Lumbar vertebra and spine rehabilitation system and method based on intelligent control

Abstract

The invention discloses a lumbar vertebra and spine rehabilitation system based on intelligent control, and belongs to the technical field of medical treatment, the system comprises a monitoring module, a control module and a rehabilitation equipment module, the monitoring module is connected to the control module, and the monitoring module is used for obtaining pathological features corresponding to the lumbar vertebra and spine of a patient and inputting the pathological features to the control module; the control module is connected to the rehabilitation equipment module and is used for generating a control signal according to the pathological characteristics of the monitoring module and outputting the control signal to the rehabilitation equipment module; the rehabilitation equipment module comprises a waist supporting unit, a waist adjusting unit, a spine traction unit and a spine correcting unit, the waist supporting unit is used for controlling signals to execute waist supporting actions, the waist adjusting unit is used for adjusting parameters of the waist supporting unit, and the spine traction unit executes spine traction actions; the spine correction unit is used for executing spine correction actions. According to the scheme, the problem that in the prior art, a lumbar vertebra and spine rehabilitation method is low in reliability for lumbar vertebra and spine rehabilitation treatment can be solved.

Description

Technical Field

[0001] The present invention belongs to the field of medical technology, and in particular relates to a lumbar vertebra and spinal rehabilitation system and method based on intelligent control. Background Art

[0002] With the acceleration of modern life and the change of working style, lumbar and spinal problems are increasingly becoming an important factor affecting people's health and quality of life. Factors such as long-term sitting, lack of exercise, and poor posture cause the lumbar spine and spine to bear huge pressure, which in turn causes a series of diseases such as lumbar disc herniation, scoliosis, and lumbar muscle strain. These diseases not only bring physical pain to patients, but also may affect their work and life ability, and even cause long-term disability. Therefore, how to effectively prevent and treat lumbar and spinal diseases has become an urgent problem to be solved in the medical and rehabilitation fields.

[0003] At present, the lumbar and spinal rehabilitation methods on the market are mainly carried out through some rehabilitation methods such as traction beds and correctors. Although they can relieve the patient's symptoms to a certain extent, most of them use fixed treatment parameters and modes, which are difficult to adjust accurately according to the patient's specific condition and physical condition; the monitoring is not comprehensive, and the existing equipment has limitations in monitoring the patient's physiological data, and cannot fully reflect the patient's rehabilitation progress and physical condition changes; the degree of automation is low, relying on manual operation and judgment, which not only increases the workload of medical staff, but also may cause treatment errors due to human factors; lack of feedback mechanism, unable to evaluate the treatment effect in real time and adjust the treatment plan in time according to the feedback results, resulting in the lack of flexibility and pertinence in the treatment process. Therefore, the lumbar and spinal rehabilitation methods of the existing technology cannot achieve reliable lumbar and spinal rehabilitation treatment. Summary of the invention

[0004] The purpose of the present invention is to solve the problem of low reliability of lumbar vertebrae and spinal rehabilitation methods in the prior art and to provide a lumbar vertebrae and spinal rehabilitation system and method based on intelligent control.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: According to a first aspect of the present invention, there is provided a lumbar vertebra and spinal rehabilitation system based on intelligent control, comprising a monitoring module, a control module and a rehabilitation equipment module, wherein the monitoring module is connected to the control module, the monitoring module is used to obtain the pathological characteristics corresponding to the patient's lumbar vertebra and spine and input them into the control module; the control module is connected to the rehabilitation equipment module, the control module is used to generate a control signal according to the pathological characteristics of the monitoring module and output it to the rehabilitation equipment module; the rehabilitation equipment module comprises a lumbar support unit, a lumbar adjustment unit, a spinal traction unit and a spinal correction unit, the lumbar support unit is used to perform a lumbar support action through the control signal of the control module, the lumbar adjustment unit is used to adjust the parameters of the lumbar support unit, the spinal traction unit is used to perform a spinal traction action according to the control signal of the control module, and the spinal correction unit is used to perform a spinal correction action according to the control signal of the control module.

[0006] In the above technical solution, the monitoring module accurately obtains the patient's lumbar and spinal pathological characteristics, and the control module can generate personalized treatment control signals based on this to ensure that each patient can obtain the treatment plan that best suits their condition. The lumbar support unit, lumbar adjustment unit, spinal traction unit and spinal correction unit in the rehabilitation equipment module can perform corresponding rehabilitation actions according to the precise control signals sent by the control module, achieve precise treatment, and improve rehabilitation effects. It can monitor the patient's treatment response in real time, and dynamically adjust the parameters and actions of the rehabilitation equipment as needed to form a closed-loop control to ensure the safety and effectiveness of the treatment process. It can automatically perform complex rehabilitation procedures, reduce manual intervention, improve treatment efficiency, and shorten the patient's rehabilitation cycle. Through precise lumbar support and adjustment, as well as gentle spinal traction and correction movements, the system can minimize the patient's discomfort during the rehabilitation process and enhance the treatment experience.

[0007] Preferably, the monitoring module includes an image acquisition unit, an image processing unit and a data analysis unit which are connected in sequence; the image acquisition unit is used to acquire three-dimensional image data corresponding to the patient's lumbar vertebrae and spine; the image processing unit is used to process the three-dimensional image data to obtain pathological characteristics; and the data analysis unit is used to set a rehabilitation plan based on the pathological characteristics or feedback signals from the rehabilitation equipment.

[0008] In the above technical solution, the image acquisition unit can collect three-dimensional image data corresponding to the patient's lumbar spine and spine, which can provide more comprehensive and accurate patient pathological information, and help to analyze the condition more accurately later. The image processing unit automatically processes the collected three-dimensional image data to extract key pathological features, reducing the time and errors of manual analysis and improving the accuracy and efficiency of diagnosis. Based on the extracted pathological features or the real-time feedback signals of the rehabilitation equipment, the data analysis unit can intelligently formulate or adjust the rehabilitation plan, provide personalized treatment suggestions based on the patient's specific condition and rehabilitation progress, and ensure the scientificity and effectiveness of the rehabilitation plan. The data analysis unit can evaluate the treatment effect in real time according to the feedback signals of the rehabilitation equipment, and dynamically adjust the rehabilitation plan accordingly, which helps to timely discover and correct deviations in the treatment process and ensure the safety and effectiveness of the rehabilitation process.

