosthesis (1) and tibial plateau (2); A fixing rod (5), wherein the fixing rod (5) is fixedly connected to the femoral condyle prosthesis (1); A platform column (3), wherein the platform column (3) is fixedly connected to the lower end of the tibial platform (2); An anti-rotation wing (4), the anti-rotation wing (4) being fixedly connected to the circumferential surface of the platform column (3); Two external brace straps (6), both of which are sleeved on the outside of the legs; A wireless charging coil (7), wherein the wireless charging coil (7) is located at the adjacent ends of the two external brace straps (6) or is built into the annular strap; An intelligent liner (8), wherein the intelligent liner (8) is arranged between the femoral condyle prosthesis (1) and the tibial platform (2); An in vitro detection sensor IMU (9), wherein the in vitro detection sensor IMU (9) is embedded on the surface of the in vitro brace strap (6).

2. According to the intelligent knee prosthesis detection system described in claim 1, it includes a personalized bone modeling module, a data acquisition module, a data transmission module, a data processing module, a visualization display module, an AI big data evaluation module and a wireless power supply module, wherein the personalized bone modeling module is used to construct a three-dimensional bone model based on the patient's knee CT image data, the data acquisition module includes an in vivo sensor and an in vitro sensor, the in vivo sensor is used to detect the knee joint gap pressure, and the in vitro sensor is used to detect the motion parameters of the knee joint, the data transmission module is used to transmit the collected data to the client via Bluetooth wireless, the data processing module is used to classify the received data, determine the data source and perform further analysis, the visualization display module is used to display the three-dimensional bone model and real-time motion status on the client, the AI ​​big data evaluation module is used to evaluate the stress state of the knee joint and provide rehabilitation suggestions, and the wireless power supply module is used to power the in vivo sensor through the wireless charging component in the external knee brace.

3. The intelligent knee joint prosthesis detection system according to claim 2, characterized in that: The personalized bone modeling module uses a deep learning model to segment and reconstruct CT images to generate a three-dimensional model that accurately matches the patient's bone structure.

4. The intelligent knee joint prosthesis detection system according to claim 3, characterized in that: The in vivo sensor in the data acquisition module is a data detection and data transmission device formed by combining a resistive pressure strain gauge and a low-power Bluetooth transmission chip, which can continuously monitor the changes in knee joint gap pressure without affecting the patient's daily life.

5. The intelligent knee joint prosthesis detection system according to claim 4, characterized in that: The data processing module can automatically identify the corresponding sensor data, and compare and analyze the data provided by the big data model to determine whether the stress state of the knee joint is within a normal range.

6. The intelligent knee joint prosthesis detection system according to claim 5, characterized in that: The visualization display module can display a dynamic three-dimensional model of the knee joint on the client, and intuitively present the real-time motion state and stress distribution of the knee joint.

7. The intelligent knee joint prosthesis detection system according to claim 6, characterized in that: The AI ​​big data assessment module can automatically identify abnormal stress states based on historical health data, and push warning information and rehabilitation suggestions to users.

8. The intelligent knee joint prosthesis detection system according to claim 7, characterized in that: The wireless power supply module adopts a combination of an inverter circuit and a charging coil circuit to realize wireless power supply of the in vivo sensor through the battery module of the external knee joint brace, thereby avoiding the safety hazards caused by the built-in battery of the implant.

9. The intelligent knee joint prosthesis detection system according to claim 8, characterized in that: The implant module formed by the in vivo sensor and the knee joint prosthesis adopts a design that adapts to the human anatomy, so as to restore the patient's original knee joint morphology and functionality to the greatest extent possible and reduce postoperative complications.

10. The intelligent knee joint prosthesis detection system according to claim 9, characterized in that: The external knee brace adopts a lightweight design to reduce the burden on the patient's knee joint and promote postoperative rehabilitation of the knee joint and the stability of daily knee joint movement function.

Images