[0009] According to a second aspect of the present invention, there is provided a lumbar vertebra and spinal rehabilitation method based on intelligent control, comprising the following steps: S1. Obtain the three-dimensional image data corresponding to the patient's lumbar spine and spine through the monitoring module and extract the corresponding pathological features; S2. analyzing the pathological features through a neural network model to determine corresponding treatment features and risk features; S3, determining a rehabilitation goal according to the treatment characteristics and the risk characteristics, and setting a rehabilitation plan in combination with the patient's demand data and the rehabilitation goal; S4, setting control parameters of a control module according to the rehabilitation plan, and controlling a rehabilitation equipment module through the control module to execute the rehabilitation plan; S5. The detection module adjusts the rehabilitation plan according to the feedback signal of the rehabilitation equipment module, and iteratively executes S3-S5 until the preset rehabilitation goal is reached.

[0010] In the above technical solution, the three-dimensional image data obtained by the monitoring module can accurately extract the pathological characteristics of the patient's lumbar spine and spine. The treatment characteristics and risk characteristics are further determined in combination with the neural network model, making the formulation of the treatment plan more accurate and scientific. Taking into account the treatment characteristics and risk characteristics, combined with the patient's demand data, it can better meet the specific needs of the patient and improve the rehabilitation effect. The control module controls the rehabilitation equipment module intelligently to achieve the precise execution of the rehabilitation plan. The control module can automatically adjust the various parameters of the rehabilitation equipment according to the control parameters in the rehabilitation plan to ensure the accuracy and safety of the treatment process. The detection module can monitor the feedback signals of the rehabilitation equipment module in real time and dynamically adjust the rehabilitation plan according to these signals. This real-time feedback mechanism can timely detect and correct deviations in the treatment process to ensure the continuity and effectiveness of the rehabilitation process. By iteratively executing steps S3-S5, the rehabilitation plan is continuously adjusted according to the feedback signal until the preset rehabilitation goal is achieved, which can continuously optimize the treatment plan, improve the rehabilitation effect, and reduce unnecessary treatment time and cost.

[0011] Preferably, S1 comprises the following steps: S11, collecting three-dimensional image data of the patient's lumbar vertebrae and spine through the image acquisition unit of the monitoring module; S12, preprocessing the three-dimensional image data, wherein the preprocessing includes denoising and contrast enhancement; S13, performing image processing on the preprocessed three-dimensional image data to obtain texture features and shape features; S14. Analyze and determine corresponding pathological features based on the texture features and the shape features.

[0012] In the above technical solution, the quality of the image can be significantly improved by preprocessing the three-dimensional image data, including denoising and contrast enhancement. It can remove noise interference in the image to make the image clearer; contrast enhancement can highlight the detail information in the image, which is helpful for subsequent image processing and feature extraction. On the basis of image preprocessing, the image is further processed to extract texture features and shape features, which can more accurately reflect the pathological condition of the patient's lumbar spine and spine, and can more accurately determine the corresponding pathological features. Due to the use of sophisticated image processing and feature extraction methods, the patient's lumbar spine and spine information can be obtained more comprehensively, thereby improving the accuracy of diagnosis, helping doctors to understand the patient's condition more accurately and formulate a more scientific and reasonable treatment plan. The automated image processing and feature extraction process reduces manual intervention and improves the efficiency of the treatment process.

[0013] Preferably, S2 comprises the following steps: S21, selecting key features from the pathological features by using a random forest method; S22, training the neural network model based on the preset treatment characteristics and risk characteristics; S23. Using the key features as input to the neural network model to obtain treatment features and risk features.

[0014] In the above technical solution, by selecting key features through the S21 random forest method, the features that have the greatest impact on the prediction results can be effectively identified, thereby eliminating redundant and unimportant information, improving the training efficiency of subsequent models, and enhancing the prediction accuracy and robustness of the model. The neural network model is trained based on preset treatment characteristics and risk characteristics to ensure that the goal of model learning is clear and targeted, so that the model can better learn the mapping relationship from pathological characteristics to treatment characteristics and risk characteristics, and improve the applicability and accuracy of the model in practical applications. Using key features as input to the neural network model, treatment characteristics and risk characteristics can be obtained at the same time. Predictions are made based on the patient's specific pathological characteristics, so that patients can be provided with more personalized treatment plans and risk assessments, which helps to better meet the needs of patients and improve treatment effects and patient satisfaction.

[0015] Preferably, the S22 includes: Setting network layer parameters of the neural network model, including an input layer, a hidden layer, and an output layer, wherein: the number of neurons in the input layer is the same as the number of the key features, and the number of neurons in the output layer is the same as the sum of the number of the treatment features and the number of the risk features; Setting the activation function corresponding to the hidden layer of the neural network model; Iteratively training the neural network model based on the treatment characteristics and the risk characteristics, calculating the predicted value by a forward propagation method, and calculating the network weight by a back propagation method; The final neural network model is determined by combining the predicted value and the network weight.

[0016] In the above technical solution, by setting the number of neurons in the input layer to be the same as the number of key features, it is ensured that each key feature can be fully received and processed by the model, avoiding information omission or redundancy. The number of neurons in the output layer is the same as the sum of the number of treatment features and risk features, so that the model can output multiple prediction results (i.e., treatment features and risk features) at the same time, meeting the needs of multi-target prediction. By setting a suitable activation function, it is possible to learn and capture complex patterns in the data, and improve the accuracy and generalization of predictions. The neural network model is iteratively trained based on treatment features and risk features, and the network weights and parameters are continuously adjusted to gradually approach the optimal solution, which helps to improve the stability and reliability of the model. By combining forward propagation and back propagation to determine the predicted value and network weight, the model can continuously optimize its own performance during the training process and improve the prediction accuracy.

[0017] Preferably, S3 comprises the following steps: S31, setting a rehabilitation goal according to the treatment characteristics and the risk characteristics; S32, obtaining patient demand data, and extracting patient demand features corresponding to the patient demand data; S33. Formulate a corresponding rehabilitation plan based on the rehabilitation goals and patient needs.

[0018] In the above technical solution, rehabilitation goals are set according to the patient's treatment characteristics and risk characteristics, fully considering the patient's specific condition and potential risks, and providing a scientific basis for the development of personalized rehabilitation plans. Obtaining and extracting patient demand characteristics corresponding to patient demand data and incorporating patient needs into the development of rehabilitation plans can help improve patient participation and satisfaction. A rehabilitation plan formulated in combination with rehabilitation goals and patient demand characteristics can more accurately guide the patient's rehabilitation process, reduce unnecessary interventions and errors, and thus improve rehabilitation outcomes.

[0019] Preferably, S4 comprises the following steps: S41, setting control parameters of the control module according to the rehabilitation plan table, and generating a control signal based on the control parameters; S42, initializing the rehabilitation equipment module to make each unit in the rehabilitation equipment module in a normal working state; S43, sending the control signal to the rehabilitation equipment module through the control module, and the rehabilitation equipment module extracting and executing corresponding treatment actions based on the control signal; S44. Monitor the patient's physiological data and the state of the rehabilitation equipment module in real time through the monitoring module.

[0020] In the above technical solution, the control parameters of the control module are set according to the rehabilitation plan table, which ensures that the generation of the control signal matches the specific requirements of the rehabilitation plan, ensures that the rehabilitation equipment module can perform actions according to the predetermined treatment plan, and improves the accuracy and effectiveness of rehabilitation treatment. Equipment initialization ensures that each unit in each rehabilitation equipment module is in normal working condition before performing treatment, avoids treatment interruption or poor effect due to equipment failure or abnormality, and improves the operation efficiency and stability of the equipment. The control module sends a control signal to the rehabilitation equipment module to perform treatment actions, and monitors the patient's physiological data and equipment status in real time through the monitoring module. The real-time feedback mechanism allows the system to promptly detect and adjust any possible deviations or problems during the treatment process to ensure the smooth progress of rehabilitation treatment.

[0021] Preferably, the rehabilitation device module extracts and executes corresponding treatment actions based on the control signal, including: parsing the control signal based on the rehabilitation device module to obtain start-stop instructions, support angle, support height, traction force, traction speed, traction time, correction path, correction amplitude and correction time; Starting the lumbar support unit, the lumbar adjustment unit, the spinal traction unit and the spinal correction unit through the start-stop command; The waist adjustment unit performs a waist supporting action by adjusting the angle and height of the waist supporting unit through the support angle and the support height; The spinal traction unit performs a spinal traction action according to the traction force, the traction speed and the traction time; the spinal correction unit performs a spinal correction action according to the correction path, the correction amplitude and the correction time.

[0022] In the above technical solution, the control signal is parsed by the rehabilitation equipment module, and the start-stop command, support angle, support height, traction force, traction speed, traction time, correction path, correction amplitude and correction time can be accurately extracted, ensuring the accurate execution of the treatment action and avoiding the treatment error caused by improper parameter setting. The lumbar support unit, lumbar adjustment unit, spinal traction unit and spinal correction unit are started by the start-stop command to achieve comprehensive treatment of the patient's waist and spine. The lumbar adjustment unit adjusts the angle and height of the lumbar support unit according to the support angle and support height to ensure the comfort and effectiveness of the lumbar support action, and can adapt to the body shape and lumbar condition of different patients, so as to improve the comfort of treatment and the patient's acceptance. The spinal traction unit and the spinal correction unit respectively perform spinal traction and correction actions according to the traction force, traction speed, traction time, correction path, correction amplitude and correction time parameters, ensuring the safety and effectiveness of the treatment, and can effectively relieve the patient's spinal pain, improve spinal morphology and other problems.

[0023] Preferably, S5 comprises the following steps: S51, the monitoring module receives a feedback signal from the rehabilitation equipment module, wherein the feedback signal includes a change in physiological data and a working status of the equipment; S52, evaluating the rehabilitation effect in combination with the physiological data changes and the working status of the device, and determining whether the patient has achieved the preset rehabilitation goal; S53, if the preset rehabilitation goal is not achieved, adjusting the rehabilitation plan according to the feedback signal evaluation result; S54, iteratively execute S3 to S5 until the preset rehabilitation goal is reached or the maximum number of iterations is reached.

[0024] In the above technical solution, the feedback signal of the rehabilitation equipment module is received in real time by the monitoring module, including the changes in the patient's physiological data and the working status of the equipment, so as to ensure that the system can obtain the latest treatment information in time. The rehabilitation effect is evaluated in combination with the changes in physiological data and the working status of the equipment, and it is judged whether the patient has reached the preset rehabilitation goal based on the evaluation results. If the goal is not reached, the rehabilitation plan is adjusted according to the evaluation results of the feedback signal, so that the rehabilitation process can be flexibly adjusted according to the actual situation of the patient, thereby improving the pertinence and effectiveness of rehabilitation treatment. Through the comprehensive analysis of the changes in physiological data and the working status of the equipment, the rehabilitation effect can be evaluated more accurately, the influence of subjective judgment can be reduced, and it is helpful to formulate a more scientific and reasonable rehabilitation plan and improve the accuracy of rehabilitation treatment. Iteratively execute steps S3 to S5 until the preset rehabilitation goal is reached or the maximum number of iterations is reached, so that the rehabilitation process can be continuously optimized and improved, and the most suitable rehabilitation plan for the patient can be found through continuous trial and error and adjustment. At the same time, it also avoids overtreatment or undertreatment, and improves the efficiency and effect of rehabilitation treatment. The real-time monitoring and dynamic adjustment mechanism helps to timely discover and deal with abnormal reactions or complications that may occur in patients during the rehabilitation process, ensuring the safety of patients.

[0025] Beneficial effects of the present invention: The system can accurately obtain the lumbar and spinal pathological characteristics of the patient through the monitoring module, and generate personalized treatment control signals accordingly, ensuring that each patient can obtain the treatment plan that best suits his or her condition. The multi-unit coordination of the rehabilitation equipment module can perform precise rehabilitation actions according to the control signal to achieve efficient treatment, and form a closed-loop control system through real-time monitoring and dynamic adjustment to improve the safety and effectiveness of treatment. The system can automatically perform complex rehabilitation procedures, significantly reducing the reliance on manual intervention, which not only improves the treatment efficiency, but also shortens the patient's rehabilitation cycle. Through precise lumbar support and adjustment and gentle spinal traction and correction movements, the patient's discomfort during the rehabilitation process is minimized and the overall treatment experience is improved. Through the combination of the image acquisition unit and the image processing unit, the preprocessing, feature extraction and analysis of the three-dimensional image data are more automated, reducing the time and error of manual analysis, and improving the accuracy and efficiency of diagnosis. The neural network model is used to analyze the patient's pathological characteristics, intelligently determine the treatment characteristics and risk characteristics, and provide a scientific basis for formulating or adjusting the rehabilitation plan. The system monitors the patient's physiological data and equipment status in real time through the monitoring module, and can promptly detect and adjust any deviations in the rehabilitation process, ensuring the continuity and optimality of treatment. Through the process of continuous iteration of rehabilitation planning, monitoring, evaluation and adjustment, the system can continuously optimize the rehabilitation plan until the preset rehabilitation goals are achieved, ensuring the quality and ultimate effect of rehabilitation treatment.

[0026] The above invention content is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Other features, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for the purpose of illustrating preferred embodiments and are not to be considered as limiting the present invention. Also, the same reference symbols are used throughout the drawings to represent the same parts.

[0028] Figure 1 A schematic diagram of the structure of a lumbar and spinal rehabilitation system based on intelligent control disclosed in an embodiment of the present invention; Figure 2 The present invention discloses a flowchart of a lumbar vertebra and spinal rehabilitation method based on intelligent control. DETAILED DESCRIPTION

[0029] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementation method described herein is only an optimal embodiment of the present invention, which is only used to explain the present invention and does not limit the scope of protection of the present invention. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0030] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the operations (or steps) as being processed sequentially, many of the operations (or steps) therein may be performed in parallel, concurrently, or simultaneously. In addition, the order of the operations may be rearranged. A process may be terminated when its operations are completed, but may also have additional steps not included in the accompanying drawings; a process may correspond to a method, function, procedure, subroutine, subprogram, etc.

[0031] Example: According to a first aspect of this embodiment, a lumbar spine and spinal rehabilitation system based on intelligent control is provided, such as Figure 1 As shown, it includes a monitoring module 1, a control module 2 and a rehabilitation equipment module 3, the monitoring module 1 is connected to the control module 2, the monitoring module 1 is used to obtain the pathological characteristics corresponding to the patient's lumbar vertebra and spine and input them into the control module 2; the control module 2 is connected to the rehabilitation equipment module 3, the control module 2 is used to generate a control signal according to the pathological characteristics of the monitoring module 1 and output it to the rehabilitation equipment module 3; the rehabilitation equipment module 3 includes a lumbar support unit 31, a lumbar adjustment unit 32, a spinal traction unit 33 and a spinal correction unit 34, the lumbar support unit 31 is used to perform a lumbar support action through the control signal of the control module 2, the lumbar adjustment unit 32 is used to adjust the parameters of the lumbar support unit 31, the spinal traction unit 33 is used to perform a spinal traction action according to the control signal of the control module 2, and the spinal correction unit 34 is used to perform a spinal correction action according to the control signal of the control module 2.

[0032] In the above embodiment, the monitoring module 1 accurately obtains the patient's lumbar and spinal pathological characteristics, and the control module 2 can generate personalized treatment control signals based on this to ensure that each patient can obtain the treatment plan that best suits their condition. The lumbar support unit 31, lumbar adjustment unit 32, spinal traction unit 33 and spinal correction unit 34 in the rehabilitation equipment module 3 can perform corresponding rehabilitation actions according to the precise control signal issued by the control module 2, achieve precise treatment, and improve the rehabilitation effect. It can monitor the patient's treatment response in real time, and dynamically adjust the parameters and actions of the rehabilitation equipment as needed to form a closed-loop control to ensure the safety and effectiveness of the treatment process. It can automatically perform complex rehabilitation procedures, reduce manual intervention, improve treatment efficiency, and shorten the patient's rehabilitation cycle. Through precise lumbar support and adjustment, as well as gentle spinal traction and correction movements, the system can minimize the patient's discomfort during the rehabilitation process and enhance the treatment experience.

[0033] Specifically, the monitoring module 1 includes an image acquisition unit, an image processing unit and a data analysis unit which are connected in sequence; the image acquisition unit is used to acquire three-dimensional image data corresponding to the patient's lumbar vertebrae and spine; the image processing unit is used to process the three-dimensional image data to obtain pathological characteristics; the data analysis unit is used to set a rehabilitation plan according to the pathological characteristics or the feedback signal of the rehabilitation equipment.

[0034] In the above embodiment, the image acquisition unit can collect three-dimensional image data corresponding to the patient's lumbar spine and spine, which can provide more comprehensive and accurate patient pathological information, and help to analyze the condition more accurately later. The image processing unit automatically processes the collected three-dimensional image data to extract key pathological features, reducing the time and errors of manual analysis and improving the accuracy and efficiency of diagnosis. Based on the extracted pathological features or the real-time feedback signals of the rehabilitation equipment, the data analysis unit can intelligently formulate or adjust the rehabilitation plan, provide personalized treatment suggestions based on the patient's specific condition and rehabilitation progress, and ensure the scientificity and effectiveness of the rehabilitation plan. The data analysis unit can evaluate the treatment effect in real time according to the feedback signals of the rehabilitation equipment, and dynamically adjust the rehabilitation plan accordingly, which helps to timely discover and correct deviations in the treatment process and ensure the safety and effectiveness of the rehabilitation process.

[0035] According to a second aspect of this embodiment, a lumbar vertebra and spinal rehabilitation method based on intelligent control is provided, such as Figure 2 As shown, the following steps are included: S1. Obtain the three-dimensional image data corresponding to the patient's lumbar spine and spine through the monitoring module 1 and extract the corresponding pathological features.

[0036] Specifically, S1 includes the following steps: S11, collecting three-dimensional image data of the patient's lumbar vertebrae and spine through the image acquisition unit of the monitoring module 1; S12, preprocessing the three-dimensional image data, the preprocessing including denoising and contrast enhancement; S13, performing image processing on the preprocessed three-dimensional image data to obtain texture features and shape features; S14. Analyze and determine corresponding pathological features based on texture features and shape features.

[0037] In this embodiment, first, the three-dimensional image data of the patient's spine and lumbar spine are collected by the image acquisition unit in the monitoring module 1. The collected three-dimensional image is denoised by using image processing software, including using algorithms such as median filtering and Gaussian filtering to remove noise points in the image and improve the signal-to-noise ratio of the image. The denoised image is contrast enhanced to highlight the detail information in the image. Methods such as histogram equalization and Laplace sharpening can be used to make the boundaries of the lumbar vertebrae and spine clearer, which is convenient for subsequent feature extraction. The lumbar vertebrae and spine regions are separated from the background by a threshold-based segmentation method. On the segmented lumbar vertebrae and spine regions, the texture features of the image are extracted. The texture features of this embodiment include grayscale co-occurrence matrix and local binary pattern, which can accurately reflect the roughness, directionality and frequency properties of the image surface. Further extraction is enough to describe the overall morphology and size information of the lumbar vertebrae and spine. The extracted texture features and shape features are compared and analyzed with the known lumbar vertebrae and spine pathological feature library. The pathological feature library contains typical image features and clinical manifestation information of various lumbar and spinal diseases. Based on the results of comparative analysis and combined with the doctor's clinical experience, the patient's lumbar and spinal pathological characteristics are diagnosed to determine whether the patient has pathological conditions such as lumbar disc herniation, scoliosis, and spinal fractures, and to assess their severity.

[0038] In the above embodiment, the quality of the image can be significantly improved by preprocessing the three-dimensional image data, including denoising and contrast enhancement. It is possible to remove noise interference in the image to make the image clearer; contrast enhancement can highlight the detail information in the image, which is helpful for subsequent image processing and feature extraction. On the basis of image preprocessing, the image is further processed to extract texture features and shape features, which can more accurately reflect the pathological condition of the patient's lumbar spine and spine, and can more accurately determine the corresponding pathological features. Due to the use of sophisticated image processing and feature extraction methods, the patient's lumbar spine and spine information can be obtained more comprehensively, thereby improving the accuracy of diagnosis, helping doctors to understand the patient's condition more accurately and formulate a more scientific and reasonable treatment plan. The automated image processing and feature extraction process reduces manual intervention and improves the efficiency of the treatment process.

[0039] S2. Analyze the pathological characteristics through the neural network model to determine the corresponding treatment characteristics and risk characteristics.

[0040] Specifically, S2 includes the following steps: S21, select key features from pathological features by random forest method; S22, training the neural network model based on the preset treatment characteristics and risk characteristics; S23. Use the key features as input to the neural network model to obtain treatment features and risk features.

[0041] In this embodiment.

[0042] In the above embodiment, by selecting key features through the S21 random forest method, the features that have the greatest impact on the prediction results can be effectively identified, thereby eliminating redundant and unimportant information, improving the training efficiency of subsequent models, and enhancing the prediction accuracy and robustness of the model. The neural network model is trained based on preset treatment characteristics and risk characteristics to ensure that the goal of model learning is clear and targeted, so that the model can better learn the mapping relationship from pathological characteristics to treatment characteristics and risk characteristics, and improve the applicability and accuracy of the model in practical applications. Using key features as input to the neural network model, treatment characteristics and risk characteristics can be obtained at the same time. Predictions are made based on the patient's specific pathological characteristics, so that patients can be provided with more personalized treatment plans and risk assessments, which helps to better meet the needs of patients and improve treatment effects and patient satisfaction.

[0043] Specifically, S22 includes: Setting the network layer parameters of the neural network model, including the input layer, hidden layer and output layer, where: the number of neurons in the input layer is the same as the number of key features, and the number of neurons in the output layer is the same as the sum of the number of treatment features and risk features; Set the activation function corresponding to the hidden layer of the neural network model; The neural network model is iteratively trained based on treatment characteristics and risk characteristics, and the prediction value is calculated by the forward propagation method, and the network weight is calculated by the back propagation method; The final neural network model is determined by combining the predicted value and network weight.

[0044] In this embodiment, the number of neurons in the input layer should be exactly the same as the number of key features selected by the random forest method. For example, if 10 key features are selected, the input layer should have 10 neurons. The number of hidden layers and the number of neurons in each layer need to be adjusted according to the characteristics of the specific task and data set. Set one or more hidden layers, and the number of neurons in each layer can be set to 1 to 2 times the number of neurons in the input layer, or the optimal number can be determined by experiment. For example, two hidden layers can be set, each with 20 neurons. Each hidden layer should be set with an activation function to increase the nonlinear ability of the model. The number of neurons in the output layer should be the same as the sum of the number of treatment features and risk features. For example, if there are 5 treatment features and 3 risk features, the output layer should have 8 neurons. Set the corresponding learning rate, which determines the step size of the weight adjustment and needs to be adjusted according to the actual situation. Too high a learning rate may cause the training process to be unstable, and too low a learning rate may make the training process too slow. Set the number of iterations and observe the changes in the loss function during the training process to determine when to stop training. A loss function is set to measure the difference between the model prediction value and the actual value. This embodiment uses the cross entropy loss function; the key features are used as input, and the forward propagation is performed through the neural network model to calculate the predicted value. The difference between the predicted value and the actual value is calculated using the set loss function. According to the gradient of the loss function, the gradient of the weights of each layer in the network is calculated by the back propagation algorithm, and the weights are updated. The network weights are updated according to the product of the learning rate and the gradient. Repeat the above process of forward propagation, loss calculation, back propagation and weight update until the preset number of iterations is reached or the loss function meets the stopping condition.

[0045] In the above embodiment, by setting the number of input layer neurons to be the same as the number of key features, it is ensured that each key feature can be fully received and processed by the model, avoiding information omission or redundancy. The number of neurons in the output layer is the same as the sum of the number of treatment features and risk features, so that the model can output multiple prediction results (i.e., treatment features and risk features) at the same time, meeting the needs of multi-target prediction. By setting a suitable activation function, it is possible to learn and capture complex patterns in the data, and improve the accuracy and generalization ability of the prediction. The neural network model is iteratively trained based on the treatment features and risk features, and the network weights and parameters are continuously adjusted to gradually approach the optimal solution, which helps to improve the stability and reliability of the model. By combining forward propagation and back propagation to determine the predicted value and network weight, the model can continuously optimize its own performance during the training process and improve the prediction accuracy.

[0046] S3. Determine rehabilitation goals based on treatment characteristics and risk characteristics, and set up a rehabilitation plan based on patient demand data and rehabilitation goals.

[0047] Specifically, S3 includes the following steps: S31. Set rehabilitation goals based on treatment characteristics and risk characteristics; S32, obtaining patient demand data, and extracting patient demand features corresponding to the patient demand data; S33. Develop a corresponding rehabilitation plan based on rehabilitation goals and patient needs.

[0048] In this embodiment, the treatment characteristics obtained by the neural network model analysis are first analyzed. For example, for patients with lumbar disc herniation, the treatment characteristics may include the degree of herniation, compressed nerve roots, etc. Then the patient's risk characteristics are evaluated, including possible complications, recurrence risks, long-term effects, etc. during the rehabilitation process. Based on the comprehensive analysis of treatment characteristics and risk characteristics, clear rehabilitation goals are set, such as "relieve the pain caused by lumbar disc herniation within 3 months" and "restore the normal range of motion of the lumbar spine within 6 months". Collect patient demand data, organize and analyze them, and extract key patient demand characteristics. Including patients' expectations for rehabilitation effects, comfort requirements for the rehabilitation process, requirements for rehabilitation time, etc. According to the rehabilitation goals and patient demand characteristics, formulate the overall framework of the rehabilitation plan. On the basis of the rehabilitation plan framework, further refine the rehabilitation schedule.

[0049] In the above embodiment, the rehabilitation goals are set according to the patient's treatment characteristics and risk characteristics, which fully considers the patient's specific condition and potential risks, and provides a scientific basis for formulating a personalized rehabilitation plan. Obtaining and extracting the patient's demand characteristics corresponding to the patient's demand data and incorporating the patient's needs into the process of formulating the rehabilitation plan will help improve the patient's participation and satisfaction. The rehabilitation plan formulated in combination with the rehabilitation goals and the patient's demand characteristics can more accurately guide the patient's rehabilitation process, reduce unnecessary interventions and errors, and thus improve the rehabilitation effect.

[0050] S4. Setting control parameters of the control module 2 according to the rehabilitation plan, and controlling the rehabilitation equipment module 3 through the control module 2 to execute the rehabilitation plan.

[0051] Specifically, S4 includes the following steps: S41, setting control parameters of the control module 2 according to the rehabilitation plan table, and generating a control signal based on the control parameters; S42, initializing the rehabilitation equipment module 3 so that each unit in the rehabilitation equipment module 3 is in a normal working state; S43, sending the control signal to the rehabilitation equipment module 3 through the control module 2, and the rehabilitation equipment module 3 extracts and executes the corresponding treatment action based on the control signal; S44, monitoring the patient's physiological data and rehabilitation equipment module status in real time through the monitoring module 1.

[0052] In the above embodiment, the control parameters of the control module 2 are set according to the rehabilitation plan table, which ensures that the generation of the control signal matches the specific requirements of the rehabilitation plan, ensures that the rehabilitation equipment module 3 can perform actions according to the predetermined treatment plan, and improves the accuracy and effectiveness of the rehabilitation treatment. Equipment initialization ensures that each unit in each rehabilitation equipment module 3 is in normal working condition before performing treatment, avoids treatment interruption or poor effect due to equipment failure or abnormality, and improves the operation efficiency and stability of the equipment. The control module 2 sends a control signal to the rehabilitation equipment module 3 to perform the treatment action, and monitors the patient's physiological data and equipment status in real time through the monitoring module 1. The real-time feedback mechanism allows the system to promptly detect and adjust any possible deviations or problems during the treatment process to ensure the smooth progress of rehabilitation treatment.

[0053] Specifically, the rehabilitation device module 3 extracts and executes corresponding treatment actions based on the control signal, including: Based on the rehabilitation equipment module 3, the control signal is analyzed to obtain the start and stop instructions, support angle, support height, traction force, traction speed, traction time, correction path, correction amplitude and correction time; The lumbar support unit 31, the lumbar adjustment unit 32, the spinal traction unit 33 and the spinal correction unit 34 are started by the start-stop command; the lumbar adjustment unit 32 adjusts the angle and height of the lumbar support unit 31 by the support angle and the support height to perform the lumbar support action; The spinal traction unit 33 performs spinal traction action according to the traction force, traction speed and traction time; The spine correction unit 34 performs spine correction actions according to a correction path, correction amplitude, and correction time.

[0054] In this embodiment, the control module 2 first needs to parse the rehabilitation schedule to extract the specific control parameters required for each rehabilitation stage. Including start-stop instructions, support angle, support height, traction force, traction speed, traction time, correction path, correction amplitude and correction time. According to the parsed control parameters, the control module 2 generates a corresponding control signal. Before receiving the control signal, the rehabilitation equipment module 3 performs a self-check to ensure that each unit is in a normal working state, confirm whether the function of each unit is normal, and whether there are any potential faults. The control module 2 sends the generated control signal to the rehabilitation equipment module 3. After receiving the control signal, the rehabilitation equipment module 3 parses it and starts the corresponding unit according to the parsing result. For example, the start-stop instruction starts the lumbar support unit 31, the lumbar adjustment unit 32, the spinal traction unit 33 and the spinal correction unit 34. The lumbar adjustment unit 32 adjusts the angle and height of the lumbar support unit 31 according to the support angle and support height to provide suitable lumbar support. The spinal traction unit 33 performs spinal traction action according to the traction force, traction speed and traction time to relieve spinal pressure. The spine correction unit 34 performs spine correction actions according to the correction path, correction amplitude, and correction time to improve the alignment and posture of the spine.

[0055] In the above embodiment, the control signal is analyzed by the rehabilitation equipment module 3, and the start-stop command, support angle, support height, traction force, traction speed, traction time, correction path, correction amplitude and correction time can be accurately extracted, ensuring the accurate execution of the treatment action and avoiding the treatment error caused by improper parameter setting. The waist support unit 31, waist adjustment unit 32, spinal traction unit 33 and spinal correction unit 34 multiple functional modules are started by the start-stop command, realizing the comprehensive treatment of the patient's waist and spine. The waist adjustment unit 32 adjusts the angle and height of the waist support unit 31 according to the support angle and support height to ensure the comfort and effectiveness of the waist support action, and can adapt to the body shape and lumbar condition of different patients, so as to improve the comfort of treatment and the patient's acceptance. The spinal traction unit 33 and the spinal correction unit 34 respectively perform spinal traction and correction actions according to the parameters such as traction force, traction speed, traction time, correction path, correction amplitude and correction time, ensuring the safety and effectiveness of the treatment, and can effectively relieve the patient's spinal pain, improve the spinal morphology and other problems.

[0056] S5. The detection module adjusts the rehabilitation plan according to the feedback signal of the rehabilitation equipment module 3, and iteratively executes S3-S5 until the preset rehabilitation goal is achieved.

[0057] Specifically, S5 includes the following steps: S51, the monitoring module 1 receives a feedback signal from the rehabilitation equipment module 3, the feedback signal including physiological data changes and equipment working status; S52, evaluating the rehabilitation effect in combination with the physiological data changes and the working status of the equipment, and determining whether the patient has achieved the preset rehabilitation goal; S53, if the preset rehabilitation goal has not been achieved, adjusting the rehabilitation plan according to the feedback signal evaluation results; S54, iteratively execute S3 to S5 until the preset rehabilitation goal is reached or the maximum number of iterations is reached.

[0058] In this embodiment, the monitoring module 1 continuously receives feedback signals from the rehabilitation equipment module 3, and the feedback signals include not only the patient's real-time physiological data (such as heart rate, blood pressure, respiratory rate, etc.), but also the working status of the equipment (such as the start and stop status of each unit, working parameters, etc.). Based on the collected physiological data, the patient's rehabilitation progress and physiological state changes are analyzed. By comparing the initial physiological data with the current physiological data, the rehabilitation effect is evaluated to see whether it is significant. At the same time, the working status of the equipment is analyzed to confirm whether there is an abnormality or failure. Combined with the results of physiological data evaluation and equipment status analysis, it is determined whether the patient has reached the preset rehabilitation goal. If the goal has been achieved, the rehabilitation end stage is entered; if the goal has not been achieved, the next adjustment is required. The reasons for not achieving the rehabilitation goal are analyzed in depth, including patient factors (such as physique, compliance), equipment factors, and factors of the rehabilitation plan itself. According to the evaluation results, the rehabilitation plan is adjusted accordingly, including modifying the treatment action, adjusting the treatment parameters (such as support angle, traction force, etc.), extending or shortening the treatment time, etc. The adjusted rehabilitation plan is updated to the control module 2 for use in the next iteration. Re-execute steps S3 to S5, set control parameters according to the new rehabilitation plan, initialize the device, perform treatment actions, and continuously monitor the patient's physiological data and device status until the patient reaches the preset rehabilitation goal or reaches the set maximum number of iterations.

[0059] In the above embodiment, the feedback signal of the rehabilitation equipment module 3 is received in real time by the monitoring module 1, including the changes in the patient's physiological data and the working status of the equipment, so that the system can obtain the latest treatment information in time. The rehabilitation effect is evaluated in combination with the changes in physiological data and the working status of the equipment, and it is judged whether the patient has reached the preset rehabilitation goal according to the evaluation results. If the goal is not reached, the rehabilitation plan is adjusted according to the evaluation results of the feedback signal, so that the rehabilitation process can be flexibly adjusted according to the actual situation of the patient, thereby improving the pertinence and effectiveness of rehabilitation treatment. Through the comprehensive analysis of the changes in physiological data and the working status of the equipment, the rehabilitation effect can be evaluated more accurately, the influence of subjective judgment can be reduced, and it is helpful to formulate a more scientific and reasonable rehabilitation plan and improve the accuracy of rehabilitation treatment. Iteratively execute steps S3 to S5 until the preset rehabilitation goal is reached or the maximum number of iterations is reached, so that the rehabilitation process can be continuously optimized and improved, and the most suitable rehabilitation plan for the patient can be found through continuous trial and error and adjustment. At the same time, it also avoids overtreatment or undertreatment, and improves the efficiency and effect of rehabilitation treatment. The real-time monitoring and dynamic adjustment mechanism helps to timely discover and deal with abnormal reactions or complications that may occur in patients during the rehabilitation process, ensuring the safety of patients.

[0060] Beneficial effects of this embodiment: Through high-precision image acquisition and processing technology, the patient's lumbar and spinal pathological characteristics can be accurately obtained, and a personalized treatment plan can be generated based on these characteristics, thereby ensuring that each patient receives the treatment most suitable for his or her condition. The multi-unit cooperation of the rehabilitation equipment module 3 can perform precise rehabilitation actions according to the control signal to achieve efficient treatment, and through real-time monitoring and dynamic adjustment, a closed-loop control system is formed to improve the safety and effectiveness of treatment. The system can automatically perform complex rehabilitation procedures, significantly reducing the reliance on manual intervention, which not only improves the treatment efficiency, but also shortens the patient's rehabilitation cycle. Accurate lumbar support and adjustment, as well as gentle spinal traction and correction movements, minimize the patient's discomfort during the rehabilitation process and enhance the overall treatment experience. The combination of the image acquisition unit and the image processing unit makes the preprocessing, feature extraction and analysis of three-dimensional image data more automated, reduces the time and error of manual analysis, and improves the accuracy and efficiency of diagnosis. The neural network model is used to analyze the patient's pathological characteristics, intelligently determine the treatment characteristics and risk characteristics, and provide a scientific basis for formulating or adjusting the rehabilitation plan. The system monitors the patient's physiological data and equipment status in real time through monitoring module 1, and can promptly detect and adjust any deviations in the rehabilitation process, ensuring the continuity and optimality of treatment. The neural network model can simultaneously predict treatment characteristics and risk characteristics, meeting the needs of multi-target prediction and helping to provide patients with a more comprehensive treatment plan. The formulation of the rehabilitation plan takes into account the specific needs of the patient, improves the patient's participation and satisfaction, and ensures that the treatment plan is more in line with the patient's actual situation.

[0061] The above specific implementation is a preferred implementation of the lumbar and spinal rehabilitation system and method based on intelligent control of the present invention, and is not intended to limit the specific implementation scope of the present invention. The scope of the present invention includes but is not limited to this specific implementation. All equivalent changes made in accordance with the shape and structure of the present invention are within the protection scope of the present invention.

Claims

1. A lumbar and spinal rehabilitation system based on intelligent control, characterized in that: The device comprises a monitoring module, a control module and a rehabilitation equipment module, wherein the monitoring module is connected to the control module, and the monitoring module is used to obtain the pathological characteristics corresponding to the patient's lumbar vertebra and spine and input them into the control module; the control module is connected to the rehabilitation equipment module, and the control module is used to generate a control signal according to the pathological characteristics of the monitoring module and output it to the rehabilitation equipment module; the rehabilitation equipment module comprises a lumbar support unit, a lumbar adjustment unit, a spinal traction unit and a spinal correction unit, the lumbar support unit is used to perform a lumbar support action through the control signal of the control module, the lumbar adjustment unit is used to adjust the parameters of the lumbar support unit, the spinal traction unit is used to perform a spinal traction action according to the control signal of the control module, and the spinal correction unit is used to perform a spinal correction action according to the control signal of the control module.

2. The lumbar vertebra and spine rehabilitation system based on intelligent control according to claim 1, characterized in that: The monitoring module includes an image acquisition unit, an image processing unit and a data analysis unit connected in sequence; the image acquisition unit is used to acquire three-dimensional image data corresponding to the patient's lumbar vertebrae and spine; the image processing unit is used to process the three-dimensional image data to obtain pathological characteristics; the data analysis unit is used to set a rehabilitation plan based on the pathological characteristics or feedback signals from the rehabilitation equipment.

3. A lumbar vertebra and spinal rehabilitation method based on intelligent control, applicable to the lumbar vertebra and spinal rehabilitation system based on intelligent control as claimed in any one of claims 1 to 2, characterized in that: The steps include: S1. Obtain the three-dimensional image data corresponding to the patient's lumbar spine and spine through the monitoring module and extract the corresponding pathological features; S2. analyzing the pathological features through a neural network model to determine corresponding treatment features and risk features; S3, determining a rehabilitation goal according to the treatment characteristics and the risk characteristics, and setting a rehabilitation plan in combination with the patient's demand data and the rehabilitation goal; S4, setting control parameters of a control module according to the rehabilitation plan, and controlling a rehabilitation equipment module through the control module to execute the rehabilitation plan; S5. The detection module adjusts the rehabilitation plan according to the feedback signal of the rehabilitation equipment module, and iteratively executes S3-S5 until the preset rehabilitation goal is reached.

4. The lumbar vertebra and spine rehabilitation method based on intelligent control according to claim 3, characterized in that: The S1 comprises the following steps: S11, collecting three-dimensional image data of the patient's lumbar vertebrae and spine through the image acquisition unit of the monitoring module; S12, preprocessing the three-dimensional image data, wherein the preprocessing includes denoising and contrast enhancement; S13, performing image processing on the preprocessed three-dimensional image data to obtain texture features and shape features; S14. Analyze and determine corresponding pathological features based on the texture features and the shape features.

5. The lumbar vertebra and spine rehabilitation method based on intelligent control according to claim 3, characterized in that: The S2 comprises the following steps: S21, selecting key features from the pathological features by using a random forest method; S22, training the neural network model based on the preset treatment characteristics and risk characteristics; S23. Using the key features as input to the neural network model to obtain treatment features and risk features.

6. The lumbar vertebra and spine rehabilitation method based on intelligent control according to claim 5, characterized in that: The S22 includes: Setting network layer parameters of the neural network model, including an input layer, a hidden layer, and an output layer, wherein: the number of neurons in the input layer is the same as the number of the key features, and the number of neurons in the output layer is the same as the sum of the number of the treatment features and the number of the risk features; Setting the activation function corresponding to the hidden layer of the neural network model; Iteratively training the neural network model based on the treatment characteristics and the risk characteristics, calculating the predicted value by a forward propagation method, and calculating the network weight by a back propagation method; The final neural network model is determined by combining the predicted value and the network weight.

7. The lumbar vertebra and spine rehabilitation method based on intelligent control according to claim 3, characterized in that: The S3 comprises the following steps: S31, setting a rehabilitation goal according to the treatment characteristics and the risk characteristics; S32, obtaining patient demand data, and extracting patient demand features corresponding to the patient demand data; S33. Formulate a corresponding rehabilitation plan based on the rehabilitation goals and patient needs.

8. The lumbar vertebra and spine rehabilitation method based on intelligent control according to claim 3, characterized in that: The S4 comprises the following steps: S41, setting control parameters of the control module according to the rehabilitation plan table, and generating a control signal based on the control parameters; S42, initializing the rehabilitation equipment modules to ensure that each unit in the rehabilitation equipment modules is in a normal working state; S43, sending the control signal to the rehabilitation equipment module through the control module, and the rehabilitation equipment module extracting and executing corresponding treatment actions based on the control signal; S44. Monitor the patient's physiological data and the state of the rehabilitation equipment module in real time through the monitoring module.

9. The lumbar vertebra and spine rehabilitation method based on intelligent control according to claim 8, characterized in that: The rehabilitation device module extracts and executes corresponding treatment actions based on the control signal, including: The control signal is parsed based on the rehabilitation equipment module to obtain start and stop instructions, support angle, support height, traction force, traction speed, traction time, correction path, correction amplitude and correction time; Starting the lumbar support unit, the lumbar adjustment unit, the spinal traction unit and the spinal correction unit through the start-stop command; The waist adjustment unit performs a waist supporting action by adjusting the angle and height of the waist supporting unit through the support angle and the support height; The spinal traction unit performs spinal traction action according to the traction force, the traction speed and the traction time; The spine correction unit performs a spine correction action according to the correction path, the correction amplitude, and the correction time.

10. The lumbar vertebra and spine rehabilitation method based on intelligent control according to claim 3, characterized in that: The S5 comprises the following steps: S51, the monitoring module receives a feedback signal from the rehabilitation equipment module, wherein the feedback signal includes a change in physiological data and a working status of the equipment; S52, evaluating the rehabilitation effect in combination with the physiological data changes and the working status of the device, and determining whether the patient has achieved the preset rehabilitation goal; S53, if the preset rehabilitation goal is not achieved, adjusting the rehabilitation plan according to the feedback signal evaluation result; S54, iteratively execute S3 to S5 until the preset rehabilitation goal is reached or the maximum number of iterations is reached.

Images